Device connection method, device, first device and computer readable storage medium
By acquiring and utilizing scene information and historical connection information, and combining the device connection network for prediction, the problem of low accuracy of multi-device connection in the prior art is solved, and high-accuracy device connection in multiple scenarios is achieved.
Patent Information
- Application Number
- CN202210419405.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-20
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-04-20
AI Technical Summary
The prior art When multiple users or multiple mobile devices are in the car at the same time, when selecting target devices to connect to the on-board device, it relies on preset rules customized by developers, resulting in limited widespread application in multiple scenarios. Moreover, the neural network method based on historical behavior data training has a single data source, which reduces the accuracy of the selection device connection.
By obtaining scene information, combining historical connection information to predict the device connection, determining the target device, including obtaining the second set of equipment, scene information, and historical connection information, using the equipment connection network to make predictions, and updating the equipment connection network to improve accuracy.
Improve the accuracy of device connection, and by perceiving scene factors in each dimension that affects device connection, the accuracy of prediction results is enhanced, ensuring the accurate selection of target devices in multiple device scenarios.
Smart Images

Figure CN115065958B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a device connection method, apparatus, first device and computer-readable storage medium. Background Art
[0002] At present, it has become a common usage scenario for mobile devices such as mobile phones to connect with vehicle-mounted devices for functional interconnection and application. For the situation where multiple users or multiple mobile devices are in the car at the same time, the relevant technology usually selects a target device from multiple mobile devices to connect with the vehicle-mounted device and use it interactively according to the preset rules customized by the developer. This method relies on the comprehensiveness of the selection rules formulated by the developer, which limits the wide application in multiple scenarios and reduces the accuracy of selecting devices for connection for scenarios not covered by the preset rules. Summary of the invention
[0003] The embodiments of the present application are intended to provide a device connection method, apparatus, first device, and computer-readable storage medium, which can accurately determine a target device from multiple devices for connection.
[0004] The technical solution of this application is implemented as follows:
[0005] The embodiment of the present application provides a device connection method, which is applied to a first device and includes:
[0006] Acquire a second device set, where the second device set includes at least one device that has a connection condition with the first device;
[0007] Acquire scenario information; the scenario information represents a usage scenario of the first device;
[0008] Based on the scenario information, combining with historical connection information, device connection prediction is performed to obtain at least one prediction result corresponding to at least one historical second device; the historical connection information includes at least one historical second device connected to the first device under at least one historical scenario information;
[0009] Determining a target device from the second set of devices according to the at least one prediction result;
[0010] Connect the target device.
[0011] The embodiment of the present application provides a device connection apparatus, applied to a first device, including:
[0012] An acquisition module, configured to acquire a second device set, where the second device set includes at least one device that has a connection condition with the first device;
[0013] A scene acquisition module, used to obtain scene information; the scene information represents the usage scene of the first device;
[0014] a connection prediction module, configured to perform device connection prediction based on the scenario information and in combination with historical connection information, and obtain at least one prediction result corresponding to at least one historical second device; the historical connection information includes at least one historical second device connected by the first device under at least one historical scenario information; and determine a target device from the set of second devices according to the at least one prediction result;
[0015] A communication connection module is used to connect to the target device.
[0016] In the above device, the scene acquisition module is further used to obtain current time information; and / or,
[0017] By receiving broadcast information of a second device in the second device set, device status information of the second device is obtained; the status information includes at least one of the power level of the second device and preset interconnection software information; the preset interconnection software is used to connect the first device on the second device to implement device interconnection application; and / or, an operator image at a preset operation position is collected, and the operator information corresponding to the first device is obtained by performing image recognition on the operator image; at least one of the current time information, the device status information and the operator information is used as the scene information.
[0018] In the above-mentioned device, the connection prediction module is also used to use the device connection network to perform device connection prediction on the scene information, and obtain at least one connection probability corresponding to the at least one historical second device as the at least one prediction result; the device connection network is obtained by training the initial device connection network through the historical connection information.
[0019] In the above-mentioned device, the device also includes: a training module, which is used to determine the connection device of the first device after connecting to the target device; record the connection device and the scene information as incremental connection information in the historical connection information; and train and update the device connection network based on the incremental connection information.
[0020] In the above-mentioned device, the training module is also used to use the target device as the connecting device when the target device interacts with the first device with application data; when a switching instruction for the target device is received, obtain the target switching device specified by the switching instruction for connection, and determine the target switching device as the connecting device.
[0021] In the above device, the training module is also used to use the incremental connection information to perform incremental training and network parameter update on the device connection network.
[0022] In the above-mentioned device, the training module is also used to obtain at least part of the information from the historical connection information when the connecting device does not belong to the at least one historical second device, and combine the at least part of the information with the incremental connection information to retrain the device connection network, and update the predicted category and network parameters of the device connection network through retraining.
[0023] In the above-mentioned device, the training module is also used to obtain target application information corresponding to the target application currently running on the connected device; the target application is used to realize functional interaction between the first device and the second device; the connected device and the target application information are recorded in an application usage information set; the application recommendation network is obtained by training the application information usage set; the application recommendation network is used to make application recommendations to the second device connected to the first device.
[0024] In the above-mentioned device, the second device set includes at least part of the historical second devices in the at least one historical second device, and the connection prediction module is also used to determine the second device corresponding to the target historical second device in the second device set with the highest connection probability as the target device in the at least one connection probability.
[0025] In the above-mentioned device, the first device includes: a vehicle-mounted device, and the second device includes: a mobile device, wherein the preset operation position includes: the main driving position of the vehicle where the vehicle-mounted device is located; and the scene information also includes: at least one of schedule information and navigation information.
[0026] The present application embodiment provides a first device, including:
[0027] The memory is used to store executable instructions;
[0028] The processor is used to implement the device connection method provided in the embodiment of the present application by executing the executable instructions stored in the memory.
[0029] An embodiment of the present application provides a computer-readable storage medium storing executable instructions for causing a processor to execute and implement the device connection method provided in the embodiment of the present application.
[0030] An embodiment of the present application provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed by a processor, the device connection method provided in the embodiment of the present application is implemented.
[0031] The embodiments of the present application have the following beneficial effects:
[0032] The first device obtains scene information and makes predictions based on the historical connection information of at least one historical second device that has been connected under at least one historical scene information, and can obtain at least one prediction result corresponding to at least one historical second device, so that the target device can be determined from the second device set for connection based on the at least one prediction result. Therefore, in the device interconnection scenario, the scene factors of various dimensions that affect the device connection can be perceived, and the scene information is added to the prediction process, which improves the accuracy of the prediction results, and further improves the accuracy of determining the target device for connection based on the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 This is an optional structural diagram of the in-vehicle interconnection system provided in an embodiment of the present application;
[0034] Figure 2 This is an optional flow chart of the device connection method provided in the embodiment of the present application;
[0035] Figure 3 This is an optional flow chart of the device connection method provided in the embodiment of the present application;
[0036] Figure 4 This is an optional flow chart of the device connection method provided in the embodiment of the present application;
[0037] Figure 5 This is an optional flow chart of the device connection method provided in the embodiment of the present application;
[0038] Figure 6 This is an optional flow chart of the device connection method provided in the embodiment of the present application;
[0039] Figure 7 This is an optional functional module framework diagram of a vehicle-mounted device provided in an embodiment of the present application;
[0040] Figure 8 This is an optional flow chart of the device connection method provided in the embodiment of the present application applied to an actual scenario;
[0041] Fig. 9 This is an optional flow chart of the device connection method provided in the embodiment of the present application applied to an actual scenario;
[0042] Fig.10 This is an optional structural diagram of the device connection device provided in the embodiment of the present application;
[0043] Fig.11It is an optional structural diagram of the first device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0044] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.
[0045] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be 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.
[0046] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.
[0047] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.
[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0049] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.
[0050] In-car interconnection software Carplay, Carlife, Android Auto: At present, the operating systems of smartphones are generally divided into: IOS system of Apple mobile phones and Android system. Correspondingly, in-car interconnection applications can also be divided into applications running on IOS system (such as Apple Carplay) and applications running on Android system (such as Android Auto, Carlife, etc.). In-car interconnection applications are implanted in the in-car multimedia system to connect compatible mobile phones to the car, and the mobile phone screen is mapped on the central control screen of the in-car multimedia system, so that the functions on the mobile phone can be controlled through the buttons on the central control screen of the in-car multimedia system or voice control.
[0051] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.
[0052] At present, for situations where multiple users or multiple mobile devices are in the car at the same time, the relevant technology usually selects a target device from multiple mobile devices to connect to the vehicle-mounted device and use it interactively according to the preset rules customized by the developer. Alternatively, the relevant technology will also train a neural network based on the user's historical behavior data, and use the trained neural network to predict the device the user wants to connect to, and then connect it to the vehicle-mounted device. Among them, the method of selecting device connection according to preset rules depends on whether the developer has comprehensively formulated the selection rules, which limits its applicability in multiple scenarios. When applied in scenarios not covered by the preset rules, it will greatly reduce the accuracy of selecting devices for connection. The method of using a neural network trained based on historical behavior data has a relatively single data source, which also reduces the accuracy of selecting devices for connection.
[0053] The present application embodiment provides a device connection method, apparatus, first device and computer-readable storage medium, which can improve the accuracy of device connection. Below, taking the vehicle-mounted scenario as an example, an exemplary application of the first device provided by the present application embodiment is described. Figure 1 As shown, the in-vehicle interconnection system 100 provided in the embodiment of the present application includes: a first device 200 and multiple second devices 400 (400-1 to 400-4 are shown as examples). Among them, the second device 400 includes a second device that has connection conditions with the first device, such as a second device with Bluetooth, wireless local area network (Wireless Local Area Network, WLAN) direct connection, near field communication (Near Field Communication, NFC) function, etc. turned on in the car. Accordingly, the first device can find the second device that has connection conditions through functions such as Bluetooth search, such as Figure 1 400-1 to 400-3 shown in FIG.
[0054] The first device provided in the embodiment of the present application can be implemented as various types of terminals or user terminals such as vehicle-mounted terminals, intelligent voice interaction devices, smart home appliances, laptop computers, tablet computers, desktop computers, set-top boxes, etc. The second device can be implemented as various types of terminals or user terminals such as smart phones, smart watches, mobile devices (e.g., mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices), etc. The specific selection is made according to the actual situation, and the embodiment of the present application is not limited.
[0055] In an embodiment of the present application, the first device 200 is used to obtain a second device set, the second device set includes at least one device that has connection conditions with the first device; obtain scenario information; the scenario information represents the usage scenario of the first device; based on the scenario information, combined with historical connection information, device connection prediction is performed to obtain at least one prediction result corresponding to at least one historical second device; the historical connection information includes at least one historical second device that the first device has been connected to under at least one historical scenario information; based on at least one prediction result, a target device is determined from the second device set; and the target device is connected.
[0056] Target device, such as Figure 1 400-3 shown in the figure is used to share the currently running application interface, such as application A interface, to the first device 200, and display the application A interface through the first device 200.
[0057] The first device 200 is further used to receive a user operation initiated by a user on the interface of application A, and based on the user operation, operate application A running on the target device 400-3, and update and display the operation response interface of application A on the interface of application A.
[0058] It can be seen that through the in-vehicle interconnection system provided in the embodiment of the present application, a first device such as a vehicle-mounted device can automatically decide and connect to a target device suitable for the usage scenario of the first device from multiple second devices based on scene information, and perform application interconnection with the target device, thereby improving the accuracy of determining the target device from multiple devices for connection.
[0059] Below, the device connection method of the embodiment of the present application is introduced with the first device as the execution subject. Figure 2 This is an optional flow chart of the device connection method provided in the embodiment of the present application, which will be combined with Figure 2 The steps shown are explained.
[0060] S101: Acquire a second device set, where the second device set includes at least one device that has a connection condition with a first device.
[0061] The embodiments of the present application are applicable to scenarios where a first device selects a target device from multiple second devices for connection, thereby performing data interaction and functional interconnection with the target device. For example, in a vehicle-mounted scenario or an autonomous driving scenario, the vehicle-mounted device selects a target device from multiple mobile devices in the vehicle for connection, and performs functional interaction with the vehicle-mounted device through the target device; or, a smart home device selects a target device from multiple devices in the room for connection, and controls the smart home device through the target device. The specific selection is based on the actual situation, and the embodiments of the present application are not limited.
[0062] In an embodiment of the present application, the first device can search in a preset communication method, such as searching through Bluetooth, WLAN, NFC, etc., to find multiple second devices that have connection conditions with itself, i.e., the first device, as a second device set.
[0063] Here, the second device that meets the connection conditions may be a second device that currently has a preset communication mode turned on and whose distance to the first device is less than or equal to a preset distance threshold corresponding to the preset communication mode, so that the second device can be searched and discovered by the first device.
[0064] S102. Acquire scenario information; the scenario information represents a usage scenario of the first device.
[0065] In an embodiment of the present application, the first device can collect scenario data that affects the selection of the mobile device in the current usage scenario as scenario information.
[0066] In an embodiment of the present application, the scenario information represents the usage scenario of the first device, and the scenario information may include scenario data of at least one dimension in the usage scenario of the first device that affects the first device's selection of the second device for connection.
[0067] In some embodiments, based on Figure 2 ,like Figure 3 As shown, S102 can be implemented by executing the process of S1021-S1024, which will be explained in combination with each step.
[0068] S1021. Obtain current time information.
[0069] In the embodiment of the present application, the current time information can represent different usage intentions of the user to use the first device in different time periods. For example, the current time information can include: whether it is a holiday, the day of the week, the time period of morning, afternoon or evening, etc. Different usage intentions may affect the first device's selection of the connected device. Therefore, the first device can obtain the current time information to use the usage intention information contained in the current time information, such as travel intentions such as going to work, going to school, and traveling, to predict device connection.
[0070] S1022: Obtain device status information of the second device by receiving broadcast information of the second device in the second device set.
[0071] In the embodiment of the present application, the second devices in the second device set generate broadcast information according to their respective device status information, and broadcast it externally through a preset communication method. In this way, when the first device searches for devices in a preset communication method, it can obtain the device status information of the second device by receiving the broadcast information of the second device.
[0072] Here, the status information includes at least one of the power level of the second device and the running status of the preset interconnection software; the preset interconnection software is used to connect the first device on the second device to implement the device interconnection application.
[0073] In some embodiments, the preset interconnection software can be vehicle-machine interconnection software, or it can be smart home appliance control software in a smart home scenario, etc. The specific selection is based on actual conditions and is not limited in the embodiments of this application.
[0074] In some embodiments, the running status of the preset interconnection software may include at least one of information such as whether the preset interconnection software is running on the second device and the version of the preset interconnection software.
[0075] S1023: Collect an image of the operator at a preset operation position, and obtain operator information corresponding to the first device by performing image recognition on the operator image.
[0076] In the embodiment of the present application, different operators of the first device, such as different vehicle drivers, may affect the first device's selection of the connection device. The first device can acquire an image of the preset operation position corresponding to the first device through a built-in or externally connected image acquisition device to obtain an image of the operator at the preset operation position. In addition, the first device can obtain the operator information corresponding to the first device by performing image recognition, such as face recognition, on the operator image.
[0077] In some embodiments, at least one operator information corresponding to at least one operator image may be pre-recorded on the first device, so that the first device can determine a matching target operator image from at least one operator image based on the result of image recognition, and then use the operator information corresponding to the target operator image as the operator information corresponding to the first device.
[0078] In some embodiments, the operator information may include at least one of operator identity information and operator device information, wherein the operator device information includes second device information corresponding to the operator identity information registered or recorded in advance.
[0079] Exemplarily, when the first device is a vehicle-mounted device, the preset operation position may include: the main driving position of the vehicle in which the vehicle-mounted device is located. The vehicle-mounted device may collect an image of the operator at the main driving position through a camera, and obtain the user identity information at the main driving position by performing face recognition on the operator image, and obtain the pre-registered user device information corresponding to the user identity information, and use the user identity information and the user device information as the operator information.
[0080] It should be noted that S1021, S1022 and S1023 are parallel method steps, and one or more of the steps can be selected to be executed, and correspondingly, at least one of the current time information, device status information and operator information can be obtained. The specific selection is made according to the actual situation, and the embodiment of the present application is not limited.
[0081] S1024. Use at least one of the current time information, device status information and operator information as scene information.
[0082] In an embodiment of the present application, the first device can obtain at least one of the current time information, device status information and operator information by executing at least one process in S1021-S1023, thereby using at least one of the current time information, device status information and operator information as scene information.
[0083] In some embodiments, for the vehicle-mounted application scenario, that is, the first device includes: a vehicle-mounted device, and the second device includes: a mobile device scenario, the scenario information may also include: at least one of schedule information and navigation information. Here, at least one of the schedule information and navigation information on the first device and / or the second device can be used to further identify the user's travel intention, so as to obtain scenario information that affects the device connection selection in more dimensions. In actual applications, other types of scenario information can also be obtained according to different scenarios, such as weather information, distance information between each second device and the first device, etc. The specific selection is based on the actual situation, and the embodiments of this application are not limited.
[0084] It can be understood that by introducing multiple influencing factors such as vehicle computer status, mobile device status, driver status, environmental status, etc. as scene information, and making device connection predictions based on scene information, the accuracy of device connection predictions can be greatly improved.
[0085] S103. Perform device connection prediction based on the scenario information and in combination with historical connection information to obtain at least one prediction result corresponding to at least one historical second device; the historical connection information includes at least one historical second device that the first device has been connected to under at least one historical scenario information.
[0086] In an embodiment of the present application, the first device can record at least one historical second device that has been connected under at least one historical scenario information during the historical device connection process to obtain the historical scenario information. In this way, the first device can obtain the historical second devices that meet the user's connection intention under different historical scenario information according to the historical second devices that are actually connected or used under each historical scenario information, so that the device connection prediction can be performed on the currently collected scenario information based on the historical second devices corresponding to the historical scenario information, and the connection probability of at least one historical second device with the first device under the scenario information can be obtained as at least one prediction result.
[0087] S104: Determine a target device from the second device set according to at least one prediction result.
[0088] In the embodiment of the present application, the second device set includes at least some historical second devices. The first device can determine, in the second device set, a second device that meets the user's current connection intention as the target device based on at least one prediction result corresponding to at least one historical second device.
[0089] In some embodiments, the first device may determine, in the set of second devices, a target historical second device corresponding to a highest connection probability among at least one connection probability, and use the second device corresponding to the target historical second device as the target device.
[0090] In some embodiments, the first device may also combine a preset probability threshold to take a historical second device with the highest connection probability and higher than the preset probability threshold as the target historical second device, and take the second device corresponding to the target historical second device in the second device set as the target device.
[0091] In some embodiments, when the target device cannot be determined based on at least one prediction result, exemplarily, when at least one prediction result predicted based on the scene information is lower than a preset probability threshold, or when the second device set does not include any of the at least one historical second device, the first device can generate corresponding information for an information prompt to remind the user that the connection probability predicted based on the scene information is low, and new scene information may have appeared; or the second device set contains all new devices that have not been connected in history, and the user is advised to make a manual selection.
[0092] S105. Connect to the target device.
[0093] In an embodiment of the present application, the first device is connected to the target device for further functional interconnection application.
[0094] In some embodiments, taking the first device as a vehicle-mounted device and the target device as a mobile device such as a mobile phone as an example, after the vehicle-mounted device is connected to the mobile phone, the screen mapping technology can be used to project the multimedia content of the mobile phone applications, such as navigation, itinerary, audio and video playback, and messages, to the multimedia playback device of the vehicle-mounted device, such as the car's central control screen. The application on the mobile phone can be operated through the vehicle-mounted device.
[0095] It is understandable that the first device can obtain at least one prediction result corresponding to at least one historical second device by acquiring scene information and combining the historical connection information of at least one historical second device that the first device has connected to under at least one historical scene information, so that the target device can be determined from the second device set for connection based on the at least one prediction result. Thus, in the device interconnection scenario, by perceiving the scene factors of various dimensions that affect the device connection, the scene information is added to the prediction process, the accuracy of the prediction result is improved, and the accuracy of determining the target device for connection based on the prediction result is improved.
[0096] In the present application embodiment, based on Figure 2 or Figure 3 , S103 can be implemented by S1031 as follows:
[0097] S1031. Use the device connection network to predict device connection for the scene information, and obtain at least one connection probability corresponding to at least one historical second device as at least one prediction result; the device connection network is obtained by training the initial device connection network with the historical connection information.
[0098] In the embodiment of the present application, the device connection network is obtained by training the initial device connection network through historical connection information. Since the historical connection information includes at least one historical second device that the first device has connected to under at least one historical scenario information, the first device uses the device connection network trained with the historical connection information to perform device connection prediction on the scenario information, and can obtain at least one connection probability corresponding to the at least one historical second device under the scenario information as at least one prediction result.
[0099] In the embodiment of the present application, the process of training the initial device connection network using historical connection information can be performed on the first device; it can also be performed on other devices, and the trained device connection network is deployed on the first device. The specific selection is based on the actual situation, and the embodiment of the present application is not limited.
[0100] It can be understood that in the embodiments of the present application, the device connection network obtained by training with historical connection information is used to predict the device connection of scene information, which can fully utilize the complex nonlinear mapping ability, self-learning ability and generalization ability of the neural network to improve the accuracy of predicting the target device through the neural network.
[0101] In the embodiment of the present application, based on S1031 or S105, the first device may further perform network training on the device connection network by executing S106-S108 to further optimize the prediction performance of the device connection network according to the user's feedback, such as Figure 4 As shown below:
[0102] S106: Determine a connection device of the first device.
[0103] In the embodiment of the present application, when the first device automatically selects and connects to the target device through the method of S101-S105, the second device to which the first device is currently actually connected can be determined as the connecting device.
[0104] In some embodiments, based on Figure 4 ,like Figure 5 As shown, S106 can be implemented by executing S1061-S1062, which will be explained in combination with each step.
[0105] S1061. When data interaction occurs between the target device and the first device, use the target device as a connecting device.
[0106] In the embodiment of the present application, when the target device interacts with the first device, it indicates that the user has started to use the target device for device interconnection, that is, the user agrees that the first device automatically selects the target device for connection. The first device uses the target device as the connection device.
[0107] S1062. When a switching instruction for a target device is received, connect to the target switching device, and obtain the target switching device specified by the switching instruction as a connected device.
[0108] In the embodiment of the present application, when a switching instruction for a target device is received, it indicates that the user did not use the currently automatically selected target device, but manually selected another second device for connection. The first device obtains the target switching device specified by the switching instruction for connection, and uses the target switching device as the connection device.
[0109] S107: The connection device and scene information are recorded as incremental connection information in the historical connection information.
[0110] In the embodiment of the present application, when the first device determines the connected device, it records the connected device and scene information as incremental connection information in the historical connection information, that is, the connected device and scene information corresponding to the current secondary device interconnection is added to the historical connection information.
[0111] S108. Based on the incremental connection information, train and update the device connection network.
[0112] In an embodiment of the present application, the first device can train and update the device connection network based on the incremental connection information.
[0113] In some embodiments, the first device can use the incremental connection information to perform online network training and network parameter updates on the device connection network in an incremental training manner, so that the device connection network with updated parameters can be used to predict the next device connection, thereby achieving continuous optimization of the device network model through user usage feedback.
[0114] In some embodiments, the first device may also utilize part or all of the historical connection information including the incremental connection information to train the device connection network and update network parameters. The specific selection is made based on actual conditions and is not limited in the embodiments of the present application.
[0115] In some embodiments, when the connected device does not belong to at least one historical second device, it means that the user manually selected the second device that was connected to the first device for the first time, that is, the predicted category output by the device connection network obtained by training based on the historical connection information does not include the connected device, and the output and network parameters of the device connection network need to be updated. The first device obtains at least part of the information from the historical connection information, and retrains the device connection network in combination with at least part of the information and the incremental connection information, and updates the predicted category and network parameters of the device connection network through retraining.
[0116] It is understandable that the first device can further optimize the network used for device connection based on the user's selection and feedback on the connected device, forming a virtuous circle that can gradually optimize the accuracy of network prediction based on usage. As user connection data continues to increase, the accuracy of device connection network prediction will gradually improve, giving users a better connection experience.
[0117] In some embodiments, after determining the connected device in S106, the first device may further execute S109-S111 to implement application recommendations for the connected device, such as Figure 6 As shown, each step will be described in combination.
[0118] S109. Obtain target application information corresponding to the target application currently running on the connected device; the target application is used to implement functional interaction between the first device and the second device.
[0119] In the embodiment of the present application, a target application is running on the connected device, and application functions are shared and interacted with the first device through the target application.
[0120] In some embodiments, the target application can be a multimedia application, such as music, radio, video, audiobooks, or an information prompt application, such as travel prompts, short message prompts, advertising prompts, or a navigation application, such as itinerary sharing, map navigation, etc. The specific selection is based on actual conditions and is not limited in the embodiments of the present application.
[0121] For example, in a car-mounted scenario, a music application may be running on the mobile phone currently connected to the car-mounted device, so that the songs played in the music application can be shared with the car-mounted device for playback. The target application information may include one or more of the application name, identifier, version, current application data of the music application, such as the navigation address set in the navigation application, etc., and the specific selection is made according to the actual situation, and the embodiment of the application is not limited.
[0122] S110: Record the connection device and target application information in an application usage information set.
[0123] S111. Obtain an application recommendation network by training using the application usage information set; the application recommendation network is used to recommend applications to a second device connected to the first device.
[0124] In the embodiment of the present application, the first device may record the connection device and the target application information as one piece of application usage information in the application usage information set, wherein the application usage information set may be obtained by recording the historical application usage information during multiple device connections and uses by the first device. Thus, the first device uses the application usage information set to train the initial application recommendation network until the application recommendation network is obtained when the preset network training conditions are met.
[0125] In some embodiments, the application recommendation network can be included in the device connection network and trained as a part of the device connection network, or it can be an independent network model. The specific selection is based on actual conditions and is not limited in the embodiments of the present application.
[0126] In the embodiment of the present application, when the second device is connected to the first device as a connecting device, the first device can use the application recommendation network to recommend applications to the second device.
[0127] It can be understood that in the embodiment of the present application, the first device can not only automatically decide from multiple second devices and determine the applicable target device under the scenario information for connection, but also further utilize the application recommendation network to recommend applications that can be run on the target device, such as recommending users to open commonly used navigation addresses, or recommending users to open music playback software, etc., thereby realizing application recommendations based on the target device, providing greater convenience for users and improving the user experience of device interconnection.
[0128] Next, combine Figure 7-Figure 8 , introduces the application of the embodiments of the present application in actual scenarios, such as the interconnection scenario of vehicle-mounted equipment.
[0129] In the vehicle-mounted device interconnection scenario, the first device may be a vehicle-mounted device, and the second device may be a mobile device. Figure 7 The functional module framework diagram of a vehicle-mounted device provided in an embodiment of the present application is shown, including a communication connection module 700, a scene perception module 701, a historical information storage module 702 and a connection decision module 703. Among them,
[0130] The communication connection module 700 is used to collect a list of connectable mobile devices in real time after the vehicle computer is started, which is equivalent to the second device set, and manage the communication connection between the vehicle computer and the mobile devices, such as connecting to the optimal device, detecting new device connections, or connecting to other devices manually switched by the user, etc.
[0131] The scene perception module 701 is used to collect scene information by perceiving the influencing factors of various dimensions that affect the selection of mobile devices in the usage scene of the first device. The scene information may include: current time information, such as the current time period, whether it is a holiday, the day of the week, morning, evening, etc., to identify travel intentions such as going to work, going to school, and traveling; mobile device status information, such as the device power level, whether the car-machine interconnection software such as Carlife is turned on, which is equivalent to the above-mentioned device status information; driver information: who is the current main driver and which mobile device he has, which is equivalent to the above-mentioned operator information.
[0132] The historical information storage module 702 is used to store and retrieve the historical connection information of the mobile devices connected to the vehicle computer, which includes not only the historical mobile devices connected, that is, the historical second devices, but also the multi-dimensional scene information perceived by the scene perception module 701, which is equivalent to at least one historical second device connected under the above-mentioned at least one historical scene information. And based on the connected devices detected by the communication connection module 700, the connected devices and the connection scenes are stored in the historical connection information.
[0133] The connection decision module 703 is used to input the scene information collected by the scene perception module 701 into the decision model of the fully connected neural network, which is equivalent to the above-mentioned device connection network, and integrates the list of connectable mobile devices of the communication connection module 700 to decide the best connected mobile device. According to the actual connection results and user feedback of the best connected mobile device, the decision model is trained and optimized online, and the device connection network is completely retrained when the user manually switches to a new mobile device, so that the device connection network on each car machine can form a unique personalized model, and continuously improve the accuracy of the device connection network in device connection prediction.
[0134] In the present application embodiment, based on Figure 7 The functional module framework shown in FIG. 1 is a process in which the vehicle-mounted device selects a mobile device for connection. Figure 8 As shown below:
[0135] S801, vehicle computer starts.
[0136] S802: The communication connection module 700 collects a list of connectable mobile devices.
[0137] S802 is consistent with the process description of S101 above, and will not be repeated here.
[0138] S803: The scene perception module 701 collects scene information.
[0139] S803 is consistent with the process description of S102 above, and will not be repeated here.
[0140] S804. The connection decision module 703 predicts at least one connection probability corresponding to at least one historical mobile device according to the scenario information through a decision model.
[0141] S804 is consistent with the process description of S1031 above, and will not be repeated here.
[0142] S805. The connection decision module 703 outputs an optimal device according to at least one connection probability and a list of connectable mobile devices.
[0143] In S805, at least one connection probability is equivalent to at least one prediction result; the optimal device is equivalent to the target device. The process of S805 is consistent with the description of S104 above, and will not be repeated here.
[0144] S806. The communication connection module 700 connects to the optimal device.
[0145] The process of S806 is consistent with the above description of S105 and will not be repeated here.
[0146] In the present application embodiment, based on Figure 7The functional module framework shown in FIG. 1 is a process in which the vehicle-mounted device further trains the decision model based on user feedback. Fig. 9 As shown below:
[0147] S807: The communication connection module 700 detects that the user has not switched to the optimal device and started to use it.
[0148] S808. The historical information storage module 702 stores the optimal device and scene information in the historical connection information.
[0149] In S807-S808, if the user does not switch devices and start using after successful connection, the historical information storage module 702 stores the optimal device and scene information; then executes S811.
[0150] S809: The communication connection module 700 detects manual switching by the user, connects to and obtains the target switching device.
[0151] S810. The historical information storage module 702 stores the target switching device and scene information in the historical connection information.
[0152] In S809-S810, if the user manually switches to the target switching device, the communication connection module 700 connects to the target switching device, and the historical information storage module stores the target switching device and scene information, and then executes S812 or S813.
[0153] The process of S807-S808 and the process of S809-S810 are consistent with the above-mentioned description of S106-S107 and will not be repeated here.
[0154] S811, the connection decision module 703 performs incremental training and network parameter updates on the decision module according to the optimal device and scenario information.
[0155] In S811, the historical information storage module 702 inputs the optimal device and scenario information into the online training module in the connection decision module 703 for incremental training, and updates and optimizes the network parameters of the decision model.
[0156] S812: When the target switching device is a historical mobile device, the connection decision module 703 performs incremental training on the decision module according to the target switching device and the scene information.
[0157] In S812, when the target switching device belongs to the historical mobile device included in the historical connection information, the historical information storage module 702 inputs the target switching device and scenario information into the online training module for incremental training to update and optimize the network parameters of the decision model.
[0158] S813. When the target switching device does not belong to the historical mobile device, the connection decision module 703 obtains at least part of the historical connection information within a preset time period; and retrains the decision module based on at least part of the historical connection information, the target switching device and the scenario information.
[0159] In S812, when the target switching device does not belong to the historical mobile device, the connection decision module 703 retrieves at least part of the historical connection information within a preset time period from the historical information storage module 702, and based on at least part of the historical connection information, plus the target switching device and scene information, adds the new device to the output of the model and retrains the decision module.
[0160] The above-mentioned processes of S811-S813 and S809-S810 are consistent with the above-mentioned description of S108 and will not be repeated here.
[0161] It should be noted that if no user use is detected after connecting to the optimal device, that is, no application data interaction is detected between the optimal device and the vehicle-mounted device, the connection between the vehicle-mounted device and the optimal device is maintained.
[0162] In some embodiments, after the vehicle-mounted device is connected to the optimal device, the various mobile devices can be connected to each other, with the optimal device connected to the vehicle computer as the main mobile device. By establishing an Internet network between the mobile devices, the vehicle computer and each mobile device can be connected, allowing the vehicle computer to connect to multiple mobile devices at the same time.
[0163] It can be understood that the device connection method provided in the embodiment of the present application greatly improves the scalability of the solution compared to the method of selecting device connection according to preset rules in the related art. Compared with the method of predicting connected devices based only on user usage data, it fully considers the influencing factors of various dimensions in the device interconnection scenario, and proposes to use a fully connected neural network for decision-making, establish a user personalized model based on user usage feedback, continuously optimize the model effect, and better generalize the model, thereby improving the accuracy of the predicted optimal device.
[0164] The present application also provides a device connection apparatus, which is applied to a first device. Fig.10 A schematic diagram of the structure of the device connection device provided in the embodiment of the present application; Fig.10 As shown, the device connection device 1 includes:
[0165] An acquisition module 11 is used to acquire a second device set, where the second device set includes at least one device that has a connection condition with the first device;
[0166] A scene acquisition module 12, used to obtain scene information; the scene information represents the usage scene of the first device;
[0167] A connection prediction module 13 is configured to perform device connection prediction based on the scenario information and in combination with historical connection information, and obtain at least one prediction result corresponding to at least one historical second device; the historical connection information includes at least one historical second device connected to the first device under at least one historical scenario information; and determine a target device from the set of second devices according to the at least one prediction result;
[0168] The communication connection module 14 is used to connect to the target device.
[0169] In some embodiments, the scene acquisition module 12 is also used to obtain current time information; and / or, by receiving broadcast information of the second device in the second device set, obtain device status information of the second device; the status information includes at least one of the power level of the second device and preset interconnection software information; the preset interconnection software is used to connect the first device on the second device to realize device interconnection application; and / or, collect the operator image at the preset operation position, and obtain the operator information corresponding to the first device by performing image recognition on the operator image; use at least one of the current time information, the device status information and the operator information as the scene information.
[0170] In some embodiments, the connection prediction module 13 is also used to use the device connection network to perform device connection prediction on the scene information, and obtain at least one connection probability corresponding to the at least one historical second device as the at least one prediction result; the device connection network is obtained by training the initial device connection network through the historical connection information.
[0171] In some embodiments, the device also includes: a training module, which is used to determine the connection device of the first device after connecting to the target device; record the connection device and the scene information as incremental connection information in the historical connection information; and train and update the device connection network based on the incremental connection information.
[0172] In some embodiments, the training module is also used to use the target device as the connecting device when the target device interacts with the first device with application data; when a switching instruction for the target device is received, obtain the target switching device specified by the switching instruction for connection, and determine the target switching device as the connecting device.
[0173] In some embodiments, the training module is further used to utilize the incremental connection information to perform incremental training and network parameter update on the device connection network.
[0174] In some embodiments, the training module is also used to obtain at least part of the information from the historical connection information when the connected device does not belong to the at least one historical second device, and to retrain the device connection network by combining the at least part of the information with the incremental connection information, and to update the predicted category and network parameters of the device connection network through retraining.
[0175] In some embodiments, the training module is also used to obtain target application information corresponding to the target application currently running on the connected device; the target application is used to implement functional interaction between the first device and the second device; the connected device and the target application information are recorded in an application usage information set; the application recommendation network is obtained by training the application information usage set; the application recommendation network is used to make application recommendations to the second device connected to the first device.
[0176] In some embodiments, the second device set includes at least some of the historical second devices in the at least one historical second device, and the connection prediction module 13 is further used to determine the second device corresponding to the target historical second device in the second device set with the highest connection probability as the target device in the at least one connection probability.
[0177] In some embodiments, the first device includes: a vehicle-mounted device, and the second device includes: a mobile device, wherein the preset operation position includes: the main driving position of the vehicle where the vehicle-mounted device is located; and the scene information also includes: at least one of schedule information and navigation information.
[0178] It should be noted that the description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.
[0179] In some embodiments, the present application also provides a first device, Fig.11 This is an optional structural diagram of the first device provided in the embodiment of the present application. Fig.11 As shown, the first device 2 includes: a memory 22 and a processor 23. The memory 22 and the processor 23 are connected via a communication bus 24; the memory 22 is used to store executable instructions; the processor 23 is used to implement the method provided in the embodiment of the present application when executing the executable instructions stored in the memory 22, for example, the device connection method provided in the embodiment of the present application.
[0180] An embodiment of the present application provides a computer-readable storage medium storing executable device connection instructions for causing the processor 23 to execute and implement the method provided by the embodiment of the present application, for example, the device connection method provided by the embodiment of the present application.
[0181] In some embodiments of the present application, the storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.
[0182] In some embodiments of the present application, the executable device connection instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine or other unit suitable for use in a computing environment.
[0183] As an example, executable device connection instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).
[0184] As an example, the executable device connection instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed at multiple sites and interconnected by a communication network.
[0185] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.
[0186] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0187] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0188] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0189] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.
Claims
1. A device connection method, applied to a first device, characterized in that: include: Acquire a second device set, where the second device set includes at least one device that has a connection condition with the first device; Get scene information; The scenario information represents a usage scenario of the first device; The first device includes: a vehicle-mounted device; Based on the scenario information, combined with the historical connection information, device connection prediction is performed to obtain at least one prediction result corresponding to at least one historical second device; the historical connection information includes at least one historical second device connected by the first device under at least one historical scenario information; the second device includes: a mobile device; Determining a target device from the second set of devices according to the at least one prediction result; connecting to the target device; The acquiring of scene information includes: By receiving broadcast information of a second device in the second device set, device status information of the second device is obtained; the status information includes at least one of power of the second device and preset interconnection software information; the preset interconnection software is used to connect the first device on the second device to implement device interconnection application; and / or, Collecting an operator image at a preset operating position, and obtaining operator information corresponding to the first device by performing image recognition on the operator image; At least one of the device status information and the operator information is used as the scene information.
2. The method according to claim 1, characterized in that The acquiring of scene information further includes: Get current time information; The current time information is used as the scene information.
3. The method according to claim 1 or 2, characterized in that: The performing device connection prediction based on the scenario information and in combination with the historical connection information to obtain at least one prediction result corresponding to at least one historical second device includes: Using the device connection network, device connection prediction is performed on the scene information to obtain at least one connection probability corresponding to the at least one historical second device as the at least one prediction result; the device connection network is obtained by training an initial device connection network through the historical connection information.
4. The method according to claim 3, characterized in that After connecting the target device, the method further includes: Determining a connected device of the first device; Taking the connection device and the scene information as incremental connection information, and recording them in the historical connection information; Based on the incremental connection information, the device connection network is trained and updated.
5. The method according to claim 4, characterized in that The determining a connection device of the first device includes: In the case where the target device interacts with the first device with application data, using the target device as the connecting device; When a switching instruction for the target device is received, a target switching device specified by the switching instruction is acquired for connection, and the target switching device is determined as the connection device.
6. The method according to claim 5, characterized in that The training and updating of the device connection network based on the incremental connection information includes: The incremental connection information is used to perform incremental training and network parameter update on the device connection network.
7. The method according to claim 5, characterized in that The training and updating of the device connection network based on the incremental connection information includes: In the case that the connecting device does not belong to the at least one historical second device, at least part of the information is obtained from the historical connection information, and the device connection network is retrained by combining the at least part of the information with the incremental connection information, and the predicted category and network parameters of the device connection network are updated through the retraining.
8. The method according to any one of claims 4 to 7, characterized in that: The method further comprises: Acquire target application information corresponding to the target application currently running on the connected device; the target application is used to implement functional interaction between the first device and the second device; Recording the connection device and the target application information in an application usage information set; An application recommendation network is obtained by training the application information usage set; the application recommendation network is used to recommend applications to a second device connected to the first device.
9. The method according to claim 3, characterized in that: The second device set includes at least some of the at least one historical second device, and determining the target device from the second device set according to the at least one prediction result includes: Among the at least one connection probability, the second device corresponding to the target historical second device with the highest connection probability in the second device set is determined as the target device.
10. The method according to claim 2, characterized in that The first device includes: a vehicle-mounted device, and the second device includes: a mobile device, wherein: The preset operation position includes: the main driving position of the vehicle where the vehicle-mounted device is located; The scenario information also includes: at least one of schedule information and navigation information.
11. A device connection device, applied to a first device, characterized in that: include: An acquisition module, configured to acquire a second device set, where the second device set includes at least one device that has a connection condition with the first device; A scene acquisition module is used to obtain scene information; The scenario information represents the usage scenario of the first device; the first device includes: an in-vehicle device; A connection prediction module, configured to perform device connection prediction based on the scenario information and in combination with historical connection information, and obtain at least one prediction result corresponding to at least one historical second device; the historical connection information includes at least one historical second device connected by the first device under at least one historical scenario information; and determine a target device from the set of second devices according to the at least one prediction result; the second device includes: a mobile device; A communication connection module, used for connecting to the target device; The scene acquisition module is specifically used to obtain device status information of the second device by receiving broadcast information of the second device in the second device set; the status information includes at least one of the power level of the second device and preset interconnection software information; the preset interconnection software is used to connect the first device on the second device to implement device interconnection application; and / or, to collect an operator image at a preset operation position, and obtain the operator information corresponding to the first device by performing image recognition on the operator image; and use at least one of the device status information and the operator information as the scene information.
12. A first device, characterized in that: include: A memory for storing executable instructions; A processor, configured to implement the method according to any one of claims 1 to 10 by executing executable instructions stored in the memory.
13. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to cause a processor to execute and implement the method described in any one of claims 1 to 10.
