Data processing method and device, electronic equipment and computer readable storage medium

Abstract

The invention discloses a data processing method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: receiving corresponding monitoring data from a plurality of pieces of monitoring equipment, and obtaining a plurality of pieces of monitoring data which are data for monitoring user behaviors; feature data in the multiple pieces of monitoring data are extracted, multiple pieces of target feature data are obtained, and the feature data are data representing user behavior features in the monitoring data; fusing the multiple pieces of target feature data to obtain target fused data; and obtaining a monitoring result corresponding to the user behavior according to the target fusion data. Therefore, the accuracy and the reliability of the monitoring data for processing and analyzing are improved, and the intelligent level and the service effect of the home system for the user service are improved.

Description

Technical Field

[0001] This application relates to the technical field of smart home, and specifically to a data processing method, apparatus, electronic device, and computer-readable storage medium. Background Art

[0002] With the continuous development of smart home technology, the intelligence of home devices has been significantly improved. Monitoring the behavior data of users through home devices has become a technical hotspot in the smart home field. How to process the behavior data of users in a smart home system to improve the service effect of the home system has become a technical problem to be solved urgently. Summary of the Invention

[0003] Embodiments of this application provide a data processing method, apparatus, electronic device, and computer-readable storage medium, which can improve the service effect of the home system.

[0004] In a first aspect, embodiments of this application disclose a data processing method, including:

[0005] Receiving monitoring data corresponding to multiple monitoring devices respectively to obtain a plurality of monitoring data, where the monitoring data is data for monitoring user behavior;

[0006] Extracting feature data from the plurality of monitoring data respectively to obtain a plurality of target feature data, where the feature data is data representing user behavior characteristics in the monitoring data;

[0007] Fusing the plurality of target feature data to obtain target fusion data;

[0008] Analyzing the target fusion data to obtain a monitoring result corresponding to the user behavior.

[0009] In a second aspect, embodiments of this application disclose a data processing apparatus, including:

[0010] A receiving unit, configured to receive monitoring data corresponding to multiple monitoring devices respectively to obtain a plurality of monitoring data, where the monitoring data is data for monitoring user behavior;

[0011] An extracting unit, configured to extract feature data from the plurality of monitoring data respectively to obtain a plurality of target feature data, where the feature data is data representing user behavior characteristics in the monitoring data;

[0012] A fusing unit, configured to fuse the plurality of target feature data to obtain target fusion data;

[0013] An analyzing unit, configured to analyze the target fusion data to obtain a monitoring result corresponding to the user behavior.

[0014] In some embodiments, the data processing apparatus further comprises:

[0015] The output unit is used to determine the corresponding behavior strategy according to the monitoring results and output the behavior strategy; or to generate the corresponding analysis chart according to the monitoring results and output the analysis chart; or to determine the corresponding device coordination strategy according to the monitoring results and output the device coordination strategy.

[0016] In some embodiments, the data processing apparatus further comprises:

[0017] A preprocessing unit is used to determine the data type of multiple monitoring data; it is also used to detect the continuity of target monitoring data when the data type of the target monitoring data is the target type, and the target monitoring data is any monitoring data among the multiple monitoring data; it is also used to eliminate the data in the target monitoring data that does not meet the preset continuity conditions when the continuity of the target monitoring data does not meet the preset continuity conditions, so as to obtain processed monitoring data.

[0018] In some embodiments, the extraction unit is further used to: extract feature data from the processed monitoring data respectively to obtain multiple target feature data.

[0019] In some embodiments, the extraction unit is further used to: extract feature data that meets preset conditions in each of the multiple monitoring data to obtain multiple feature data; and perform standardization processing on the multiple feature data to obtain multiple target feature data.

[0020] In some embodiments, the fusion unit is also used to: determine the weighted ratio corresponding to each monitoring device according to the device priority corresponding to each monitoring device in multiple monitoring devices, and the weighted ratio is used to fuse the target feature data corresponding to each monitoring device; according to the weighted ratio, fuse multiple target feature data to obtain target fusion data.

[0021] In some embodiments, the data processing apparatus further comprises:

[0022] The division unit is used to determine the division reference points corresponding to the target fusion data according to the credibility of different time periods; and is also used to divide the target fusion data according to the division reference points to obtain the target fusion data of multiple time periods.

[0023] In some embodiments, the data processing apparatus further comprises:

[0024] The adjustment unit is used to receive user feedback information on the monitoring results; and is also used to adjust the monitoring results according to the feedback information.

[0025] In some embodiments, the adjustment unit is further configured to: adjust the device priorities corresponding to multiple monitoring devices according to the feedback information; adjust the weighted ratios corresponding to the device priorities according to the adjusted device priorities of the multiple monitoring devices; fuse the multiple target feature data corresponding to the multiple monitoring devices according to the adjusted weighted ratios to obtain adjusted fused data; and analyze the adjusted fused data to obtain corresponding adjusted monitoring results.

[0026] In a third aspect, an embodiment of the present application discloses an electronic device, which includes a processor and a memory. The memory stores a computer program, and the processor calls the computer program to implement the above data processing method.

[0027] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, in which program code is stored, and the program code can be called by a processor to implement the above data processing method.

[0028] In a fifth aspect, an embodiment of the present application discloses a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium.

[0029] In the embodiments of the present application, multiple monitoring data can be obtained by respectively receiving the monitoring data corresponding to multiple monitoring devices. The monitoring data is data for monitoring user behavior; the feature data in the multiple monitoring data can be respectively extracted to obtain multiple target feature data. The feature data is data representing user behavior characteristics in the monitoring data; the multiple target feature data is fused to obtain target fused data; and the monitoring result corresponding to the user behavior is obtained from the target fused data. In this way, the home system can improve the accuracy and reliability of the monitoring data for processing and analysis by receiving the monitoring data from multiple monitoring devices. It can also fuse the monitoring data from multiple monitoring devices to obtain the fused target fused data, and analyze the target fused data to determine the detection result corresponding to the user behavior, thereby improving the intelligent level and service effect of the home system for user services. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is a schematic diagram of a system architecture of a home system provided by an embodiment of the present application;

[0032] Figure 2 It is a schematic flowchart of a data processing method disclosed in an embodiment of the present application;

[0033] Figure 2A It is a schematic scenario diagram of a data processing method disclosed in an embodiment of the present application;

[0034] Figure 3 It is another schematic flowchart of a data processing method disclosed in an embodiment of the present application;

[0035] Figure 3A It is another schematic scenario diagram of a data processing method disclosed in an embodiment of the present application;

[0036] Figure 3B It is another schematic scenario diagram of a data processing method disclosed in an embodiment of the present application;

[0037] Figure 3C It is a schematic flowchart of a data processing method disclosed in an embodiment of the present application;

[0038] Figure 4 It is a schematic structural diagram of a data processing device disclosed in an embodiment of the present application;

[0039] Figure 5 It is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application;

[0040] Figure 6 It is a schematic structural diagram of a computer-readable storage medium disclosed in an embodiment of the present application. Detailed implementation manners

[0041] The following details the implementation manners of the present application. The examples of the implementation manners are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The implementation manners described below by referring to the accompanying drawings are exemplary only for explaining the present application and should not be construed as a limitation to the present application.

[0042] To enable those skilled in the art of the present technology to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of them. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0043] With the continuous development of smart home technology, the number of home devices capable of monitoring users' behaviors in the home system is increasing. However, when there are multiple monitoring devices in the home system, the monitoring data collected by the multiple monitoring devices will have problems of information overload or information conflict, resulting in low accuracy and poor reliability of the multiple monitoring data collected by the multiple monitoring devices in the home system in reflecting users' behaviors. Moreover, the analysis results of analyzing users based on the monitoring data with low accuracy and poor reliability are difficult to meet users' needs, resulting in a low level of intelligence and poor service effect of the home system in providing services to users.

[0044] To solve the above technical problems, in the embodiments of the present application, multiple monitoring data can be obtained by respectively receiving the monitoring data corresponding to multiple monitoring devices, and the monitoring data is data for monitoring users' behaviors; the feature data in the multiple monitoring data can be respectively extracted to obtain multiple target feature data, and the feature data is data representing users' behavior characteristics in the monitoring data; the multiple target feature data can be fused to obtain target fusion data; and the monitoring result corresponding to the users' behaviors can be obtained from the target fusion data. In this way, the home system can improve the accuracy and reliability of the monitoring data for processing and analysis by receiving the monitoring data from multiple monitoring devices. It can also fuse the monitoring data from multiple monitoring devices to obtain the fused target fusion data, and analyze the target fusion data to determine the detection result corresponding to the users' behaviors, thereby improving the level of intelligence and service effect of the home system in providing services to users.

[0045] To enable those skilled in the art to better understand the solution of the present application, the application environment of the solution of the present application will be described first. The data processing method provided by the present application can be applied to a system architecture as Figure 1 shown.

[0046] Please refer to Figure 1 , Figure 1 which is a schematic diagram of a system architecture of a home system 100 provided by an embodiment of the present application. As Figure 1 shown, the home system 100 includes a monitoring device 110, a network device 120, a cloud server 130, and a user terminal 140. Among them, the monitoring device 110 is communicatively connected to the network device 120, the cloud server 130, and the user terminal 140.

[0047] Among them, the home system 100 may include multiple monitoring devices 110, and the monitoring devices 110 may be home devices in the home system. The home devices may include: sleep detectors, smart mattresses, smart alarm clocks, human sensors, smart watches, smart lights, air conditioners, refrigerators, washing machines, etc., which are not specifically limited herein. The monitoring devices 110 are connected to the network device 120 in the home system 100 and communicate with the network device 120 through the communication modules configured in themselves.

[0048] The network device 120 can access the cloud server 130 and the user terminal 140 through a local area network path or a wide area network path. Among them, the local area network may include ZIGBEE or Bluetooth, etc., and the wide area network may include 2G / 3G / 4G / 5G / WIFI, etc. As an information transfer station of the home system 100, the network device 120 can establish a local area network connection between the monitoring device 110 and the cloud server 130 through a router. A network connection can be established between the network device 120 and the user terminal 140 through a local area network or a wide area network path. The network device 120 can interact with the user terminal 140 through this network connection, so that the user can control the monitoring device 110 connected to the network device 120 through the user terminal 140 to perform corresponding actions.

[0049] The cloud server 130 may be an independent server or a server cluster composed of multiple servers. On the one hand, the cloud server 130 can receive data such as monitoring information from the monitoring device 110 through the network device 120, and can also receive user instructions from the user terminal 140 through the network device 120. On the other hand, the cloud server 130 can also send corresponding control instructions to the monitoring device 110 through the network device 120, and can also send interaction data to the user terminal 140 through the network device 120 to achieve interaction with the user.

[0050] The user terminal 140 may be a smart phone, a laptop computer, a personal computer, a tablet computer, a smart control panel or other electronic devices that can implement network connections, which are not specifically limited herein. Exemplarily, the user terminal 140 can generate corresponding interaction instructions in response to the user's operations.

[0051] As a specific embodiment, the data processing method can be applied to the cloud server 130. Specifically, in this home system, the cloud server 130 can receive a plurality of monitoring data corresponding to a plurality of monitoring devices 110. After obtaining the plurality of monitoring data, the cloud server 130 can also extract the feature data from the plurality of monitoring data respectively to obtain a plurality of target feature data, where the feature data is the data representing the user behavior characteristics in the monitoring data. After obtaining the plurality of target feature data, the cloud server 130 can also fuse the plurality of target feature data to obtain target fusion data. After obtaining the fused target fusion data, the cloud server 130 can also analyze the target fusion data to obtain the monitoring result corresponding to the user behavior.

[0052] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of a data processing method disclosed in an embodiment of the present application. Among them, the data processing method can be applied to an electronic device in the home system 100, and the electronic device can be Figure 1 the monitoring device 110, the network device 120, the cloud server 130, the user terminal 140, etc. in Figure 2 . For better explaining the embodiment of the present application, the data processing method is described by taking the application to the cloud server 130 as an example. As Figure 2 shown, the data processing method may include the following steps.

[0053] 201. Receive the monitoring data from a plurality of monitoring devices respectively to obtain a plurality of monitoring data.

[0054] Among them, the monitoring data is the data for monitoring the user behavior.

[0055] The home system may include a plurality of monitoring devices, and the cloud server may obtain the monitoring data for monitoring the user behavior through the plurality of monitoring devices in the home system. The cloud server can receive the monitoring data corresponding to the plurality of monitoring devices.

[0056] The plurality of monitoring devices may be a plurality of execution devices that perform different related tasks in the working area corresponding to the home system. For example, devices such as a smart bed, a smart light, a smart curtain, and a smart alarm clock in the bedroom area. Devices such as a smart light, a smart refrigerator, a smart dishwasher, and a smart rice cooker in the kitchen area. The user terminal can also be used as one of the monitoring devices.

[0057] Refer to Figure 2A , Figure 2ASchematic diagram of a scenario disclosed in this application. Specifically, all intelligent devices in the home system can be added to the home system as monitoring devices for monitoring user behavior through a user terminal. Specifically, the user can add or delete intelligent devices for monitoring user behavior through the user terminal. After the user sets an intelligent device as a monitoring device, the cloud server in the home system can receive monitoring data corresponding to the monitoring device. Multiple monitoring devices can be added to the home system, and multiple monitoring data corresponding to multiple monitoring devices can be received. In another implementation, the user can also set the device priority of multiple monitoring devices in the home system through the user terminal.

[0058] During the use of the home system, the cloud server can communicate with each intelligent device in different working areas. The cloud server can receive in real time monitoring data corresponding to multiple monitoring devices when the intelligent devices are turned on, and obtain the monitoring data corresponding to the monitoring devices executing relevant operations. The cloud server can also receive the processed monitoring data from the monitoring devices after the monitoring devices complete the execution of relevant operations.

[0059] Among them, the monitoring data can include log data, user data, feedback data, status data, etc. Specifically, the log data can be the log data of the intelligent device during the execution of the corresponding work. For example, the start time of the intelligent bed working, the time to turn on the massage mode, the mode gear of the massage mode when turned on, the time to turn off the massage mode, and the end time of the work, etc. The user data can be the user data detected by the monitoring device when the user uses the monitoring device. For example, the intelligent bed can detect the time period when the user lies down, the user's sleep quality, the heart rate at different time periods, and the breathing conditions at different time periods and other user data. The feedback data can be the operation data of the user's operation on the intelligent device. For example, after the intelligent lamp is turned off, whether the user turns on the intelligent lamp within a preset time period, and after the intelligent alarm rings, whether the user triggers the alarm button, etc. The status data can be the device status of the intelligent device. For example, the battery status of the intelligent alarm, the non-plugged state (using battery for lighting) or the plugged state when the intelligent table lamp is illuminating, etc.

[0060] It should be noted that multiple monitoring devices in the home system can repeatedly collect the same type of monitoring data (log data, user data, feedback data or status data), and there may be duplicate and same-type monitoring data in the monitoring data received by the cloud server. For example, in the home system, there can be different multiple monitoring devices collecting the user's heart rate. The intelligent bed can detect the user's heart rate data, and the intelligent watch can also detect the user's heart rate data.

[0061] 202. Respectively extract the feature data from multiple monitoring data to obtain multiple target feature data.

[0062] Among them, the feature data is the data representing the user behavior features in the monitoring data.

[0063] After receiving multiple monitoring data corresponding to multiple monitoring devices, feature extraction can be respectively performed on different monitoring data corresponding to different monitoring devices to obtain multiple target feature data corresponding to multiple different monitoring data.

[0064] Among them, the target feature data can be the user behavior feature data determined according to the monitoring data. Exemplarily, the monitoring data can be log data. After receiving the log data from the monitoring device, feature data such as the high-frequency period of the user using the monitoring device can be determined according to the frequency of the monitoring device being turned on in the log data. For example, the cloud server can receive multiple time information about the opening of the smart refrigerator door. Specifically, the time points of the refrigerator door opening within the same day can include 8:03, 10:09, 11:04, 11:12, 11:25, 11:40, and 13:20. After analyzing the time points of the refrigerator door opening within the day, it can be determined that the high-frequency period of the refrigerator door opening is 36 minutes from 11:04 to 11:40. After analyzing the time periods of the refrigerator door opening within multiple days, it can also be obtained that the product period of the refrigerator door opening can also include multiple periods from 11:07 to 11:50, from 11:14 to 11:55, and from 11:04 to 11:35. Thus, it can be determined that the feature data of the user using the refrigerator is that the user tends to open the refrigerator door within the time period from 11:04 to 11:55.

[0065] The monitoring data can also be user data collected during the use of the monitoring device. After receiving the user data from the monitoring device, feature data such as the user's health status and active time can be determined according to the user data. For example, the cloud server can receive the heart rate information of the user detected by the smart bed. Specifically, within a certain time period, it can be detected that the user's heart rate maintains at 77 beats per minute to 92 beats per minute, and it can be determined that the user's heart rate is in a normal sleep state. Within another time period, it is detected that the user's heart rate continuously remains at 50 beats per minute to 61 beats per minute. It can be determined that the user's heart rate is in a lower deep sleep state.

[0066] The monitoring data can also be feedback data when the user performs relevant work on the monitoring device. After receiving the feedback data from the monitoring device, feature data such as the execution method preferred by the user when performing relevant work on the monitoring device can be determined according to the user's feedback data. For example, the cloud server can receive the target massage mode set by the user detected by the smart bed. After determining the target massage mode set by the user, the cloud server can determine the massage state of the smart bed preferred by the user when performing massage work.

[0067] The monitoring data can also be the status data of the monitoring device. After receiving the status data from the monitoring device, feature data such as the status of the monitoring device preferred by the user can be determined according to the target status of the monitoring device after use in the status data. For example, the cloud server can receive the irradiation mode number set by the user for the smart lamp. Specifically, the smart lamp can implement multiple different irradiation modes under different parameters such as the irradiation lamp beads, brightness, and color temperature, and each irradiation mode in the multiple irradiation modes can have a corresponding irradiation mode number. After the home system turns on the smart lamp, the user can adjust the irradiation mode of the smart lamp. After the user sets the irradiation mode of the smart lamp, the cloud server can determine the target irradiation mode preferred by the user.

[0068] After determining the feature data in each of the multiple monitoring data from different monitoring devices, multiple target feature data corresponding to the multiple monitoring data can be determined.

[0069] 203. Fuse the multiple target feature data to obtain target fusion data.

[0070] After obtaining the multiple target feature data in the multiple monitoring data, the multiple target feature data corresponding to different multiple monitoring devices can also be fused to obtain target fusion data. Among them, the multiple target feature data can include multiple feature data of different types. Fusing the multiple target feature data of different types can be to select the multiple target feature data of the same type among the multiple target feature data of different types. After determining the multiple target feature data of the same type, the multiple target feature data of the same type are fused to obtain the corresponding target fusion data.

[0071] In some embodiments, the weighted ratio corresponding to each monitoring device can be determined according to the device priority corresponding to each monitoring device in the multiple monitoring devices. Among them, the weighted ratio can be used to fuse the target feature data corresponding to each monitoring device. After determining the weighted ratio corresponding to each monitoring device, the multiple target feature data are fused according to the weighted ratio corresponding to each monitoring device to obtain target fusion data.

[0072] Specifically, weights can be added to each of the multiple target feature data according to the different credibility or user behavior preferences corresponding to the multiple target feature data, and after adding the weights, each weighted target feature data is fused to obtain target fusion data.

[0073] Exemplarily, a home system may include the following three monitoring devices to monitor the sleep quality of a user (the sleep quality may be a type of user data), and respectively obtain characteristic data (multiple target characteristic data of the same type) corresponding to different monitoring devices:

[0074] Monitoring device A: uses a heart rate sensor to obtain the heart rate data of the user, monitors the sleep physical state of the user according to the heart rate data, and determines the sleep quality data A1 of the user during sleep according to the heart rate data.

[0075] Monitoring device B: uses an accelerometer to obtain the getting-up-at-night data of the user, monitors the active state of the user according to the getting-up-at-night data, and determines the sleep quality data B1 of the user during sleep according to the getting-up-at-night data.

[0076] Monitoring device C: uses an environmental sensor to obtain the environmental data of the user's sleep environment, monitors the sleep environment of the user based on the environmental data, and determines the sleep quality data C1 of the user during sleep according to the environmental data.

[0077] Among them, different monitoring devices may have different priorities. In the case where different monitoring devices have different priorities, the fusion weights corresponding to different monitoring data collected by different monitoring devices are correspondingly different. Exemplarily, the fusion weight of the above-mentioned monitoring device A may be 30%, the fusion weight of monitoring device B may be 40%, and the fusion weight of monitoring device C may be 30%.

[0078] After determining multiple sleep quality data (target characteristic data) A1, B1, and C1 corresponding to different monitoring devices, data fusion can be performed according to the fusion weights corresponding to the monitoring devices A, B, and C of the target characteristic data, 30%*A1 + 40%*B1 + 30%*C1, to obtain the fused sleep quality data.

[0079] In some other embodiments, the user can set the priorities of different multiple monitoring devices in the home system through a user terminal. The cloud server can receive the priorities set by the user for different multiple monitoring devices on the user terminal. After determining the priorities set by the user, the cloud server can also determine the fusion weights corresponding to different monitoring devices according to the set priorities.

[0080] 204. Analyze the target fusion data to obtain the monitoring results corresponding to the user's behavior.

[0081] After determining the target fusion data, data analysis can also be performed on the target fusion data to obtain a monitoring result for monitoring user behavior. Among them, the monitoring result can be data representing the user behavior in the target fusion data. Exemplarily, based on multiple sleep quality data corresponding to different monitoring devices, the fused sleep quality data is determined. After determining the fused sleep quality data, the fused sleep quality data can be analyzed to determine the behavioral data of the user's sleep in the fused sleep quality data. For example, the user's sleep quality score can be determined according to the fused sleep quality data. Among them, the user's sleep quality score can be a monitoring result for monitoring the user's sleep.

[0082] In Figure 2 In the method embodiments described above, multiple monitoring data can be obtained by respectively receiving the monitoring data corresponding to multiple monitoring devices. The monitoring data is data for monitoring user behavior; the feature data in the multiple monitoring data is respectively extracted to obtain multiple target feature data. The feature data is data representing the user behavior characteristics in the monitoring data; the multiple target feature data is fused to obtain the target fusion data; from the target fusion data, the monitoring result corresponding to the user behavior is obtained. In this way, the home system can improve the accuracy and reliability of the monitoring data for processing and analysis by receiving the monitoring data from multiple monitoring devices. It can also fuse the monitoring data from multiple monitoring devices to obtain the fused target fusion data, and analyze the target fusion data to determine the detection result corresponding to the user behavior, thereby improving the intelligent level and service effect of the home system for user services.

[0083] Please refer to Figure 3 , Figure 3 is a schematic flowchart of another data processing method disclosed in the embodiments of the present application. This data processing method can be applied to an electronic device capable of data processing. The electronic device can be Figure 1 the monitoring device 110, network device 120, cloud server 130, user terminal 140, etc. in Figure 3 As shown, this data processing method can include the following steps.

[0084] 301. Respectively receive the monitoring data corresponding to multiple monitoring devices to obtain multiple monitoring data.

[0085] Among them, the monitoring data is data for monitoring user behavior.

[0086] Among them, the description of step 301 can specifically refer to the specific description of step 201 in the above embodiment, and will not be repeated here.

[0087] 302. Perform data preprocessing on multiple monitoring data to obtain the processed multiple monitoring data.

[0088] After receiving multiple monitoring data corresponding to multiple monitoring devices, the cloud server can also perform data preprocessing on the received multiple monitoring data. Specifically, data cleaning and denoising can be performed on each monitoring data in the multiple monitoring data to obtain the processed multiple monitoring data.

[0089] Among them, performing data preprocessing on the monitoring data may include the following steps:

[0090] 1. Determine the data types of the multiple monitoring data.

[0091] After receiving multiple monitoring data corresponding to multiple monitoring devices, the cloud server can determine the data types of the monitoring data. Among them, the data types of the monitoring data can be used to represent different types of monitoring data. Exemplarily, the data types of the monitoring data can be monitoring information of time type (e.g., time points and time periods), monitoring information of descriptive language type (environmental description information and status description information), monitoring information of rate type (e.g., heart rate information and pulse information), etc. Different data types of monitoring information. For the specific data types of the monitoring information, no specific limitations are made here.

[0092] Thus, after receiving multiple monitoring data corresponding to multiple monitoring devices, the cloud server can determine the data types corresponding to each monitoring data in the multiple monitoring data. After determining the data types of the monitoring data, classify the monitoring data according to the data types of the monitoring data to determine multiple monitoring data corresponding to different multiple data types.

[0093] 2. When the data type of the target monitoring data is the target type, detect the continuity of the target monitoring data.

[0094] Among them, the target monitoring data is any one of the multiple monitoring data.

[0095] After determining the data types corresponding to each monitoring data in the multiple monitoring data, at least one monitoring data corresponding to the target type can be selected from the multiple monitoring data corresponding to different multiple data types. Among them, the target type can be at least one data type preset for monitoring user behavior. Exemplarily, the target type can be monitoring information of time type and monitoring information of rate type. Thus, after determining the data types corresponding to each monitoring data in the multiple monitoring data, the monitoring information of time type and the monitoring information of rate type can be screened out from the multiple monitoring data to obtain the target monitoring data corresponding to the target type.

[0096] After determining the target monitoring data of the target type, the continuity of the target monitoring data can be detected. Among them, the continuity of the target monitoring data can be used to represent the credibility of the target monitoring data. Specifically, the target monitoring data of the target type within a preset time period (for example, 1 day, half a day, or several hours, and the specific time period can be determined according to the accuracy of cleaning the monitoring data, and no specific limitation is made on the preset time period here) can be obtained, and the continuity detection is performed on the target monitoring data of the target type to determine the continuity of the target monitoring data.

[0097] Specifically, performing continuity detection on the target monitoring data to determine the continuity of the target monitoring data can be by determining whether the target monitoring data meets the preset continuous conditions to determine whether there is continuity in the target monitoring data.

[0098] Exemplarily, it can be determined whether there is isolated data in the target monitoring data within a preset time period to determine whether the target monitoring data meets the preset continuous conditions. Specifically, the isolated data can be a monitoring data value that deviates from the normal range. In the monitoring information of the rate type, the monitoring data with a rate exceeding the normal range is isolated data. For example, the normal range of heart rate information can be from 60 beats per minute to 100 beats per minute. When the monitoring device detects that the user's heart rate information is 120 beats per minute, it can be determined that this monitoring data is isolated data exceeding the range. In the monitoring information of the time type, the monitoring data not within the preset time interval is isolated data. For example, the intelligent door lock usually does not open or close during the working hours on weekdays. In the case where the log data (target monitoring data) of the intelligent door lock includes corresponding monitoring data during the sleep time, it can be determined that this monitoring data is isolated data occurring at an abnormal time.

[0099] Thus, it can be determined the continuity of the target monitoring data by judging whether there is isolated data in the target monitoring data or judging whether the number of isolated data in the target monitoring data exceeds the preset abnormal number.

[0100] 3. In the case where the continuity of the target monitoring data does not meet the preset continuous conditions, the data in the target monitoring data that does not meet the preset continuous conditions is removed to obtain the processed monitoring data.

[0101] In the case where it is determined that the continuity of the target monitoring data does not meet the preset continuous conditions, data cleaning can be performed on the target monitoring data to obtain the processed monitoring data. Among them, the target monitoring data not meeting the preset continuity conditions can be that there is isolated data in the energy meter monitoring data or the number of isolated data in the target monitoring data exceeds the preset abnormal number. In this case, it can be determined that the target monitoring data does not meet the preset continuous conditions.

[0102] In the case where the continuity of the target monitoring data does not meet the preset continuous condition, the data in the target monitoring data that does not meet the preset continuous condition can be removed to achieve data cleaning of the target monitoring data and obtain the processed monitoring data.

[0103] 303. Extract the characteristic data that meets the preset conditions from each of the multiple monitoring data to obtain multiple pieces of characteristic data.

[0104] Among them, the characteristic data is the data representing the user behavior characteristics in the monitoring data.

[0105] After performing data preprocessing on each of the multiple monitoring data to obtain the corresponding multiple processed monitoring data, feature extraction can also be performed on the multiple processed monitoring data, and the characteristic data that meets the preset conditions in the multiple monitoring data can be screened out to obtain the corresponding multiple pieces of characteristic data. Among them, the characteristic data can be device data and user behavior data collected by the monitoring device. When the device data or user behavior data meets the preset conditions, the device data and user behavior data that meet the preset conditions in the monitoring data can be determined as the multiple characteristic data in the monitoring data.

[0106] In one embodiment, the preset condition of the monitoring data can be the data in the device data whose triggering method of the monitoring device can represent the user behavior characteristics of the user, that is, when the device data in the monitoring data represents that the triggering method corresponding to the monitoring device is user behavior triggering, it is determined that the monitoring data meets the preset condition.

[0107] Exemplarily, the multiple monitoring data can include monitoring data of multiple triggering types. For example, the log data of the smart light turning on can include multiple triggering types such as instruction triggering, sensor triggering, and user active triggering of the smart light. Among the multiple monitoring data including multiple triggering types such as instruction triggering, sensor triggering, and user active triggering, the triggering type data that can represent user behavior can be screened out. It should be noted that the monitoring data of the instruction triggering type can be the device triggering implemented by the monitoring device according to the pre-set instructions (such as timing on and timing off instructions). Therefore, the monitoring data of the instruction triggering type cannot represent the user behavior of the user in the area corresponding to the monitoring device. Correspondingly, the multiple monitoring data of multiple triggering types such as sensor triggering and user active triggering can represent that the monitoring device realizes the triggering function after obtaining user data, and the multiple monitoring data of multiple triggering types such as sensor triggering and user active triggering can be the characteristic data representing user behavior.

[0108] 304. Perform standardization processing on the multiple pieces of characteristic data to obtain multiple target characteristic data.

[0109] In one embodiment, after determining multiple feature data corresponding to multiple monitoring data, the multiple feature data may be standardized to obtain multiple target feature data. It should be noted that the multiple feature data may include different data types, and the feature data of each data type may have different data storage methods. The feature data with different storage methods can be uniformly processed into a standard storage method through standardization. Exemplarily, user data of the time type can calculate the time period in seconds or in hours. For example, the sleep time can be recorded as 34355445 seconds, and the sleep time can also be recorded as 4h32m23s. For different data storage methods, in the embodiments of the present application, one specific data storage method can be set as the standard data storage method, and when the feature data of this data type appears subsequently, the feature data with different storage methods can be unified into the standard target feature data. After standardizing the multiple target feature data, multiple target feature data corresponding to the multiple feature data are obtained.

[0110] 305. Fuse the multiple target feature data to obtain target fusion data.

[0111] Among them, the description of step 305 can specifically refer to the specific description of step 203 in the above embodiment, and will not be elaborated here.

[0112] 306. Determine the division reference point corresponding to the target fusion data according to the credibility of different time periods.

[0113] In one embodiment, after determining the corresponding addition weights through the priorities of different monitoring devices, performing data fusion to obtain target fusion data, the fused target fusion data can also be divided by determining the division reference point corresponding to the target fusion data. Among them, the division reference point can be a division point determined according to the credibility of different time periods corresponding to the target fusion data. Exemplarily, within the working area corresponding to the home system, the credibility of the target fusion data corresponding to the rest day can be greater than the credibility of the target fusion data corresponding to the working day. Therefore, the time intersection point between the working day and the rest day can be used as the division reference point corresponding to this monitoring device. The credibility of the target fusion data corresponding to the daytime period from 06:00 to 21:00 can be greater than the credibility of the target fusion data corresponding to the evening period from 21:00 to 06:00 the next day. Therefore, 06:00 and 21:00 every day can be used as the two division reference points for the two time periods respectively.

[0114] 307. Divide the target fusion data according to the division reference point to obtain target fusion data for multiple time periods.

[0115] After partitioning the target fusion data according to the partitioning reference points, multiple target fusion data for different time periods can be obtained.

[0116] 308. Analyze the target fusion data to obtain the monitoring results corresponding to the user behavior.

[0117] After obtaining the target fusion data corresponding to different time periods, data analysis can be performed on the target fusion data corresponding to different time periods. After performing data analysis on the target fusion data corresponding to different time periods, the monitoring results for analyzing the user behavior can be obtained. Among them, the monitoring results can be the analysis results of the user behavior in the target fusion data corresponding to different time periods. Exemplarily, the monitoring results can be determining the sleep quality corresponding to the user at different time periods when monitoring the user's sleep quality.

[0118] 309. Determine the corresponding behavior strategy according to the monitoring results and output the behavior strategy; or

[0119] Generate the corresponding analysis chart according to the monitoring results and output the analysis chart; or

[0120] Determine the corresponding device collaboration strategy according to the monitoring results and output the device collaboration strategy.

[0121] After determining the monitoring results corresponding to the monitoring of the user behavior, the corresponding behavior strategy can be generated. Among them, the behavior strategy can be the behavior strategy provided for the user according to the corresponding analysis results after analyzing the target fusion data of different time periods corresponding to the user behavior. After determining the behavior strategy, the behavior strategy can also be output to the user. Specifically, the behavior strategy can be sent to the user terminal, and the behavior strategy can be used to prompt the user.

[0122] Refer to Figure 3A , Figure 3A which is a schematic diagram of a scenario disclosed in this application. After determining the detection result of the poor sleep quality of the user, the corresponding behavior strategy can be output. It can be recommended that the user try to establish a fixed sleep schedule to ensure sufficient sleep time every night. At the same time, avoid excessive excitement before going to bed. For example, do not use electronic devices for a long time.

[0123] After determining the monitoring results corresponding to the monitoring of the user behavior, the corresponding analysis chart can also be generated. Among them, the analysis chart can be used to represent the visual distribution of the user behavior in the target fusion data of different time periods of the user.

[0124] Refer to Figure 3B , Figure 3BSchematic diagram of another scenario disclosed in this application. According to the monitoring results of the user's sleep quality, for example, the sleep onset time, sleep duration, wake-up time, number of nocturia, and sleep score, corresponding visual charts can be generated. Corresponding visual data can also be generated based on the monitoring data from different monitoring devices, and the visual data generated corresponding to the monitoring data from different monitoring devices can be presented to the user on the display page of the analysis chart corresponding to the monitoring results.

[0125] After determining the monitoring results obtained by monitoring the user's behavior, a corresponding device collaboration strategy can also be generated. Among them, the device collaboration strategy can be used to send relevant device linkage instructions to multiple other execution devices in the home system after determining the monitoring results of monitoring the user. After generating the device collaboration strategy corresponding to the monitoring results, the device collaboration strategy can be sent to the user terminal. After the user determines the device collaboration strategy through the user terminal, a corresponding device linkage instruction can be generated and sent to the corresponding execution device to complete the corresponding device linkage.

[0126] In some other embodiments, feedback information from the user regarding the monitoring results is received. After determining the user's feedback information on the monitoring results, the monitoring results can also be adjusted according to the feedback information. Specifically, adjusting the monitoring results according to the feedback information may include: adjusting the device priorities corresponding to multiple monitoring devices according to the feedback information. According to the adjusted device priorities of the multiple monitoring devices, adjust the weighted ratios corresponding to the device priorities. Fuse the multiple target feature data corresponding to the multiple monitoring devices according to the adjusted weighted ratios to obtain the adjusted fused data. Analyze the adjusted fused data to obtain the corresponding adjusted monitoring results.

[0127] Refer to Figure 3C , Figure 3C Flow schematic diagram of a specific application scenario disclosed in this application. This method can be used to monitor the user's sleep quality and perform corresponding intelligent regulation. The smart home system includes monitoring devices such as a smart bed, sleep sensing devices, a smart alarm sleep tracker, a heart rate monitor, etc., and also includes mobile devices such as a smartphone. The smartphone is used to connect to the smart home system and display the sleep monitoring results. The user can add each monitoring device to the sleep monitoring system and set the preference priorities of each monitoring device, and determine the weights of the detection data corresponding to each monitoring device according to the preference priorities.

[0128] At the beginning, data collection can be carried out on monitoring devices from multiple data sources. The collected data can be preprocessed first, such as data cleaning, noise removal, feature extraction, and normalization. After obtaining the monitoring data from multiple data sources, feature extraction and normalization can be performed on the monitoring data from multiple data sources to obtain multiple target feature data. And corresponding weights are determined according to different data sources, and the multiple target feature data are weighted and fused to obtain target fusion data. After obtaining the target fusion data, the target fusion data is analyzed to determine the monitoring result, and the monitoring result can include the user's corresponding sleep preferences and corresponding usage suggestions, such as suggestions on sleep time, environmental adjustment, and diet health.

[0129] After the user receives the monitoring result, if the user believes that the monitoring result needs to be optimized, the calculation method of the monitoring result can also be modified. After receiving the user's adaptive modification of the monitoring result, the data weighting strategy and data fusion method can be adjusted to improve the accuracy and reliability of the later sleep monitoring result, so as to achieve the self-optimization of the sleep monitoring strategy. Exemplarily, the process of strategy self-optimization includes: when the user finds that the sleep monitoring result is inaccurate, relevant information can be fed back to the system through the feedback mechanism provided by the system, such as data on sleep time, sleep quality, and sleep environment. The system adjusts the original data according to the user's feedback data, such as changing the weights of some data sources, deleting or adding some data, etc., to improve the accuracy of the later sleep monitoring result. According to the adjusted weighting strategy, the data from different data sources are re-weighted and fused to obtain a more accurate and reliable sleep monitoring result. The system outputs the adjusted sleep monitoring result to the user and provides corresponding sleep preferences and suggestions to help the user improve sleep quality and health level.

[0130] In Figure 3 In the method embodiments described above, multiple monitoring data can be obtained by respectively receiving the monitoring data corresponding to multiple monitoring devices, and the monitoring data is the data for monitoring the user's behavior; the feature data in the multiple monitoring data can be respectively extracted to obtain multiple target feature data, and the feature data is the data representing the user's behavior characteristics in the monitoring data; the multiple target feature data are fused to obtain target fusion data; from the target fusion data, the monitoring result corresponding to the user's behavior is obtained. In this way, the home system can improve the accuracy and reliability of the monitoring data used for processing and analysis by receiving the monitoring data from multiple monitoring devices. It can also fuse the monitoring data from multiple monitoring devices to obtain the fused target fusion data, and analyze the target fusion data to determine the detection result corresponding to the user's behavior, thereby improving the intelligent level and service effect of the home system for user services.

[0131] It should be understood that the same or corresponding information in the above different embodiments can be referred to each other.

[0132] It should be understood that, although Figure 2 、 3 each step in the flowchart is shown in sequence according to the indication of the arrow, these steps are not necessarily executed in sequence according to the indication of the arrow. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, Figure 2 、 3 at least a part of the steps in

[0133] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of the data processing device 400 disclosed in the embodiment of the present application. The data processing device 400 may include:

[0134] A receiving unit 401, configured to respectively receive monitoring data corresponding to a plurality of monitoring devices to obtain a plurality of monitoring data, where the monitoring data is data for monitoring user behavior;

[0135] An extraction unit 402, configured to respectively extract feature data from the plurality of monitoring data to obtain a plurality of target feature data, where the feature data is data representing user behavior characteristics in the monitoring data;

[0136] A fusion unit 403, configured to fuse the plurality of target feature data to obtain target fusion data;

[0137] An analysis unit 404, configured to analyze the target fusion data to obtain a monitoring result corresponding to the user behavior.

[0138] In some embodiments, the data processing device 400 further includes:

[0139] An output unit 405, configured to determine a corresponding behavior strategy according to the monitoring result and output the behavior strategy; or

[0140] generate a corresponding analysis chart according to the monitoring result and output the analysis chart; or

[0141] determine a corresponding device cooperation strategy according to the monitoring result and output the device cooperation strategy.

[0142] In some embodiments, the data processing device 400 further includes:

[0143] A preprocessing unit 406, configured to determine the data types of the multiple pieces of monitoring data;

[0144] The preprocessing unit 406 is further configured to, when the data type of the target monitoring data is a target type, detect the continuity of the target monitoring data, where the target monitoring data is any one of the multiple pieces of monitoring data;

[0145] The preprocessing unit 406 is further configured to, when the continuity of the target monitoring data does not meet a preset continuity condition, remove the data that does not meet the preset continuity condition from the target monitoring data, so as to obtain processed monitoring data.

[0146] In some embodiments, the extraction unit 402 may be specifically configured to:

[0147] Extract the feature data from the processed monitoring data respectively, so as to obtain multiple target feature data.

[0148] In some embodiments, the extraction unit 402 may be specifically configured to:

[0149] Extract the feature data that meets a preset condition from each piece of monitoring data among the multiple pieces of monitoring data, so as to obtain multiple pieces of feature data;

[0150] Perform normalization processing on the multiple pieces of feature data, so as to obtain multiple target feature data.

[0151] In some embodiments, the fusion unit 403 may be specifically configured to:

[0152] Determine the weighted ratio corresponding to each monitoring device according to the device priority corresponding to each monitoring device among the multiple monitoring devices, where the weighted ratio is used to fuse the target feature data corresponding to each monitoring device;

[0153] Fuse the multiple target feature data according to the weighted ratio, so as to obtain target fusion data.

[0154] In some embodiments, the data processing device 400 further includes:

[0155] A partitioning unit 407, configured to determine a partitioning reference point corresponding to the target fusion data according to the credibility of different time periods;

[0156] The partitioning unit 407 is further configured to partition the target fusion data according to the partitioning reference point, so as to obtain target fusion data of multiple time periods.

[0157] In some embodiments, the data processing device 400 further includes:

[0158] An adjustment unit 408, configured to receive feedback information from a user regarding the monitoring result;

[0159] The adjustment unit 408 is further configured to adjust the monitoring result according to the feedback information.

[0160] In some embodiments, the adjustment unit 408 may specifically be configured to:

[0161] Adjust the device priorities corresponding to multiple monitoring devices according to the feedback information;

[0162] According to the adjusted device priorities of the multiple monitoring devices, adjust the weighted ratios corresponding to the device priorities;

[0163] Fuse the multiple target feature data corresponding to the multiple monitoring devices according to the adjusted weighted ratios to obtain adjusted fused data;

[0164] Analyze the adjusted fused data to obtain a corresponding adjusted monitoring result.

[0165] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0166] In several embodiments disclosed in the present application, the coupling between units may be electrical, mechanical, or other forms of coupling.

[0167] In addition, in each embodiment of the present application, each functional unit may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units.

[0168] As Figure 6 shown, an embodiment of the present application further discloses a schematic structural diagram of an electronic device. The electronic device includes a processor 601 and a memory 602. The memory 602 stores computer program instructions. When the computer program instructions are called by the processor 601, various method steps disclosed in the foregoing embodiments can be executed. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Among them:

[0169] The processor 601 may include one or more processing cores. The processor 601 uses various interfaces and lines to connect various parts within the entire battery management system. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 602, calling the data stored in the memory 602, executing various functions of the battery management system and processing data, and executing various functions of the electronic device and processing data, the electronic device can be monitored as a whole. Optionally, the processor 601 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 601 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the displayed content; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 601 and can be implemented separately through a communication chip.

[0170] The memory 602 may include random access memory (RAM) and may also include read-only memory. The memory 602 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 602 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data created during the use of the electronic device (such as phone book, audio and video data, chat record data, etc.). Correspondingly, the memory 602 may also include a memory controller to expose the access of the processor 601 to the memory 602.

[0171] Although not shown, the electronic device may also include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 601 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 will run the application programs stored in the memory 602 to implement the various method steps disclosed in the foregoing embodiments.

[0172] The embodiments of the present application also disclose a computer-readable storage medium, in which computer program instructions are stored and can be called by a processor to execute the methods described in the above embodiments.

[0173] The computer-readable storage medium may be an electronic memory such as a flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has a storage space for program codes for executing any method steps in the above methods. These program codes can be read out from or written into one or more computer program products. The program codes can be compressed in a suitable form, for example.

[0174] According to one aspect of the present application, a computer program product or a computer program is disclosed. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the methods disclosed in the various optional implementation manners disclosed in the above embodiments.

[0175] The above are only the preferred embodiments of the present application, and do not impose any form of limitation on the present application. Although the present application has been disclosed above with the preferred embodiments, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to equivalent embodiments by using the technical content disclosed above without departing from the technical solution scope of the present application. However, any brief modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application still fall within the scope of the technical solution of the present application.

Claims

1. A data processing method, characterized in that, The method includes: Receiving monitoring data corresponding to multiple monitoring devices respectively to obtain multiple monitoring data, where the monitoring data is data for monitoring user behavior; Extracting feature data from the multiple monitoring data respectively to obtain multiple target feature data, where the feature data is data representing user behavior characteristics in the monitoring data; Fusing the multiple target feature data to obtain target fusion data; Analyzing the target fusion data to obtain a monitoring result corresponding to the user behavior.

2. The method according to claim 1, characterized in that, The method further includes: Determining the data types of the multiple monitoring data; When the data type of target monitoring data is a target type, detecting the continuity of the target monitoring data, where the target monitoring data is any one of the multiple monitoring data; When the continuity of the target monitoring data does not meet a preset continuous condition, removing the data in the target monitoring data that does not meet the preset continuous condition to obtain processed monitoring data; The extracting feature data from the multiple monitoring data respectively to obtain multiple target feature data includes: Extracting the feature data from the processed monitoring data to obtain the target feature data.

3. The method according to claim 1, characterized in that, The extracting feature data from the multiple monitoring data respectively to obtain multiple target feature data includes: Extracting the feature data that meets a preset condition from each of the multiple monitoring data to obtain multiple feature data; Performing standardization processing on the multiple feature data to obtain multiple target feature data.

4. The method according to claim 1, characterized in that, The fusing the multiple target feature data to obtain target fusion data includes: Determining a weighted ratio corresponding to each monitoring device according to the device priority corresponding to each monitoring device among the multiple monitoring devices, where the weighted ratio is used to fuse the target feature data corresponding to each monitoring device; Fusing the multiple target feature data according to the weighted ratio to obtain target fusion data.

5. The method according to claim 4, characterized in that, The method further includes: Determining a division reference point corresponding to the target fusion data according to the credibility at different time periods; Dividing the target fusion data according to the division reference point to obtain target fusion data for multiple time periods.

6. The method according to any one of claims 1-5, characterized in that, The method further includes at least one of the following: Determining a corresponding behavior strategy according to the monitoring result and outputting the behavior strategy; Generating a corresponding analysis chart according to the monitoring result and outputting the analysis chart; Determining a corresponding device collaboration strategy according to the monitoring result and outputting the device collaboration strategy.

7. The method according to claim 6, characterized in that, The method further includes: Receiving feedback information from the user regarding the monitoring result; Adjusting the monitoring result according to the feedback information.

8. The method according to claim 7, characterized in that, The adjusting the monitoring result according to the feedback information includes: Adjusting the device priorities corresponding to multiple monitoring devices according to the feedback information; Adjusting the weighted ratio corresponding to the device priority according to the adjusted device priorities of the multiple monitoring devices; Fusing the multiple target feature data corresponding to the multiple monitoring devices according to the adjusted weighted ratio to obtain adjusted fusion data; Analyzing the adjusted fusion data to obtain a corresponding adjusted monitoring result.

9. A data processing device, characterized in that, The data processing device includes: A receiving unit, configured to respectively receive monitoring data corresponding to a plurality of monitoring devices to obtain a plurality of monitoring data, where the monitoring data is data for monitoring user behavior; An extraction unit, configured to respectively extract feature data from the plurality of monitoring data to obtain a plurality of target feature data, where the feature data is data representing user behavior characteristics in the monitoring data; A fusion unit, configured to fuse the plurality of target feature data to obtain target fusion data; An analysis unit, configured to analyze the target fusion data to obtain a monitoring result corresponding to the user behavior.

10. An electronic device, characterized in that, It includes a memory and a processor, where the memory stores a computer program, and the processor calls the computer program to implement the method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, A computer program or computer instructions are stored in the computer-readable storage medium, and when the computer program or the computer instructions are run by a processor, the method according to any one of claims 1-8 is implemented.

Images