Equipment control methods, devices, electronic equipment and computer storage media

Abstract

This application provides a device control method, apparatus, electronic device, and computer storage medium. The method includes: acquiring a context feature vector corresponding to the current context; determining the current target context based on the context feature vector; generating a target control instruction based on the current target context, the target control instruction being used to instruct a target device associated with the target context to perform a target control operation, the target control operation being related to the target context; and sending the target control instruction to the target device. Through this technical solution, target control operations on the target device can be automatically triggered in different contexts without requiring manual operation by the user, reducing the complexity of user operations on the device cluster and improving the user experience.

Description

Technical Field

[0001] This application relates to the field of interactive control technology, and in particular to a device control method, apparatus, electronic device, and computer storage medium. Background Technology

[0002] With the widespread adoption of wearable devices, smartphones, in-vehicle infotainment (IVI) systems, and smart TVs, users need to operate different devices in different usage scenarios to control different objectives.

[0003] For example, in a meeting scenario, a user might need to operate their smartphone to set the device to "Do Not Disturb" mode; or, in a driving scenario, a user might need to operate the vehicle's infotainment system to launch a navigation application for driving navigation; or, in a home scenario, a user might need to operate their smartphone and TV to achieve screen mirroring, etc.

[0004] Controlling multiple terminal devices increases the complexity of user operations, and the user experience needs to be improved. Summary of the Invention

[0005] In view of this, embodiments of this application provide a device control method, apparatus, electronic device, and computer storage medium to solve the above problems.

[0006] According to a first aspect of the embodiments of this application, a device control method is provided, applied to an execution device, the method comprising: obtaining a context feature vector corresponding to a current context, the context feature vector including scene feature parameters, device feature parameters, and user parameters; determining a target context based on the context feature vector corresponding to the current context; generating a target control instruction based on the target context, the target control instruction being used to instruct a target device associated with the target context to perform a target control operation, the target control operation being related to the target context; and sending the target control instruction to the target device.

[0007] According to a second aspect of the embodiments of this application, a device control apparatus is provided, comprising: a data acquisition module, configured to acquire a context feature vector corresponding to a current context, the context feature vector including scene feature parameters, device feature parameters, and user parameters; a decision module, configured to determine a target context based on the context feature vector corresponding to the current context; an execution module, configured to generate a target control instruction based on the target context, the target control instruction being used to instruct a target device associated with the target context to perform a target control operation, the target control operation being related to the target context; and a sending module, configured to send the target control instruction to the target device.

[0008] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, wherein the executable instruction causes the processor to perform an operation corresponding to the method described in the first aspect.

[0009] According to a fourth aspect of the embodiments of this application, a computer storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0010] The above technical solution enables automatic triggering of target control operations on target devices in different scenarios, eliminating the need for manual user operation. This reduces the complexity of operating device clusters and improves user experience. Furthermore, the solution utilizes multi-dimensional sensor data for scenario recognition, enhancing accuracy and ensuring that automatically triggered control operations better meet user expectations. Additionally, the scenario categories, corresponding target devices, and control rules can all be expanded via configuration files, supporting user customization without requiring firmware upgrades and demonstrating excellent scalability. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0012] Figure 1 This is a schematic diagram of a device cluster provided in an embodiment of this application; Figure 2 A flowchart of a device control method provided in an embodiment of this application; Figure 3 A schematic diagram of the structure of a decision tree model provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of a device control system provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of the device control apparatus provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in the embodiments of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art should fall within the protection scope of the embodiments of this application.

[0014] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0015] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0016] It should also be noted that the terms "first, second, and third" used in the embodiments of this application are only used to distinguish similar objects and do not represent a specific order of objects. It is understood that "first, second, and third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0017] Furthermore, in the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0018] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0019] This application provides a device control method that can be used to automatically identify a target device associated with the current situation from a device cluster based on situational changes, and generate target control instructions to control the target device to perform control operations related to the current situation.

[0020] Figure 1 A schematic diagram of the device cluster provided in this application, such as Figure 1As shown, the device cluster may include multiple terminal devices, which can be of different types, such as smartphones, smartwatches, Bluetooth headsets, in-vehicle systems, smart TVs, smart home devices, etc.

[0021] The device control method provided in this application can be applied to any type of terminal device in a device cluster, such as a smartphone, to control other terminal devices in the device cluster; alternatively, the device control method provided in this application can also be executed collaboratively by multiple terminal devices in the device cluster, such as by a smartphone and a smartwatch, to control other terminal devices in the device cluster. This application does not impose any limitations on this.

[0022] The specific implementation of the device control method provided in this application will be described below with reference to the accompanying drawings. For ease of description and understanding, in the subsequent embodiments of this application, the device used to execute the device control method provided in the embodiments of this application will be referred to as the "execution device," and the controlled device of the device control method provided in the embodiments of this application will be referred to as the "target device."

[0023] Figure 2 This is a flowchart illustrating a device control method provided in an embodiment of this application. Figure 2 As shown, the device control method provided in this application embodiment may include: 101. Obtain the context feature vector corresponding to the current context.

[0024] In this embodiment, the context feature vector may include scene feature parameters, device feature parameters, and user parameters. Scene feature parameters may include at least one of the following: average ambient brightness, location information, and time period information. Device feature parameters may include at least one of the following: average acceleration, acceleration variance, average motion speed, and external device connection status. External device connection status may include, for example, in-vehicle Bluetooth connection status, Wi-Fi connection status, and screen projection device connection status. User parameters may include user physiological feature parameters and historical behavior logs. Historical behavior logs may include the probability of being in various contexts during the current time period. User physiological feature parameters may include, for example, average heart rate. Different feature parameters can be obtained based on context-aware data collected by various sensing units in the device.

[0025] Specifically, firstly, the execution device can acquire context-aware data collected by each sensing unit within a preset time period. Each sensing unit can include, for example, an accelerometer, an ambient light sensor, a heart rate sensor, a positioning device, and a system clock. Each sensing unit can collect context-aware data in real time according to a set cycle, including acceleration data, ambient light intensity data, heart rate data, positioning data, and time data. Furthermore, context-aware data collected within the most recent preset time period (e.g., the last 5 seconds) can be cached to obtain context-aware data collected within the preset time period. In this implementation, each sensing unit can be located within the execution device, allowing the execution device to directly obtain context-aware data based on its own configured sensing units. Alternatively, each sensing unit can be located in another device, allowing another device (e.g., a smartwatch) to collect context-aware data and send it to the execution device (e.g., a smartphone).

[0026] Then, the execution device can perform target calculations on the context-aware data collected by each sensing unit to obtain the feature parameters corresponding to the context-aware data collected by each sensing unit. For example, it can calculate the mean and variance of acceleration data within a preset time period to obtain the mean acceleration and variance acceleration; it can calculate the mean of ambient light brightness data within a preset time period to obtain the mean ambient light; it can calculate the mean of heart rate data within a preset time period to obtain the mean heart rate; it can perform time period matching on time data to obtain the time period to which the current time belongs, such as determining the late night period when the time is between 0 and 6; it can perform geofencing matching on location data to obtain the current location, such as determining the current location as "company" or "home" based on location data.

[0027] Finally, the execution device can obtain the context feature vector corresponding to the current context based on the feature parameters corresponding to the context perception data collected by each sensing unit. The context feature vector may include, for example, a set of feature parameters corresponding to each context perception data. For example, the context feature vector can be implemented as V = [F1, F2… Fn].

[0028] Based on the aforementioned multi-dimensional feature parameters, the accuracy of subsequent context recognition can be improved.

[0029] 102. Identify the target context based on the context feature vector corresponding to the current context.

[0030] In this embodiment, after obtaining the current context feature vector, the context vector features can be input into a pre-trained target model. The target model can be, for example, a decision tree model, such as a Classification and Regression Tree (CART). When the execution device is a device with low computing power or short battery life (such as a watch), the decision tree model deployed in the execution device can be, for example, a lightweight decision tree model with a depth of no more than 6 layers. Decision tree models have shorter inference time and higher recognition accuracy in context recognition scenarios. Compared with neural network model solutions, they can reduce the power consumption of a single inference. Furthermore, by deploying the model on the execution device side, the efficiency of the execution device in obtaining context recognition results can be improved, which in turn helps to improve the control efficiency of the target device. Thus, based on context switching, low-latency control of the target device can be achieved, resulting in a smoother user experience.

[0031] Furthermore, the current target context can be determined based on the output of the target model. The context category of the target context may include, for example, exercise, commuting, sleeping, driving, meeting, and staying at home. The output of the target model may include, for example, the context recognition result and the confidence level of the context recognition result. In this embodiment, if the confidence level of the context recognition result is not less than a confidence threshold, the context recognition result can be determined as the current target context. If the confidence level of the context recognition result is less than the confidence threshold, the aforementioned method steps can be repeated to determine the target context again. The confidence threshold may, for example, be 85%.

[0032] In one specific implementation, the feature parameters included in the aforementioned context feature vector may further include prior data, which may include the probability of occurrence of different contexts within the same historical time period. In this implementation, after obtaining the confidence level of the context recognition result based on the target model, the confidence level output by the target model can be corrected based on the prior data to obtain a corrected confidence level. For example, based on the prior data, the probability of occurrence of the context indicated by the context recognition result within the same historical time period can be obtained. Then, the confidence level output by the target model can be corrected based on this probability of occurrence to obtain a corrected confidence level for the context recognition result. For example, a correction weight can be determined based on the probability of occurrence, and then the confidence level output by the target model can be weighted using the correction weight to obtain a corrected confidence level. Furthermore, based on the corrected confidence level, the context recognition result output by the target model can be judged. If the corrected confidence level is not less than a confidence threshold, the context recognition result output by the target model can be determined to be the current target context. Based on this implementation method, prior data can be used to improve the accuracy of the target model's context recognition results, which in turn helps to improve the precision of the equipment control method and make the control operation more in line with user expectations.

[0033] 103. Generate target control instructions based on the current target context.

[0034] In this embodiment of the application, before performing the step of generating target control instructions based on the current target situation, it can be determined that the detected target situation meets the preset conditions.

[0035] In one possible implementation, the preset condition may include: the target context detected this time is different from the previously detected context. In this implementation, after each detection of the current target context, it can be first determined whether the current detected context is consistent with the previously detected context. Only if it is inconsistent with the previously detected context, a target control command can be generated based on the current target context; otherwise, no processing is required, and the aforementioned method flow is re-executed to perform context detection again. This implementation method can prevent the repeated initiation of the same control operation on the same target device under the same context.

[0036] In another possible implementation, the preset conditions may include: the duration for which the confidence level of the target situation is not less than a confidence threshold is not less than a preset duration threshold. The preset duration threshold could be, for example, 2 seconds. This implementation method can prevent situation recognition errors caused by sensor data jitter.

[0037] 104. Send the target control command to the target device.

[0038] The target device can be a device associated with a target context, and the target control command can be used to instruct the target device to perform a target control operation. The target control operation can be a control operation related to the target context. In one possible implementation, the target control operation can be consistent with the current control operation on the executing device. In this implementation, the information about the target control operation contained in the target control command can be generated based on the current control operation on the executing device. For example, in a driving context, if the executing device currently has a navigation application running and the navigation address is a first address, the target control operation could be to launch the vehicle navigation application and navigate to the first address. Alternatively, in another possible implementation, the target control operation can be inconsistent with the current control operation on the executing device. In this implementation, the information about the target control operation contained in the target control command can be pre-configured, or it can be determined based on the user's historical operation data on the target device in this context.

[0039] In this embodiment, the devices associated with different scenarios can be different, and the target control operations indicated by the target control commands in different scenarios can also be different. The target devices corresponding to different scenarios and the target control operations to be performed by the target devices can be pre-configured. Alternatively, the target control operations to be performed by the target devices corresponding to different scenarios can be determined based on the user's historical operation data of the target devices in that scenario.

[0040] For example, assuming the target scenario is a driving scenario, the associated target device can be an in-vehicle infotainment system. The target control operation can include launching the in-vehicle navigation application, and can also include automatically navigating to the target address after launching the in-vehicle navigation application. The target address can be the address currently being navigated to on the executing device, or it can be the address most frequently navigated to by the user during the same historical period. Alternatively, in a driving scenario, the target control operation can also be launching the in-vehicle music playback application, and can also include automatically playing the target audio after launching the in-vehicle music playback application. The target audio can be, for example, the audio currently playing on the executing device, or it can be the audio last played by the user. Assuming the target scenario is a sleep scenario, the associated target device can be a mobile phone, and the target control operation can be launching "Do Not Disturb" mode, etc. Assuming the target scenario is a sports scenario, the associated target device can be a smartwatch, and the target control operation can be launching a sports tracking function, etc.

[0041] The execution device can, for example, send target control commands to the target device based on a preset communication protocol. Different target devices may use different communication protocols. For instance, when the target device is an in-vehicle infotainment system, the communication protocol could be based on Bluetooth Hands-Free Profile (HFP) protocol; when the target device is a mobile phone or tablet, the communication protocol could be Bluetooth Low Energy (BLE) protocol or Wi-Fi Direct protocol; and when the target device is a television, the communication protocol could be the Discovery and Launch (DIAL) protocol within a local area network.

[0042] The above technical solution enables automatic triggering of target control operations on target devices in different scenarios, eliminating the need for manual user operation. This reduces the complexity of operating device clusters and improves user experience. Furthermore, the solution utilizes multi-dimensional sensor data for scenario recognition, enhancing accuracy and ensuring that automatically triggered control operations better meet user expectations. Additionally, the scenario categories, corresponding target devices, and control rules can all be expanded via configuration files, supporting user customization without requiring firmware upgrades and demonstrating excellent scalability.

[0043] The following is an exemplary illustration of how the decision tree model identifies the target context based on the context feature vector corresponding to the current context.

[0044] For example, such as Figure 3 As shown, the decision tree model can include acceleration feature nodes, heart rate feature nodes, time feature nodes, location feature nodes, and multiple leaf nodes. Multiple leaf nodes can be used to output different context recognition results, including sports context, commuting context, driving context, meeting context, home context, etc.

[0045] Based on such Figure 3 The decision tree model shown in the figure has the following characteristics: First, the acceleration node can identify whether there is high-frequency vibration based on characteristic parameters such as the mean acceleration and the variance of acceleration.

[0046] In the presence of high-frequency vibrations, the system can further identify whether the heart rate is continuously increasing based on characteristic parameters such as the mean heart rate using heart rate feature nodes. If a continuous increase in heart rate is detected, the scenario identification result can be output as an exercise scenario. If no continuous increase in heart rate is detected, the scenario identification result can be output as a commuting scenario.

[0047] In the absence of high-frequency vibrations, the system can further identify whether it is nighttime based on time-period feature parameters using time feature nodes. If nighttime is detected, the scenario identification result can be output as a sleep scenario. If it is not nighttime, the system can further identify whether the current location is inside a vehicle based on location feature parameters using location feature nodes. If inside a vehicle, the scenario identification result can be output as a driving scenario. If not inside a vehicle, the scenario identification result can be output as a meeting or home scenario.

[0048] In some examples, it is assumed that the average acceleration in the context feature vector is 0.05 (approaching stillness), the average ambient light is 0 lux (light blocking / lights off), the time period is late at night, and the average heart rate is 55 bpm (resting heart rate). Then, the decision tree model, following the above decision path, can output a "sleep" context with a confidence level of 0.93. When the confidence level in the sleep context is not less than the confidence threshold for at least 2 seconds, a context switch can be triggered, i.e., switching from the previous context to the sleep context. Furthermore, the executing device can send a "Enter Do Not Disturb Mode" control command to the target device (such as a mobile phone).

[0049] The following morning, as the sensor data changes, the decision tree model outputs a "home" scenario. Subsequently, the executing device can send a "cancel Do Not Disturb" control command to the target device (such as a mobile phone) to automatically cancel the Do Not Disturb mode without requiring manual settings from the user.

[0050] Figure 4This is a schematic diagram of a device control system provided in an embodiment of this application. Figure 4 As shown, the system may include a sensor data acquisition layer, a decision-making layer, and a control layer.

[0051] The sensor data acquisition layer can include a variety of sensors, which can be used to collect various types of context-aware data, including acceleration data, ambient light intensity data, heart rate data, positioning data, time data, etc.

[0052] The decision layer may include a feature extraction unit, which processes the context-aware data acquired by the sensor data acquisition layer to obtain a context feature vector corresponding to the current context. Furthermore, the decision layer may also include a decision tree model, which learns the context feature vector to obtain a context recognition result. Additionally, the decision layer may include a historical behavior data analysis unit, which uses the user's historical behavior data to refine the context recognition result and ultimately determine the current target context. The user's historical behavior data may include, for example, the contexts the user was in during similar historical periods.

[0053] The control layer can generate target control commands for the target device based on the current target context, and then send the target control commands to the target device. The target device is the device associated with the current target context, and the target control commands are the control commands associated with the target device under the current target context.

[0054] This application also provides a device control apparatus, such as... Figure 5 As shown, the device control unit may include a data acquisition module 401, a decision-making module 402, an execution module 403, and a transmission module 404.

[0055] The system comprises the following modules: Acquisition module 401, which acquires a context feature vector corresponding to the current context, including scene feature parameters, device feature parameters, and user parameters; Decision module 402, which determines the current target context based on the context feature vector; Execution module 403, which generates a target control command based on the current target context, instructing the target device associated with the target context to perform a target control operation; and Sending module 404, which sends the target control command to the target device.

[0056] In one specific implementation, the acquisition module 401 is specifically used to: acquire the context perception data collected by each sensing unit within a preset time period; perform target operations on the context perception data collected by each sensing unit to obtain the feature parameters corresponding to the context perception data collected by each sensing unit; and obtain the context feature vector corresponding to the current context based on the feature parameters corresponding to the context perception data collected by each sensing unit.

[0057] In one specific implementation, the decision module 402 is specifically used to input the context feature vector corresponding to the current context into the trained target model; and to obtain the current target context based on the output of the target model; the target model includes a decision tree model.

[0058] In one specific implementation, the output of the target model includes the context recognition result and the confidence level of the context recognition result; the decision module 402 is specifically used to determine the context recognition result as the current target context when the confidence level of the context recognition result is not less than the confidence level threshold.

[0059] In one specific implementation, the decision module 402 is further configured to determine the probability of occurrence of the situation indicated by the situation recognition result in the same historical period; and to correct the confidence of the output of the target model based on the probability of occurrence, so as to obtain the corrected confidence of the situation recognition result.

[0060] In one specific implementation, before generating the target control instruction based on the current target situation, the execution module 403 is further configured to determine whether the target situation detected this time meets preset conditions; the preset conditions include: the target situation detected this time is different from the previously detected situation; and / or, the duration for which the confidence level of the target situation is not less than the confidence level threshold is not less than the duration threshold.

[0061] The specific implementation process of the equipment control method executed by the above-mentioned device has been described in detail in the foregoing embodiments, and will not be repeated here.

[0062] Figure 6 A schematic diagram of an electronic device according to an embodiment of this application is shown. The electronic device can be used to execute the device control method provided in the embodiment of this application. The specific embodiments of this application do not limit the specific implementation of the electronic device.

[0063] like Figure 6 As shown, the electronic device may include: a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0064] The processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508. Communication interface 504 is used to communicate with other electronic devices or servers. The processor 502 executes program 510, specifically performing the relevant steps in the above-described device control method embodiments.

[0065] Specifically, program 510 may include program code that includes computer operation instructions.

[0066] Processor 502 may be a CPU, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The smart device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0067] Memory 506 is used to store program 510. Memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0068] Specifically, program 510 can be used to cause processor 502 to perform the following operations: In an optional embodiment, program 510 is further used to cause processor 502 to perform each step in program 510. The specific implementation of each step in program 510 can be found in the corresponding steps and system descriptions in the above-described device control method embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0069] This application also provides a computer program product, including computer instructions that instruct a computing device to perform an operation corresponding to any of the device control methods in the above-described plurality of method embodiments. It should be noted that, depending on implementation needs, the various components / steps described in the embodiments of this application can be broken down into more components / steps, or two or more components / steps or parts of the operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of this application.

[0070] This application also provides a computer-readable storage medium in which the methods described in this application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code downloaded over a network that is originally stored in a remote recording medium or a non-transitory machine-readable medium and will be stored in a local recording medium. Thus, the methods described herein can be processed by software stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as ASIC or FPGA). It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components (e.g., RAM, ROM, flash memory, etc.) capable of storing or receiving software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the device control methods described herein. Furthermore, when a general-purpose computer accesses code used to implement the device control methods shown herein, the execution of the code transforms the general-purpose computer into a dedicated computer for executing the device control methods shown herein.

[0071] Those skilled in the art will recognize that the units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this application.

[0072] It should be noted that, in this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0073] Furthermore, it should be noted that the user-related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data used for training the model, data used for analysis, stored data, displayed data, etc.) involved in the embodiments of this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0074] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0075] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0076] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0077] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0078] The above embodiments are only used to illustrate the embodiments of this application, and are not intended to limit the embodiments of this application. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of this application. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of this application, and the patent protection scope of the embodiments of this application should be defined by the claims.

Claims

1. A device control method, characterized in that, Applied to an execution device, the method includes: Obtain the context feature vector corresponding to the current context, wherein the context feature vector includes scene feature parameters, device feature parameters, and user parameters; Based on the context feature vector corresponding to the current context, determine the current target context; Based on the current target context, a target control command is generated. The target control command is used to instruct the target device associated with the target context to perform a target control operation, which is related to the target context. The target control command is sent to the target device.

2. The method according to claim 1, characterized in that, The step of obtaining the context feature vector corresponding to the current context includes: Acquire context-aware data collected by each sensing unit within a preset time period; Target operations are performed on the context-aware data collected by each of the sensing units to obtain the feature parameters corresponding to the context-aware data collected by each of the sensing units. Based on the feature parameters corresponding to the context perception data collected by each perception unit, the context feature vector corresponding to the current context is obtained.

3. The method according to claim 1, characterized in that, The step of determining the current target context based on the context feature vector corresponding to the current context includes: Input the context feature vector corresponding to the current context into the trained target model; Based on the output of the target model, the current target situation is obtained; the target model includes a decision tree model.

4. The method according to claim 3, characterized in that, The output of the target model includes the context recognition result and the confidence level of the context recognition result; obtaining the current target context based on the output of the target model includes: If the confidence level of the situation identification result is not less than the confidence level threshold, the situation identification result is determined to be the current target situation.

5. The method according to claim 4, characterized in that, The method further includes: Determine the probability of the situation indicated by the situation recognition result occurring in the same historical time period; Based on the occurrence probability, the confidence level of the target model's output is corrected to obtain the corrected confidence level of the context recognition result.

6. The method according to claim 1, characterized in that, Before generating target control instructions based on the current target context, the method further includes: The detected target situation is determined to meet preset conditions; the preset conditions include: The target situation detected this time is different from the situation detected previously; and / or, The duration for which the confidence level of the target scenario is not less than the confidence threshold is not less than the preset duration threshold.

7. The method according to claim 1, characterized in that, The scene feature parameters include at least one of the following: average ambient brightness, location information, and time period information; the device feature parameters include at least one of the following: average acceleration, acceleration variance, average movement speed, and external device connection status; the user parameters include user physiological feature parameters and historical behavior logs, and the user physiological feature parameters include average heart rate. The target context categories include exercise, commuting, sleep, driving, meetings, and home.

8. A device control apparatus, characterized in that, include: The acquisition module is used to obtain the context feature vector corresponding to the current context. The context feature vector includes scene feature parameters, device feature parameters, and user parameters. The decision-making module is used to determine the current target context based on the context feature vector corresponding to the current context. An execution module is configured to generate target control instructions based on the current target context, wherein the target control instructions are used to instruct a target device associated with the target context to perform a target control operation, and the target control operation is related to the target context; The sending module is used to send the target control command to the target device.

9. An electronic device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation corresponding to the method as described in any one of claims 1-7.

10. A computer storage medium storing at least one piece of program code, the program code being loaded and executed by a processor to implement the method as described in any one of claims 1 to 7.

Images