Detailed Description
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
In the following description, references to the terms "first \ second \ third" are only to distinguish similar objects and do not denote a particular order, but rather the terms "first \ second \ third" are used to interchange specific orders or sequences, where appropriate, so as to enable the embodiments of the application described herein to be practiced in other than the order shown or described herein.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
Before further detailed description of the embodiments of the present application, terms and expressions referred to in the embodiments of the present application will be described, and the terms and expressions referred to in the embodiments of the present application will be used for the following explanation.
On-vehicle interconnection software Carplay, Carlife, Android Auto: currently, the operating systems of smart phones are generally classified into: the IOS system and the Android system of the Apple phone, accordingly, the vehicle-mounted internet application can be divided into an application (such as Apple display) running on the IOS system and an application (such as Android Auto, carrife, etc.) running on the Android system. The vehicle-mounted interconnection application is implanted in the vehicle-mounted multimedia system and used for connecting a compatible mobile phone with an automobile, and a mobile phone screen is mapped on a central control screen of the vehicle-mounted multimedia system, so that functions on the mobile phone can be controlled through keys or voice control on the central control screen of the vehicle-mounted multimedia system.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
At present, for the situation that a plurality of users or a plurality of mobile devices are in a vehicle at the same time, the related art generally selects a target device from the plurality of mobile devices to connect with the in-vehicle device and perform interactive use according to preset rules customized by a developer. Or, the related art may train a neural network based on historical behavior data of the user, predict a device to which the user wants to connect using the trained neural network, and then connect with the vehicle-mounted device. The method for selecting the equipment connection according to the preset rule depends on whether the selection rule is formulated by a developer comprehensively, so that the applicability under multiple scenes is limited, and the accuracy of selecting the equipment connection can be greatly reduced when the method is applied under the scene not covered by the preset rule. The method for predicting by using the neural network trained based on the historical behavior data has a single data source, and the accuracy of selecting equipment for connection is also reduced.
The embodiment of the application provides a device connection method, a device, a first device and a computer readable storage medium, which can improve the accuracy of device connection. An exemplary application of the first device provided in the embodiment of the present application is described below by taking an in-vehicle scene as an example. As shown in fig. 1, a vehicle-mounted interconnection system 100 provided in an embodiment of the present application includes: a first device 200 and a plurality of second devices 400 (400-1 through 400-4 are exemplarily shown). The second device 400 includes a second device having a connection condition with the first device, such as a second device having a bluetooth, Wireless Local Area Network (WLAN) direct connection, Near Field Communication (NFC) function, and the like, which are turned on in the vehicle. Accordingly, the first device may discover the second device having the connection condition, such as 400-1 to 400-3 shown in fig. 1, through a bluetooth search or the like.
The first device provided by the embodiment of the application can be implemented as various types of terminals or user terminals such as a vehicle-mounted terminal, an intelligent voice interaction device, an intelligent household appliance, a notebook computer, a tablet computer, a desktop computer and a set-top box. The second device may be embodied as various types of terminals or user terminals, such as a smart phone, a smart watch, a mobile device (e.g., a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable gaming device), and so on. The specific selection is performed according to actual conditions, and the embodiments of the present application are not limited.
In this embodiment of the present application, the first device 200 is configured to obtain a second device set, where the second device set includes at least one device having a connection condition with the first device; acquiring scene information; the scene information represents a use scene of the first device; performing equipment connection prediction by combining historical connection information based on the scene information to obtain at least one prediction result corresponding to at least one historical second equipment; the historical connection information comprises at least one historical second device which is connected by the first device under at least one piece of historical scene information; determining a target device from the second device set according to the at least one prediction result; and connecting the target equipment.
The target device, such as 400-3 shown in fig. 1, is configured to share a currently running application interface, such as an application a interface, to the first device 200, and display the application a interface through the first device 200.
The first device 200 is further configured to receive a user operation initiated by a user for the application a interface, operate the application a running on the target device 400-3 based on the user operation, and update and display an operation response interface of the application a on the application a interface.
It can be seen that, with the vehicle-mounted interconnection system provided in the embodiment of the present application, the first device, such as the vehicle-mounted device, can automatically make a decision from the plurality of second devices according to the scene information, connect to the target device suitable for the usage scene of the first device, and perform application interconnection with the target device for use, thereby improving the accuracy of determining the target device from the plurality of devices for connection use.
Next, a device connection method according to an embodiment of the present application will be described with a first device as an execution subject. Fig. 2 is an alternative flowchart of a device connection method provided in an embodiment of the present application, and will be described with reference to the steps shown in fig. 2.
S101, acquiring a second device set, wherein the second device set comprises at least one device which has a connection condition with the first device.
The method and the device are suitable for a scene that the first device selects the target device from the plurality of second devices to connect, and therefore data interaction and function interconnection are conducted between the first device and the target device. In an exemplary vehicle-mounted scene or an automatic driving scene, the vehicle-mounted device selects a target device from a plurality of mobile devices in a vehicle to connect, and performs function interaction with the vehicle-mounted device through the target device; or the intelligent household equipment selects target equipment from a plurality of indoor equipment to connect, and the target equipment is used for controlling the intelligent household equipment. The specific selection is performed according to actual conditions, and the embodiments of the present application are not limited.
In this embodiment of the application, the first device may perform searching in a preset communication manner, for example, search in a bluetooth search manner, a WLAN manner, an NFC manner, and the like, and discover a plurality of second devices that have connection conditions with itself, that is, the first device, as a second device set.
Here, the second device with the connection condition may be the second device which is currently opened by the preset communication method, and the distance between the second device and the first device is less than or equal to a preset distance threshold corresponding to the preset communication method, so that the second device can be searched and found by the first device.
S102, acquiring scene information; the context information characterizes a usage context of the first device.
In the embodiment of the application, the first device may collect scene data affecting the selection of the mobile device in a current usage scene as scene information.
In this embodiment of the application, the context information represents a usage scenario of the first device, and the context information may include at least one dimension of context data that affects the first device to select the second device for connection in the usage scenario of the first device.
In some embodiments, based on fig. 2, as shown in fig. 3, S102 may be implemented by performing the processes of S1021-S1024, which will be described in conjunction with the steps.
And S1021, acquiring the current time information.
In the embodiment of the present application, the current time information may represent different usage intentions of the user to use the first device at different time periods, and for example, the current time information may include: whether holidays, days of the week, morning, afternoon, or evening hours, etc. And different usage intents may affect the selection of the connected device by the first device. Thus, the first device can acquire the current time information to perform device connection prediction by using the use intention information included in the current time information, such as travel intentions of work, school, trip, and the like.
S1022, acquiring device status information of the second device by receiving broadcast information of the second device in the second device set.
In the embodiment of the application, the second devices in the second device set generate broadcast information according to their respective device state information, and broadcast the broadcast information externally in a preset communication mode. In this way, the first device may acquire the device state information of the second device by receiving the broadcast information of the second device when performing the device search in the preset communication manner.
Here, the state information includes at least one of the second device power and the operation condition of the preset interconnection software; and the preset interconnection software is used for connecting the first equipment on the second equipment to realize equipment interconnection application.
In some embodiments, the preset interconnection software may be vehicle-mounted interconnection software, or intelligent household appliance control software in an intelligent home scene, and the preset interconnection software is specifically selected according to actual conditions, and the embodiment of the present application is not limited.
In some embodiments, the presetting of the operation condition of the interconnection software at least may include: and presetting at least one of information such as whether the interconnection software runs on the second equipment, and presetting the version of the interconnection software.
And S1023, acquiring an operator image on a preset operation position, and performing image recognition on the operator image to obtain operator information corresponding to the first equipment.
In an embodiment of the application, different operators of the first device, such as different vehicle drivers, may influence the selection of the connection device by the first device. The first device can acquire images of a preset operation position corresponding to the first device through a built-in or externally connected image acquisition device to obtain an operator image on the preset operation position. Moreover, the first device may obtain the operator information corresponding to the first device by performing image recognition, such as face recognition, on the operator image.
In some embodiments, at least one piece of operator information corresponding to at least one operator image may be pre-recorded on the first device, so that the first device may determine a matching target operator image from the at least one operator image according to the result of the image recognition, and further use the operator information corresponding to the target operator image as the operator information corresponding to the first device.
In some embodiments, the operator information may include at least one of operator identity information, and operator device information. The operator equipment information comprises second equipment information corresponding to pre-registered or recorded operator identity information.
For example, for the case where the first device is an in-vehicle device, the preset operation position may include: the vehicle-mounted equipment is located at the main driving position of the vehicle. The vehicle-mounted equipment can acquire an operator image on the main driving position through the camera, perform face recognition on the operator image to obtain user identity information on the main driving position, acquire pre-registered user equipment information corresponding to the user identity information, and take the user identity information and the user equipment information as the operator information.
S1021, S1022, and S1023 are parallel method steps, and one or more of the steps may be selected to be executed actually, and accordingly, at least one of the current time information, the device state information, and the operator information may be obtained. The specific selection is performed according to actual conditions, and the embodiments of the present application are not limited.
And S1024, taking at least one of the current time information, the equipment state information and the operator information as scene information.
In this embodiment, the first device may obtain at least one of the current time information, the device state information, and the operator information by performing at least one process in S1021-S1023, so that the at least one of the current time information, the device state information, and the operator information is used as the scene information.
In some embodiments, for an in-vehicle application scenario, the first device comprises: an in-vehicle apparatus, the second apparatus including: the scene information of the mobile device may further include: at least one of schedule information and navigation information. Here, the travel intention of the user may be further identified by using at least one of schedule information and navigation information on the first device and/or the second device, so as to obtain scene information influencing device connection selection in more dimensions. In practical application, other types of scene information, such as weather information, distance information between each second device and the first device, and the like, may also be obtained according to different scenes, and the selection is specifically performed according to actual situations, which is not limited in the embodiment of the present application.
It can be understood that various influence factors such as the vehicle machine state, the mobile device state, the driver state and the environment state are introduced as scene information, so that the device connection prediction is carried out based on the scene information, and the accuracy of the device connection prediction can be greatly improved.
S103, based on the scene information, performing equipment connection prediction by combining historical connection information to obtain at least one prediction result corresponding to at least one historical second equipment; the historical connection information comprises at least one historical second device which is connected by the first device under at least one piece of historical scene information.
In this embodiment of the application, the first device may record, in a historical device connection process, at least one historical second device that is connected under at least one piece of historical context information, to obtain the historical context information. In this way, the first device may obtain, according to each piece of historical scene information, a historical second device that is actually connected or used and meets the connection intention of the user under different pieces of historical scene information, and thus, device connection prediction may be performed on currently acquired scene information based on the historical second device corresponding to the historical scene information, and a connection probability of at least one piece of historical second device with the first device under the scene information is obtained as at least one prediction result.
And S104, determining the target equipment from the second equipment set according to at least one prediction result.
In this embodiment, the second device set includes at least part of the historical second devices. The first device may determine, as the target device, a second device that meets the current connection intention of the user in the second device set according to at least one prediction result corresponding to at least one historical second device.
In some embodiments, the first device may determine, in the second device set, a target history second device corresponding to a highest connection probability of the at least one connection probability, and use the second device corresponding to the target history second device as the target device.
In some embodiments, the first device may also, in combination with a preset probability threshold, use a historical second device with the highest connection probability and higher than the preset probability threshold as a target historical second device, and use a second device corresponding to the target historical second device in the second device set as the target device.
In some embodiments, when the target device cannot be determined according to at least one prediction result, for example, under the condition that the at least one prediction result predicted according to the scenario information is lower than a preset probability threshold, or the second device set does not include any historical second device in the at least one historical second device, the first device may generate corresponding information for information prompt to remind a user that the connection probability predicted according to the scenario information is low and new scenario information may appear; or all the second equipment set are new equipment which is not connected in history, and the user is advised to select manually.
And S105, connecting the target equipment.
In the embodiment of the application, the first device is connected with the target device to perform further function interconnection application.
In some embodiments, for example, the first device is a vehicle-mounted device, and the target device is a mobile device such as a mobile phone, after the vehicle-mounted device is connected to the mobile phone, multimedia content of applications on the mobile phone, such as applications of navigation, travel, audio/video playing, and messages, may be projected to a multimedia playing device of the vehicle-mounted device, such as a central control screen of an automobile, by using a screen mapping technology. And operating the application on the mobile phone through the vehicle-mounted device.
It can be understood that the first device obtains the context information, and performs prediction by combining with the historical connection information of at least one historical second device connected by the first device under the at least one historical context information, so as to obtain at least one prediction result corresponding to the at least one historical second device, and thus, the target device may be determined to be connected from the second device set according to the at least one prediction result. Therefore, under the scene of equipment interconnection, scene factors influencing each dimensionality of equipment connection are sensed, scene information is added into the prediction process, the accuracy of the prediction result is improved, and the accuracy of determining the target equipment to be connected according to the prediction result is improved.
In the embodiment of the present application, based on fig. 2 or fig. 3, S103 may be implemented by S1031, as follows:
s1031, utilizing the equipment connection network to predict the equipment connection of the scene information, and obtaining at least one connection probability corresponding to at least one historical second equipment as at least one prediction result; the device connection network is obtained by training an initial device connection network through historical connection information.
In the embodiment of the application, the device connection network is obtained by training the initial device connection network through historical connection information. Because the historical connection information includes at least one historical second device connected by the first device under at least one piece of historical scene information, the first device performs device connection prediction on the scene information by using a device connection network obtained by training the historical connection information, and at least one connection probability corresponding to the at least one historical second device under the scene information can be obtained and used as at least one prediction result.
In the embodiment of the application, the process of training the initial device connection network by using the historical connection information can be executed on the first device; or on other devices and deploying the trained device connection network on the first device. The specific selection is performed according to actual conditions, and the embodiments of the present application are not limited.
It can be understood that in the embodiment of the application, the device connection prediction is performed on the scene information by using the device connection network obtained by training the historical connection information, so that the complex nonlinear mapping capability, the self-learning capability and the generalization capability of the neural network can be fully utilized, and the accuracy of predicting the target device through the neural network is improved.
In this embodiment of the application, after based on S1031 or S105, the first device may further perform network training on the device connection network by performing S106-S108, so as to further optimize the predicted performance of the device connection network according to the feedback used by the user, as shown in fig. 4, as follows:
and S106, determining the connection equipment of the first equipment.
In the embodiment of the present application, in the case that the first device automatically selects and connects to the target device by the method in S101-S105, the second device to which the first device is currently actually connected may be determined as the connection device.
In some embodiments, based on FIG. 4, as shown in FIG. 5, S106 may be implemented by performing S1061-S1062, which will be described in conjunction with the various steps.
And S1061, taking the target device as a connecting device under the condition that the target device and the first device generate data interaction.
In the embodiment of the present application, in a case that the target device generates data interaction with the first device, it indicates that the user has started using the target device for device interconnection, that is, the user agrees with the first device to automatically select the connected target device. The first device takes the target device as the connection device.
S1062, in a case that the handover instruction for the target device is received, connecting the target handover device, and acquiring the target handover device specified by the handover instruction as the connection device.
In this embodiment, when a switching instruction for a target device is received, it is described that a user does not use the currently automatically selected target device, but manually selects another second device to connect. And the first equipment acquires the target switching equipment specified by the switching instruction to carry out connection and takes the target switching equipment as the connecting equipment.
And S107, recording the connection equipment and the scene information in the historical connection information as incremental connection information.
In the embodiment of the application, the first device takes the connection device and the scene information as incremental connection information and records the incremental connection information in the historical connection information under the condition that the connection device is determined. That is, the information of the connection device and the scene corresponding to the current device interconnection is added to the historical connection information.
And S108, training and updating the equipment connection network based on the incremental connection information.
In this embodiment, the first device may train and update the device connection network based on the incremental connection information.
In some embodiments, the first device may perform online network training and network parameter updating on the device connection network in an incremental training manner by using incremental connection information, so that next device connection prediction may be performed by using the device connection network after updating parameters, and continuous optimization of the device network model through user feedback is implemented.
In some embodiments, the first device may also train the device connection network and update the network parameters by using part or all of the historical connection information including the incremental connection information, which is specifically selected according to an actual situation, and the embodiments of the present application are not limited.
In some embodiments, in a case that the connected device does not belong to at least one historical second device, it indicates that the user manually selects the second device that is connected to the first device for the first time, that is, the prediction category output by the device connection network trained according to the historical connection information does not include the connected device, and the output of the device connection network and the network parameter need to be updated. The first device obtains at least part of information from the historical connection information, retrains the device connection network by combining at least part of information and the incremental connection information, and updates the prediction type and the network parameters of the device connection network through retraining.
It can be understood that the first device can further optimize the device connection network according to the selection and feedback of the user on the connection device, so as to form a virtuous cycle capable of gradually optimizing the network prediction accuracy according to the use condition, and along with the continuous enrichment of the user connection data, the device connection network prediction accuracy can be gradually improved, so as to bring better connection experience to the user.
In some embodiments, after determining the connection device in S106, the first device may further perform S109-S111 to implement application recommendation for the connection device, as shown in fig. 6 and described with reference to the steps.
S109, acquiring target application information corresponding to a currently running target application on the connection equipment; the target application is used for realizing functional interaction between the first device and the second device.
In the embodiment of the application, the target application runs on the connection device, and the application function sharing and interaction are performed with the first device through the target application.
In some embodiments, the target application may be a multimedia application, such as music, radio station, video, listening book, or an information prompt application, such as a travel prompt, a short message prompt, an advertisement prompt, or a navigation application, such as trip sharing, map navigation, and the like, which is specifically selected according to the actual situation, and the embodiments of the present application are not limited.
For example, in an in-vehicle scene, a music application may be run on a mobile phone to which the in-vehicle device is currently connected, so that songs played in the music application are shared to the in-vehicle device for playing. The target application information may include one or more of an application name, an identifier, a version, current application data of the music application, such as a navigation address set in the navigation application, and the like, which is specifically selected according to the actual situation, and the embodiment of the present application is not limited.
And S110, recording the information of the connection device and the target application in the application use information set.
S111, training by utilizing an application use information set to obtain an application recommendation network; the application recommendation network is used for recommending the application to a second device connected to the first device.
In this embodiment of the application, the first device may record the connection device and the target application information as one piece of application use information in an application use information set, where the application use information set may be obtained by recording historical application use information of the first device in multiple device connection and use processes. Therefore, the first device trains the initial application recommendation network by using the application use information set until the application recommendation network is obtained under the condition that the preset network training condition is met.
In some embodiments, the application recommendation network may be included in the device connection network, and is trained as a part of the device connection network, or may be an independent network model, which is specifically selected according to actual situations, and the embodiments of the present application are not limited.
In this embodiment of the application, when a second device is connected to a first device as a connection device, the first device may perform application recommendation on the second device by using an application recommendation network.
It can be understood that, in the embodiment of the application, the first device may not only automatically make a decision from the plurality of second devices and determine that the target device suitable for the context information is connected, but also further recommend an application that may be run on the target device by using the application recommendation network, for example, a recommended user opens a common navigation address, or a recommended user opens music playing software, and the like, so that application recommendation based on the target device is achieved, greater convenience is provided for the user to use, and user experience of device interconnection use is improved.
Next, with reference to fig. 7 to 8, an application of the embodiment of the present application in an actual scenario, such as an interconnection scenario of vehicle-mounted devices, is described.
In an interconnection scenario of vehicle-mounted devices, the first device may be a vehicle-mounted device, the second device may be a mobile device, and fig. 7 shows a functional module framework diagram of a vehicle-mounted device according to an embodiment of the present application, where the functional module framework diagram includes a communication connection module 700, a scene sensing module 701, a history information storage module 702, and a connection decision module 703. Wherein,
the communication connection module 700 is configured to collect, in real time, a list of connectable mobile devices, which is equivalent to a second device set, after the car machine is started, and manage communication connections between the car machine and the mobile devices, such as connection of an optimal device, connection detection of a new device, or connection of other devices that are manually switched by a user.
The scene sensing module 701 is configured to acquire scene information by sensing influence factors affecting mobile device selection of each dimension in a usage scene of the first device. The scene information may include: current time information, such as a current time period, whether a holiday, a day of week, morning, evening, etc., to identify travel intentions such as work, school, trip, etc.; the mobile device state information, such as the device power, whether car interconnection software such as a carrife is opened or not, is equivalent to the device state information; driver information: which position the current primary driving is, which mobile device is, corresponds to the operator information described above.
The history information storage module 702 is configured to store and retrieve history connection information of the mobile device connected to the car, where the history connection information includes not only which history mobile devices are connected, that is, history second devices, but also multi-dimensional scene information sensed by the scene sensing module 701, which is equivalent to at least one history second device connected under the at least one history scene information. And stores the connection device and the connection scenario in the history connection information based on the connection device detected by the communication connection module 700.
And the connection decision module 703 is used for inputting the scene information acquired by the scene sensing module 701 into a decision model of the fully-connected neural network, which is equivalent to the above device connection network, and synthesizing the connectable mobile device list of the communication connection module 700 to decide the mobile device with the optimal connection. And training and optimizing the decision model on line according to the actual connection result and user feedback of the mobile equipment with the optimal connection, and completely retraining the equipment connection network under the condition that the user manually switches to new mobile equipment, so that the equipment connection network on each vehicle machine can form a unique personalized model, and the accuracy of equipment connection prediction of the equipment connection network is continuously improved.
In the embodiment of the present application, based on the functional module framework shown in fig. 7, a process of selecting a mobile device for connection by an in-vehicle device may be as shown in fig. 8, as follows:
and S801, starting the vehicle machine.
S802, the communication connection module 700 collects a list of connectable mobile devices.
S802 is consistent with the above description of the process of S101, and is not described here again.
S803, the scene sensing module 701 collects scene information.
S803 is consistent with the above description of the process of S102, and is not described here again.
S804, the connection decision module 703 predicts at least one connection probability corresponding to at least one historical mobile device according to the scene information through the decision model.
S804 is consistent with the process description of S1031, and is not described herein again.
S805, the connection decision module 703 outputs the optimal device according to the at least one connection probability and the connectable mobile device list.
In S805, at least one connection probability corresponds to at least one prediction result; the optimal device corresponds to the target device. The process of S805 is the same as that described above in S104, and is not described here again.
And S806, connecting the optimal equipment by the communication connection module 700.
The process of S806 is consistent with the description of S105 above, and is not described again here.
In this embodiment of the application, based on the functional module framework shown in fig. 7, a process of further training a decision model by the vehicle-mounted device according to the user usage feedback may be as shown in fig. 9, as follows:
s807, the communication connection module 700 detects that the user does not switch the optimal device and starts using the device.
S808, the history information storage module 702 stores the optimal device and scene information in the history connection information.
In S807-S808, if the user does not switch devices and starts using the devices after the connection is successful, the history information storage module 702 stores the optimal device and scene information; s811 is further performed.
And S809, the communication connection module 700 detects that the user manually switches, connects and acquires the target switching device.
S810, the history information storage module 702 stores the target switching device and the scene information in the history connection information.
In S809 to S810, if the user manually switches to the target switching device, the communication connection module 700 connects to the target switching device, and the history information storage module stores the target switching device and the scene information, thereby performing S812 or S813.
The processes of S807-S808 and the processes of S809-S810 are consistent with the descriptions of S106-S107, and are not described again here.
S811, the connection decision module 703 performs incremental training and network parameter updating on the decision module according to the optimal device and scene information.
In S811, the historical information storage module 702 inputs the optimal device and scene information to the online training module in the connection decision module 703 for incremental training, and updates and optimizes the network parameters of the decision model.
S812, under the condition that the target switching device belongs to the 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.
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 the scene information to the online training module for incremental training, and updates and optimizes the network parameters of the decision model.
S813, in a case that the target handover device does not belong to the historical mobile device, the connection decision module 703 acquires at least part of the historical connection information within a preset time period; and retraining the decision module according to at least part of the historical connection information, the target switching equipment and the scene information.
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 in the historical information storage module 702 within a preset time period, adds a new device to the output of the model according to at least part of the historical connection information and the target switching device and scene information, and retrains the decision module.
The above-mentioned processes of S811-S813 and the processes of S809-S810 are consistent with the above-mentioned description of S108, and are not described again here.
It should be noted that, if the user usage is not detected after the connection to the optimal device, that is, the application data interaction between the optimal device and the vehicle-mounted device is not detected, the connection between the vehicle-mounted device and the optimal device is maintained.
In some embodiments, after the vehicle-mounted device is connected to the optimal device, the mobile devices may be connected to each other, the optimal device connected to the vehicle-mounted device is used as a main mobile device, and an internet is established between the mobile devices, so that the vehicle-mounted device and the mobile devices can be connected to each other, and the vehicle-mounted device can be connected to multiple mobile devices at the same time.
It can be understood that the device connection method provided by the embodiment of the application greatly improves the expansibility of the scheme compared with a method for selecting device connection according to a preset rule in the related art, fully considers all dimension influence factors in the device interconnection scene compared with a method for predicting the connected device according to user use data, proposes to adopt a full-connection neural network for decision making, establishes a user personalized model according to user use feedback, continuously optimizes the model effect, and has better model generalization formation, thereby improving the accuracy of the predicted optimal device.
The application also provides an equipment connecting device which is applied to the first equipment. FIG. 10 is a schematic structural diagram of an apparatus connecting device according to an embodiment of the present disclosure; as shown in fig. 10, the device connecting apparatus 1 includes:
an obtaining module 11, configured to obtain 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 12, configured to acquire scene information; the scene information represents a usage scene of the first device;
the connection prediction module 13 is configured to perform device connection prediction based on the scene 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 comprises at least one historical second device connected by the first device under at least one piece of historical scene information; determining target equipment from the second equipment set according to the at least one prediction result;
and a communication connection module 14, configured to connect to the target device.
In some embodiments, the scene capturing module 12 is further configured to obtain current time information; and/or acquiring the device state information of the second device by receiving the broadcast information of the second device in the second device set; the state information comprises at least one of the electric quantity of the second equipment and preset interconnection software information; the preset interconnection software is used for connecting the first equipment on the second equipment to realize equipment interconnection application; and/or acquiring an operator image on a preset operation position, and performing image recognition on the operator image to obtain operator information corresponding to the first equipment; and taking at least one of the current time information, the equipment state information and the operator information as the scene information.
In some embodiments, the connection prediction module 13 is further configured to perform device connection prediction on the context information by using a device connection network, 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 an initial device connection network through the historical connection information.
In some embodiments, the apparatus further comprises: a training module, configured to determine a connection device of the first device after the target device is connected; taking the connection equipment and the scene information as incremental connection information, and recording the incremental connection information in the historical connection information; training and updating the device connection network based on the incremental connection information.
In some embodiments, the training module is further configured to treat the target device as the connection device if the target device generates application data interaction with the first device; and under the condition of receiving a switching instruction aiming at the target equipment, acquiring the target switching equipment specified by the switching instruction to connect, and determining the target switching equipment as the connecting equipment.
In some embodiments, the training module is further configured to perform incremental training and network parameter updating on the device connection network by using the incremental connection information.
In some embodiments, the training module is further configured to, in a case that the connection device does not belong to the at least one historical second device, obtain at least part of information from the historical connection information, retrain the device connection network by combining the at least part of information with the incremental connection information, and update the predicted class and the network parameter of the device connection network by retraining.
In some embodiments, the training module is further configured to obtain target application information corresponding to a target application currently running on the connection device; the target application is used for realizing functional interaction between the first device and the second device; recording the connection device and the target application information in an application use information set; training by using the application information use set to obtain an application recommendation network; the application recommendation network is used for recommending applications to a second device connected to the first device.
In some embodiments, the second device set includes at least a part of the at least one historical second device, and the connection prediction module 13 is further configured to determine, as the target device, a target historical second device with a highest connection probability among the at least one connection probability, where the target historical second device corresponds to the second device set.
In some embodiments, the first device comprises: an in-vehicle apparatus, the second apparatus including: a mobile device, wherein the preset operation position comprises: the main driving position of the vehicle where the vehicle-mounted equipment is located; the scene information further includes: at least one of schedule information and navigation information.
It should be noted that the above description of the embodiment of the apparatus, similar to the description of the embodiment of the method, has similar beneficial effects as the embodiment of the method. For technical details not disclosed in the embodiments of the apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.
In some embodiments, the present application further provides a first device, and fig. 11 is an alternative structural schematic diagram of the first device provided in the present application. As shown in fig. 11, the first device 2 includes: a memory 22 and a processor 23. Wherein, the memory 22 and the processor 23 are connected through a communication bus 24; a memory 22 for storing executable instructions; the processor 23 is configured to, when executing the executable instructions stored in the memory 22, implement the method provided in the embodiment of the present application, for example, the device connection method provided in the embodiment of the present application.
An embodiment of the present application provides a computer-readable storage medium, which stores executable device connection instructions, and is configured to cause the processor 23 to implement the method provided in the embodiment of the present application when executed, for example, the device connection method provided in the embodiment of the present application.
In some embodiments of the present application, the storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.
In some embodiments of the application, the executable device connection instructions may be in the form of a program, 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 stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, the executable device connection instructions may, but need not, correspond to files in a file system, may be stored in a portion of a file that holds other programs or data, such as 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 that store one or more modules, sub-programs, or portions of code).
By way of 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 distributed across multiple sites and interconnected by a communication network.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application.