Data transmission method and device, electronic equipment, chip and medium

Abstract

The invention provides a user data processing method and device, electronic equipment, a chip and a medium, and the user data processing method comprises the steps: obtaining the original data of at least two pieces of equipment of a user from a cloud end, and enabling the original data of different pieces of equipment to have different formats; performing format conversion on the original data of the at least two devices to form event data of the at least two devices, the event data being a trigger-condition-action data pair; performing data learning on the event data by using a preset algorithm to obtain task data of the user; and pushing the task data to the cloud and / or the at least two devices. According to the user data processing method provided by the invention, data can be acquired from multiple devices, user operation habits can be learned, and flexible and intelligent task pushing can be realized in multiple scenes, so that the user experience and the system adaptability are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and in particular to a data transmission method, device, electronic device, chip and medium. Background Art

[0002] The intelligent push system learns based on user data, thereby pushing information that meets user needs to users. Currently, traditional methods rely on a single data source from a single device, and often push tasks through simple manual rule matching or predefined patterns. These systems cannot achieve comprehensive and accurate learning of user operating habits, nor can they understand and adapt to user personalized needs. Summary of the invention

[0003] The present disclosure provides a user data processing method, device, electronic device, chip and medium, which acquire user data of multiple devices, learn the user data, adapt to the complex behavior patterns of users, and implement flexible and intelligent task push in multiple scenarios, thereby improving user experience and system adaptability.

[0004] The first aspect embodiment of the present disclosure proposes a user data processing method, which includes: obtaining raw data of at least two devices of a user from the cloud, wherein the raw data of different devices have different formats; converting the format of the raw data of at least two devices to form event data of at least two devices, wherein the event data is a trigger-condition-action data pair; using a preset algorithm, performing data learning on the event data to obtain the user's task data; and pushing the task data to the cloud and / or at least two devices.

[0005] In some embodiments of the present disclosure, obtaining the original data of at least two devices of a user from the cloud includes at least two of the following items: obtaining the original data of the Internet of Things device related to the user from the Internet of Things device cloud in the cloud; obtaining the original data of the terminal device related to the user from the terminal cloud in the cloud; obtaining the original data of the wearable device related to the user from the wearable device cloud in the cloud; obtaining the original data of the vehicle related to the user from the vehicle cloud in the cloud.

[0006] In some embodiments of the present disclosure, format conversion of raw data of at least two devices to form event data of at least two devices includes: establishing data tables for raw data of different devices, respectively, wherein the data tables of different devices are identified by device categories or device models; determining labels of the raw data in the data table based on user usage data of at least two devices, wherein the labels include triggers, conditions, and actions; and forming event data from the raw data based on the labels of the raw data.

[0007] In some embodiments of the present disclosure, a preset algorithm is used to perform data learning on event data to obtain the user's task data, including: obtaining a preset algorithm from an algorithm cloud control platform or an event library platform in the cloud, wherein the preset algorithm is trained through device usage data of multiple users; extracting multiple fields of the event data, and using the preset algorithm to learn the user's device usage rules to obtain the user's task data, wherein the task data is a trigger-condition-action data pair.

[0008] In some embodiments of the present disclosure, after obtaining the user's task data, the method also includes: obtaining the user's historical data from the cloud or a local database, the historical data being the historical task data generated previously; determining whether there is a conflict between the user's historical data and the task data; sending a deletion instruction to the cloud to instruct the cloud to delete the historical data that conflicts with the task data, or deleting the historical data that conflicts with the task data from the local database.

[0009] In some embodiments of the present disclosure, pushing task data to the cloud and / or at least two devices includes at least one of the following: pushing task data to a cloud synchronization platform on the cloud; when the task data meets the trigger condition, pushing the task data to the device corresponding to the task data to instruct the device to perform the operation corresponding to the task data; when the task data meets the trigger condition, pushing the task data to the cloud platform corresponding to the device.

[0010] In some embodiments of the present disclosure, original data of at least two devices are unstructured data, and the original data includes at least one of device information, operation information, and status information.

[0011] The second aspect embodiment of the present disclosure proposes a user data processing device, including: an acquisition module, used to obtain the original data of at least two devices of the user from the cloud, wherein the original data of different devices have different formats; a format conversion module, used to convert the format of the original data of at least two devices to form event data of at least two devices, the event data being a trigger-condition-action data pair; a learning module, used to use a preset algorithm to perform data learning on the event data to obtain the user's task data; and a push module, used to push the task data to the cloud and / or at least two devices.

[0012] The third aspect embodiment of the present disclosure proposes an electronic device, comprising: a memory for storing processor-executable instructions; and a processor configured to execute the executable instructions in the memory to implement the method described in the first aspect embodiment of the present disclosure.

[0013] The fourth aspect embodiment of the present disclosure proposes a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in the first aspect embodiment of the present disclosure is implemented.

[0014] The fifth aspect embodiment of the present disclosure proposes a chip, including one or more interface circuits and one or more processors; the interface circuit is used to receive signals from a memory of an electronic device and send signals to the processor, the signals including computer instructions stored in the memory; when the processor executes the computer instructions, the method described in the first aspect embodiment of the present disclosure is implemented.

[0015] In summary, the user data processing method proposed in the present disclosure obtains the original data of at least two devices of the user from the cloud, wherein the original data of different devices have different formats; converts the format of the original data of at least two devices to form event data of at least two devices, wherein the event data is a trigger-condition-action data pair; uses a preset algorithm to perform data learning on the event data to obtain the user's task data; and pushes the task data to the cloud and / or at least two devices. The method can obtain data from multiple devices, learn user operation habits, and implement flexible and intelligent task push in multiple scenarios, thereby improving user experience and system adaptability.

[0016] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0018] Figure 1 A system architecture diagram proposed for an embodiment of the present disclosure;

[0019] Figure 2 A schematic diagram of a system proposed in an embodiment of the present disclosure;

[0020] Figure 3 A flowchart of a user data processing method provided by an embodiment of the present disclosure;

[0021] Figure 4 A flowchart of a user data processing method provided by an embodiment of the present disclosure;

[0022] Figure 5 A flowchart of a user data processing method provided by an embodiment of the present disclosure;

[0023] Figure 6 A flowchart of a user data processing method provided by an embodiment of the present disclosure;

[0024] Figure 7 A flowchart of an embodiment of the present disclosure is shown;

[0025] Figure 8 A schematic diagram of the structure of a user data processing device provided by an embodiment of the present disclosure;

[0026] Fig. 9 is a structural diagram of an electronic device 900 for implementing the above-mentioned user data processing method according to an exemplary embodiment;

[0027] Fig.10 FIG. 1 is a schematic diagram showing the structure of a chip 1000 for implementing the above user data processing method according to an exemplary embodiment. DETAILED DESCRIPTION

[0028] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0029] The existing intelligent push systems mainly rely on single data from a single device to learn user behavior and complete tasks through simple direct push. Although this method can meet basic push needs, it has some limitations, such as: it cannot handle multi-device cross-modal data well, it cannot update user habits in real time and give push, it cannot track and record user habits for a long time and learn users' complex behavior patterns from multi-device data. This leads to negative feedback from users because the system cannot fully understand and adapt to users' personalized needs.

[0030] In recent years, with the rapid development of intelligent computing and machine learning technologies, there have been some attempts to use multi-source device data for user behavior learning. However, these systems still have certain limitations in data processing and learning algorithms, and cannot achieve comprehensive and accurate learning of user operating habits, limited by manually set rules or relying on data from specific devices. Many smart assistant applications (such as voice assistants and smart home control systems) use a single data source from a single device for user behavior learning and task push. These applications usually obtain user input through voice or image recognition technology, and then perform tasks based on predefined rules or simple pattern matching.

[0031] The workflow of the traditional intelligent push system:

[0032] (1) Voice / image input: Users input voice or image information through the smart assistant application. For example, users may say “turn on the lights when I get home at night” or take a photo of the lighting status at home.

[0033] (2) Rule matching: The application has a set of predefined rules built in, which are based on common user needs and simple pattern matching. For example, a rule may include "turn on the lights when you get home at night."

[0034] (3) Task execution: When the user’s voice or image input matches a rule, the system executes the task associated with the rule, for example, turning on the lights in a smart home.

[0035] Technical bottlenecks of traditional intelligent push systems:

[0036] (1) Limited learning ability: The learning ability of existing systems is limited to predefined rules and cannot adapt to complex and changing user needs and environmental changes.

[0037] (2) Single data source: Most systems rely on data from a single device and are unable to fully understand user behavior in different scenarios.

[0038] (3) Simple task push: The task push of existing systems is usually based on simple rule matching, lacks intelligence, and cannot achieve deep understanding and dynamic response to users' personalized needs.

[0039] (4) Users need to set rules manually: Existing systems usually require users to set rules manually, which increases the user's operational burden and fails to accurately capture the user's potential and subtle habits.

[0040] In summary, in order to solve the technical problems in the related art, the embodiments of the present disclosure provide a method for processing user data, which obtains the original data of at least two devices of the user from the cloud, wherein the original data of different devices have different formats; converts the format of the original data of at least two devices to form event data of at least two devices, and the event data is a trigger-condition-action data pair; uses a preset algorithm to perform data learning on the event data to obtain the user's task data; and pushes the task data to the cloud and / or at least two devices. By integrating multi-source device data, adopting deep learning algorithms, and realizing time-driven task push. This technical solution aims to improve user experience and system adaptability by efficiently learning the user's operating habits and realizing more flexible and intelligent task push in various application scenarios.

[0041] The data transmission method provided by the present application will be described in detail below with reference to the accompanying drawings.

[0042] Figure 1 This is a system architecture diagram proposed for an embodiment of the present disclosure, the system 100 includes a terminal 101 and a cloud 102, wherein the terminal can be a user's mobile device, such as a mobile phone, etc., and the cloud can be a network device, such as a server, etc., which is not limited by the present disclosure.

[0043] In some embodiments of the present disclosure, the terminal may include a raw data acquisition layer, a data processing layer, a habit learning layer, and an execution layer. The raw data acquisition layer can be used to acquire data from the cloud or other devices, such as usage data of other devices related to the user. The data processing layer can process the raw data, such as performing format conversion to convert the acquired raw data format into a unified format. The habit learning layer can learn the data to generate task data that conforms to the user's habits. The execution layer can determine whether the trigger conditions are met and execute the corresponding task.

[0044] The cloud can include the IoT device cloud (i.e., IOT cloud), terminal cloud (e.g., mobile phone tapping), wearable device cloud (e.g., sports health cloud), car cloud, data cloud, algorithm cloud control and event library input, cloud synchronization platform, etc. The IoT device cloud (i.e., IOT cloud), terminal cloud (e.g., mobile phone tapping), wearable device cloud (e.g., sports health cloud), and car cloud can store data from different devices. Data cloud can be used to store data of various devices in a unified format. Algorithm cloud control and event library input can store machine learning and deep learning algorithms, as well as some scenarios of multi-user learning, such as an action being executed after each trigger action performed by a user.

[0045] Figure 2 A schematic diagram of a system proposed in an embodiment of the present disclosure is shown.

[0046] like Figure 2 As shown in the figure, the system includes the cloud and the terminal. The terminal pushes the task to the device center and the audio and video center through data acquisition service, mobile phone behavior monitoring service, algorithm, local database, task push library, task execution library, and automated task processing service. The cloud includes data storage, data cloud, algorithm cloud control & event library input, cloud synchronization & IOT cloud.

[0047] The data stored includes IOT cloud, mobile phone management, sports health cloud, car cloud and other data. Mobile phone management refers to the data stored in the local database of the mobile phone for uploading various data, such as GPS data or WIFI data, etc. The sports health cloud stores information such as the user's running heart rate and pace stored on the sports equipment, and the car cloud stores information such as the driving speed, location, parking position and other information of the user's vehicle equipment.

[0048] Data upload to the cloud means converting the data uploaded in the previous step into formatted data and uploading it to the cloud. For example, unstructured data from different devices can be converted into structured data and uploaded to the cloud for subsequent learning.

[0049] Algorithm cloud control & event library input includes some scenarios to be learned and the algorithm library also needs to be saved in the cloud for terminal calls to learn. This part is used for learning automatic tasks, that is, the algorithm can be learned flexibly and the learning library can also be added, deleted, modified and checked.

[0050] Cloud Sync & IOT Cloud saves the tasks that have not been pushed and the automatic tasks that have been generated by the terminal through this method. This part includes the generated automatic tasks, that is, the tasks that have been pushed to the user according to the user's operating habits, and some tasks that have been automatically learned, that is, the tasks generated by the terminal through learning but not yet pushed to the user.

[0051] Figure 3 1 is a flow chart of a method for processing user data proposed in an embodiment of the present disclosure. The method is executed by a terminal, specifically, the terminal may be the above-mentioned terminal 101, such as a mobile phone. Figure 3 As shown, the method includes the following steps.

[0052] Step 301, obtaining original data of at least two devices of the user from the cloud.

[0053] In some embodiments, a user (e.g., user A) may have operation permissions for a terminal and at least two devices. The terminal of user A may obtain original data of at least two devices of user A from the cloud. The at least two devices may include the terminal itself (e.g., the terminal may obtain historical data of the terminal from the cloud, such as data from two years ago), or other devices except the terminal itself.

[0054] In some optional embodiments, the original data of different devices may have different formats. For example, the original data of each device may be unstructured data. After the terminal obtains the original data of each device, it may convert the data format of the unstructured data so that the original data of each device is structured data.

[0055] In some optional embodiments, the original data of different devices may be data that has been format-converted by each device, that is, the original data of each device acquired by the terminal are all formatted data.

[0056] In some embodiments, the raw data may include at least one of device information, operation information, and status information. For example, the device information may be the type, name, or model of the device, where the type may be a major category or a sub-category under a major category, such as wearable devices (major category), sports watches (sub-category under the major category of wearable devices); the name may be the name of the same type of device, such as bedroom door, kitchen door; the model may be the model of the same type of device, for example, different lamps have different models. Operation information may be operations on the device, such as opening and closing a door. Status information may be the continuous state of the device, such as a sweeping robot being in working state or standby state, or in wifi connected state, etc.

[0057] Optionally, the terminal can obtain the original data of the user's related IoT devices from the IoT device cloud in the cloud, such as the original data of the sweeping robot. Optionally, the terminal can obtain the original data of the terminal device related to the user from the terminal cloud in the cloud, such as the GPS data or wifi data of the terminal, or the historical usage data of the terminal. Optionally, the terminal can obtain the original data of the wearable device related to the user from the wearable device cloud in the cloud, such as the user's motion data, or the connection status of the wearable device and the terminal; Optionally, the terminal can obtain the original data of the vehicle related to the user from the vehicle cloud in the cloud, such as the opening and closing status of the door, the vehicle location, etc.

[0058] Step 302: Convert the format of original data of at least two devices to form event data of at least two devices.

[0059] In some embodiments, the event data is a trigger-condition-action data pair.

[0060] In some embodiments, the terminal may convert the format of the original data obtained from at least two devices so that the original data of each of the multiple devices can form an event data pair of "trigger-condition-action", thereby breaking through the data barriers between the multiple devices.

[0061] In some embodiments, the terminal can extract fields or tags in the original data, and determine which part of the original data is a "trigger", which part is a "condition", and which part is an "action" based on the fields or tags of the original data of each device, thereby forming event data between multiple devices.

[0062] For example, the terminal obtains the original data and weather data of a certain number of curtains of the user. The user is accustomed to opening the curtains in the morning when the sun comes out and the weather is fine. The original data can form event data of "when the sun comes out" (trigger) - "fine weather" (condition) - "open the curtains" (action).

[0063] In the embodiments of the present disclosure, by converting the raw data of multiple devices into event data in a fixed format, the data barriers between multiple devices can be broken down, facilitating subsequent data learning, thereby generating and pushing data that conforms to user habits.

[0064] Step 303: Use a preset algorithm to perform data learning on the event data to obtain the user's task data.

[0065] In some embodiments, the preset algorithm may be a machine learning algorithm, a deep learning algorithm, a neural network algorithm, etc., which is not limited by the present disclosure.

[0066] In some embodiments, the terminal may obtain the preset algorithm from the cloud. For example, the terminal may obtain the preset algorithm from an algorithm cloud control platform or an event library platform in the cloud.

[0067] In some embodiments, the preset algorithm may be trained by device usage data of multiple users. For example, the training data of the preset algorithm may be obtained by training the usage data of multiple users on various devices, wherein the training data may be high-frequency data, such as a certain proportion of users opening curtains within a certain time range.

[0068] In some embodiments, the learned task data may be encapsulated into a unified format, namely, a trigger-condition-action pair. In other words, the task data and the event data may have the same data structure. The learned task data reflects the user's device usage habits.

[0069] For example, the terminal may learn from event data that the user turns on the light after opening the door at 10 pm, thus forming a trigger-condition-action pair, where the trigger is 10 pm, the condition is opening the door, and the action is turning on the light, forming task data. The task data reflects the user's habit of turning on the light.

[0070] For another example, the task data may be "open the curtains when the sun is out and it is sunny", where the trigger is the time when the sun is out, the condition is sunny, and the action is to open the curtains. This task data reflects the user's operating habits on the curtains.

[0071] Step 304: Push the task data to the cloud and / or at least two devices.

[0072] In some embodiments, the terminal may push the learned task data to the cloud, for example, to a cloud synchronization platform in the cloud, so as to save the user's operating habits in the cloud.

[0073] In some embodiments, the terminal may store the learned task data locally, for example, in a local database, so that the terminal can perform related tasks locally.

[0074] In some embodiments, the terminal can make a conflict judgment on the learned task data. For example, if the previously generated task data indicates "turn on the lights at 10 o'clock" and the currently generated task data indicates "turn off the lights at 10 o'clock", then there is a conflict between the current task data and the historical task data. The terminal can adopt an appropriate conflict resolution mechanism, such as deleting historical data, or further judging whether the current task data reflects the user's true intention (for example, popping up a window to the user to ask whether to turn off the lights at 10 o'clock).

[0075] In some embodiments, the terminal can perform a push operation when the trigger condition is met, for example, at ten o'clock, the task data is pushed to the home smart light to instruct the smart light to turn off. Optionally, the terminal can also directly push the task data to the home smart light, and the smart light determines whether the trigger condition is currently met, and performs the turn-off operation when the trigger condition is met.

[0076] In the embodiments of the present disclosure, the task data obtained through learning can be pushed or executed as an automatic task, thereby simplifying user operations and improving the intelligence level of multi-device interaction.

[0077] In some embodiments, the event data, such as structured data, may be converted back into a form executable by devices such as IOT, such as JSON format, before executing step 304. It should be understood that the converted JSON format data still conforms to the data structure before conversion, that is, including the three parts of trigger-condition-action.

[0078] In summary, according to the embodiments of the present disclosure, the terminal obtains the original data of at least two devices of the user from the cloud, converts the format of the original data of at least two devices to form a trigger-condition-action data pair, uses a preset algorithm to perform data learning on the event data to obtain the user's task data, and pushes the task data to the cloud and / or at least two devices, thereby realizing cross-device collaborative interaction, being able to continuously learn the user's behavior changes, realizing personalized task push and accurate automatic push for the user, reducing the user's operating burden, and improving the device's usability and flexibility.

[0079] Figure 4 A flowchart of a user data processing method provided by an embodiment of the present disclosure. Figure 3 The embodiment shown, Figure 4 right Figure 3 Step 302 in is further described. Figure 4 The illustrated embodiment may include the following steps.

[0080] Step 401, respectively establish data tables for the original data of different devices.

[0081] In some embodiments, data tables for different devices are identified by device class or device model.

[0082] In some embodiments, the raw data from different devices is unstructured data.

[0083] In some embodiments, the unstructured data may be data in a json structure, including device information and the following operation and status information.

[0084] The operation information may be instantaneous information, and the state information may be continuous information. For example, the original data is that the light is turned on when the door is opened at 10 o'clock, the operation information is the door is opened, the state information is 10 o'clock, and the corresponding action is to turn on the light.

[0085] In some embodiments, the raw data includes at least one of device information, operation information, and status information.

[0086] For example, the user needs to open the curtains when the sun is out and it is sunny. In this scenario, the curtains and local sunrise and sunset information are needed. At this time, it is necessary to create separate tables and select different fields to save in the database according to different categories and device models under the category. For example, the categories are curtains and lights. Different lights have different models. The collected fields need to meet the needs of various automatic tasks.

[0087] In some embodiments, data tables of different categories correspond to different classes and inheritance relationships and may share some attributes.

[0088] Step 402: Determine the label of the original data in the data table according to the user's usage data of at least two devices.

[0089] In some embodiments, tags include triggers, conditions, and actions.

[0090] Step 403: transform the original data into event data according to the label of the original data.

[0091] In some embodiments, the event data is a trigger-condition-action data pair.

[0092] In the embodiments of the present disclosure, unstructured raw data is converted into structured event data by converting the format of raw data on different devices, and the same data format is used for subsequent learning so that the system can push accurate information to users.

[0093] Figure 5 A flowchart of a user data processing method provided by an embodiment of the present disclosure. Figure 3The embodiment shown, Figure 5 right Figure 3 Step 303 in the embodiment is further described. Figure 5 The illustrated embodiment may include the following steps:

[0094] Step 501, obtaining a preset algorithm from the algorithm cloud control platform or event library platform in the cloud.

[0095] In some embodiments, the preset algorithm is trained using device usage data of multiple users.

[0096] In some embodiments, the preset algorithm may be trained by the present device, or may be trained by other devices and provided to the present device for use.

[0097] Step 502, extract multiple fields of event data, use a preset algorithm to learn the user's device usage rules to obtain the user's task data.

[0098] In some embodiments, the task data is a trigger-condition-action data pair.

[0099] For example, if the system learns that the user turns on the lights after opening the door at 10 pm, a trigger-condition-action pair will be formed, where the trigger is 10 pm, the condition is opening the door, and the action is turning on the lights.

[0100] In the embodiments of the present disclosure, a preset algorithm is applied based on event data to learn the user's operating habits, and the user habits are encapsulated into unified task data so that the system can push the corresponding operating habits to the user when conditions are met.

[0101] Figure 6 A flowchart of a user data processing method provided by an embodiment of the present disclosure. Based on the embodiment shown in 3, Figure 6 Yes Figure 3 Further description of the embodiments. Figure 3 The step 304 shown further includes the following steps:

[0102] Step 601, obtaining the user's historical data from the cloud or local database.

[0103] In some embodiments, the historical data is previously generated historical task data.

[0104] In some embodiments, the historical data is a trigger-condition-action data pair.

[0105] Step 602: Determine whether there is a conflict between the user's historical data and the task data.

[0106] In some embodiments, it is determined whether there is a difference between the data pair of the user history data and the data pair of the task data. If there is a difference between the data pairs, it indicates that there is a conflict.

[0107] Step 603: Send a deletion instruction to the cloud to instruct the cloud to delete the historical data that conflicts with the task data, or delete the historical data that conflicts with the task data from the cloud and / or the local database.

[0108] In the embodiments of the present disclosure, conflict detection of historical data in the cloud and / or local database can update the database in a timely manner to ensure the accuracy of the information pushed by the system.

[0109] Figure 7 FIG. 1 is a flow chart of an embodiment of the present disclosure. Figure 7 As shown,.

[0110] 1. First, save the users of mobile phones, IOT, wearable devices and cars, and save the data in the cloud after structured processing.

[0111] (I) Obtaining data

[0112] 1. The data obtained from mobile phones, IOT devices, and vehicle systems are some unstructured JSON structured data, including device information as well as some operation and status information.

[0113] 2. It is necessary to define the databases of the devices that need to be collected and create database tables for these devices. For example, the user needs to open the curtains when the sun is out and it is sunny. In this scenario, the curtains and the local sunrise and sunset information are needed, so we need to create tables separately.

[0114] 3. According to different categories (curtains, lights, etc.) and device models under the categories (different lights have different models), select different fields and save them in the database. These collected fields need to meet the needs of various automatic tasks.

[0115] 4. The database tables for all the above categories correspond to different classes and inheritance relationships in the code, and share some attributes.

[0116] 5. After getting the data of the corresponding class in the code, you can start learning. Different scenarios correspond to the acquisition of different fields of different classes, as well as the learning of different algorithms.

[0117] Step (a) shows Figure 4 The method flow chart of step 401 is as follows, that is, data tables are established respectively for the original data of different devices.

[0118] (II) Automatic task generation

[0119] 1. The automatic tasks learned by the algorithm will be generated in the form of trigger-condition-action, such as when the trigger event is triggered (the time when the sun rises locally), the condition (it is sunny at this time), and the action (open the curtains).

[0120] 2. The task is divided into three parts: trigger-condition-action. At this time, we need to convert the structured data (data in the database table) back into an executable form such as IOT devices, such as json format. This json includes the three parts of trigger-condition-action and the operation information of different devices.

[0121] 3. At this time, the json corresponding to the automatic task will be saved in the push library and pushed to the user. If the user agrees to generate the automatic task, it will be inserted into the task execution library and will be backed up in the cloud to handle automatic task conflicts.

[0122] Step (ii) shows Figure 5 The method flow chart shown includes obtaining a preset algorithm from the cloud algorithm cloud control platform or event library platform in the cloud, extracting multiple fields of event data, and using the preset algorithm to learn the user's device usage rules to obtain the user's task data, wherein the task data is a trigger-condition-action data pair.

[0123] Second, a case library is also saved in the cloud, which stores some scenarios that we hope to teach a certain user. For example, when a user executes a certain trigger each time, an action is executed. If this case is added to the cloud case library, the user may learn from it when he has this habit.

[0124] The case library is Figure 2 The event library in is input, and the case library is used to investigate user needs and high-frequency automatic tasks, which are saved in the cloud case library for subsequent algorithm calls.

[0125] 3. After a user's data is obtained in the cloud, we filter and learn the user's operation records based on the case library in the previous step. This step can be done by modifying the cloud code to perform cloud control of the learning task.

[0126] Step 3 shows that Figure 6The method flow chart includes: obtaining the user's historical data from the cloud or local database, where the historical data is the historical task data generated in advance; determining whether the user's historical data conflicts with the task data; sending a deletion instruction to the cloud to instruct the cloud to delete the historical data that conflicts with the task data, or deleting the historical data that conflicts with the task data from the local database.

[0127] 4. The tasks learned in the previous step will be synchronized to the task push library. After the push library is pushed and the user agrees, it will be saved as an automatic task. When a trigger is triggered, an action will be executed to realize the interconnection of all things.

[0128] Step 4 shows that Figure 3 The method flow shown in step 304 in FIG.

[0129] Figure 8 FIG. 1 is a schematic diagram of the structure of a user data processing device according to an embodiment of the present disclosure. Figure 8 As shown, the device comprises:

[0130] An acquisition module 810 is used to acquire original data of at least two devices of a user from the cloud, wherein the original data of different devices have different formats;

[0131] The format conversion module 820 is used to convert the format of the original data of at least two devices to form event data of at least two devices, where the event data is a trigger-condition-action data pair;

[0132] The learning module 830 is used to perform data learning on the event data using a preset algorithm to obtain the user's task data;

[0133] The push module 840 is used to push the task data to the cloud and / or at least two devices.

[0134] In some embodiments, the original data obtained by the acquisition module 810 from the cloud includes at least two of the following: obtaining the original data of the Internet of Things devices related to the user from the Internet of Things device cloud in the cloud; obtaining the original data of the terminal devices related to the user from the terminal cloud in the cloud; obtaining the original data of the wearable devices related to the user from the wearable device cloud in the cloud; obtaining the original data of the vehicles related to the user from the vehicle cloud in the cloud.

[0135] In some embodiments, the format conversion module 820 is used to: establish data tables for the raw data of different devices, respectively, wherein the data tables of different devices are identified by device categories or device models; determine labels of the raw data in the data table based on user usage data of at least two devices, wherein the labels include triggers, conditions, and actions; and form the raw data into event data based on the labels of the raw data.

[0136] In some embodiments, the learning module 830 is used to: obtain a preset algorithm from an algorithm cloud control platform or an event library platform in the cloud, wherein the preset algorithm is trained through device usage data of multiple users; extract multiple fields of event data, and use the preset algorithm to learn the user's device usage rules to obtain the user's task data, wherein the task data is a trigger-condition-action data pair.

[0137] In some embodiments, the task data pushed by the push module 840 to the cloud and / or at least two devices includes at least one of the following: pushing the task data to a cloud synchronization platform on the cloud; when the task data meets the trigger conditions, pushing the task data to the device corresponding to the task data to instruct the device to perform the operation corresponding to the task data; when the task data meets the trigger conditions, pushing the task data to the cloud platform corresponding to the device.

[0138] In some embodiments, the device 800 also includes a conflict detection module, which is used to: obtain the user's historical data from the cloud or a local database, where the historical data is the historical task data generated in advance; determine whether there is a conflict between the user's historical data and the task data; send a deletion instruction to the cloud to instruct the cloud to delete the historical data that conflicts with the task data, or delete the historical data that conflicts with the task data from the local database.

[0139] In some embodiments, the original data of at least two devices are unstructured data, and the original data includes at least one of device information, operation information, and status information.

[0140] Fig. 9 is a schematic structural diagram of an electronic device 900 for implementing the above-mentioned user data processing method according to an exemplary embodiment.

[0141] For example, the electronic device 900 may be a mobile phone, a computer, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0142] Reference Fig. 9 , the electronic device 900 may include one or more of the following components: a processing component 902 , a memory 904 , a power component 906 , a multimedia component 908 , an audio component 910 , an input / output (I / O) interface 912 , a sensor component 914 , and a communication component 916 .

[0143] The processing component 902 generally controls the overall operation of the electronic device 900, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.

[0144] The memory 904 is configured to store various types of data to support operations on the electronic device 900. Examples of such data include instructions for any application or method operating on the electronic device 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0145] The power supply component 906 provides power to the various components of the electronic device 900. The power supply component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 900.

[0146] The multimedia component 908 includes a screen that provides an output interface between the electronic device 900 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 908 includes a front camera and / or a rear camera. When the electronic device 900 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0147] The audio component 910 is configured to output and / or input audio signals. For example, the audio component 910 includes a microphone (MIC), and when the electronic device 900 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 904 or sent via the communication component 916. In some embodiments, the audio component 910 also includes a speaker for outputting audio signals.

[0148] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0149] The sensor assembly 914 includes one or more sensors for providing various aspects of status assessment for the electronic device 900. For example, the sensor assembly 914 can detect the open / closed state of the electronic device 900, the relative positioning of components, such as the display and keypad of the electronic device 900, and the sensor assembly 914 can also detect the position change of the electronic device 900 or a component of the electronic device 900, the presence or absence of user contact with the electronic device 900, the orientation or acceleration / deceleration of the electronic device 900, and the temperature change of the electronic device 900. The sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 914 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 914 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0150] The communication component 916 is configured to facilitate wired or wireless communication between the electronic device 900 and other devices. The electronic device 900 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR (NewRadio) or a combination thereof. In an exemplary embodiment, the communication component 916 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 916 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0151] In an exemplary embodiment, the electronic device 900 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0152] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, and the instructions can be executed by the processor 920 of the electronic device 900 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0153] The embodiments of the present disclosure further provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the power determination method described in the above embodiments of the present disclosure.

[0154] The embodiments of the present disclosure further provide a computer program product, including a computer program, and the computer program is executed by a processor to execute the data transmission method described in the above embodiments of the present disclosure.

[0155] Fig.10 FIG. 1 is a schematic diagram of a structure of a chip 1000 for implementing the above-mentioned user data processing method according to an exemplary embodiment. Fig.10 The chip 1000 includes at least one communication interface 1001 and a processor 1002. The communication interface 1001 is used to receive a signal input to the chip 1000 or a signal output from the above chip 1000. The processor 1002 communicates with the communication interface 1001 and implements the power determination method described in the above embodiment of the present disclosure through a logic circuit or executing code instructions.

[0156] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0157] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0158] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present disclosure includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0159] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processing module, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (control method), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0160] It should be understood that the various parts of the embodiments of the present disclosure can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0161] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0162] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0163] Although the embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present disclosure. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A user data processing method, characterized in that: The method comprises: Obtaining original data of at least two devices of the user from the cloud, wherein the original data of different devices have different formats; Performing format conversion on the original data of the at least two devices to form event data of the at least two devices, wherein the event data is a trigger-condition-action data pair; Using a preset algorithm, performing data learning on the event data to obtain the task data of the user; The task data is pushed to the cloud and / or the at least two devices.

2. The method according to claim 1, characterized in that The obtaining of original data of at least two devices of the user from the cloud includes at least two of the following: Obtaining original data of the IoT device related to the user from the IoT device cloud in the cloud; Acquire original data of the terminal device related to the user from the terminal cloud in the cloud; Acquire raw data of the wearable device related to the user from the wearable device cloud in the cloud; The original data of the vehicle related to the user is obtained from the vehicle cloud in the cloud.

3. The method according to claim 1, characterized in that The converting the format of the original data of the at least two devices to form the event data of the at least two devices includes: For the original data of different devices, data tables are established respectively, where the data tables of different devices are identified by device category or device model; Determine, according to the usage data of the at least two devices by the user, a label of the original data in the data table, wherein the label includes a trigger, a condition, and an action; The original data is transformed into the event data according to the label of the original data.

4. The method according to claim 1, characterized in that The using a preset algorithm to perform data learning on the event data to obtain the task data of the user includes: Obtaining the preset algorithm from the algorithm cloud control platform or event library platform in the cloud, wherein the preset algorithm is trained by device usage data of multiple users; Extract multiple fields of the event data, and use the preset algorithm to learn the device usage rules of the user to obtain the task data of the user, wherein the task data is a trigger-condition-action data pair.

5. The method according to claim 1, characterized in that After obtaining the task data of the user, the method further includes: Acquire the user's historical data from the cloud or local database, where the historical data is previously generated historical task data; Determine whether the historical data of the user conflicts with the task data; A deletion instruction is sent to the cloud to instruct the cloud to delete the historical data that conflicts with the task data, or the historical data that conflicts with the task data is deleted from the local database.

6. The method according to any one of claims 1 to 5, characterized in that The pushing of the task data to the cloud and / or the at least two devices comprises at least one of the following: Pushing the task data to the cloud synchronization platform in the cloud; When the task data meets the trigger condition, the task data is pushed to the device corresponding to the task data to instruct the device to perform the operation corresponding to the task data; When the task data meets the triggering condition, the task data is pushed to the cloud platform corresponding to the device.

7. The method according to claims 1 to 5, characterized in that The original data of the at least two devices are unstructured data, and the original data includes at least one of device information, operation information and status information.

8. A user data processing device, characterized in that: include: An acquisition module, used to acquire original data of at least two devices of a user from the cloud, wherein the original data of different devices have different formats; a format conversion module, used for performing format conversion on the original data of the at least two devices to form event data of the at least two devices, wherein the event data is a trigger-condition-action data pair; A learning module, used to perform data learning on the event data using a preset algorithm to obtain the task data of the user; A push module is used to push the task data to the cloud and / or the at least two devices.

9. An electronic device, characterized in that: include: A memory for storing processor executable instructions; A processor is configured to execute the executable instructions in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A chip, characterized in that: include: one or more interface circuits and one or more processors; The interface circuit is used to receive a signal from a memory of an electronic device and send the signal to the processor, wherein the signal includes a computer instruction stored in the memory; when the processor executes the computer instruction, the electronic device executes the method according to any one of claims 1 to 7.

Images