Method and apparatus for generating user health profiles based on wearable devices

Abstract

This application relates to a method and apparatus for generating user health profiles based on wearable devices. The specific solution includes: acquiring multi-source vital sign data of an object; fusing the multi-source vital sign data to obtain fused data; determining the data type of the multi-source vital sign data; updating a pre-constructed conventional user profile of the object based on the fused data if the multi-source vital sign data is normal data; and generating a biased user profile based on the fused data if the multi-source vital sign data is abnormal data. This application improves the accuracy of user profiles.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and apparatus for generating user health profiles based on wearable devices. Background Technology

[0002] In related technologies, user profiling methods mostly rely on users actively using relevant devices and apps to collect data and build behavioral habit profiles. Few methods can be combined with wearable devices, resulting in a lack of real-time data updates. On the other hand, most user profiling methods use single batches of data to build user profiles independently, failing to utilize long-term and real-time data, leading to low profile scalability. Finally, user profiling methods only extract features and build profiles based on users' current physical and behavioral characteristics, making it impossible to cope with rapid deviations in user characteristics in the short term caused by factors such as illness or changes in behavioral habits, thus resulting in an overall biased profile. Summary of the Invention

[0003] Therefore, this application provides a method and apparatus for generating user health profiles based on wearable devices. The technical solution of this application is as follows:

[0004] According to a first aspect of the embodiments of this application, a method for generating a user health profile based on a wearable device is provided, the method comprising:

[0005] Obtain multi-source vital sign data of the object;

[0006] The multi-source vital sign data are fused to obtain fused data;

[0007] Determine the data type of the multi-source vital sign data; the data type includes normal data and abnormal data;

[0008] In response to the fact that the data type of the multi-source vital signs data is normal data, the pre-constructed user profile of the object is updated based on the fused data;

[0009] In response to the fact that the data type of the multi-source vital signs data is abnormal data, a user bias profile is generated based on the fused data.

[0010] According to one embodiment of this application, the multi-source vital sign data of the object includes the vital sign status of the object; determining the data type of the multi-source vital sign data includes:

[0011] Based on the multi-source vital sign data of the object, the vital sign status of the object is obtained;

[0012] In response to the abnormal state of the vital signs, the type of the multi-source vital signs data is determined to be abnormal data;

[0013] In response to the condition that the vital signs are in a normal state, the type of the multi-source vital signs data is determined to be normal data.

[0014] According to one embodiment of this application, the step of generating a user bias profile based on the fused data in response to the data type of the multi-source vital signs being anomalous data further includes:

[0015] In response to the fact that the data type of the multi-source vital signs data is abnormal data, the vital signs status is determined as the first label corresponding to the multi-source vital signs data;

[0016] Find the user bias profile corresponding to the first tag;

[0017] In response to finding the user bias profile corresponding to the first tag, the user bias profile corresponding to the first tag is updated based on the fused data;

[0018] In response to the absence of a user bias profile corresponding to the tag, a user bias profile corresponding to the first tag is generated based on the fused data.

[0019] According to one embodiment of this application, determining the data type of the multi-source vital sign data further includes:

[0020] In response to receiving an abnormal data time period and a second tag corresponding to the abnormal data time period sent by the client, the data type of the multi-source vital signs data corresponding to the abnormal data time period is determined to be abnormal data.

[0021] According to one embodiment of this application, the step of generating a user bias profile based on the fused data in response to the multi-source vital sign data being abnormal data further includes:

[0022] In response to the fact that the multi-source vital sign data is abnormal data, the user bias profile corresponding to the second label is searched.

[0023] In response to finding the user bias profile corresponding to the second label, the user bias profile corresponding to the second label is updated based on the fused data;

[0024] In response to the absence of a user bias profile corresponding to the second label, a user bias profile corresponding to the second label is generated based on the fused data.

[0025] According to one embodiment of this application, after determining that the data type of the multi-source vital signs data corresponding to the abnormal data time period is abnormal data in response to receiving the abnormal data time period sent by the client and the second tag corresponding to the abnormal data time period, the method further includes:

[0026] In response to the fact that the user's regular profile has been updated based on the multi-source vital sign data corresponding to the abnormal data time period, the updated user's regular profile is adjusted to the user's regular profile before the update.

[0027] According to a second aspect of the embodiments of this application, a user health profile generation device based on a wearable device is provided, the device comprising:

[0028] The acquisition module is used to acquire multi-source vital sign data of an object;

[0029] The fusion module is used to perform fusion processing on the multi-source vital sign data to obtain fused data;

[0030] A determination module is used to determine the data type of the multi-source vital sign data; the data type includes normal data and abnormal data.

[0031] The update module is used to update the pre-built user profile of the object based on the fused data in response to the data type of the multi-source vital signs data being normal data.

[0032] The generation module is used to generate a user bias profile based on the fused data in response to the data type of the multi-source vital signs data being abnormal data.

[0033] According to a third aspect of the embodiments of this application, an electronic device is provided, including: a processor, and a memory communicatively connected to the processor;

[0034] The memory stores computer-executed instructions;

[0035] The processor executes computer execution instructions stored in the memory to implement the method as described in any one of the first aspects.

[0036] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein computer execution instructions are stored therein, and when executed by a processor, the computer execution instructions are used to implement the method as described in any one of the first aspects.

[0037] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in any one of the first aspects.

[0038] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0039] By acquiring multi-source vital sign data of an object; fusing the multi-source vital sign data to obtain fused data; determining the data type of the multi-source vital sign data; updating the pre-built user profile of the object based on the fused data when the multi-source vital sign data is normal; and generating a user bias profile based on the fused data when the multi-source vital sign data is abnormal, the system ensures timely updates to user profiles while improving their accuracy. Furthermore, by constructing both a regular user profile and a user bias profile for the same object, the system can more accurately understand the object's physical condition in both healthy and diseased states, thereby enhancing the effectiveness of downstream early warning functions.

[0040] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0042] Figure 1 This is a flowchart of a user health profile generation method based on wearable devices in an embodiment of this application;

[0043] Figure 2 This is a flowchart of another user health profile generation method based on wearable devices in the embodiments of this application;

[0044] Figure 3 This is a structural block diagram of a user health profile generation device based on a wearable device, as described in an embodiment of this application.

[0045] Figure 4 This is a block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0047] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0048] It's important to note that wearable devices can monitor users' vital signs in real time, such as heart rate, blood oxygen saturation, heart rate variability, body temperature, and activity levels, enabling real-time monitoring of individual health. This vital sign information can also be used to construct a user's personal health profile, which can then be applied to downstream recommendation and early warning scenarios. Generally, a user's personal health profile differs from traditional health profiles. Traditional user profiles focus on learning user behavior habits and personal characteristics to create tags, primarily used in product and service recommendation scenarios. In contrast, user health profiles utilize short-term or long-term health information to learn and construct the normal steady-state values ​​of different vital signs, thereby providing crucial patient health information in downstream disease early warning and assisted diagnosis scenarios, improving the effectiveness of subsequent applications. Current user profiling methods mostly rely on users actively using relevant devices and apps to collect data and build behavioral habit profiles. Few methods can be combined with wearable devices, resulting in a lack of real-time data updates. On the other hand, most current user profiling methods use single batches of data to build user profiles independently, failing to utilize long-term and real-time data, leading to low profile scalability. Finally, current user profiling methods extract features and build profiles based solely on users' current physical and behavioral characteristics, failing to address situations such as users developing illnesses or changes in behavioral habits that cause rapid deviations in user characteristics in the short term, thus resulting in an overall biased profile.

[0049] To address the aforementioned issues, this application proposes a method and apparatus for generating user health profiles based on wearable devices. This method involves: acquiring multi-source vital sign data of an individual; fusing the multi-source vital sign data to obtain fused data; determining the data type of the multi-source vital sign data; updating a pre-constructed user profile of the individual based on the fused data if the multi-source vital sign data is of normal type; and generating a user bias profile based on the fused data if the multi-source vital sign data is of abnormal type. This ensures timely updates to the user profile while improving its accuracy. Furthermore, by constructing both a normal user profile and a user bias profile for the same individual, it is possible to more accurately understand the individual's physical condition in both healthy and diseased states, thereby enhancing the effectiveness of downstream early warning functions.

[0050] Figure 1 This is a flowchart of a user health profile generation method based on wearable devices in an embodiment of this application.

[0051] like Figure 1 As shown, the method for generating user health profiles based on wearable devices includes:

[0052] Step 101: Obtain multi-source vital sign data of the object.

[0053] As one possible implementation example, multi-source vital sign data can be collected by wearable devices, which can be any one or more of wristbands, watches, skin patches, and glasses. This multi-source vital sign data may include, but is not limited to, information such as body temperature, heart rate, heart rate variability, respiratory rate, blood oxygen saturation, activity level, and sleep patterns.

[0054] Step 102: Perform fusion processing on the multi-source vital sign data to obtain fused data.

[0055] As an example of a possible implementation, step 102 includes the following steps:

[0056] Step A1: Obtain the vital signs data of the object from various data sources during the first time period.

[0057] In this embodiment of the application, the vital signs data of each data source includes multiple vital sign values ​​and the collection time of each of the multiple vital sign values.

[0058] As a possible implementation example, the data collected from different sources during the first time period measured by the wearable device can be extracted. Sensor-collected data may include temperature calculated by a temperature sensor, activity frequency calculated by an accelerometer, respiratory rate calculated by a respiration sensor, heart rate calculated by an optical heart rate sensor, and blood oxygen saturation calculated by an optical blood oxygen sensor. Electrical signal data may include raw electrical signal waveforms such as PPG skin conductance signals, ECG electrocardiogram signals, EEG electroencephalogram signals, and EMG electromyogram signals. User information may include basic user information, corresponding App tracking information, and user health profiles. Public datasets may include various electrical signal datasets such as the MIT-BIH ECG dataset from the United States and the AHA ECG dataset for arrhythmias from the United States.

[0059] Step A2: Based on the collection time of each of the multiple vital signs, divide the vital sign data from each data source into multiple groups of sub-data according to the first preset duration.

[0060] In some embodiments of this application, there are multiple first preset durations. Step A2 specifically includes: for each first preset duration, according to the collection time of each of the multiple vital signs, the vital signs data of each data source are divided into multiple groups of sub-data according to the first preset duration.

[0061] Optionally, the first preset duration can be a duration pre-set according to actual needs.

[0062] As a possible implementation example, to increase the applicability of the integrated data, the vital sign data from each data source can be divided into sub-data of varying lengths according to different preset durations. For example, the first preset duration could be 5 minutes, 10 minutes, or 20 minutes, with the first time period being 2 hours. Based on the collection time of each of the multiple vital sign values, the vital sign data from each data source can be divided into 36 sub-data groups for every 5 minutes collected; 18 sub-data groups for every 10 minutes collected; and 9 sub-data groups for every 20 minutes collected.

[0063] Step A3: Based on the vital sign values ​​of multiple sub-data sets, determine the target indicator value for each sub-data set.

[0064] In some embodiments of this application, step A3 includes:

[0065] Step A31: Determine the type of each group of sub-data.

[0066] Step A32: Based on the type of each group of sub-data, determine the type of at least one target indicator value for each group of sub-data.

[0067] Understandably, vital sign data from different data sources belong to different types. Therefore, based on the specific type of each sub-data set, the type of at least one target indicator value for each sub-data set must be determined. For example, for all types of vital sign data, the following target indicator values ​​need to be calculated: mean, median, standard deviation, interquantile interval (IQR), kurtosis, skewness, number of measurement points, and binning percentage. If the vital sign data type is heart rate data, the target indicator value type also includes heart rate variability.

[0068] Step A33: Based on the phenotypic values ​​of the sub-data, calculate the target indicator value corresponding to each type of at least one target indicator value.

[0069] Step A4: Determine the sub-data belonging to the same acquisition time and the target index values ​​corresponding to each sub-data belonging to the same acquisition time as a set of fused sub-data.

[0070] Step A5: Determine the multiple sets of fused sub-data as fused data from multiple sources.

[0071] As an example of possible implementation, the server determines the sub-data belonging to the same collection time and the target indicator value corresponding to each sub-data belonging to the same collection time as a set of fused sub-data, and determines multiple sets of fused sub-data as fused data of multi-source data.

[0072] Step 103: Determine the data type of the multi-source vital signs data.

[0073] In this embodiment of the application, the data types include normal data and abnormal data.

[0074] In some embodiments of this application, the multi-source vital sign data of the object includes the vital sign status of the object, and step 103 includes:

[0075] Step a1: Obtain the object's vital sign status based on the object's multi-source vital sign data.

[0076] As an example of a possible implementation, multi-source vital sign data includes the vital sign status of an object, and the object's vital sign status can be obtained from the multi-source vital sign data. For example, if the multi-source vital sign data includes the object's medical history information, the object's vital sign status, such as fever or hypertension, can be obtained from the medical history information.

[0077] Step a2: In response to the abnormal state of vital signs, determine that the type of multi-source vital signs data is abnormal data.

[0078] As an example of a possible implementation, in response to a non-healthy state of vital signs, the state of vital signs is determined to be an abnormal state, and the type of multi-source vital signs data is determined to be abnormal data.

[0079] Step a3: In response to the vital signs being in a normal state, determine the type of the multi-source vital signs data as normal data.

[0080] As an example of a possible implementation, in response to the health status of vital signs, the vital signs status is determined to be normal, and then the type of multi-source vital signs data is determined to be normal data.

[0081] Step 104: In response to the fact that the data type of the multi-source vital signs data is normal data, the pre-built user profile of the object is updated based on the fused data.

[0082] As an example of a possible implementation, user profile updating is the process of updating a user's profile using newly collected normal data, based on an existing regular user profile. Depending on the statistical indicators used in the profile, the calculation methods differ; common methods for updating the mean and standard deviation are as follows:

[0083]

[0084]

[0085] Where m0 is the mean of vital signs before the portrait update, v0 is the standard deviation of vital signs before the portrait update, and n0 is the number of vital sign data points before the portrait update. All three data points are obtained from the established portrait; D n This is the new vital sign data queue, where n1 is the number of vital sign data entries in this queue, and both of these data are obtained from the newly collected data; m1 is the mean of vital signs after the portrait update, and v1 is the standard deviation of vital signs after the portrait update. The number of vital sign data entries in the portrait also needs to be updated.

[0086] Step 105: In response to the fact that the data type of the multi-source vital signs data is abnormal data, a user bias profile is generated based on the fused data.

[0087] In some embodiments of this application, step 105 includes:

[0088] Step b1: In response to the fact that the data type of the multi-source vital signs data is abnormal data, the vital signs status is determined as the first label corresponding to the multi-source vital signs data.

[0089] For example, if an object's vital signs state is fever, then the data type of the object's multi-source vital signs data is determined to be abnormal data, and fever is determined as the first label corresponding to the multi-source vital signs data.

[0090] Step b2: Locate the user bias profile corresponding to the first label.

[0091] Step b3: In response to finding the user bias profile corresponding to the first label, update the user bias profile corresponding to the first label based on the fused data.

[0092] As an example of a possible implementation, in response to finding a user bias profile corresponding to the first label, it indicates that a user bias profile corresponding to the first label has been established, and the user bias profile corresponding to the first label is updated based on the fused data.

[0093] Step b4: In response to the absence of a user bias profile corresponding to the tag, a user bias profile corresponding to the first tag is generated based on the fused data.

[0094] As an example of a possible implementation, in response to the absence of a user bias profile corresponding to the label, it indicates that a user bias profile corresponding to the first label has not yet been established. Therefore, a user bias profile corresponding to the first label is generated based on the fused data.

[0095] The user health profile generation method based on wearable devices according to embodiments of this application involves: acquiring multi-source vital sign data of an object; fusing the multi-source vital sign data to obtain fused data; determining the data type of the multi-source vital sign data; updating the pre-constructed user profile of the object based on the fused data in response to the data type of the multi-source vital sign data being normal data; and generating a user bias profile based on the fused data in response to the data type of the multi-source vital sign data being abnormal data. This ensures timely updates to the user profile while improving its accuracy. Furthermore, by constructing both a normal user profile and a user bias profile for the same object, the method can more accurately grasp the object's physical condition in both healthy and diseased states, while also enhancing the effectiveness of downstream early warning functions.

[0096] Figure 2 This is a flowchart of another user health profile generation method based on wearable devices in the embodiments of this application.

[0097] like Figure 2 As shown, the method for generating user health profiles based on wearable devices includes:

[0098] Step 201: Obtain multi-source vital sign data of the object.

[0099] In the embodiments of this application, step 201 can be implemented in any of the ways described in the various embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0100] Step 202: Perform fusion processing on the multi-source vital sign data to obtain fused data.

[0101] In the embodiments of this application, step 202 can be implemented in any of the ways described in the various embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0102] Step 203: Determine the data type of the multi-source vital signs data.

[0103] In this embodiment of the application, the data types include normal data and abnormal data.

[0104] In some embodiments of this application, step 203 includes: in response to receiving the abnormal data time period and the second tag corresponding to the abnormal data time period sent by the client, determining that the data type of the multi-source vital signs data corresponding to the abnormal data time period is abnormal data.

[0105] Optionally, the client can mark the start and end times and event types of abnormal events such as illness, so as to facilitate the subsequent statistical calculation of bias profiles based on when and why. The sources of marking can include, but are not limited to, user-selected data, automatic parsing of hospital medical records, and automatic classification through vital sign monitoring.

[0106] Step 204: In response to the fact that the user's regular profile has been updated based on the multi-source vital signs data corresponding to the abnormal data time period, the updated user's regular profile is adjusted to the user's regular profile before the update.

[0107] Optionally, you can select the start time after the event begins and the end time after the event ends, or you can select the start and end times all at once after the event ends.

[0108] As a possible implementation example, in response to the fact that the user's regular profile has been updated based on the multi-source vital signs data corresponding to the abnormal data period, and the user's regular profile has become biased, the updated user's regular profile is then backdated to the user's regular profile before the update, thereby removing the abnormal data from the user's regular profile and ensuring the accuracy of the user's regular profile.

[0109] Step 205: In response to the fact that the data type of the multi-source vital signs data is normal data, the pre-built user profile of the object is updated based on the fused data.

[0110] In the embodiments of this application, step 205 can be implemented in any of the ways described in the various embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0111] Step 206: In response to the fact that the data type of the multi-source vital signs data is abnormal data, a user bias profile is generated based on the fused data.

[0112] In some embodiments of this application, step 206 includes:

[0113] Step b1: In response to the multi-source vital signs data being abnormal, find the user bias profile corresponding to the second label.

[0114] Step b2: In response to finding the user bias profile corresponding to the second label, update the user bias profile corresponding to the second label based on the fused data.

[0115] As an example of a possible implementation, in response to finding a user bias profile corresponding to the second label, it indicates that a user bias profile corresponding to the second label has been established, and the user bias profile corresponding to the second label is updated based on the fused data.

[0116] Step b3: In response to the absence of a user bias profile corresponding to the second label, a user bias profile corresponding to the second label is generated based on the fused data.

[0117] As an example of a possible implementation, in response to the absence of a user bias profile corresponding to the label, it indicates that a user bias profile corresponding to the second label has not yet been established. Therefore, a user bias profile corresponding to the second label is generated based on the fused data.

[0118] According to the user health profile generation method based on wearable devices in this application, by responding to the received abnormal data time period and the second tag corresponding to the abnormal data time period sent by the client, the data type of the multi-source vital signs data corresponding to the abnormal data time period is determined to be abnormal data. This improves the flexibility of user bias profile construction and updating, enabling the generation of user bias profiles according to actual needs.

[0119] Figure 3 This is a structural block diagram of a user health profile generation device based on a wearable device, as described in an embodiment of this application.

[0120] like Figure 3 As shown, the user health profile generation device based on wearable devices includes:

[0121] Module 301 is used to acquire multi-source vital sign data of an object;

[0122] The fusion module 302 is used to fuse multi-source vital sign data to obtain fused data;

[0123] Module 303 is used to determine the data type of multi-source vital signs data; the data type includes normal data and abnormal data.

[0124] Update module 304 is used to update the pre-built user profile of the object based on the fused data in response to the data type of the multi-source vital signs data being normal data.

[0125] The generation module 305 is used to generate a user bias profile based on the fused data in response to the data type of the multi-source vital signs data being anomalous data.

[0126] The user health profile generation device based on wearable devices according to embodiments of this application acquires multi-source vital sign data of an object; fuses the multi-source vital sign data to obtain fused data; determines the data type of the multi-source vital sign data; updates the pre-constructed user profile of the object based on the fused data in response to the data type of the multi-source vital sign data being normal data; and generates a user bias profile based on the fused data in response to the data type of the multi-source vital sign data being abnormal data. This ensures timely updates to the user profile while improving its accuracy. Furthermore, by constructing both a normal user profile and a user bias profile for the same object, the device can more accurately grasp the object's physical condition in both healthy and diseased states, while also enhancing the effectiveness of downstream early warning functions.

[0127] Figure 4 This is a block diagram of an electronic device according to an embodiment of this application. For example... Figure 4 As shown, the electronic device may include: transceiver 41, processor 42, and memory 43.

[0128] Processor 42 executes computer execution instructions stored in memory, causing processor 42 to perform the scheme in the above embodiments. Processor 42 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0129] The memory 43 is connected to the processor 42 via the system bus and completes communication between them. The memory 43 is used to store computer program instructions.

[0130] Transceiver 41 can be used to obtain the task to be run and its configuration information.

[0131] The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. Transceivers are used to enable communication between database access devices and other computers (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and may also include non-volatile memory.

[0132] The electronic device provided in this application embodiment can be the terminal device described in the above embodiments.

[0133] This application also provides a chip for executing instructions, which is used to execute the message processing method described in the above embodiments.

[0134] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the message processing method described in the above embodiments.

[0135] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, it can implement the technical solution of the message processing method in the above embodiments.

[0136] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0137] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for generating user health profiles based on wearable devices, characterized in that, The method includes: Obtain multi-source vital sign data of the object; The multi-source vital sign data are fused to obtain fused data; Determine the data type of the multi-source vital sign data; the data type includes normal data and abnormal data; In response to the fact that the data type of the multi-source vital signs data is normal data, the pre-constructed user profile of the object is updated based on the fused data; In response to the fact that the data type of the multi-source vital signs data is abnormal data, a user bias profile is generated based on the fused data; Wherein, the multi-source vital sign data of the object includes the vital sign status of the object; determining the data type of the multi-source vital sign data includes: Based on the multi-source vital sign data of the object, the vital sign status of the object is obtained; In response to the abnormal state of the vital signs, the type of the multi-source vital signs data is determined to be abnormal data; In response to the condition that the vital signs are in a normal state, the type of the multi-source vital signs data is determined to be normal data; Wherein, the data type of the multi-source vital sign data is abnormal data, and the user bias profile is generated based on the fused data, the method further includes: In response to the fact that the data type of the multi-source vital signs data is abnormal data, the vital signs status is determined as the first label corresponding to the multi-source vital signs data; Find the user bias profile corresponding to the first tag; In response to finding the user bias profile corresponding to the first tag, the user bias profile corresponding to the first tag is updated based on the fused data; In response to the absence of a user bias profile corresponding to the tag, a user bias profile corresponding to the first tag is generated based on the fused data.

2. The method according to claim 1, characterized in that, The step of determining the data type of the multi-source vital signs data further includes: In response to receiving an abnormal data time period and a second tag corresponding to the abnormal data time period sent by the client, the data type of the multi-source vital signs data corresponding to the abnormal data time period is determined to be abnormal data.

3. The method according to claim 2, characterized in that, The step of generating a user bias profile based on the fused data in response to the multi-source vital sign data being abnormal data further includes: In response to the fact that the multi-source vital sign data is abnormal data, the user bias profile corresponding to the second label is searched. In response to finding the user bias profile corresponding to the second label, the user bias profile corresponding to the second label is updated based on the fused data; In response to the absence of a user bias profile corresponding to the second label, a user bias profile corresponding to the second label is generated based on the fused data.

4. The method according to claim 2, characterized in that, After determining that the data type of the multi-source vital signs data corresponding to the abnormal data time period is abnormal data in response to receiving the abnormal data time period sent by the client and the second tag corresponding to the abnormal data time period, the method further includes: In response to the fact that the user's regular profile has been updated based on the multi-source vital sign data corresponding to the abnormal data time period, the updated user's regular profile is adjusted to the user's regular profile before the update.

5. A user health profile generation device based on wearable devices, characterized in that, The apparatus comprising the method according to any one of claims 1-4, wherein the apparatus includes: The acquisition module is used to acquire multi-source vital sign data of an object; The fusion module is used to perform fusion processing on the multi-source vital sign data to obtain fused data; A determination module is used to determine the data type of the multi-source vital sign data; the data type includes normal data and abnormal data. The update module is used to update the pre-built user profile of the object based on the fused data in response to the data type of the multi-source vital signs data being normal data. The generation module is used to generate a user bias profile based on the fused data in response to the data type of the multi-source vital signs data being abnormal data.

6. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-4.

8. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-4.

Images