Control method, electronic equipment and device
By combining mobile phone trajectory data, relative angle and distance data with user profiles, the problem of accurate mobile phone recognition under different usage habits is solved, and stable display control is achieved in scenarios where calls are answered quickly.
Patent Information
- Application Number
- CN202510887531.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-27
- Publication Date
- 2025-11-14
AI Technical Summary
Existing technologies struggle to accurately identify whether a user is holding their phone close to their ear to make a call, given the differences in user habits and device usage. Furthermore, they require collecting dynamic data for a certain duration to perform the detection.
By combining trajectory data of electronic devices with relative angle and distance data of target objects, a comprehensive judgment is made using a hybrid Bayesian model and a CNN-GRU multimodal fusion model. Combined with user profiles, accurate identification is achieved, and the display status is dynamically adjusted.
It improves the accuracy of recognizing whether the phone is close to the ear during a call, ensuring stable triggering of display status control in fast-answering scenarios and reducing false alarms and missed alarms.
Smart Images
Figure CN120956829A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing, and more particularly to a control method, electronic device, and apparatus. Background Technology
[0002] When a user holds the phone close to their ear during a call, the phone automatically turns off the screen. When the user removes the phone from their ear after the call, the screen turns back on. Currently, this detection typically uses sensor data on the phone's movement and echo information from the ultrasonic signals emitted by the phone. However, achieving 100% accuracy is difficult due to varying user habits and device differences. Furthermore, collecting dynamic data for a certain duration is necessary for detection. Summary of the Invention
[0003] This application provides a control method, electronic device, and apparatus.
[0004] One embodiment of this application provides a control method, the method comprising:
[0005] Obtain the first data;
[0006] If the first data indicates that there is a target area where a target object is close to an electronic device, a judgment is made using the target model based on the second data and the user profile corresponding to the target object to obtain a judgment result; the second data includes at least the relative angle and distance between the electronic device and the target object.
[0007] Based on the judgment result, the display state of the display area of the electronic device is changed.
[0008] The target model includes a first identification module and a second identification module. The step of using the target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtaining a judgment result, includes:
[0009] If the first identification module cannot identify the trajectory data of the electronic device in the first data, the second data is obtained;
[0010] The second identification module uses the second data and the user profile corresponding to the target object to make a judgment, and obtains the judgment result.
[0011] The target model includes a first identification module and a second identification module. The step of using the target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtaining a judgment result, includes:
[0012] If the trajectory data of the electronic device in the first data is identified using the first identification module, a first candidate judgment result is obtained based on the trajectory data;
[0013] Obtain the second data;
[0014] The second identification module uses the second data and the user profile corresponding to the target object to make a judgment and determine the second candidate judgment result;
[0015] The first candidate judgment result and the second candidate judgment result are fused together to obtain the judgment result.
[0016] The step of fusing the first candidate judgment result and the second candidate judgment result to obtain the judgment result includes:
[0017] The first candidate judgment result and the second candidate judgment result are fused based on dynamic weights to obtain the judgment result. The dynamic weights are determined based on the number of training iterations of the second recognition module.
[0018] The target model includes a first recognition module, and the method further includes:
[0019] If the trajectory data of the electronic device in the first data is identified using the first identification module, a judgment is made based on the trajectory data to obtain the judgment result.
[0020] Wherein, controlling the change of the display state of the display area of the electronic device based on the judgment result includes:
[0021] If the determination result indicates that the electronic device is in a call state and the display state of the display area of the electronic device is on, then the first target operation is executed, the first target operation including at least controlling the brightness of the display area of the electronic device to decrease;
[0022] If the determination result indicates that the electronic device is not in a call state and the display state of the display area of the electronic device is low brightness, then a second target operation is performed, the second target operation including at least controlling the brightness of the display area of the electronic device to increase.
[0023] The method further includes:
[0024] Multiple sample data are obtained, and the sample data includes at least the trajectory data of the electronic device for a preset duration;
[0025] The first identification module is used to identify the multiple sample data to obtain the corresponding multiple label data;
[0026] Obtain the second data corresponding to the sample data;
[0027] The initial second recognition module is trained using the second data and label data corresponding to the multiple sample data to obtain the second recognition module.
[0028] The acquisition of the second data includes:
[0029] The relative angle and distance between the electronic device and the target object are extracted from the first data or the third data to obtain the second data;
[0030] Alternatively, the second data can be obtained by collecting the relative angle and distance between the electronic device and the target object that are adjacent in time to the first data or the third data.
[0031] Another embodiment of this application provides an electronic device, including: an input / output system, a processor, and a control module; the input / output system and the processor are electrically connected; the processor and the control module are electrically connected;
[0032] The input / output system obtains the first data;
[0033] When the first data characterizes a target area where a target object is close to an electronic device, the processor uses a target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtains a judgment result; the second data includes at least the relative angle and distance between the electronic device and the target object.
[0034] The control module controls the display state of the electronic device's display area to change based on the judgment result.
[0035] This application also provides a control device, the device comprising:
[0036] The acquisition module is used to obtain the initial data.
[0037] The processing module is configured to, when the first data characterizes a target area where a target object is close to an electronic device, use a target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtain a judgment result; the second data includes at least the relative angle and distance between the electronic device and the target object; and control the display state of the display area of the electronic device to change based on the judgment result.
[0038] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description
[0039] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of this application are illustrated in the drawings by way of example and not limitation, in which:
[0040] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
[0041] Figure 1 A flowchart of a control method according to an embodiment of this application is shown;
[0042] Figure 2 A flowchart of a control method according to another embodiment of this application is shown;
[0043] Figure 3 A flowchart of a control method according to another embodiment of this application is shown;
[0044] Figure 4 A flowchart of a control method according to another embodiment of this application is shown;
[0045] Figure 5 A flowchart of a control method according to another embodiment of this application is shown;
[0046] Figure 6 A flowchart of a control method according to another embodiment of this application is shown;
[0047] Figure 7 A flowchart of a control method according to another embodiment of this application is shown;
[0048] Figure 8 A flowchart of a control method according to another embodiment of this application is shown;
[0049] Figure 9 A schematic diagram of the composition structure of an electronic device according to an embodiment of this application is shown;
[0050] Figure 10 A schematic diagram of the structure of a control device according to an embodiment of this application is shown. Detailed Implementation
[0051] To make the objectives, features, and advantages of this application more apparent and understandable, 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 without creative effort are within the scope of protection of this application.
[0052] To improve the accuracy of identifying whether an electronic device has been picked up by a user and a phone call has been answered, and to perform corresponding control on the display area of the electronic device after identification, one embodiment of this application provides a control method, such as... Figure 1 As shown, the method includes:
[0053] Step 101: Obtain the first data.
[0054] The first data is obtained by using the detection elements in the electronic device to collect the trajectory data of the electronic device and the relative angle and distance between the electronic device and the target object.
[0055] In this embodiment, ultrasonic waves can be emitted from the transmitting end (such as a handset or speaker) of an audio device in the electronic device, and the ultrasonic echo signal can be received by the receiving end (such as a microphone) of the audio device. The distance between the electronic device and the target object can then be determined based on the ultrasonic echo signal. Motion sensors (such as accelerometers or gyroscopes) in the electronic device can be used to collect trajectory data of the electronic device and the relative angle between the electronic device and the target object. In other embodiments, any other detection device capable of collecting trajectory data of the electronic device and the relative angle and distance between the electronic device and the target object can be used to collect the first data.
[0056] Step 102: If the first data indicates that a target object is near an electronic device in a target area, a judgment is made using the target model based on the second data and the user profile corresponding to the target object to obtain a judgment result; the second data includes at least the relative angle and distance between the electronic device and the target object.
[0057] The target area of the electronic device can be set based on the relative distance between the user and the electronic device when the user frequently answers a call. For example, if the relative distance between the user and the electronic device when answering a call is 20cm, the target area of the electronic device is set to an area with a radius of 20cm centered on the electronic device. Then, the trajectory data of the electronic device in the first data and the distance between the electronic device and the target object are used to determine whether the target object is close to the target area of the electronic device. If so, the target model is used to determine whether the user has picked up the electronic device and answered the call based on the first data.
[0058] Because the duration of the electronic device's trajectory data in the first set of data is too short, it may be impossible to determine whether the electronic device was picked up and used to answer a call based solely on the trajectory data. Therefore, it is necessary to make a judgment based on the second set of data (i.e., the relative angle and distance between the electronic device and the target object) and the user profile corresponding to the target object. Based on the user profile corresponding to the target object, the relative angle and distance between the electronic device and the target object when the target object frequently answers calls are determined. Then, based on the second set of data, a comprehensive judgment is made on whether the electronic device was picked up and used to answer the call, resulting in the final judgment.
[0059] Step 103: Based on the judgment result, control the display state of the display area of the electronic device to change.
[0060] The system controls the display state of the electronic device's display area based on the judgment result. For example, if the judgment result is that the electronic device has been picked up by the user and a phone call has been answered, the display state of the electronic device's display area can be turned off (i.e., screen off) or the brightness can be reduced. Conversely, if the judgment result is that the electronic device has not been picked up by the user and a phone call has not been answered, the display state of the electronic device's display area can be turned on or the brightness can be increased.
[0061] In the above solution, when the electronic device's collected trajectory data is too short to support the recognition model's judgment based solely on trajectory data, a comprehensive decision is made by combining the relative angle and distance data between the electronic device and the target object, as well as the user profile corresponding to the target object. The user profile pre-stores historical call-answering habit data for individual users (such as commonly used answering angles and distances). By comparing the current second data with the habit data in the profile, even if the trajectory data is insufficient to independently support the judgment, it can still accurately identify whether the user has actually picked up the electronic device and brought it close to their ear. This effectively overcomes the problem of misjudgment or missed judgment caused by short trajectory data duration, enabling accurate detection even in fast-answering scenarios, thereby stably triggering control of the display state and accurately executing the state control of the display area based on the judgment result.
[0062] This application also provides a control method in one example, such as Figure 2 As shown, the target model includes a first recognition module and a second recognition module. The step of using the target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtaining a judgment result, includes:
[0063] Step 201: If the first identification module cannot identify the trajectory data of the electronic device in the first data, obtain the second data.
[0064] In this embodiment, the target model includes a first recognition module and a second recognition module. The first recognition module can be a hybrid Bayesian model or a 3D-CNNResNet (image coding model), etc. The second recognition module can be a CNN-GRU multimodal fusion model or a state-space model, etc. In other embodiments, the first recognition module can be any other model capable of performing three-class classification based on the trajectory data of the electronic device. The second recognition module can be any other model capable of performing binary classification based on the relative angle and distance between the electronic device and the user, as well as the user's profile.
[0065] When the first recognition module in the target model cannot recognize the electronic device because the trajectory data of the electronic device in the first data is missing or the duration is too short, the relative angle and distance between the electronic device and the target object are obtained.
[0066] Step 202: The second identification module uses the second data and the user profile corresponding to the target object to make a judgment, and obtains the judgment result. The judgment result output by the second identification module is the confidence score corresponding to the binary classification, representing the probability of each category.
[0067] For example, the second recognition module outputs a judgment result with a confidence level of 0.9 for the electronic device moving closer to the target object and a confidence level of 0.1 for the electronic device not moving closer to the target object.
[0068] The second recognition module uses the relative angle and distance data between the electronic device and the target object, as well as the user profile corresponding to the target object, to make a judgment and obtain the judgment result.
[0069] In the above solution, a comprehensive decision is made by combining the relative angle and distance data between the electronic device and the target object, as well as the user profile corresponding to the target object. The user profile pre-stores historical call-answering habit data for individual users. By comparing the current second data with the habit data in the profile, even if the trajectory data is insufficient to independently support the judgment, it can still accurately identify whether the user has actually picked up the electronic device and brought it close to their ear. This effectively overcomes the problem of misjudgment or missed judgment caused by short trajectory data duration, enabling accurate detection even in scenarios where the electronic device answers quickly, thereby stably triggering control of the display state and accurately executing the state control of the display area based on the judgment result.
[0070] This application also provides a control method in one example, such as Figure 3 As shown, the target model includes a first recognition module and a second recognition module. The step of using the target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtaining a judgment result, includes:
[0071] Step 301: If the trajectory data of the electronic device in the first data is identified by the first identification module, a judgment is made based on the trajectory data to obtain a first candidate judgment result.
[0072] When the first recognition module in the target model can make a judgment based on the trajectory data of the electronic device in the first data, the judgment is made based on the trajectory data to obtain the first candidate judgment result. The first candidate judgment result is the confidence score corresponding to the three categories, representing the probability of each category.
[0073] For example, the confidence level of the first candidate judgment result is 0.8 for the electronic device moving closer to the target object, 0.1 for the electronic device moving away from the target object, and 0.1 for the electronic device not moving.
[0074] Step 302: Obtain the second data.
[0075] Obtain the relative angle and distance between the electronic device and the target object.
[0076] Step 303: The second identification module makes a judgment based on the second data and the user profile corresponding to the target object to determine the second candidate judgment result.
[0077] The second identification module uses the relative angle and distance between the electronic device and the target object, along with the user profile corresponding to the target object, to make a judgment and obtain a second candidate judgment result. The second judgment result is the confidence score corresponding to the binary classification, representing the probability of each category.
[0078] For example, the confidence level of the second candidate judgment result is 0.9 for the electronic device moving closer to the target object and 0.1 for the electronic device not moving closer to the target object.
[0079] Step 304: The first candidate judgment result and the second candidate judgment result are fused to obtain the judgment result.
[0080] The final judgment result is obtained by merging the confidence scores of the electronic devices approaching the target object in the first and second candidate judgment results through weighted summation or averaging.
[0081] For example, if the confidence level of the electronic device moving closer to the target object is 0.8 in the first candidate judgment result and 0.9 in the second candidate judgment result, with a weight of 0.4 for the first candidate judgment result and a weight of 0.6 for the second candidate judgment result, then the confidence level of the electronic device moving closer to the target object in the final judgment result is 0.86, which means that the probability of the electronic device moving closer to the target is 86%.
[0082] In the above scheme, the first recognition module outputs a three-class confidence score based on trajectory data, while the second recognition module outputs a two-class confidence score by combining the relative angle and distance between the electronic device and the user, as well as the user's profile. Finally, a comprehensive judgment is formed by weighted fusion of the confidence scores of the two classes, specifically the class indicating the electronic device's approach to the target object. This fusion of confidence scores from the two modules preserves the dynamic motion characteristics of the trajectory data while incorporating long-term behavioral patterns from the user profile. This effectively solves the problem of misjudgment caused by relying on single data points, enabling the electronic device to accurately identify its approach to the target object under various usage habits and environmental interferences, providing a highly reliable basis for subsequent display control.
[0083] In one example of this application, a control method is also provided, wherein fusing the first candidate judgment result and the second candidate judgment result to obtain the judgment result includes:
[0084] The first candidate judgment result and the second candidate judgment result are fused based on dynamic weights to obtain the judgment result. The dynamic weights are determined based on the number of training iterations of the second recognition module.
[0085] The dynamic weights are determined based on the number of training iterations of the second recognition module. Generally, the higher the number of training iterations for the second recognition module, the better the recognition performance. However, excessively high iteration counts can lead to overfitting. Therefore, in the early stages of training, when the number of training iterations is low, the dynamic weights for the first recognition module are higher, and the dynamic weights for the second recognition module are lower. During the growth phase of training, the dynamic weights for the first and second recognition modules are relatively similar. After a significant number of training iterations, the dynamic weights for the first recognition module become lower, and the dynamic weights for the second recognition module become higher. Finally, after an excessive number of training iterations, the dynamic weights for the first and second recognition modules are set back to a more similar state.
[0086] For example, when the number of training iterations is less than 100, the dynamic weight corresponding to the first recognition module is 0.8, and the dynamic weight corresponding to the second recognition module is 0.2. When the number of training iterations is greater than 100 but less than 500, the dynamic weight corresponding to both the first and second recognition modules is 0.5. When the number of training iterations is greater than 500 but less than 1000, the dynamic weight corresponding to the first recognition module is 0.2, and the dynamic weight corresponding to the second recognition module is 0.8. When the number of training iterations is greater than 1000, the dynamic weight corresponding to both the first and second recognition modules is 0.5.
[0087] For example, the dynamic weight W1 corresponding to the first recognition module and the dynamic weight W2 corresponding to the second recognition module can be determined by the following formula:
[0088]
[0089] W2 = 1 - W1
[0090] Where σ is the sigmoid function (a type of S-shaped function), and T is the number of training iterations for the second recognition module.
[0091] The optimal solution is to stop training the second recognition module once it reaches the target optimum (e.g., the minimum loss value). Setting too many training iterations for weight allocation is to improve the robustness of this solution.
[0092] In the above scheme, during the initial training of the second recognition module, the system prioritizes the trajectory data from the first recognition module for judgment, assigning it a higher weight to effectively mitigate initial misjudgments caused by insufficient user profile data. As the training iterations increase and the system enters a growth phase, the weights of the two modules are evenly distributed, promoting collaborative learning between trajectory data features and user profile features. When training matures, the focus shifts to the user profile features of the second recognition module, fully leveraging its advantage in recognizing long-term behavioral patterns. When the number of training iterations exceeds a threshold, the system reverts to a balanced weight distribution, avoiding the risk of overfitting in the second recognition module while retaining the cross-validation capability of the two channels. This ensures that the most reliable recognition module always dominates, enabling stable recognition throughout the entire lifecycle of electronic devices, from initial deployment to long-term use, significantly improving the robustness and accuracy of the recognition.
[0093] In one example of this application, a control method is also provided, wherein the target model includes a first recognition module, and the method further includes:
[0094] If the trajectory data of the electronic device in the first data is identified using the first identification module, a judgment is made based on the trajectory data to obtain the judgment result.
[0095] When the first recognition module in the target model can make a judgment based on the trajectory data of the electronic device in the first data, it can also make a judgment based solely on the trajectory data, and the result output by the first recognition module can be determined as the judgment result. The result output by the first recognition module is the confidence score corresponding to the three categories, representing the probability of each category.
[0096] In the above scheme, when the trajectory data meets the conditions for recognition by the first recognition module, the first recognition module independently completes the behavior judgment and directly outputs the three-class confidence score as the final judgment result. This enables electronic devices to respond quickly when data conditions are ideal, and ensures the accuracy of judgment through other schemes in complex scenarios, significantly improving the flexibility of the recognition method.
[0097] This application also provides a control method in one example, such as Figure 4As shown, controlling the change of the display state of the electronic device's display area based on the judgment result includes:
[0098] Step 401: If the judgment result indicates that the electronic device is in a call state and the display state of the display area of the electronic device is on, then execute the first target operation, which includes at least controlling the brightness of the display area of the electronic device to decrease.
[0099] Step 402: If the judgment result indicates that the electronic device is not in a call state and the display state of the display area of the electronic device is low brightness, then perform a second target operation, which includes at least controlling the brightness of the display area of the electronic device to increase.
[0100] The determination of whether an electronic device is in a call state (i.e., the user picks up the electronic device and answers a call) can be made by comparing the judgment result with a preset threshold.
[0101] For example, if the preset threshold is set to 0.8, and the confidence level of the electronic device moving closer to the target object in the judgment result is greater than 0.8, then the electronic device is determined to be in a call state; if the confidence level of the electronic device moving closer to the target object in the judgment result is less than 0.8, then the electronic device is determined to be not in a call state.
[0102] If it is determined that the electronic device is in a call state and the display area of the electronic device is on, then the first target operation is executed to control the brightness of the display area of the electronic device to decrease.
[0103] For example, if it is determined that the electronic device is in a call state and the display area of the electronic device is on, then the display area of the electronic device is turned off.
[0104] For example, if it is determined that the electronic device is in a call state and the brightness of the display area of the electronic device is greater than the preset brightness, then the brightness of the display area of the electronic device is reduced to below the preset brightness.
[0105] If it is determined that the electronic device is not in a call state and the display area of the electronic device is in a low brightness state, then the second target operation is performed to control the brightness of the display area of the electronic device to increase.
[0106] For example, if it is determined that the electronic device is not in a call state and the display area of the electronic device is off, then the display area of the electronic device is turned on.
[0107] For example, if it is determined that the electronic device is not in a call state and the brightness of the display area of the electronic device is less than the preset brightness, then the brightness of the display area of the electronic device is controlled to be increased to above the preset brightness.
[0108] In the above solution, when it is determined that the electronic device is in a call and the screen is on, the first objective is to reduce the brightness of the display area, effectively avoiding accidental touches and power consumption when the device is close to the face. When it is determined that the device is not in a call and the screen is in a low-brightness state, the second objective is to increase the brightness to a visible level. Through this adaptive adjustment strategy, the device ensures both uninterrupted screen comfort during calls and rapid restoration of usability after calls, achieving precise matching between brightness status and user intent. This significantly improves the intelligence level and energy efficiency of display control in call scenarios.
[0109] This application also provides a control method in one example, such as Figure 5 As shown, the method further includes:
[0110] Step 501: Obtain multiple sample data, the sample data including at least the trajectory data of the electronic device for a preset duration.
[0111] Multiple sample data, including trajectory data of electronic devices exceeding a preset time, are obtained; that is, the first data that can be successfully identified by the first identification module is collected as sample data.
[0112] Step 502: Use the first identification module to identify the multiple sample data to obtain the corresponding multiple label data.
[0113] The first identification module identifies the sample data to obtain corresponding tag data. The tag data indicates whether the electronic device is in a call state (i.e., the user picks up the electronic device and answers a call). This can be determined based on the judgment result output by the first identification module after identifying the sample data. When the confidence level of the electronic device moving closer to the target object in the judgment result is greater than a preset threshold, the tag data is determined to indicate that the electronic device is in a call state. When the confidence level of the electronic device moving closer to the target object in the judgment result is less than the preset threshold, the tag data is determined to indicate that the electronic device is not in a call state.
[0114] For example, with a preset threshold set to 0.9, the first recognition module identifies sample data A and sample data B, obtaining the judgment results for sample data A and sample data B respectively. If the confidence level for the electronic device approaching the target object in the judgment result for sample data A is 0.95, then the label data corresponding to sample data A is determined to be 1, indicating that the electronic device is in a call state. If the confidence level for the electronic device approaching the target object in the judgment result for sample data B is 0.6, then the label data corresponding to sample data B is determined to be 0, indicating that the electronic device is not in a call state.
[0115] Step 503: Obtain the second data corresponding to the sample data.
[0116] Step 504: Train the initial second recognition module using the second data and label data corresponding to the multiple sample data to obtain the second recognition module.
[0117] The initial second recognition module is used to identify the second data corresponding to the sample data, and the judgment result of the initial second recognition module is output. Based on the judgment result and the corresponding label data, the loss value is calculated, and the parameters of the initial second recognition module are optimized based on the loss value. After achieving the training objective (minimizing the loss value or reaching the maximum number of iterations), the second recognition module is obtained.
[0118] In the above scheme, the judgment results of the first recognition module on the sample data are used to generate label data, providing high-quality training samples for the second recognition module. Then, the second data corresponding to the sample data is used to train the initial model, gradually learning user behavioral characteristics (i.e., user profiles) through loss optimization. Without manual annotation intervention, the second recognition module can associate user profiles with the second data, thereby achieving accurate recognition and significantly improving the accuracy and adaptability of the second recognition module.
[0119] This application also provides a control method in one example, such as Figure 6 As shown, obtaining the second data includes:
[0120] Step 601: Extract the relative angle and distance between the electronic device and the target object from the first data or the third data to obtain the second data.
[0121] Step 602: Collect the relative angle and distance between the electronic device and the target object that are adjacent in time to the first data or the third data to obtain the second data.
[0122] The second data corresponding to the first data, or the second data corresponding to the sample data, can be obtained directly from the first data or the sample data. If the second data does not exist in the first data or the sample data, or if the second data is scarce, the second data can be collected for a subsequent period of time, and then the second recognition module can be used for judgment.
[0123] Since the only accurate trajectory data for determining the approach of an electronic device to a target object is the segment when the user picks up the device to answer a call, if this trajectory data is missing from the first set of data, or if the duration of this trajectory data is too short for the first recognition module to make an accurate judgment, subsequent trajectory data collection will also fail to provide accurate data. However, when the user is answering a call, the relative angle and distance data between the electronic device and the target object will remain within the first range for a subsequent period. Therefore, in the above scheme, if second data exists in the first set of data that supports the judgment of the second recognition module, it can be directly extracted from the first set of data; otherwise, second data can be collected over a subsequent period, and then the second recognition module can be used for judgment. This significantly improves the stability and robustness of the recognition method.
[0124] This application also provides a control method in one example, such as Figure 7 As shown, the method includes:
[0125] Step 701: Obtain the first data.
[0126] Step 7021: If the first data characterizes a target area where a target object is close to an electronic device and the trajectory data of the electronic device in the first data is identified by the first identification module, then the first identification module makes a judgment based on the trajectory data to obtain a judgment result.
[0127] Step 7031: If the first data characterizes a target area where a target object is close to an electronic device and the trajectory data of the electronic device in the first data cannot be identified using the first identification module, then the second data is obtained.
[0128] Step 7032: The second identification module makes a judgment based on the second data to obtain a judgment result.
[0129] Step 704: Based on the judgment result, control the display state of the display area of the electronic device to change.
[0130] This application also provides a control method in one example, such as Figure 8 As shown, the method includes:
[0131] Step 801: Obtain the first data.
[0132] Step 8021: If the first data characterizes a target area where a target object is close to an electronic device and the trajectory data of the electronic device in the first data cannot be identified using the first identification module, then the second data is obtained.
[0133] Step 8022: The second identification module makes a judgment based on the second data to obtain a judgment result.
[0134] Step 8031: If the first data characterizes a target area where a target object is close to an electronic device and the trajectory data of the electronic device in the first data is identified by the first identification module, then the first identification module makes a judgment based on the trajectory data to obtain a first candidate judgment result.
[0135] Step 8032: Obtain the second data.
[0136] Step 8033: The second identification module makes a judgment based on the second data to obtain a second candidate judgment result.
[0137] Step 8034: The first candidate judgment result and the second candidate judgment result are fused to obtain the judgment result.
[0138] Step 804: Based on the judgment result, control the display state of the display area of the electronic device to change.
[0139] This application provides an example of an electronic device, Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0140] like Figure 9 As shown, the electronic device 900 includes an input / output system 901, a processor 902, and a control module 903; the input / output system 901 and the processor 902 are electrically connected; the processor 902 and the control module 903 are electrically connected.
[0141] The input / output system 901 obtains the first data;
[0142] When the first data characterizes a target area where a target object is close to an electronic device, the processor 902 uses a target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtains a judgment result; the second data includes at least the relative angle and distance between the electronic device and the target object.
[0143] The control module 903 controls the display state of the display area of the electronic device to change based on the judgment result.
[0144] Wherein, the input / output system 901 obtains second data when the first recognition module cannot recognize the trajectory data of the electronic device in the first data, and the target model includes the first recognition module and the second recognition module;
[0145] The processor 902 uses the second recognition module to make a judgment based on the second data and the user profile corresponding to the target object, and obtains the judgment result.
[0146] Wherein, when the processor 902 uses the first identification module to identify the trajectory data of the electronic device in the first data, it makes a judgment based on the trajectory data to obtain a first candidate judgment result, and the target model includes a first identification module and a second identification module;
[0147] The input / output system 901 obtains the second data;
[0148] The processor 902 uses the second recognition module to make a judgment based on the second data and the user profile corresponding to the target object to determine a second candidate judgment result; and fuses the first candidate judgment result and the second candidate judgment result to obtain the judgment result.
[0149] The processor 902 fuses the first candidate judgment result and the second candidate judgment result based on dynamic weights to obtain the judgment result, and the dynamic weights are determined based on the number of training iterations of the second recognition module.
[0150] Wherein, when the processor 902 uses the first identification module to identify the trajectory data of the electronic device in the first data, it makes a judgment based on the trajectory data and obtains the judgment result.
[0151] Wherein, when the judgment result indicates that the electronic device is in a call state and the display state of the display area of the electronic device is on, the control module 903 performs a first target operation, the first target operation including at least controlling the brightness of the display area of the electronic device to decrease; and when the judgment result indicates that the electronic device is not in a call state and the display state of the display area of the electronic device is low brightness, the control module 903 performs a second target operation, the second target operation including at least controlling the brightness of the display area of the electronic device to increase.
[0152] The input / output system 901 obtains multiple sample data, which includes at least the trajectory data of the electronic device for a preset duration.
[0153] The processor 902 uses the first identification module to identify the multiple sample data to obtain the corresponding multiple label data;
[0154] The input / output system 901 obtains the second data corresponding to the sample data;
[0155] The processor 902 uses the second data and label data corresponding to the multiple sample data to train the initial second recognition module, thereby obtaining the second recognition module.
[0156] The input / output system 901 extracts the relative angle and distance between the electronic device and the target object from the first data or the third data to obtain the second data; or, it collects the relative angle and distance between the electronic device and the target object that are adjacent to the first data or the third data in time to obtain the second data.
[0157] To achieve the above control method, such as Figure 10 As shown, an example of this application provides a control device, including:
[0158] Acquisition module 1001 is used to obtain the first data;
[0159] Processing module 1002 is configured to, when the first data characterizes a target area where a target object is close to an electronic device, use a target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtain a judgment result; the second data includes at least the relative angle and distance between the electronic device and the target object; and control the display state of the display area of the electronic device to change based on the judgment result.
[0160] The acquisition module 1001 is further configured to obtain second data when the trajectory data of the electronic device in the first data cannot be identified by the first identification module. The target model includes the first identification module and the second identification module.
[0161] The processing module 1002 is further configured to use the second identification module to make a judgment based on the second data and the user profile corresponding to the target object, and obtain the judgment result.
[0162] The processing module 1002 is further configured to, when the trajectory data of the electronic device in the first data is identified by the first identification module, make a judgment based on the trajectory data to obtain a first candidate judgment result, wherein the target model includes a first identification module and a second identification module;
[0163] The acquisition module 1001 is also used to obtain second data;
[0164] The processing module 1002 is further configured to use the second identification module to make a judgment based on the second data and the user profile corresponding to the target object, and determine the second candidate judgment result;
[0165] The processing module 1002 is further configured to fuse the first candidate judgment result and the second candidate judgment result to obtain the judgment result.
[0166] The processing module 1002 is further configured to fuse the first candidate judgment result and the second candidate judgment result based on dynamic weights to obtain the judgment result, wherein the dynamic weights are determined based on the number of training iterations of the second recognition module.
[0167] The processing module 1002 is further configured to, when the trajectory data of the electronic device in the first data is identified by the first identification module, make a judgment based on the trajectory data to obtain the judgment result.
[0168] The processing module 1002 is further configured to perform a first target operation when the judgment result indicates that the electronic device is in a call state and the display state of the display area of the electronic device is on, wherein the first target operation includes at least controlling the brightness of the display area of the electronic device to decrease.
[0169] The processing module 1002 is further configured to perform a second target operation when the judgment result indicates that the electronic device is not in a call state and the display state of the display area of the electronic device is in a low brightness state, the second target operation including at least controlling the brightness of the display area of the electronic device to increase.
[0170] The acquisition module 1001 is also used to acquire multiple sample data, the sample data including at least the trajectory data of the electronic device for a preset time.
[0171] The processing module 1002 is further configured to use the first identification module to identify the plurality of sample data to obtain the corresponding plurality of label data;
[0172] The acquisition module 1001 is also used to obtain second data corresponding to the sample data;
[0173] The processing module 1002 is further configured to train the initial second recognition module using the second data and label data corresponding to the plurality of sample data, thereby obtaining the second recognition module.
[0174] The acquisition module 1001 is further configured to extract the relative angle and distance between the electronic device and the target object from the first data or the third data to obtain the second data; or, to acquire the relative angle and distance between the electronic device and the target object that are adjacent in time to the first data or the third data to obtain the second data.
[0175] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.
[0176] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0177] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0178] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0179] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0180] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.
[0181] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0182] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise explicitly specified.
[0183] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.
Claims
1. A control method, the method comprising: Obtain the first data; If the first data indicates that there is a target area where a target object is close to an electronic device, a judgment is made using the target model based on the second data and the user profile corresponding to the target object to obtain a judgment result; the second data includes at least the relative angle and distance between the electronic device and the target object. Based on the judgment result, the display state of the display area of the electronic device is changed.
2. The method according to claim 1, wherein the target model includes a first identification module and a second identification module, and the step of using the target model to make a judgment based on the second data and the user profile corresponding to the target object to obtain a judgment result includes: If the first identification module cannot identify the trajectory data of the electronic device in the first data, the second data is obtained; The second identification module uses the second data and the user profile corresponding to the target object to make a judgment, and obtains the judgment result.
3. The method according to claim 1, wherein the target model includes a first identification module and a second identification module, and the step of using the target model to make a judgment based on the second data and the user profile corresponding to the target object to obtain a judgment result includes: If the trajectory data of the electronic device in the first data is identified using the first identification module, a first candidate judgment result is obtained based on the trajectory data; Obtain the second data; The second identification module uses the second data and the user profile corresponding to the target object to make a judgment and determine the second candidate judgment result; The first candidate judgment result and the second candidate judgment result are fused together to obtain the judgment result.
4. The method according to claim 3, wherein fusing the first candidate judgment result and the second candidate judgment result to obtain the judgment result includes: The first candidate judgment result and the second candidate judgment result are fused based on dynamic weights to obtain the judgment result. The dynamic weights are determined based on the number of training iterations of the second recognition module.
5. The method according to claim 1, wherein the target model includes a first recognition module, and the method further includes: If the trajectory data of the electronic device in the first data is identified using the first identification module, a judgment is made based on the trajectory data to obtain the judgment result.
6. The method according to claim 2, 3, or 5, wherein controlling the change of the display state of the display area of the electronic device based on the judgment result includes: If the determination result indicates that the electronic device is in a call state and the display state of the display area of the electronic device is on, then the first target operation is executed, the first target operation including at least controlling the brightness of the display area of the electronic device to decrease; If the determination result indicates that the electronic device is not in a call state and the display state of the display area of the electronic device is low brightness, then a second target operation is performed, the second target operation including at least controlling the brightness of the display area of the electronic device to increase.
7. The method according to claim 1, further comprising: Multiple sample data are obtained, and the sample data includes at least the trajectory data of the electronic device for a preset duration; The first identification module is used to identify the multiple sample data to obtain the corresponding multiple label data; Obtain the second data corresponding to the sample data; The initial second recognition module is trained using the second data and label data corresponding to the multiple sample data to obtain the second recognition module.
8. The method according to claim 2, 3, or 7, wherein obtaining the second data comprises: The relative angle and distance between the electronic device and the target object are extracted from the first data or the third data to obtain the second data; Alternatively, the second data can be obtained by collecting the relative angle and distance between the electronic device and the target object that are adjacent in time to the first data or the third data.
9. An electronic device, comprising: Input / output system, processor, and control module; The input / output system and the processor are electrically connected; The processor and the control module are electrically connected; The input / output system obtains the first data; When the first data characterizes a target area where a target object is close to an electronic device, the processor uses a target model to make a judgment based on the second data and the user profile corresponding to the target object, and obtains a judgment result; the second data includes at least the relative angle and distance between the electronic device and the target object. The control module controls the display state of the electronic device's display area to change based on the judgment result.
10. A control device, the device comprising: The acquisition module is used to obtain the initial data. The processing module is used to determine the target object's proximity to the electronic device by using the target model and based on the second data and the user profile corresponding to the target object when the first data characterizes a target area. The second data includes at least the relative angle and distance between the electronic device and the target object; And based on the judgment result, control the display state of the display area of the electronic device to change.