Processing method, device, electronic device and readable storage medium

Abstract

The present application discloses a processing method, an apparatus, an electronic device and a readable storage medium. The processing method includes: obtaining data information of a first object, environmental information of a user's environment, and historical behavior data of an object played by the user. The first object may include either video or audio; obtaining a probability of switching the first object based on the data information, environmental information and historical behavior data; and performing a corresponding switching operation based on the probability.

Description

Technical Field

[0001] The present application belongs to the field of terminal technology, and specifically relates to a processing method, device, electronic device and readable storage medium. Background Art

[0002] In the related art, when using an audio or video application, if you encounter a situation where you need to switch playback, you need to manually switch the currently playing audio or video, such as by clicking the previous or next button to switch the audio or video, or by clicking the switch button on the headset to switch the audio or video. However, this technical solution requires the user to manually participate in the audio or video switching process. When the user is busy, switching the audio or video becomes very difficult and inconvenient for the user to control.

[0003] There is currently a solution for automatically switching audio and video, which does not require the user to manually participate in the audio and video switching process. For example, by analyzing the audio and video files, the end of the audio and video can be determined, and each time the audio and video is played to this position, it is automatically switched.

[0004] Since each user has different preferences, not all users think that switching at the end of the audio or video is the most reasonable time to switch. For example, some users think that switching at the end of the audio or video is just right, while for some users, switching at the end of the audio or video will be abrupt and there will be an abrupt experience. Therefore, the existing technical solutions cannot meet the preferences of users. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a processing method, an apparatus, an electronic device, and a readable storage medium, which can meet the personalized needs of users, reduce the abrupt user experience in the process of switching the first object, and improve the accuracy of switching the first object.

[0006] In a first aspect, an embodiment of the present application provides a processing method, including: obtaining data information of a first object, environmental information of a user's environment, and historical behavior data of an object played by the user, where the first object may include either video or audio; obtaining a probability of switching the first object based on the data information, environmental information, and historical behavior data; and performing a corresponding switching operation based on the probability.

[0007] In the second aspect, an embodiment of the present application provides a processing device, including: a first acquisition unit, used to acquire data information of a first object, environmental information of a user's environment, and historical behavior data of an object played by the user, where the first object may include either video or audio; a second acquisition unit, used to acquire the probability of switching the first object based on the data information, environmental information and historical behavior data; and an execution unit, used to execute a corresponding switching operation based on the probability.

[0008] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the processing method of the first aspect.

[0009] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the processing method of the first aspect are implemented.

[0010] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the processing method of the first aspect.

[0011] In an embodiment of the present application, the probability of switching the first object is obtained by obtaining the data of the first object, the user's environmental information, and the user's historical behavior data of playing the object, and the corresponding switching operation is performed according to the probability.

[0012] In this process, determining the probability of switching the first object involves the historical behavior data of the user's playback object, and the historical behavior data of the user's playback object can reflect the user's preferences, that is, the user's personalized needs. Therefore, performing the corresponding switching operation based on the probability can meet the user's personalized needs.

[0013] In addition, in the process of determining the probability of switching the first object, the user's environmental information is also obtained, that is, the user's environmental information is also used as a reference factor for determining the probability of switching the first object. Therefore, performing corresponding switching operations according to the probability can meet the user's personalized needs in different scenarios, reduce the abrupt user experience in the process of switching the first object, and improve the accuracy of switching the first object. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic diagram showing a process flow of a processing method in an embodiment of the present application is shown;

[0015] Figure 2 A schematic diagram of a process of obtaining a probability of switching a first object according to data information, environmental information and historical behavior data in an embodiment of the present application is shown;

[0016] Figure 3 A schematic diagram showing that the moment corresponding to the maximum value of the probability in the embodiment of the present application is the moment when the first object ends playing;

[0017] Figure 4A schematic diagram showing that the time corresponding to the maximum value of the probability in the embodiment of the present application is before the end playback time of the first object;

[0018] Figure 5 A schematic diagram showing the first prompt information in an embodiment of the present application;

[0019] Figure 6 One of the schematic diagrams showing the second prompt information in an embodiment of the present application;

[0020] Figure 7 A second schematic diagram showing the second prompt information in an embodiment of the present application;

[0021] Figure 8 One of the schematic diagrams of the training samples in the embodiment of the present application is shown;

[0022] Fig. 9 A second schematic diagram of a training sample in an embodiment of the present application is shown;

[0023] Fig.10 A third schematic diagram showing a training sample in an embodiment of the present application;

[0024] Fig.11 A schematic block diagram of a processing device in an embodiment of the present application is shown;

[0025] Fig.12 A schematic block diagram of an electronic device in an embodiment of the present application is shown;

[0026] Fig.13 A schematic diagram of the hardware structure of an electronic device in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0028] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0029] The processing method, device, electronic device and readable storage medium provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0030] In some embodiments of the present application, Figure 1 As shown, a processing method is provided, comprising:

[0031] Step 102, obtaining data information of a first object, environmental information of a user's environment, and historical behavior data of a user playing an object. The first object may include any one of video and audio.

[0032] Step 104, obtaining a probability of switching the first object according to the data information, the environment information and the historical behavior data;

[0033] Step 106: Execute corresponding switching operations according to the probability.

[0034] In an embodiment of the present application, the probability of switching the first object is obtained by obtaining the data of the first object, the user's environmental information, and the user's historical behavior data of playing the object, and the corresponding switching operation is performed according to the probability.

[0035] In this process, determining the probability of switching the first object involves the historical behavior data of the user's playback object, and the historical behavior data of the user's playback object can reflect the user's preferences, that is, the user's personalized needs. Therefore, performing the corresponding switching operation based on the probability can meet the user's personalized needs.

[0036] In addition, in the process of determining the probability of switching the first object, the user's environmental information is also obtained, that is, the user's environmental information is also used as a reference factor for determining the probability of switching the first object. Therefore, performing corresponding switching operations according to the probability can meet the user's personalized needs in different scenarios, reduce the abrupt user experience in the process of switching the first object, and improve the accuracy of switching the first object.

[0037] In addition, the above-mentioned solution of the present application can realize automatic switching of the first object without manual operation by the user, thereby improving user convenience.

[0038] In some embodiments, Figure 2 As shown, obtaining the probability of switching the first object according to the data information, the environment information and the historical behavior data specifically includes:

[0039] Step 202, classify the data information, environmental information and historical behavior data into feature types to obtain classification results.

[0040] In this embodiment, a target network model is used to determine the probability of switching the first object, wherein the target network model is a pre-trained neural network model.

[0041] Specifically, when using the target network model, the data information, environmental information and historical behavior data are first divided into feature types so that they can be input into the target network model.

[0042] Among them, the results after feature type classification include numerical features, categorical features and sequence features.

[0043] In one of the embodiments, for data information, the data information includes basic information and statistical information, wherein the basic information includes but is not limited to the name of the singer, the gender of the singer, the release time, the style type, the length of the video, the length of the end of the video, etc.; the statistical information includes but is not limited to the number of times the audio or video is played among all users, the number of complete plays, the number of collections, the number of switches, the average playing time per person, the distribution of video switching times, etc.

[0044] In this embodiment, statistical information can be used as numerical features, that is, the number of audio or video plays among all users, the number of complete plays, the number of favorites, the number of switches, the average playback time per person, the distribution of video switching times, etc. can be used as numerical features.

[0045] In one embodiment, a log1p function mapping can be performed based on numerical features, such as the number of times the audio or video is played among all users, the number of complete plays, the number of favorites, the number of switches, the average playing time per person, the distribution of video switching times, etc., and the features can be rounded down to categorical features.

[0046] In this embodiment, since the categorical features are obtained based on log1p function mapping and rounding down, the deviation of the probability value caused by the different orders of magnitude of different features is prevented. That is, through the above scheme, the accuracy of the obtained probability of switching the first object can be ensured.

[0047] In one of the embodiments, with respect to the environmental information, the scene in which the user is located may be determined based on the environmental information, and the determined scene may be used as a category feature.

[0048] For example, environmental information includes user status information. Specifically, the status information can be obtained by using the global positioning system set on the user terminal to obtain the user's location changes to determine whether the user is in motion or still; and the connection status of the mobile hotspot can be used to determine whether the user is in motion or still. By limiting the environmental information to include the above information, the accuracy of the probability of switching the first object can be ensured.

[0049] For example, environmental information includes environmental noise information. Specifically, the microphone on the user terminal is used to obtain the environmental noise value, so as to determine whether the user is in a quiet scene or a noisy scene based on the environmental noise value. By limiting the environmental information to include the above information, the accuracy of the probability of switching the first object can be ensured.

[0050] In one embodiment, if the environmental information includes quantitative information, such information can be used as a numerical feature, that is, the noise decibel of the environmental noise information can be used as a numerical feature.

[0051] For example, the environment information includes time information, that is, the time in the current time zone. The accuracy of the obtained probability of switching the first object is ensured by limiting the environment information to include the above information.

[0052] In one of the embodiments, the environmental information includes user status information, environmental noise information, and time information, so as to ensure the accuracy of the obtained probability of switching the first object.

[0053] For example, the GPS determines that the user is moving at a uniform speed of 10km / h, and the phone is shaking regularly, so it is inferred that the user is most likely running outdoors. For example, if the user moves at a speed of 70km / h, occasionally stops in the middle, and the background sound is loud, and the time is around 9 am, it is inferred that the user is most likely on the subway or bus during rush hour. For example, if the user's mobile hotspot link is normal, the location information given by the GPS does not move, the phone is not shaking, and the time is 3 pm, it is inferred that the user is most likely listening to music while working or studying.

[0054] In one of the embodiments, for historical behavior data, the characteristics of the historical behavior data are determined based on the historical behavior data, which involves sequence information about fully playing videos and switching videos, and is converted into a song Embedding summed and averaged representation obtained through Node2Vec pre-training.

[0055] For example, if a user has finished playing three songs, A, B, and C, then the user's completion Embedding can be expressed as (Embedding(A)+Embedding(B)+Embedding(C)) / 3. If a user has switched songs B, C, D, and E, then the user's song switching Embedding can be expressed as (Embedding(B)+Embedding(C)+Embedding(D)+Embedding(E)) / 4. When a user is listening to a song, the song's Embedding can be used to perform inner product operations with the user's completion Embedding and song switching Embedding to obtain a similarity value. The meaning of this similarity value is a dimensional way of considering the user's possibility of finishing the current song and the possibility of switching songs. The similarity value is also used as a numerical feature. At the same time, the completion Embedding and song switching Embedding can also be used as sequence features.

[0056] In some embodiments, artificial feature cross-fusion may be introduced. Most of these cross-features are binary features of 0 or 1. Artificial feature cross-fusion is introduced to enhance the correlation between different features.

[0057] For example, whether the user is in rush hour and the number of song switching in history is greater than 100. There are three-order cross features, such as whether the user is in a quiet environment, the number of songs in history collection is less than 10, and the user is male.

[0058] Step 204: input the division result into a preset target network model.

[0059] Step 206, obtaining the decisive features and generalization features in the segmentation results through the target network model.

[0060] Step 208, input the generalization features into the neural network layer through the target network model to perform feature crossover to obtain a crossover result.

[0061] Step 210, determining a mapping value of an evaluation result after the cross result is connected with the decisive feature string in a preset range through a target network model, and using the mapping value as a probability of switching the first object.

[0062] In the above embodiment, the decisive features and generalized features in the division results are determined so that the decisive features can be selected separately to avoid the decisive effects of the decisive features being generalized when they are input into the neural network layer for feature crossing, thereby affecting the accuracy of the target network model; and the determined generalized features are input into the neural network layer, wherein the neural network layer can be a neural network layer of a PNN, so that feature crossing is performed using an inner product method, so as to improve the ability to learn crossed features, thereby improving the accuracy of the output results given by the target network model.

[0063] In one of the embodiments, historical behavior data is obtained after obtaining the user's basic information, wherein the user's basic information includes basic information such as gender, age, and city of identity authentication, so as to obtain the client's historical tracking points based on the basic information such as gender, age, and city of identity authentication, and then obtain all the songs played by the user, and count the number of times each song is played, the number of complete plays, the number of song switches, whether it is collected, and the time when the user switches the video for all audio and video switching behaviors.

[0064] In one of the embodiments, the preset interval is [0, 1].

[0065] In one embodiment, the decisive feature can be directly connected with the result of the generalization feature output at the neural network layer, that is, the cross result, to finally obtain an evaluation result, wherein the evaluation result can be obtained based on a logit model, and the logit model can output a score of 0 to 1 after function transformation.

[0066] In one embodiment, a Sigmoid function is used for transformation.

[0067] In one of the embodiments, the decisive features and generalized features in the segmentation result are obtained through the target network model, specifically including: determining the correlation coefficient between any feature in the segmentation result and the switching of the first object through the target network model; when the correlation coefficient is greater than or equal to a preset value, taking any feature as a decisive feature; when the correlation coefficient is less than a preset value, taking any feature as a generalized feature.

[0068] In the above embodiment, by determining the decisive features and generalized features in the division results, the decisive features can be selected separately to avoid the decisive effects of the decisive features being generalized when they are input into the neural network layer for feature crossing, thereby affecting the accuracy of the target network model.

[0069] Since the decisive features are highly correlated with the labels, there is no need to learn the parameters of the multi-layer neural network. Instead, the determined generalized features are input into the neural network layer, where the neural network layer can be a neural network layer of a PNN, so that the inner product method can be used to cross features, so as to improve the ability to learn cross features, thereby improving the accuracy of the output results given by the target network model.

[0070] In one embodiment, a Pearson correlation coefficient is calculated between any feature in the segmentation result and the switched first object to obtain a correlation coefficient.

[0071] In one embodiment, the preset value may be 0.8, and its specific value may be selected according to the actual usage scenario.

[0072] In one embodiment, if Figure 3 and Figure 4 As shown, the corresponding switching operation is performed according to the probability, specifically including: determining the maximum value of the probability during the playback of the first object; if the moment corresponding to the maximum value of the probability is determined to be the end playback moment of the first object, canceling the switching of the first object; if the moment corresponding to the maximum value of the probability is determined to be before the end playback moment of the first object, switching the first object at the moment corresponding to the maximum value of the probability.

[0073] In this embodiment, a specific scheme for executing corresponding switching operations according to probability is defined. Specifically, when the first object is in a playing state, the maximum value of the probability of switching the first object is obtained. If the moment corresponding to the maximum value of the probability is determined to be the end playback moment of the first object, it is considered that for the current user, the possibility of switching at the end playback moment of the first object is the greatest. At the end playback moment of the first object, the first object has been completed, and therefore, the switching of the first object is canceled. If the moment corresponding to the maximum value of the probability is before the end playback moment of the first object, that is, during the playing of the first object, it is most likely that the first object will be switched. In this case, at the moment corresponding to the maximum value of the probability, the first object is switched, so as to meet the user's switching habits to the greatest extent and make the switching of the first object the most reasonable.

[0074] In some embodiments, such as Figure 5 As shown, before switching the first object at the moment corresponding to the maximum probability, it also includes: outputting a first prompt information, wherein the first prompt information is used to indicate switching the first object; receiving a first input to the first prompt information; and in response to the first input, switching the first object or canceling switching the first object at the moment corresponding to the maximum probability.

[0075] In this embodiment, since there is still inaccuracy in executing the corresponding switching operation according to probability, a first prompt message is output to the user within a preset time period before the moment corresponding to the maximum probability, that is, within the preset time period for automatically executing the switching of the first object, so that the user can choose whether to switch the first object. In this process, the decision-making power of whether to switch the first object is transferred to the user, thereby improving the accuracy of the switching.

[0076] In addition, the first input of the first prompt information can also be used as an evaluation criterion for determining this switch. If the operation performed is to switch the first object, and the first input selects not to switch in the first prompt information, then the current switching operation is deemed unreasonable. This switch and the switching result can be used as positive and negative samples to update the target network model, thereby improving the learning ability of the target network model, thereby improving the accuracy of the subsequent output results.

[0077] In some embodiments, Figure 6 and Figure 7 As shown, after canceling the switching of the first object, it also includes: outputting a second prompt information, wherein the second prompt information is used to indicate feedback on canceling the switching of the first object; receiving a second input to the second prompt information; and updating the target network model according to the second input.

[0078] In this embodiment, a second prompt message is output so that the user can provide feedback on the switching failure based on the output prompt message. After receiving the second input, the target network model can be updated based on the second input to ensure that the output results given by the target network model later can meet the user's usage requirements.

[0079] In some embodiments, the first object continues to be played without switching the first object.

[0080] In this embodiment, there is no need to output a prompt message and the first object continues to be played directly. At this time, in order to reduce the impact of the above scheme on the playback process of the first object, for example, without switching the first object, the first object can be played smoothly, reducing freezes and the like.

[0081] In one of the embodiments, a training process of a target network model is defined.

[0082] First, construct training samples. Specifically, for the user's historical behavior data, such as Figure 8 As shown in the figure, if a video is not switched by the user in a certain playback history and is eventually played completely, the probability score samples of switching at each moment (second interval) of the video are linearly related, such as the probability of the last second of the video is 1, the probability of the first second of the song is 0, and the linear function interpolation is used in the middle part.

[0083] like Fig. 9 As shown, if a video is switched by the user during a certain playback in the history, the probability score samples of the song switching at each moment (second interval) of the video are as follows: the probability of the switching moment is 1, the first second of the video is 0, and the last second of the video is also 0, and the middle part is interpolated by a piecewise linear function.

[0084] like Fig.10 As shown in the figure, if a video has been played or switched by the user multiple times in history, the probability score sample of switching at each moment (interval of seconds) of the video is the average score of multiple behaviors. The example is as follows: If user B has played video A once and switched songs once, then the training sample of user B for video A is the sum of the vertical coordinates of each point on the green line and the blue line divided by 2. If it is switched or played for 3 times or more, the method is similar to the example.

[0085] Secondly, the training samples are input into the network model to be trained to obtain the predicted probability. The predicted probability is compared with the probability corresponding to the training sample to obtain the difference, which is the loss of the network model to be trained. The calculation logic of the back-propagation gradient descent is used to return from the scoring prediction output layer to the feature input layer layer by layer, and the weights of each layer of the neural network are updated to finally obtain the target network model.

[0086] In some embodiments, Fig.11 As shown, a processing device 1100 is proposed, including: a first acquisition unit 1102, used to obtain data information of a first object, environmental information of a user's environment, and historical behavior data of a user's playback object, and the first object may include either video or audio; a second acquisition unit 1104, used to obtain a probability of switching the first object based on the data information, environmental information and historical behavior data; and an execution unit 1106, used to execute a corresponding switching operation based on the probability.

[0087] In an embodiment of the present application, the probability of switching the first object is obtained by obtaining the data of the first object, the user's environmental information, and the user's historical behavior data of playing the object, and the corresponding switching operation is performed according to the probability.

[0088] In this process, determining the probability of switching the first object involves the historical behavior data of the user's playback object, and the historical behavior data of the user's playback object can reflect the user's preferences, that is, the user's personalized needs. Therefore, performing the corresponding switching operation based on the probability can meet the user's personalized needs.

[0089] In addition, in the process of determining the probability of switching the first object, the user's environmental information is also obtained, that is, the user's environmental information is also used as a reference factor for determining the probability of switching the first object. Therefore, performing corresponding switching operations according to the probability can meet the user's personalized needs in different scenarios, reduce the abrupt user experience in the process of switching the first object, and improve the accuracy of switching the first object.

[0090] In addition, the above-mentioned solution of the present application can realize automatic switching of the first object without manual operation by the user, thereby improving user convenience.

[0091] In some embodiments, the second acquisition unit 1104 is specifically used to: divide the data information, environmental information and historical behavior data into feature types to obtain the division results; input the division results into a preset target network model; obtain the decisive features and generalization features in the division results through the target network model; input the generalization features into the neural network layer through the target network model for feature crossover to obtain the crossover results; determine the mapping value of the evaluation result after the crossover result and the decisive feature string are connected in the preset interval through the target network model, and use the mapping value as the probability of switching the first object. In the above embodiment, by determining the decisive features and generalization features in the division results, the decisive features can be selected separately to avoid the decisive effects of the decisive features being generalized when the decisive features are input into the neural network layer for feature crossover, thereby affecting the accuracy of the target network model; and for the determined generalization features, they are input into the neural network layer, wherein the neural network layer can be the neural network layer of the PNN, so as to use the inner product method to perform feature crossover, so as to improve the ability to learn the crossover features, thereby improving the accuracy of the output results given by the target network model.

[0092] In some of the embodiments, the second acquisition unit 1104 is also specifically used to: determine the correlation coefficient between any feature in the division result and the switching first object through the target network model; when the correlation coefficient is greater than or equal to a preset value, take any feature as a decisive feature; when the correlation coefficient is less than a preset value, take any feature as a generalized feature.

[0093] In the above embodiment, by determining the decisive features and generalized features in the division results, the decisive features can be selected separately to avoid the decisive effects of the decisive features being generalized when they are input into the neural network layer for feature crossing, thereby affecting the accuracy of the target network model.

[0094] In some of the embodiments, the execution unit 1106 is specifically used to: determine the maximum value of the probability during the process of playing the first object; if the moment corresponding to the maximum value of the probability is determined to be the end playback moment of the first object, cancel the switching of the first object; if the moment corresponding to the maximum value of the probability is determined to be before the end playback moment of the first object, switch the first object at the moment corresponding to the maximum value of the probability.

[0095] In this embodiment, a specific scheme for executing corresponding switching operations according to probability is defined. Specifically, when the first object is in a playing state, the maximum value of the probability of switching the first object is obtained. If the moment corresponding to the maximum value of the probability is determined to be the end playback moment of the first object, it is considered that for the current user, the possibility of switching at the end playback moment of the first object is the greatest. At the end playback moment of the first object, the first object has been completed, and therefore, the switching of the first object is canceled. If the moment corresponding to the maximum value of the probability is before the end playback moment of the first object, that is, during the playing of the first object, it is most likely that the first object will be switched. In this case, at the moment corresponding to the maximum value of the probability, the first object is switched, so as to meet the user's switching habits to the greatest extent and make the switching of the first object the most reasonable.

[0096] In some of the embodiments, the execution unit 1106 is further used to: output a first prompt information, wherein the first prompt information is used to indicate switching of the first object; receive a first input to the first prompt information; and in response to the first input, switch the first object or cancel switching of the first object at a moment corresponding to a maximum probability.

[0097] In this embodiment, since there is still inaccuracy in executing the corresponding switching operation according to probability, a first prompt message is output to the user within a preset time period before the moment corresponding to the maximum probability, that is, within the preset time period for automatically executing the switching of the first object, so that the user can choose whether to switch the first object. In this process, the decision-making power of whether to switch the first object is transferred to the user, thereby improving the accuracy of the switching.

[0098] The processing device 1100 in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0099] The processing device 1100 in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0100] The processing device 1100 provided in the embodiment of the present application can implement each process implemented in the above method embodiment, and will not be described again here to avoid repetition.

[0101] Alternatively, if Fig.12 As shown, the embodiment of the present application further provides an electronic device 1200, Fig.12 A structural block diagram of an electronic device according to an embodiment of the present application is shown. Fig.12 As shown, it includes a processor 1202, a memory 1204, and a program or instruction stored in the memory 1204 and executable on the processor 1202. When the program or instruction is executed by the processor 1202, each process of the above-mentioned method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0102] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0103] Fig.13 A schematic diagram of the hardware structure of an electronic device 1300 for implementing an embodiment of the present application.

[0104] The electronic device 1300 includes but is not limited to: a radio frequency unit 1301, a network module 1302, an audio output unit 1303, an input unit 1304, a sensor 1305, a display unit 1306, a user input unit 1307, an interface unit 1308, a memory 1309, and a processor 1310 and other components.

[0105] Those skilled in the art will appreciate that the electronic device 1300 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 1310 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Fig.13 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0106] Among them, the processor 1310 is used to obtain data information of the first object, environmental information of the user's environment, and historical behavior data of the user's playback object. The first object may include either video or audio; obtain the probability of switching the first object based on the data information, environmental information and historical behavior data; and perform corresponding switching operations based on the probability.

[0107] In one of the embodiments, the probability of switching the first object is obtained based on the data information, environmental information and historical behavior data, and the processor 1310 is specifically used to: perform feature type classification on the data information, environmental information and historical behavior data to obtain classification results; input the classification results into a preset target network model; obtain decisive features and generalization features in the classification results through the target network model; input the generalization features into the neural network layer through the target network model to perform feature crossover to obtain crossover results; determine a mapping value of an evaluation result after connecting the crossover result with the decisive feature string in a preset interval through the target network model, and use the mapping value as the probability of switching the first object.

[0108] In one of the embodiments, the decisive features and generalized features in the segmentation result are obtained through the target network model, and the processor 1310 is specifically used to: determine the correlation coefficient between any feature in the segmentation result and the switching of the first object through the target network model; when the correlation coefficient is greater than or equal to a preset value, use any feature as a decisive feature; when the correlation coefficient is less than a preset value, use any feature as a generalized feature.

[0109] In one of the embodiments, the corresponding switching operation is performed according to the probability, and the processor 1310 is specifically used to: determine the maximum value of the probability during the playback of the first object; if the moment corresponding to the maximum value of the probability is determined to be the end playback moment of the first object, cancel the switching of the first object; if the moment corresponding to the maximum value of the probability is determined to be before the end playback moment of the first object, switch the first object at the moment corresponding to the maximum value of the probability.

[0110] In one embodiment, before switching the first object at the moment corresponding to the maximum probability, the processor 1310 is also used to: output a first prompt message, wherein the first prompt message is used to indicate switching the first object; receive a first input to the first prompt message; and in response to the first input, switch the first object or cancel switching the first object at the moment corresponding to the maximum probability.

[0111] It should be understood that in an embodiment of the present application, the input unit 1304 may include a graphics processor (GPU) 13041 and a microphone 13042, and the graphics processor 13041 processes image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode.

[0112] The display unit 1306 may include a display panel 13061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1307 includes a touch panel 13071 and other input devices 13072. The touch panel 13071 is also called a touch screen. The touch panel 13071 may include two parts: a touch detection device and a touch controller. Other input devices 13072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not repeated here. The memory 1309 may be used to store software programs and various data, including but not limited to applications and operating systems. The processor 1310 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and applications, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1310.

[0113] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0114] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0115] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0116] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0117] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "including one" do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0119] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A processing method, characterized in that: include: Acquire data information of a first object, environmental information of a user's environment, and historical behavior data of the user playing an object, wherein the first object may include any one of video and audio; Acquire a probability of switching the first object according to the data information, the environment information and the historical behavior data; Perform a corresponding switching operation according to the probability; Acquiring the probability of switching the first object according to the data information, the environment information and the historical behavior data specifically includes: Performing feature type classification on the data information, the environmental information, and the historical behavior data to obtain a classification result; Inputting the division results into a preset target network model; Obtaining decisive features and generalization features in the segmentation results through the target network model; Inputting the generalization features into the neural network layer through the target network model to perform feature crossover and obtain crossover results; The target network model is used to determine a mapping value of an evaluation result obtained by connecting the cross result with the decisive feature string in a preset interval, and the mapping value is used as a probability of switching the first object.

2. The processing method according to claim 1, characterized in that: Obtaining the decisive features and generalization features in the segmentation result through the target network model specifically includes: Determine, by using the target network model, a correlation coefficient between any feature in the segmentation result and switching the first object; When the correlation coefficient is greater than or equal to a preset value, any one of the features is used as the decisive feature; When the correlation coefficient is less than a preset value, any one of the features is used as the generalization feature.

3. The processing method according to claim 1 or 2, characterized in that: The performing a corresponding switching operation according to the probability specifically includes: Determining a maximum value of the probability during the playing of the first object; If it is determined that the time corresponding to the maximum value of the probability is the end time of playing the first object, cancel switching the first object; If it is determined that the time corresponding to the maximum value of the probability is before the end time of playing the first object, the first object is switched at the time corresponding to the maximum value of the probability.

4. The processing method according to claim 3, characterized in that: At the moment corresponding to the maximum probability, before switching the first object, the method further includes: Outputting first prompt information, wherein the first prompt information is used to indicate switching of the first object; receiving a first input of the first prompt information; In response to the first input, at a time corresponding to the maximum probability, the first object is switched or the switching of the first object is canceled.

5. A processing device, characterized in that: include: A first acquisition unit, configured to acquire data information of a first object, environmental information of a user's environment, and historical behavior data of the user playing the object, wherein the first object may include any one of video and audio; A second acquisition unit, configured to acquire a probability of switching the first object according to the data information, the environment information and the historical behavior data; An execution unit, configured to execute a corresponding switching operation according to the probability; The second acquisition unit is specifically used for: Performing feature type classification on the data information, the environmental information, and the historical behavior data to obtain a classification result; Inputting the division results into a preset target network model; Obtaining decisive features and generalization features in the segmentation results through the target network model; Inputting the generalization features into the neural network layer through the target network model to perform feature crossover and obtain crossover results; The target network model is used to determine a mapping value of an evaluation result obtained by connecting the cross result with the decisive feature string in a preset interval, and the mapping value is used as a probability of switching the first object.

6. The processing device according to claim 5, characterized in that The second acquisition unit is further specifically configured to: Determine, by using the target network model, a correlation coefficient between any feature in the segmentation result and switching the first object; When the correlation coefficient is greater than or equal to a preset value, any one of the features is used as the decisive feature; When the correlation coefficient is less than a preset value, any one of the features is used as the generalization feature.

7. The processing device according to claim 5 or 6, characterized in that: The execution unit is specifically used for: Determining a maximum value of the probability during the playing of the first object; If it is determined that the time corresponding to the maximum value of the probability is the end time of playing the first object, cancel switching the first object; If it is determined that the time corresponding to the maximum value of the probability is before the end time of playing the first object, the first object is switched at the time corresponding to the maximum value of the probability.

8. The processing device according to claim 7, characterized in that The execution unit is also used for: Outputting first prompt information, wherein the first prompt information is used to indicate switching of the first object; receiving a first input of the first prompt information; In response to the first input, at a time corresponding to the maximum probability, the first object is switched or the switching of the first object is canceled.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the processing method according to any one of claims 1 to 4.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the processing method according to any one of claims 1 to 4 are implemented.

Images