CN111986804A - Method and device for model training based on body temperature data and computer equipment - Google Patents
Method and device for model training based on body temperature data and computer equipment Download PDFInfo
- Publication number
- CN111986804A CN111986804A CN202010900302.XA CN202010900302A CN111986804A CN 111986804 A CN111986804 A CN 111986804A CN 202010900302 A CN202010900302 A CN 202010900302A CN 111986804 A CN111986804 A CN 111986804A
- Authority
- CN
- China
- Prior art keywords
- body temperature
- model
- temperature data
- user
- data
- 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
- 230000036760 body temperature Effects 0.000 title claims abstract description 192
- 238000012549 training Methods 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004458 analytical method Methods 0.000 claims abstract description 74
- 230000033764 rhythmic process Effects 0.000 claims abstract description 64
- 238000001514 detection method Methods 0.000 claims abstract description 45
- 238000007477 logistic regression Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 15
- 230000002776 aggregation Effects 0.000 claims abstract description 11
- 238000004220 aggregation Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000007621 cluster analysis Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 206010037660 Pyrexia Diseases 0.000 description 1
- 238000000692 Student's t-test Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012353 t test Methods 0.000 description 1
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
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The application relates to the technical field of artificial intelligence, and provides a method, a device, computer equipment and a storage medium for model training based on body temperature data, wherein each user terminal respectively collects continuous body temperature data of a sample user and correspondingly analyzes the body temperature rhythm characteristic data of the collected body temperature data; respectively inputting the parameters into a logistic regression model for training so as to update the model parameters; when the server determines that the model training is finished, each user terminal sends the updated model parameters to the server, so that the server performs aggregation operation on the model parameters sent by all the user terminals to obtain weighted average model parameters; and updating the logistic regression model according to the weighted average model parameters and stopping model training to obtain a detection model for detecting the body temperature rhythm characteristic data. Training obtains detection model in this application and is convenient for carry out the physical sign characteristic of analysis user from body temperature data, is convenient for carry out analysis processes to body temperature rhythm characteristic data based on this detection model.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a method and a device for model training based on body temperature data, computer equipment and a storage medium.
Background
At present, the auxiliary judgment of depression is usually based on the biorhythm data of patients, and the abnormal biorhythm is considered as an obvious symptom of depression and is often reflected in the change of physical sign data (such as body temperature data) of people.
Therefore, the physical sign data of the human body is reasonably utilized, and the method is favorable for auxiliary judgment of the depression. However, at present, doctors usually perform manual analysis on the physical sign data based on diagnosis experience, and the professional requirement is high, so that the physical sign data of patients cannot be reasonably analyzed and utilized by an automatic machine, and cannot be applied to patient testing.
Disclosure of Invention
The application mainly aims to provide a method, a device, computer equipment and a storage medium for model training based on body temperature data, and aims to overcome the defects that reasonable analysis cannot be carried out on the body temperature data and the body temperature data cannot be applied to patient testing at present.
In order to achieve the above object, the present application provides a method for model training based on body temperature data, comprising the following steps:
each user terminal respectively collects continuous body temperature data of a sample user and correspondingly analyzes the body temperature rhythm characteristic data of the collected body temperature data;
each user terminal inputs the corresponding body temperature rhythm characteristic data into a logistic regression model for training so as to update model parameters;
when the server determines that the model training is finished, each user terminal sends the updated model parameters to the server, so that the server performs aggregation operation on the model parameters sent by all the user terminals to obtain weighted average model parameters;
each user terminal receives the weighted average model parameters sent by the server terminal, updates the logistic regression model according to the weighted average model parameters and stops model training to obtain a detection model for detecting body temperature rhythm characteristic data; the detection model is used for automatically analyzing the body temperature data of the user when the body temperature data of the user is collected.
Further, after the steps of receiving, by each user terminal, the weighted average model parameter sent by the server, updating the logistic regression model according to the weighted average model parameter, and stopping model training to obtain a detection model for detecting body temperature rhythm characteristic data, the method includes:
the user terminal collects continuous body temperature data of a new user and correspondingly analyzes the body temperature rhythm characteristic data of the collected continuous body temperature data of the new user;
and inputting the body temperature rhythm characteristic data of the continuous body temperature data of the new user into the detection model to obtain a prediction result as a detection result of the new user.
Further, after the step of inputting the corresponding body temperature rhythm characteristic data into a logistic regression model for training by each user terminal to update the model parameters, the method includes:
each user terminal sends the current loss value of the loss function of the logistic regression model to the server, so that whether the model is trained or not is determined according to the loss value sent by each user terminal by the server; the server is used for receiving the loss value, judging whether a loss function on the server is converged according to the loss value, and determining that the model training is finished by the server when the loss function on the server is converged.
Further, the calculation formula of the loss function of the logistic regression model on the user terminal is as follows:
wherein the content of the first and second substances,
is a loss value, xiAs body temperature data, yiFor the output value of the logistic regression model, the loss function on the server side is:
further, after the step of acquiring the continuous body temperature data of the new user by the user terminal, the method includes:
inputting the new user body temperature data into a preset clustering anomaly analysis model for clustering analysis to obtain a clustering analysis result;
inputting the body temperature data into a preset prediction analysis model for prediction to obtain a predicted temperature, and calculating a residual error value between the body temperature data of the new user and the predicted temperature; comparing the residual value with a preset value, and outputting a prediction analysis result;
comparing whether the clustering analysis result is the same as the prediction analysis result; and when the clustering analysis result and the prediction analysis result are both results of normal body temperature data, entering the body temperature rhythm characteristic data of the new user continuous body temperature data acquired by corresponding analysis.
Further, the training process of the predictive analysis model and the clustering anomaly analysis model includes:
collecting a plurality of normal body temperature data of a normal user;
calculating the average value and standard deviation of the plurality of normal body temperature data, subtracting the average value from each normal body temperature data, and dividing the average value by the standard deviation to obtain corresponding body temperature processing data;
for the body temperature processing data, establishing the clustering anomaly analysis model using density clustering analysis, and establishing the predictive analysis model using regression prediction.
The application also provides a device for model training based on body temperature data, including:
the first acquisition unit is used for acquiring continuous body temperature data of a sample user on each user terminal respectively and analyzing the body temperature rhythm characteristic data of the acquired body temperature data correspondingly;
the training unit is used for inputting the corresponding body temperature rhythm characteristic data into a logistic regression model for training on each user terminal so as to update model parameters;
the sending unit is used for sending the updated model parameters to the server by each user terminal when the server determines that the model training is finished, so as to perform aggregation operation on the model parameters sent by all the user terminals through the server to obtain weighted average model parameters;
the updating unit is used for receiving the weighted average model parameters sent by the server terminal by each user terminal, updating the logistic regression model according to the weighted average model parameters and stopping model training to obtain a detection model for detecting the body temperature rhythm characteristic data; the detection model is used for automatically analyzing the body temperature data of the user when the body temperature data of the user is collected.
Further, the apparatus further comprises:
the second acquisition unit is used for acquiring the continuous body temperature data of the new user on the user terminal and correspondingly analyzing the acquired body temperature rhythm characteristic data of the continuous body temperature data of the new user;
and the prediction unit is used for inputting the body temperature rhythm characteristic data of the continuous body temperature data of the new user into the detection model to obtain a prediction result as a detection result of the new user.
The present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of any of the above.
According to the method, the device, the computer equipment and the storage medium for model training based on the body temperature data, each user terminal respectively collects continuous body temperature data of a sample user and correspondingly analyzes the collected body temperature rhythm characteristic data of the body temperature data; respectively inputting the parameters into a logistic regression model for training so as to update the model parameters; when the server determines that the model training is finished, each user terminal sends the updated model parameters to the server, so that the server performs aggregation operation on the model parameters sent by all the user terminals to obtain weighted average model parameters; and updating the logistic regression model according to the weighted average model parameters and stopping model training to obtain a detection model for detecting the body temperature rhythm characteristic data. Training obtains detection model in this application and is convenient for carry out the physical sign characteristic of analysis user from body temperature data, is convenient for carry out analysis processes to body temperature rhythm characteristic data based on this detection model.
Drawings
FIG. 1 is a schematic diagram illustrating the steps of a method for model training based on body temperature data according to an embodiment of the present disclosure;
FIG. 2 is a block diagram of an apparatus for model training based on body temperature data according to an embodiment of the present disclosure;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, in an embodiment of the present application, a method for model training based on body temperature data is provided, including the following steps:
step S1, each user terminal respectively collects continuous body temperature data of a sample user and correspondingly analyzes the collected body temperature rhythm characteristic data of the body temperature data;
step S2, each user terminal inputs the corresponding body temperature rhythm characteristic data into a logistic regression model for training so as to update model parameters;
step S3, when the server determines that the model training is finished, each user terminal sends the updated model parameters to the server, so that the server performs aggregation operation on the model parameters sent by all the user terminals to obtain weighted average model parameters;
step S4, each user terminal receives the weighted average model parameters sent by the server terminal, updates the logistic regression model according to the weighted average model parameters and stops model training to obtain a detection model for detecting body temperature rhythm characteristic data; the detection model is used for automatically analyzing the body temperature data of the user when the body temperature data of the user is collected.
In this embodiment, the method is used for training a detection model for detecting the body temperature rhythm characteristic data, and the body temperature rhythm characteristic data is conveniently predicted based on the detection model to obtain a result of whether the user has depression.
As described in the step S1, the intelligent temperature detector may be worn on the sample user to collect continuous body temperature data of the sample user, and the cosine analysis algorithm is further used to analyze the body temperature data to obtain body temperature rhythm characteristic data.
Specifically, the continuous body temperature data is xi＝[xi1,xi2,…,xit,xiT]The calculation process of the cosine analysis algorithm is as follows:
Y(t)＝M+βx+γz+e(t)；
where M is the median, A is the amplitude, β is the cosine component, and γ is the sine component.
The residual error is optimized by means of a least-squares method,
in the body temperature rhythm detection algorithm, TSS (total error) ═ MSS (expected error) + RSS (empirical error), the error function can be represented by Ftest, and F ═ MSS/2)/(RSS/(N-3)), where 2 and N-3 are the number of model degrees of freedom and the number of error terms. When F is present>F1-α(2, N-3), no rhythm is rejected.
For estimating the parameters, the median values M and (. beta.,. gamma.) are considered separately, 1-. alpha.being
Is confidence interval of
Wherein
Is s-1，
tp(f) Denotes the P-th probability point of the t-test in the degree of freedom f,
has a covariance matrix of
Rhythm detection based on F-statistic, using the estimated value
Instead of calculating when a is 0;
wherein the content of the first and second substances,
obtaining body temperature data corresponding to each sample user through the operation
And F value, which is the above-mentioned body temperature rhythm characteristic data.
As described in step S2, each user terminal inputs the corresponding body temperature rhythm characteristic data into a logistic regression model for training to update model parameters
It can be understood that, in this embodiment, each of the user terminals respectively performs communication transmission with the same server, and in this scheme, based on a secure average algorithm, the training of the logistic regression model is completed by one server and a plurality of user terminals together.
Specifically, the logistic regression model on each user terminal is the initial model parameter w0And the server side initializes the model parameters and broadcasts the model parameters to all the user terminals. In an embodiment, the server transmits the model parameters through a semi-homomorphic encryption algorithm when broadcasting the model parameters to the ue.
The user terminal receives the initialized model parameters, and updates the model parameters of the primary logistic regression model; at the moment, iterative training is carried out based on the body temperature rhythm characteristic data, so that model parameters are continuously optimized and updated, and updated model parameters are obtained
Specifically, the logistic regression model on the user terminal is iteratedLine gradient
Calculating to update the model parameters
Wherein the content of the first and second substances,
as described in the above step S3, each of the user terminals respectively updates the model parameters
And sending it to the server, which receives the model parameters sent by all the user terminals
Performing aggregation operation to obtain weighted average model parameters
It can be understood that, when the user terminal sends the updated model parameter, the model parameter can also be transmitted by using a semi-homomorphic encryption algorithm.
When the server determines that the training of the model at each ue is finished, as described in step S4 above, the server broadcasts to each ue to stop training and sends the weighted average model parameters to each ue. And after receiving the weighted average model parameters, the user terminal updates the logistic regression model according to the weighted average model parameters and stops training to obtain a detection model for detecting the body temperature rhythm characteristic data. The detection model can be used for detecting the depression of a new user, diagnosis can be implemented through remote medical treatment, and the user does not need to queue and register for medical treatment; the method has the advantages that the method is based on a scientific diagnosis mode of data, subjective diagnosis is eliminated, and diseases are found; the user can secretly carry out independent self-test, and personal data is ensured by a private party.
In an embodiment, after step S4, in which each of the user terminals receives the weighted average model parameter sent by the server, updates the logistic regression model according to the weighted average model parameter, and stops model training to obtain a detection model for detecting body temperature rhythm characteristic data, the method includes:
step S5, the user terminal collects the continuous body temperature data of the new user and correspondingly analyzes the body temperature rhythm characteristic data of the collected continuous body temperature data of the new user;
and step S6, inputting the body temperature rhythm characteristic data of the continuous body temperature data of the new user into the detection model to obtain a prediction result as a detection result of the new user.
In this embodiment, depression can be detected for a new user by using the detection model obtained by the training, specifically, continuous body temperature data is collected by an intelligent temperature detector worn by the new user, and corresponding body temperature rhythm characteristic data is obtained by analysis based on a cosine analysis method. And then, inputting the obtained body temperature rhythm characteristic data into a corresponding detection model on the user terminal, and outputting a corresponding result. The process of analyzing the corresponding body temperature rhythm characteristic data by the cosine analysis method is consistent with the step S1, and is not repeated herein.
In an embodiment, after the step S2 of inputting the corresponding body temperature rhythm characteristic data into a logistic regression model for training to update model parameters, the method includes:
step S2a, each user terminal sends the current loss value of the loss function of the logistic regression model to the server, so as to determine whether the model is trained or not through the loss value sent by the server based on each user terminal; the server is used for receiving the loss value, judging whether a loss function on the server is converged according to the loss value, and determining that the model training is finished by the server when the loss function on the server is converged.
In this embodiment, the user terminal sends the updated loss values to the server, the server performs aggregation operation on the loss values, and when a loss function on the server converges, it is determined that the model training is finished; in other embodiments, when the training times have reached the maximum, the server determines that the model training is finished.
In an embodiment, the calculation formula of the loss function of the logistic regression model on the user terminal is as follows:
wherein the content of the first and second substances,
is a loss value, xiAs body temperature data, yiFor the output value of the logistic regression model, the loss function on the server side is:
in an embodiment, in the step S5, after the step of acquiring continuous body temperature data of the new user by the user terminal, the method includes:
step S501, inputting the new user body temperature data into a preset clustering anomaly analysis model for clustering analysis to obtain a clustering analysis result;
step S502, inputting the body temperature data into a preset prediction analysis model for prediction to obtain a predicted temperature, and calculating a residual error value between the body temperature data of the new user and the predicted temperature; comparing the residual value with a preset value, and outputting a prediction analysis result;
step S503, comparing whether the cluster analysis result is the same as the prediction analysis result; and when the clustering analysis result and the prediction analysis result are both results of normal body temperature data, entering the body temperature rhythm characteristic data of the new user continuous body temperature data acquired by corresponding analysis.
In this embodiment, before analyzing the collected body temperature rhythm characteristic data of the continuous body temperature data of the new user, it is further required to determine whether the body temperature data of the new user is normal, for example, when the user is in a fever state, the analysis of the body temperature rhythm characteristic of the new user is obviously affected.
Therefore, in this embodiment, the preset clustering abnormality analysis model and the prediction analysis model are adopted to jointly perform abnormality judgment on the body temperature data of the new user, and only when the results predicted by the two models are consistent, the results are used as the judgment result of whether the body temperature data of the new user is abnormal, so as to improve the accuracy of the judgment. The prediction analysis model and the clustering abnormity analysis model are obtained by training in advance based on body temperature data of a normal user.
In an embodiment, the training process of the predictive analysis model and the cluster anomaly analysis model includes:
a. collecting a plurality of normal body temperature data of a normal user;
b. calculating the average value and standard deviation of the plurality of normal body temperature data, subtracting the average value from each normal body temperature data, and dividing the average value by the standard deviation to obtain corresponding body temperature processing data;
c. for the body temperature processing data, establishing the clustering anomaly analysis model using density clustering analysis, and establishing the predictive analysis model using regression prediction.
Referring to fig. 2, an embodiment of the present application further provides an apparatus for model training based on body temperature data, including:
the first acquisition unit 10 is used for acquiring continuous body temperature data of sample users on each user terminal respectively and analyzing the body temperature rhythm characteristic data of the acquired body temperature data correspondingly;
a training unit 20, configured to input the corresponding body temperature rhythm characteristic data into a logistic regression model for training on each user terminal, so as to update model parameters;
the sending unit 30 is configured to send the updated model parameters to the server by each user terminal when the server determines that the model training is finished, so as to perform aggregation operation on the model parameters sent by all the user terminals through the server, and obtain weighted average model parameters;
the updating unit 40 is configured to receive, by each user terminal, the weighted average model parameter sent by the server, update the logistic regression model according to the weighted average model parameter, and stop model training to obtain a detection model for detecting body temperature rhythm characteristic data; the detection model is used for automatically analyzing the body temperature data of the user when the body temperature data of the user is collected.
In one embodiment, the apparatus further comprises:
the second acquisition unit is used for acquiring the continuous body temperature data of the new user on the user terminal and correspondingly analyzing the acquired body temperature rhythm characteristic data of the continuous body temperature data of the new user;
and the prediction unit is used for inputting the body temperature rhythm characteristic data of the continuous body temperature data of the new user into the detection model to obtain a prediction result as a detection result of the new user.
In one embodiment, the apparatus further comprises:
a loss sending unit, configured to send, by each ue, a current loss value of a loss function of the logistic regression model to the server, so as to determine whether the model is trained completely according to the loss value sent by the server based on each ue; the server is used for receiving the loss value, judging whether a loss function on the server is converged according to the loss value, and determining that the model training is finished by the server when the loss function on the server is converged.
In one embodiment, the apparatus further comprises:
the calculation formula of the loss function of the logistic regression model on the user terminal is as follows:
wherein L is a loss value of the logistic regression model, xiAs body temperature data, yiFor the output value of the logistic regression model, the loss function on the server side is:
in one embodiment, the apparatus further comprises:
the cluster analysis unit is used for inputting the new user body temperature data into a preset cluster anomaly analysis model for cluster analysis to obtain a cluster analysis result;
the temperature prediction unit is used for inputting the body temperature data into a preset prediction analysis model for prediction to obtain a predicted temperature, and calculating a residual error value between the body temperature data of the new user and the predicted temperature; comparing the residual value with a preset value, and outputting a prediction analysis result;
a comparison unit for comparing whether the cluster analysis result is the same as the prediction analysis result; and when the clustering analysis result and the prediction analysis result are both results of normal body temperature data, entering the body temperature rhythm characteristic data of the new user continuous body temperature data acquired by corresponding analysis.
In an embodiment, the training process of the predictive analysis model and the cluster anomaly analysis model includes:
collecting a plurality of normal body temperature data of a normal user;
calculating the average value and standard deviation of the plurality of normal body temperature data, subtracting the average value from each normal body temperature data, and dividing the average value by the standard deviation to obtain corresponding body temperature processing data;
for the body temperature processing data, establishing the clustering anomaly analysis model using density clustering analysis, and establishing the predictive analysis model using regression prediction.
In this embodiment, please refer to the method described in the above embodiment for specific implementation of each unit, which is not described herein again.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing body temperature data, detection models and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method for model training based on body temperature data.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
An embodiment of the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for model training based on body temperature data. It is to be understood that the computer-readable storage medium in the present embodiment may be a volatile-readable storage medium or a non-volatile-readable storage medium.
In summary, in the method, the apparatus, the computer device and the storage medium for model training based on body temperature data provided in the embodiments of the present application, each user terminal respectively collects continuous body temperature data of a sample user, and correspondingly analyzes the collected body temperature rhythm characteristic data of the body temperature data; respectively inputting the parameters into a logistic regression model for training so as to update the model parameters; when the server determines that the model training is finished, each user terminal sends the updated model parameters to the server, so that the server performs aggregation operation on the model parameters sent by all the user terminals to obtain weighted average model parameters; and updating the logistic regression model according to the weighted average model parameters and stopping model training to obtain a detection model for detecting the body temperature rhythm characteristic data. Training obtains detection model in this application and is convenient for carry out the physical sign characteristic of analysis user from body temperature data, is convenient for carry out analysis processes to body temperature rhythm characteristic data based on this detection model.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only for the preferred embodiment of the present application and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.
Claims (10)
1. A method for model training based on body temperature data is characterized by comprising the following steps:
each user terminal respectively collects continuous body temperature data of a sample user and correspondingly analyzes the body temperature rhythm characteristic data of the collected body temperature data;
each user terminal inputs the corresponding body temperature rhythm characteristic data into a logistic regression model for training so as to update model parameters;
when the server determines that the model training is finished, each user terminal sends the updated model parameters to the server, so that the server performs aggregation operation on the model parameters sent by all the user terminals to obtain weighted average model parameters;
each user terminal receives the weighted average model parameters sent by the server terminal, updates the logistic regression model according to the weighted average model parameters and stops model training to obtain a detection model for detecting body temperature rhythm characteristic data; the detection model is used for automatically analyzing the body temperature data of the user when the body temperature data of the user is collected.
2. The method of claim 1, wherein after the step of receiving the weighted average model parameters from the server, updating the logistic regression model according to the weighted average model parameters and stopping model training to obtain a detection model for detecting the body temperature rhythm characteristic data, the method comprises:
the user terminal collects continuous body temperature data of a new user and correspondingly analyzes the body temperature rhythm characteristic data of the collected continuous body temperature data of the new user;
and inputting the body temperature rhythm characteristic data of the continuous body temperature data of the new user into the detection model to obtain a prediction result as a detection result of the new user.
3. The method of claim 1, wherein the step of inputting the corresponding body temperature rhythm characteristic data into a logistic regression model for training by each user terminal to update the model parameters comprises:
each user terminal sends the current loss value of the loss function of the logistic regression model to the server, so that whether the model is trained or not is determined according to the loss value sent by each user terminal by the server; the server is used for receiving the loss value, judging whether a loss function on the server is converged according to the loss value, and determining that the model training is finished by the server when the loss function on the server is converged.
4. The method of claim 3, wherein the logistic regression model loss function at the user terminal is calculated as:
wherein L is a loss value of the logistic regression model, xiAs body temperature data, yiFor the output value of the logistic regression model, the loss function on the server side is:
5. the method of claim 2, wherein the step of the user terminal acquiring continuous body temperature data of the new user is followed by the steps of:
inputting the new user body temperature data into a preset clustering anomaly analysis model for clustering analysis to obtain a clustering analysis result;
inputting the body temperature data into a preset prediction analysis model for prediction to obtain a predicted temperature, and calculating a residual error value between the body temperature data of the new user and the predicted temperature; comparing the residual value with a preset value, and outputting a prediction analysis result;
comparing whether the clustering analysis result is the same as the prediction analysis result; and when the clustering analysis result and the prediction analysis result are both results of normal body temperature data, entering the body temperature rhythm characteristic data of the new user continuous body temperature data acquired by corresponding analysis.
6. The method of claim 5, wherein the training process of the predictive analysis model and the cluster anomaly analysis model comprises:
collecting a plurality of normal body temperature data of a normal user;
calculating the average value and standard deviation of the plurality of normal body temperature data, subtracting the average value from each normal body temperature data, and dividing the average value by the standard deviation to obtain corresponding body temperature processing data;
for the body temperature processing data, establishing the clustering anomaly analysis model using density clustering analysis, and establishing the predictive analysis model using regression prediction.
7. An apparatus for model training based on body temperature data, comprising:
the first acquisition unit is used for acquiring continuous body temperature data of a sample user on each user terminal respectively and analyzing the body temperature rhythm characteristic data of the acquired body temperature data correspondingly;
the training unit is used for inputting the corresponding body temperature rhythm characteristic data into a logistic regression model for training on each user terminal so as to update model parameters;
the sending unit is used for sending the updated model parameters to the server by each user terminal when the server determines that the model training is finished, so as to perform aggregation operation on the model parameters sent by all the user terminals through the server to obtain weighted average model parameters;
the updating unit is used for receiving the weighted average model parameters sent by the server terminal by each user terminal, updating the logistic regression model according to the weighted average model parameters and stopping model training to obtain a detection model for detecting the body temperature rhythm characteristic data; the detection model is used for automatically analyzing the body temperature data of the user when the body temperature data of the user is collected.
8. The apparatus for model training based on body temperature data of claim 7, further comprising:
the second acquisition unit is used for acquiring the continuous body temperature data of the new user on the user terminal and correspondingly analyzing the acquired body temperature rhythm characteristic data of the continuous body temperature data of the new user;
and the prediction unit is used for inputting the body temperature rhythm characteristic data of the continuous body temperature data of the new user into the detection model to obtain a prediction result as a detection result of the new user.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010900302.XA CN111986804A (en) | 2020-08-31 | 2020-08-31 | Method and device for model training based on body temperature data and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010900302.XA CN111986804A (en) | 2020-08-31 | 2020-08-31 | Method and device for model training based on body temperature data and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111986804A true CN111986804A (en) | 2020-11-24 |
Family
ID=73447013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010900302.XA Pending CN111986804A (en) | 2020-08-31 | 2020-08-31 | Method and device for model training based on body temperature data and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111986804A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113704778A (en) * | 2021-07-16 | 2021-11-26 | 杭州医康慧联科技股份有限公司 | Machine learning linear model prediction method based on homomorphic encryption |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886417A (en) * | 2019-03-01 | 2019-06-14 | 深圳前海微众银行股份有限公司 | Model parameter training method, device, equipment and medium based on federation's study |
| CN110490251A (en) * | 2019-03-08 | 2019-11-22 | 腾讯科技（深圳）有限公司 | Prediction disaggregated model acquisition methods and device, storage medium based on artificial intelligence |
| CN110517774A (en) * | 2019-08-06 | 2019-11-29 | 国云科技股份有限公司 | A method of prediction abnormal body temperature |
| CN110991905A (en) * | 2019-12-05 | 2020-04-10 | 支付宝(杭州)信息技术有限公司 | Risk model training method and device |
| CN111191773A (en) * | 2020-01-07 | 2020-05-22 | 泰康保险集团股份有限公司 | Method, apparatus, medium, and device for updating network parameters of information prediction network |
| CN111275207A (en) * | 2020-02-10 | 2020-06-12 | 深圳前海微众银行股份有限公司 | Semi-supervision-based horizontal federal learning optimization method, equipment and storage medium |
| CN111403024A (en) * | 2019-01-02 | 2020-07-10 | 天津幸福生命科技有限公司 | Method and device for obtaining disease judgment model based on medical data |
-
2020
- 2020-08-31 CN CN202010900302.XA patent/CN111986804A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111403024A (en) * | 2019-01-02 | 2020-07-10 | 天津幸福生命科技有限公司 | Method and device for obtaining disease judgment model based on medical data |
| CN109886417A (en) * | 2019-03-01 | 2019-06-14 | 深圳前海微众银行股份有限公司 | Model parameter training method, device, equipment and medium based on federation's study |
| CN110490251A (en) * | 2019-03-08 | 2019-11-22 | 腾讯科技（深圳）有限公司 | Prediction disaggregated model acquisition methods and device, storage medium based on artificial intelligence |
| CN110517774A (en) * | 2019-08-06 | 2019-11-29 | 国云科技股份有限公司 | A method of prediction abnormal body temperature |
| CN110991905A (en) * | 2019-12-05 | 2020-04-10 | 支付宝(杭州)信息技术有限公司 | Risk model training method and device |
| CN111191773A (en) * | 2020-01-07 | 2020-05-22 | 泰康保险集团股份有限公司 | Method, apparatus, medium, and device for updating network parameters of information prediction network |
| CN111275207A (en) * | 2020-02-10 | 2020-06-12 | 深圳前海微众银行股份有限公司 | Semi-supervision-based horizontal federal learning optimization method, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113704778A (en) * | 2021-07-16 | 2021-11-26 | 杭州医康慧联科技股份有限公司 | Machine learning linear model prediction method based on homomorphic encryption |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020220545A1 (en) | Long short-term memory model-based disease prediction method and apparatus, and computer device | |
| CN110334722B (en) | Image classification method and device, computer equipment and storage medium | |
| CN110752035A (en) | Health data processing method and device, computer equipment and storage medium | |
| WO2019232851A1 (en) | Method and apparatus for training speech differentiation model, and computer device and storage medium | |
| CN112017789B (en) | Triage data processing method, triage data processing device, triage data processing equipment and triage data processing medium | |
| CN112035674B (en) | Diagnosis guiding data acquisition method, device, computer equipment and storage medium | |
| CN114041796B (en) | Concentration assessment method and device based on brain wave signal and storage medium | |
| CN111862020A (en) | Method, device, server and storage medium for predicting physiological age of anterior segment | |
| US20220165417A1 (en) | Population-level gaussian processes for clinical time series forecasting | |
| CN111008643A (en) | Image classification method and device based on semi-supervised learning and computer equipment | |
| CN112801224A (en) | Diabetes typing probability prediction method, device, equipment and storage medium | |
| CN116863522A (en) | Acne grading method, device, equipment and medium | |
| CN111986804A (en) | Method and device for model training based on body temperature data and computer equipment | |
| CN111759304A (en) | Electrocardiogram abnormity identification method and device, computer equipment and storage medium | |
| CN113012803A (en) | Computer device, system, readable storage medium and medical data analysis method | |
| CN110555846A (en) | full-automatic bone age assessment method based on convolutional neural network | |
| CN111354463A (en) | Human health measuring method, device, computer equipment and storage medium | |
| CN111317458A (en) | Blood pressure detection system based on deep learning | |
| CN112036750A (en) | Abnormity identification method, device, equipment and storage medium suitable for medical wind control | |
| CN111657921A (en) | Real-time electrocardio abnormality monitoring method and device, computer equipment and storage medium | |
| CN115662595A (en) | User information management method and system based on online diagnosis and treatment system | |
| CN112397179A (en) | Medical electrocardiogram intelligent analysis system and analysis method | |
| CN111241084A (en) | Medical information cleaning method, device, computer equipment and storage medium | |
| CN113724898A (en) | Intelligent inquiry method, device, equipment and storage medium | |
| CN112957018A (en) | Heart state detection method and device based on artificial intelligence |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220520 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Block H, 666 Beijing East Road, Huangpu District, Shanghai 200000 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |