CN111797072A

CN111797072A - Data processing method, data processing device, storage medium and electronic equipment

Info

Publication number: CN111797072A
Application number: CN201910282455.XA
Authority: CN
Inventors: 陈仲铭; 何明
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date: 2019-04-09
Filing date: 2019-04-09
Publication date: 2020-10-20

Abstract

The application discloses a data processing method, a data processing device, a storage medium and electronic equipment. The method can be applied to an electronic device, which includes: acquiring a data sequence, wherein the data sequence is formed by data acquired by the electronic equipment within a time interval according to a time sequence format; acquiring a data segmentation strategy, and segmenting the data sequence into a plurality of sub-data sequences according to the acquired data segmentation strategy, wherein each sub-data sequence corresponds to a time slice in the time interval; extracting the characteristics of each subdata sequence to obtain the data characteristics corresponding to each subdata sequence; acquiring operation information of a user on the electronic equipment; and learning a required data segmentation strategy according to the operation information and the data characteristics corresponding to the sub data sequences so as to improve the data segmentation strategy. The embodiment can improve the accuracy of the electronic equipment for segmenting the data.

Description

Data processing method, data processing device, storage medium and electronic equipment

Technical Field

The present application belongs to the technical field of electronic devices, and in particular, to a data processing method, apparatus, storage medium, and electronic device.

Background

The electronic device may identify a user's activity over a period of time. For example, the electronic device may recognize that the user engaged in activity A between 08:00 and 08:30, activity B between 08:30 and 09:00, and so on. In identifying user activity, the electronic device may obtain user and device data and segment the user and device data, and identify user activity based on the segmented data. However, in the related art, the accuracy of segmenting data by the electronic device is poor.

Disclosure of Invention

The embodiment of the application provides a data processing method and device, a storage medium and electronic equipment, which can improve the accuracy of the electronic equipment in segmenting data.

The embodiment of the application provides a data processing method, which is applied to electronic equipment and comprises the following steps:

acquiring a data sequence, wherein the data sequence is formed by data acquired by the electronic equipment within a time interval according to a time sequence format;

acquiring a data segmentation strategy, and segmenting the data sequence into a plurality of sub-data sequences according to the acquired data segmentation strategy, wherein each sub-data sequence corresponds to a time slice in the time interval;

extracting the characteristics of each subdata sequence to obtain the data characteristics corresponding to each subdata sequence;

acquiring operation information of a user on the electronic equipment;

and learning a required data segmentation strategy according to the operation information and the data characteristics corresponding to the sub data sequences so as to improve the data segmentation strategy.

An embodiment of the present application provides a data processing apparatus, which is applied to an electronic device, and includes:

the first acquisition module is used for acquiring a data sequence, wherein the data sequence is formed by data acquired by the electronic equipment within a time interval according to a time sequence format;

the second obtaining module is used for obtaining a data segmentation strategy and segmenting the data sequence into a plurality of sub-data sequences according to the obtained data segmentation strategy, wherein each sub-data sequence corresponds to a time slice in the time interval;

the extraction module is used for extracting the characteristics of each subdata sequence to obtain the data characteristics corresponding to each subdata sequence;

the third acquisition module is used for acquiring the operation information of the user on the electronic equipment;

and the learning module is used for learning the required data segmentation strategy according to the operation information and the data characteristics corresponding to the sub data sequences so as to improve the data segmentation strategy.

The embodiment of the application provides a storage medium, wherein a computer program is stored on the storage medium, and when the computer program is executed on a computer, the computer is enabled to execute the data processing method provided by the embodiment of the application.

The embodiment of the present application further provides an electronic device, which includes a memory and a processor, where the processor is configured to execute the data processing method provided in the embodiment of the present application by calling the computer program stored in the memory.

In this embodiment, the electronic device may learn a required data segmentation policy according to the operation information of the device by the user and the data characteristics corresponding to each sub-data sequence, so as to improve the data segmentation policy, thereby more accurately dividing the data segmentation boundary. Therefore, the data segmentation accuracy of the electronic equipment can be improved.

Drawings

The technical solutions and advantages of the present application will become apparent from the following detailed description of specific embodiments of the present application when taken in conjunction with the accompanying drawings.

Fig. 1 is a schematic diagram of a panoramic sensing architecture of an electronic device provided in an embodiment of the present application.

Fig. 2 is a schematic flowchart of a data processing method according to an embodiment of the present application.

Fig. 3 is a schematic diagram of a data segmentation processing method in the related art according to an embodiment of the present application.

Fig. 4 is another schematic flow chart of a data processing method according to an embodiment of the present application.

Fig. 5 is a schematic diagram of a data segmentation processing method according to an embodiment of the present application.

Fig. 6 is a scene schematic diagram of a data processing method according to an embodiment of the present application.

Fig. 7 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application.

Fig. 8 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.

Fig. 9 is another schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Referring to the drawings, wherein like reference numbers refer to like elements, the principles of the present application are illustrated as being implemented in a suitable computing environment. The following description is based on illustrated embodiments of the application and should not be taken as limiting the application with respect to other embodiments that are not detailed herein.

Referring to fig. 1, fig. 1 is a schematic view of an application scenario of a data processing method according to an embodiment of the present application. The data processing method can be applied to electronic equipment. A panoramic perception framework is arranged in the electronic equipment. The panoramic sensing architecture is an integration of hardware and software for implementing the data processing method in an electronic device.

The panoramic perception architecture comprises an information perception layer, a data processing layer, a feature extraction layer, a scene modeling layer and an intelligent service layer.

The information perception layer is used for acquiring information of the electronic equipment or information in an external environment. The information-perceiving layer may include a plurality of sensors. For example, the information sensing layer includes a plurality of sensors such as a distance sensor, a magnetic field sensor, a light sensor, an acceleration sensor, a fingerprint sensor, a hall sensor, a position sensor, a gyroscope, an inertial sensor, an attitude sensor, a barometer, and a heart rate sensor.

Among other things, a distance sensor may be used to detect a distance between the electronic device and an external object. The magnetic field sensor may be used to detect magnetic field information of the environment in which the electronic device is located. The light sensor can be used for detecting light information of the environment where the electronic equipment is located. The acceleration sensor may be used to detect acceleration data of the electronic device. The fingerprint sensor may be used to collect fingerprint information of a user. The Hall sensor is a magnetic field sensor manufactured according to the Hall effect, and can be used for realizing automatic control of electronic equipment. The location sensor may be used to detect the geographic location where the electronic device is currently located. Gyroscopes may be used to detect angular velocity of an electronic device in various directions. Inertial sensors may be used to detect motion data of an electronic device. The gesture sensor may be used to sense gesture information of the electronic device. A barometer may be used to detect the barometric pressure of the environment in which the electronic device is located. The heart rate sensor may be used to detect heart rate information of the user.

And the data processing layer is used for processing the data acquired by the information perception layer. For example, the data processing layer may perform data cleaning, data integration, data transformation, data reduction, and the like on the data acquired by the information sensing layer.

The data cleaning refers to cleaning a large amount of data acquired by the information sensing layer to remove invalid data and repeated data. The data integration refers to integrating a plurality of single-dimensional data acquired by the information perception layer into a higher or more abstract dimension so as to comprehensively process the data of the plurality of single dimensions. The data transformation refers to performing data type conversion or format conversion on the data acquired by the information sensing layer so that the transformed data can meet the processing requirement. The data reduction means that the data volume is reduced to the maximum extent on the premise of keeping the original appearance of the data as much as possible.

The characteristic extraction layer is used for extracting characteristics of the data processed by the data processing layer so as to extract the characteristics included in the data. The extracted features may reflect the state of the electronic device itself or the state of the user or the environmental state of the environment in which the electronic device is located, etc.

The feature extraction layer may extract features or process the extracted features by a method such as a filtering method, a packing method, or an integration method.

The filtering method is to filter the extracted features to remove redundant feature data. Packaging methods are used to screen the extracted features. The integration method is to integrate a plurality of feature extraction methods together to construct a more efficient and more accurate feature extraction method for extracting features.

The scene modeling layer is used for building a model according to the features extracted by the feature extraction layer, and the obtained model can be used for representing the state of the electronic equipment, the state of a user, the environment state and the like. For example, the scenario modeling layer may construct a key value model, a pattern identification model, a graph model, an entity relation model, an object-oriented model, and the like according to the features extracted by the feature extraction layer.

The intelligent service layer is used for providing intelligent services for the user according to the model constructed by the scene modeling layer. For example, the intelligent service layer can provide basic application services for users, perform system intelligent optimization for electronic equipment, and provide personalized intelligent services for users.

In addition, a plurality of algorithms can be included in the panoramic perception architecture, each algorithm can be used for analyzing and processing data, and the plurality of algorithms can form an algorithm library. For example, the algorithm library may include algorithms such as a markov algorithm, a hidden dirichlet distribution algorithm, a bayesian classification algorithm, a support vector machine, a K-means clustering algorithm, a K-nearest neighbor algorithm, a conditional random field, a residual error network, a long-short term memory network, a convolutional neural network, and a cyclic neural network.

It is understood that the execution subject of the embodiment of the present application may be an electronic device such as a smart phone or a tablet computer.

Referring to fig. 2, fig. 2 is a schematic flow chart of a data processing method according to an embodiment of the present application, where the flow chart may include:

in 101, a data sequence is obtained, wherein the data sequence is formed by data collected by an electronic device in a time interval according to a time sequence format.

The electronic device may identify a user's activity over a period of time. For example, the electronic device may recognize that the user engaged in activity A between 08:00 and 08:30, activity B between 08:30 and 09:00, and so on. In identifying user activity, the electronic device may obtain user and device data and segment the user and device data, and identify user activity based on the segmented data. However, in the related art, the accuracy of segmenting data by the electronic device is poor. For example, in the related art, the electronic device generally divides the data sequence according to a fixed time interval, that is, each sub-data sequence obtained by dividing the data sequence is data collected within a fixed time period.

Referring to fig. 3, for example, the electronic device collects data in time intervals 08:00 to 08:20, and the collected data form a data sequence C according to a time-series format. In the related art, the electronic device divides the data sequence C at regular time intervals of 5 minutes, and sub-data sequences C1, C2, C3 and C4 are obtained after division. The data acquisition method comprises the steps of acquiring data of 08: 00-08: 05 points by C1, acquiring data of 08: 05-08: 10 points by C2, acquiring data of 08: 10-08: 15 points by C3 and acquiring data of 08: 15-08: 20 points by C4. However, since the activity time corresponding to different activities is different, the data segmentation boundary cannot be accurately determined by segmenting the data sequence at fixed time intervals, i.e. the accuracy of data segmentation is poor.

In 101 of this embodiment, the electronic device may acquire a data sequence, where the data sequence is formed by data acquired by the electronic device in a time interval according to a time-series format.

For example, the electronic device may collect data within 24 hours of the day, and then store the collected data in a time series format and form a data series. The electronic device may then retrieve the data sequence. For example, the data sequence acquired by the electronic device is D.

At 102, a data division strategy is obtained, and the data sequence is divided into a plurality of sub data sequences according to the obtained data division strategy, wherein each sub data sequence corresponds to a time slice in the time interval.

For example, after obtaining the data sequence, the electronic device may obtain a data segmentation policy, and segment the data sequence into a plurality of sub-data sequences according to the obtained data segmentation policy, where each sub-data sequence corresponds to a time segment in the time interval.

For example, after acquiring the data sequence D, the electronic device may acquire a current data splitting policy p, and split the data sequence D according to the data splitting policy p, for example, to obtain 5 sub-data sequences, which are D1, D2, D3, D4, and D5. The time interval corresponding to the data sequence D is t1 to t6, the sub data sequence D1 corresponds to t1 to t2 in the time interval, the sub data sequence D2 corresponds to t2 to t3 in the time interval, the sub data sequence D3 corresponds to t3 to t4 in the time interval, the sub data sequence D4 corresponds to t4 to t5 in the time interval, and the sub data sequence D5 corresponds to t5 to t6 in the time interval.

In 103, feature extraction is performed on each sub data sequence to obtain data features corresponding to each sub data sequence.

For example, after the sub-data sequences D1, D2, D3, D4, and D5 are obtained by segmentation, the electronic device may perform feature extraction on each sub-data sequence, so as to obtain data features corresponding to each sub-data sequence.

For example, the data characteristic corresponding to the sub-data sequence D1 is D1, the data characteristic corresponding to the sub-data sequence D2 is D2, the data characteristic corresponding to the sub-data sequence D3 is D3, the data characteristic corresponding to the sub-data sequence D4 is D4, and the data characteristic corresponding to the sub-data sequence D5 is D5.

At 104, operation information of the electronic device by the user is acquired.

For example, the electronic device may also obtain operation information of the electronic device by the user. The operation information may be, for example, history data of the operation of the electronic device by the user. The historical data may represent or reflect historical activities performed by the user.

In 105, a required data partitioning strategy is learned to improve the data partitioning strategy according to the operation information and the data characteristics corresponding to each sub data sequence.

For example, after obtaining the operation information of the user on the electronic device, the electronic device may learn a required data segmentation policy according to the operation information and the data features corresponding to the sub-data sequences, so as to improve the data segmentation policy. For example, the electronic device may learn a required data segmentation policy by using a reinforcement learning method according to the operation information of the user on the electronic device and the data features corresponding to the sub data sequences, and improve the data segmentation policy according to the reinforcement learning result.

It can be understood that, in this embodiment, the electronic device may learn a required data partitioning policy according to the operation information of the device by the user and the data characteristics corresponding to each sub data sequence, so as to improve the data partitioning policy, and thus partition the data partitioning boundary more accurately. Therefore, the data segmentation accuracy of the electronic equipment can be improved.

It should be noted that the data processing method provided by this embodiment may be applied to the feature extraction layer in the panoramic sensing architecture shown in fig. 1. The electronic device can collect data and input the collected data into the data processing layer for processing, and the data processed by the data processing layer can be input into the feature extraction layer for feature extraction. The data processing method provided by the embodiment can learn the required data segmentation strategy according to the operation information of the device by the user and the data characteristics corresponding to each sub data sequence so as to improve the data segmentation strategy, thereby dividing the data segmentation boundary more accurately. The scene modeling layer can perform modeling according to the data features extracted by the feature extraction layer. The data obtained through modeling can be input into an intelligent service layer, and the intelligent service layer can provide intelligent services for users of the electronic equipment according to the data, such as pushing information suitable for the current situation for the users.

Referring to fig. 4, fig. 4 is another schematic flow chart of a data processing method according to an embodiment of the present application, where the flow chart may include:

in 201, an electronic device acquires data acquired over a time interval.

At 202, the electronic device performs synchronization processing based on the timestamp on the collected data to obtain synchronized data.

In 203, the electronic device converts the synchronized data into a data sequence in a time-series format.

For example, 201, 202, and 203 may include:

the electronic device may acquire data collected within 24 hours of a day. In one embodiment, the collected data may be historical data. After the acquired data is acquired, the electronic device may perform synchronization processing on the acquired data based on the timestamp, so as to obtain the data after the synchronization processing.

It should be noted that, because the electronic device has different acquisition frequencies and acquisition timings for different types of data, the acquisition time of each data may be different. Therefore, in the embodiment of the present application, synchronization processing based on a timestamp may be performed on the acquired data first. For example, the acquisition time of the data1 is t10, the acquisition time of the data2 is t11, and the acquisition time of the data3 is t 12. If the time intervals of t10, t11 and t12 are short (for example, the time intervals are less than a preset time duration), the data1, data2 and data3 can be considered as synchronously acquired data, and the electronic device can perform synchronous processing on the data1, data2 and data3 based on time stamps. For example, the electronic device may determine the data1, data2, and data3 as t10, and so on.

After the acquired data is synchronized, the electronic device may convert the synchronized data into a data sequence according to a time sequence format.

At 204, the electronic device acquires a data sequence.

For example, the electronic device may obtain 203 the data sequence obtained.

In 205, the electronic device obtains a data division policy, divides the data sequence into a plurality of sub-data sequences according to the obtained data division policy, and obtains division start time information and division end time information corresponding to each sub-data sequence, where each sub-data sequence corresponds to a time slice in a time interval.

For example, after obtaining the data sequence, the electronic device may obtain a data segmentation policy, and segment the data sequence into a plurality of sub-data sequences according to the obtained data segmentation policy, where each sub-data sequence corresponds to a time segment in the time interval. Also, the electronic device may acquire division start time information and division end time information corresponding to each sub data sequence.

It is understood that, taking the sub-data sequence D1 and the time information t1, t2 as examples, the time information t1 represents the partition start time information corresponding to the sub-data sequence D1, and the time information t2 represents the partition end time information corresponding to the sub-data sequence D1. For another example, taking the sub-data sequence D2 and the time information t2 and t3 as examples, the time information t2 represents the partition start time information corresponding to the sub-data sequence D2, and the time information t3 represents the partition end time information corresponding to the sub-data sequence D2.

In one embodiment, the partition start time information and the partition end time information corresponding to the sub-data sequence may be stored in a vector form. For example, the partition start time information t1 and the partition end time information t2 corresponding to the sub data sequence D1 may be stored as [ t1, t2 ]. The division start time information and the division end time information stored in the form of a vector may form a correspondence with the corresponding sub-data sequence. It is understood that t1 and t2 are the corresponding front and back partition positions of the sub data sequence D1.

At 206, the electronic device performs feature extraction on each sub-data sequence to obtain data features corresponding to each sub-data sequence.

In 207, the electronic device obtains operation information of the electronic device by a user, wherein the operation information further comprises operation starting time information and operation ending time information.

For example, the electronic device may also obtain operation information of the electronic device by the user. The operation information may be, for example, history data of the operation of the electronic device by the user. The historical data may represent or reflect historical activities performed by the user. The operation information may further include operation start time information and operation end time information.

For example, if the user performs an operation of listening to music in a certain time period, the electronic device may record the operation of listening to music, and record the time when the user starts listening to music and the time when the user finishes listening to music. For example, if the user is listening to music between 08:00 and 08:20, the electronic device may generate a correspondence relationship between the operation of listening to music and the time period of 08:00 to 08:20, which indicates that the user is listening to music between 08:00 and 08: 20.

At 208, the electronic device determines valid and invalid segmentation positions according to the operation information and the operation start time information and the operation end time information included in the operation information, and the data characteristics corresponding to each sub-data sequence and the segmentation start time information and the segmentation end time information corresponding to the data characteristics.

For example, after obtaining the operation information of the user on the electronic device, the operation start time information and the operation end time information included in the operation information, and the data features corresponding to the sub-data sequences, the segmentation start time information and the segmentation end time information corresponding to the data features, the electronic device may determine the valid segmentation position and the invalid segmentation position according to the information.

For example, as shown in fig. 5, the electronic device divides the data sequence D into sub-data sequences D1, D2, D3, D4, and D5, and extracts data characteristics for each sub-data sequence, where the data characteristic corresponding to sub-data sequence D1 is D1, the data characteristic corresponding to sub-data sequence D2 is D2, the data characteristic corresponding to sub-data sequence D3 is D3, the data characteristic corresponding to sub-data sequence D4 is D4, and the data characteristic corresponding to sub-data sequence D5 is D5. The division start time and the division end time corresponding to the sub-data sequence D1 are t1 and t2, respectively. The division start time and the division end time corresponding to the sub-data sequence D2 are t2 and t3, respectively. The division start time and the division end time corresponding to the sub-data sequence D3 are t3 and t4, respectively. The division start time and the division end time corresponding to the sub-data sequence D4 are t4 and t5, respectively. The division start time and the division end time corresponding to the sub-data sequence D5 are t5 and t6, respectively.

For example, t1 is 08:00, t2 is 08:10, and t3 is 08: 20. By comparing the data characteristic D1 of the sub-data sequence D1 with the data characteristic D2 of the sub-data sequence D2, the electronic device determines that D1 and D2 are the same data characteristic. By inquiring the operation information of the user on the electronic equipment, the electronic equipment determines that the user performs the operation of listening to music in the time period from 08:00 to 08: 20. Then the electronic device may determine that the t2 split position is an invalid split position and t1 and t3 are valid split positions. That is, since the user performs an operation of listening to music between t1 and t3, it is not appropriate to divide the original data sequence D at the position of t2, that is, it is not necessary to divide the original data sequence D at the position of t 2.

In one embodiment, the electronic device may execute 208 a Monte Carlo method to determine valid and invalid segmentation positions according to the operation information, the operation start time information and the operation end time information included in the operation information, and the data characteristics corresponding to each sub-data sequence, the segmentation start time information and the segmentation end time information corresponding to the data characteristics.

In 209, the electronic device outputs parameters for updating the data segmentation strategy including target segmentation interval durations corresponding to different features according to the valid segmentation position and the invalid segmentation position.

For example, after determining the valid segmentation position and the invalid segmentation position, the electronic device may output a parameter for updating the data segmentation policy according to information of the valid segmentation position and the invalid segmentation position. The output parameters for updating the data segmentation strategy may include target segmentation interval durations corresponding to different features.

For example, after determining that t2 is an invalid segmentation position, the electronic device may output a parameter for updating the data segmentation policy, where the parameter may include a target segmentation interval duration corresponding to the feature d1, for example, the target segmentation interval duration corresponding to the feature d1 is a time interval between t1 and t3 of 20 minutes.

In 210, the electronic device learns the desired data partitioning strategy to improve the data partitioning strategy based on the output parameters for updating the data partitioning strategy.

For example, after obtaining the parameters for updating the data partitioning policy, the electronic device may learn the required data partitioning policy according to the output parameters for updating the data partitioning policy to improve the data partitioning policy.

That is, the electronic device may update the currently used data partitioning policy using the outputted parameters for updating the data partitioning policy. For example, after obtaining the information that the target division interval duration corresponding to the feature d1 is 20 minutes, the electronic device may determine the division interval corresponding to the feature d1 (corresponding to music listening activities) in the currently used data division strategy to be 20 minutes.

It is understood that the process of updating the currently used data segmentation strategy is the process of learning the required data segmentation strategy. The data segmentation strategy can be improved by learning the required data segmentation strategy through the output parameters for updating the data segmentation strategy.

For example, the electronic device learns that for listening to music activity, the corresponding division interval is 20 minutes. Then, subsequently, when it is detected that the user performs an activity of listening to music, the electronic device may determine the division boundary of the data sequence 20 minutes after the start of listening to music.

As another example, the electronic device learns that the corresponding segmentation interval is 30 minutes for reading a news activity. Then, subsequently, when it is detected that the user is engaged in an activity to read news, the electronic device may determine the segmentation boundary of the data sequence 30 minutes after the start of reading the news.

It can be understood that the time sequence division boundaries corresponding to the activities can be determined through learning in the embodiment of the application. That is, the present embodiment can more accurately divide the data division boundary. Therefore, the data segmentation accuracy of the electronic equipment can be improved.

In one embodiment, the process of acquiring, by the electronic device in 205, the data splitting policy may include: the electronic equipment acquires a data segmentation strategy, wherein the acquired data segmentation strategy comprises segmentation interval duration.

Then, the process of the electronic device in 205 dividing the data sequence into a plurality of sub-data sequences according to the obtained data division policy may include: and the electronic equipment adjusts the used segmentation interval duration by using a greedy algorithm when performing data segmentation each time according to the obtained data segmentation strategy so as to segment the data sequence into a plurality of sub-data sequences.

For example, when the electronic device first acquires the data splitting policy, the acquired data splitting policy may include a splitting interval duration. For example, the division interval duration included in the acquired data division policy is 5 minutes. That is, the acquired data splitting policy instructs the electronic device to split the data sequence at 5 minute intervals.

In the embodiment of the application, the electronic device may not completely segment the data sequence according to the segmentation interval duration in the data segmentation strategy, but may adjust the used segmentation interval duration by using a greedy algorithm every time data segmentation is performed, so as to segment the data sequence into a plurality of sub-data sequences.

For example, if the data sequence D is completely divided according to the division interval duration in the obtained data division policy, the division start time and the division end time of each sub data sequence obtained by division are both separated by 5 minutes. In the embodiment of the present application, the electronic device may adjust the time interval for segmenting the data sequence by using a greedy algorithm according to the segmentation interval duration carried in the data segmentation policy. For example, when the electronic device performs the first segmentation on the data sequence D, the electronic device performs segmentation according to a segmentation interval duration of 5 minutes to obtain the sub-data sequence D1, where an interval between the segmentation start time and the segmentation end time of D1 is 5 minutes. Then, when the electronic device performs the second segmentation on the data sequence D, the greedy algorithm is used to adjust the segmentation interval duration to 6 minutes, and perform the second segmentation on the data sequence D according to the segmentation interval of 6 minutes, so as to obtain a sub-data sequence D2, where an interval between the segmentation start time and the segmentation end time of D2 is 6 minutes. For another example, when the electronic device performs the third segmentation on the data sequence D, the greedy algorithm is used to adjust the segmentation interval duration to 5.5 minutes, and perform the third segmentation on the data sequence D according to the segmentation interval of 5.5 minutes, so as to obtain the sub-data sequence D3, where an interval between the segmentation start time and the segmentation end time of D3 is 5.5 minutes.

For example, if the division interval duration carried in the data division strategy is t, the electronic device may adjust the division interval duration to be between t + greedy () and t-greedy () in a small scale by using a greedy algorithm, so as to implement exploration learning for dynamically dividing the data sequence.

The greedy algorithm is used with a probability of 1 by searching for the probability. The formula is as follows:

where the parameter Q (a) represents the Q value of the strategy selection partition and random (a) represents the possibility of random selection according to a given action a.

Referring to fig. 6, fig. 6 is a schematic view of a scenario of a data processing method according to an embodiment of the present application.

For example, as shown in the figure, the electronic device may collect data first, and the collected data may include various types of data, such as operation state data (e.g., data of application opening, operation, closing, etc.) of the electronic device, data collected by various types of sensors, and the like.

After collecting the data, the electronic device may perform synchronization processing on the data based on the time stamp to obtain synchronized data, and then the electronic device may convert and store the synchronized data according to a time-series format to obtain a data sequence. For example a data sequence D.

After obtaining the data sequence D, the electronic device may obtain a data segmentation policy, and segment the data sequence D into a plurality of sub data sequences (the sub data sequences are time window data) according to the obtained data segmentation policy. For example, when the electronic device performs data division for the first time, the electronic device may divide the data sequence D using the random policy p 1. In this embodiment, the random policy p1 used by the electronic device may include the division interval duration t.

Then, when the data sequence D is segmented using the random strategy p1, the electronic device may also adjust the used segmentation interval duration on a t basis at each segmentation. For example, the electronic device uses the segmentation interval duration t20 when segmenting the data sequence D for the first time and t21 when segmenting the data sequence D for the second time, where t20 and t21 are different interval durations.

For example, the electronic device divides the data sequence D into sub-data sequences D1, D2, D3. The start position of the sub-data sequence D1 is a1, and the end position of the division is a 2. The start position of the sub data sequence D2 is a2, and the end position of the division is A3. The start position of the sub data sequence D1 is A3, and the end position of the division is a 4. Wherein, A1, A2, A3 and A4 are all one time point on the time sequence. That is, a1, a2, A3, a4 may all be timestamp information.

After that, the electronic device may generate the sub-data sequence and the corresponding relationship between the segmentation start position and the segmentation end position corresponding to the sub-data sequence. For example, the electronic device may store the split start position and the split end position of the sub-data sequence in the form of a vector. For example, the sub-data sequence D1 has a division start position of a1 and a division end position of a2, the electronic device may generate a vector [ a1, a2] and establish a correspondence between the vector [ a1, a2] and the sub-data sequence D1.

After that, the electronic device may perform feature extraction on each sub data sequence. For example, the extracted sub data sequence D1 corresponds to a data characteristic D1, the sub data sequence D2 corresponds to a data characteristic D2, and the sub data sequence D3 corresponds to a data characteristic D3.

After that, the electronic device may obtain operation information of the electronic device by the user, where the operation information may include operation start time information and operation end time information. The operation information may be, for example, history data of the operation of the electronic device by the user. The historical data may represent or reflect historical activities performed by the user.

After the operation information of the user on the electronic device, the operation start time information and the operation end time information included in the operation information, the data characteristics corresponding to each sub data sequence, the segmentation start position and the segmentation end position corresponding to each sub data sequence are acquired, the electronic device can determine an effective segmentation position and an ineffective segmentation position according to the information.

For example, the electronic device divides the data sequence D into sub-data sequences D1, D2, and D3, and the time corresponding to the division start position and the division end position corresponding to the sub-data sequence D1 is 08:00 and 08:10 in sequence. The time corresponding to the division start position and the division end position of the sub-data sequence D2 is 08:10 and 08:20 in sequence. The division start time and the division end time of sub-data sequence D3 are 08:20 and 08:30 in this order.

By comparing the data characteristic D1 of the sub-data sequence D1 with the data characteristic D2 of the sub-data sequence D2, the electronic device determines that D1 and D2 are the same data characteristic. By inquiring the operation information of the user on the electronic equipment, the electronic equipment determines that the user performs the operation of listening to music in the time period from 08:00 to 08: 20. Then the electronic device may determine that the a2 split position is an invalid split position and that a1 and A3 are valid split positions. That is, since the user performs an operation of listening to music between a1 and A3, it is not appropriate to divide the original data sequence D at the position of a2, that is, it is not necessary to divide the original data sequence D at the position of a 2.

After the effective segmentation position and the ineffective segmentation position are determined, the electronic equipment can output parameters for updating the data segmentation strategy according to the information of the effective segmentation position and the ineffective segmentation position. The output parameters for updating the data segmentation strategy may include target segmentation interval durations corresponding to different features.

For example, after determining that a2 is an invalid segmentation position, the electronic device may output parameters for updating the data segmentation policy, where the parameters may include a target segmentation interval duration corresponding to the feature d1, for example, the target segmentation interval duration corresponding to the feature d1 is a time interval between a1 and A3 of 20 minutes.

After obtaining the parameters for updating the data partitioning policy, the electronic device may learn a desired data partitioning policy according to the outputted parameters for updating the data partitioning policy to improve the data partitioning policy. That is, the electronic device may update the currently used data partitioning policy using the outputted parameters for updating the data partitioning policy. For example, after obtaining the information that the target division interval duration corresponding to the feature d1 is 20 minutes, the electronic device may determine the division interval corresponding to the feature d1 (corresponding to music listening activities) in the currently used data division strategy to be 20 minutes.

Referring to fig. 7, fig. 7 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present disclosure. The data processing apparatus 300 may include: a first obtaining module 301, a second obtaining module 302, an extracting module 303, a third obtaining module 304, and a learning module 305.

A first obtaining module 301, configured to obtain a data sequence, where the data sequence is formed by data acquired by the electronic device in a time interval according to a time sequence format.

A second obtaining module 302, configured to obtain a data partitioning policy, and partition the data sequence into a plurality of sub-data sequences according to the obtained data partitioning policy, where each sub-data sequence corresponds to a time slice in the time interval.

The extracting module 303 is configured to perform feature extraction on each sub-data sequence to obtain data features corresponding to each sub-data sequence.

A third obtaining module 304, configured to obtain operation information of the electronic device by the user.

A learning module 305, configured to learn a required data partitioning policy according to the operation information and the data features corresponding to the sub-data sequences, so as to improve the data partitioning policy.

In an embodiment, the second obtaining module 302 may be further configured to: division start time information and division end time information corresponding to each sub data sequence are acquired.

The third obtaining module 304 may be configured to: and acquiring operation information of the electronic equipment by a user, wherein the operation information further comprises operation starting time information and operation ending time information.

The learning module 305 may be configured to: determining an effective segmentation position and an invalid segmentation position according to the operation information, the operation starting time information and the operation ending time information which are contained in the operation information, and the data characteristics corresponding to each sub-data sequence, the segmentation starting time information and the segmentation ending time information which correspond to the sub-data sequence; outputting parameters for updating a data segmentation strategy according to the effective segmentation position and the ineffective segmentation position; and learning the required data segmentation strategy according to the parameters for updating the data segmentation strategy so as to improve the data segmentation strategy.

In one embodiment, the learning module 305 may be configured to: and outputting parameters for updating the data segmentation strategy according to the effective segmentation position and the ineffective segmentation position, wherein the parameters for updating the data segmentation strategy comprise target segmentation interval duration corresponding to different features.

In one embodiment, the first obtaining module 301 may further be configured to:

acquiring data acquired by the electronic equipment within a time interval;

carrying out synchronous processing based on the timestamp on the acquired data to obtain the data after synchronous processing;

and converting the data after the synchronous processing into a data sequence according to a time sequence format.

In one embodiment, the second obtaining module 302 may be configured to:

and acquiring a data segmentation strategy, wherein the acquired data segmentation strategy comprises segmentation interval duration.

And adjusting the used segmentation interval duration by using a greedy algorithm when performing data segmentation each time according to the obtained data segmentation strategy, and segmenting the data sequence into a plurality of sub-data sequences.

The present embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed on a computer, the computer is caused to execute the flow in the data processing method provided in this embodiment.

The embodiment of the present application further provides an electronic device, which includes a memory and a processor, where the processor is configured to execute the flow in the data processing method provided in this embodiment by calling the computer program stored in the memory.

For example, the electronic device may be a mobile terminal such as a tablet computer or a smart phone. Referring to fig. 8, fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

The electronic device 400 may include components such as a sensor 401, a memory 402, a processor 403, and the like. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 8 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The sensors 401 may include a gyro sensor (e.g., a three-axis gyro sensor), an acceleration sensor, and the like.

The memory 402 may be used to store applications and data. The memory 402 stores applications containing executable code. The application programs may constitute various functional modules. The processor 403 executes various functional applications and data processing by running an application program stored in the memory 402.

The processor 403 is a control center of the electronic device, connects various parts of the whole electronic device by using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing an application program stored in the memory 402 and calling data stored in the memory 402, thereby performing overall monitoring of the electronic device.

In this embodiment, the processor 403 in the electronic device loads the executable code corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 403 runs the application programs stored in the memory 402, so as to execute:

acquiring operation information of a user on the electronic equipment;

Referring to fig. 9, an electronic device 500 may include a sensor 501, a memory 502, a processor 503, a speaker 504, a display 505, a battery 506, and the like.

The sensor 501 may include a gyro sensor (e.g., a three-axis gyro sensor), an acceleration sensor, and the like.

The memory 502 may be used to store applications and data. Memory 502 stores applications containing executable code. The application programs may constitute various functional modules. The processor 503 executes various functional applications and data processing by running an application program stored in the memory 502.

The processor 503 is a control center of the electronic device, connects various parts of the whole electronic device by using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing an application program stored in the memory 502 and calling the data stored in the memory 502, thereby performing overall monitoring of the electronic device.

The speaker 504 may be used to play sound signals. The display screen 505 may be used to display information such as images and text. The battery 506 may provide power to the electronic device.

In this embodiment, the processor 503 in the electronic device loads the executable code corresponding to the processes of one or more application programs into the memory 502 according to the following instructions, and the processor 503 runs the application programs stored in the memory 502, so as to execute:

acquiring operation information of a user on the electronic equipment;

In one embodiment, after the data sequence is divided into a plurality of sub-data sequences according to the obtained data division policy, the processor 503 may further perform: division start time information and division end time information corresponding to each sub data sequence are acquired.

Then, when the processor 503 executes the operation information of the electronic device obtained by the user, it may execute: and acquiring operation information of the electronic equipment by a user, wherein the operation information further comprises operation starting time information and operation ending time information.

When the processor 503 performs learning of the required data partitioning policy according to the operation information and the data characteristics corresponding to each sub data sequence, so as to improve the data partitioning policy, it may perform: determining an effective segmentation position and an invalid segmentation position according to the operation information, the operation starting time information and the operation ending time information which are contained in the operation information, and the data characteristics corresponding to each sub-data sequence, the segmentation starting time information and the segmentation ending time information which correspond to the sub-data sequence; outputting parameters for updating a data segmentation strategy according to the effective segmentation position and the ineffective segmentation position; and learning the required data segmentation strategy according to the parameters for updating the data segmentation strategy so as to improve the data segmentation strategy.

In one embodiment, when the processor 503 executes the output of the parameter for updating the data splitting policy according to the valid splitting position and the invalid splitting position, it may execute: and outputting parameters for updating the data segmentation strategy according to the effective segmentation position and the ineffective segmentation position, wherein the parameters for updating the data segmentation strategy comprise target segmentation interval duration corresponding to different features.

In one embodiment, before the acquiring the data sequence, the processor 503 may further perform: acquiring data acquired by the electronic equipment within a time interval; carrying out synchronous processing based on the timestamp on the acquired data to obtain the data after synchronous processing; and converting the data after the synchronous processing into a data sequence according to a time sequence format.

In one embodiment, when the processor 503 executes the data segmentation policy, it may perform: and acquiring a data segmentation strategy, wherein the acquired data segmentation strategy comprises segmentation interval duration.

Then, when the processor 503 executes the obtained data division policy to divide the data sequence into a plurality of sub-data sequences, it may execute: and adjusting the used segmentation interval duration by using a greedy algorithm when performing data segmentation each time according to the obtained data segmentation strategy, and segmenting the data sequence into a plurality of sub-data sequences.

In the above embodiments, the descriptions of the embodiments have respective emphasis, and parts that are not described in detail in a certain embodiment may refer to the above detailed description of the data processing method, and are not described herein again.

The data processing apparatus provided in the embodiment of the present application and the data processing method in the above embodiment belong to the same concept, and any method provided in the embodiment of the data processing method may be run on the data processing apparatus, and a specific implementation process thereof is described in the embodiment of the data processing method in detail, and is not described herein again.

It should be noted that, for the data processing method described in the embodiment of the present application, it can be understood by those skilled in the art that all or part of the process of implementing the data processing method described in the embodiment of the present application can be completed by controlling the relevant hardware through a computer program, where the computer program can be stored in a computer-readable storage medium, such as a memory, and executed by at least one processor, and during the execution, the process of the embodiment of the data processing method can be included. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.

In the data processing apparatus according to the embodiment of the present application, each functional module may be integrated into one processing chip, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, or the like.

The foregoing detailed description has provided a data processing method, an apparatus, a storage medium, and an electronic device according to embodiments of the present application, and specific examples are applied herein to explain the principles and implementations of the present application, and the descriptions of the foregoing embodiments are only used to help understand the method and the core ideas of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A data processing method applied to electronic equipment is characterized by comprising the following steps:

acquiring operation information of a user on the electronic equipment;

2. The data processing method according to claim 1, after dividing the data sequence into a plurality of sub-data sequences according to the obtained data division policy, further comprising: acquiring segmentation start time information and segmentation end time information corresponding to each subdata sequence;

the acquiring operation information of the user on the electronic device includes: acquiring operation information of a user on the electronic equipment, wherein the operation information further comprises operation starting time information and operation ending time information;

learning a required data segmentation strategy according to the operation information and the data characteristics corresponding to each sub data sequence so as to improve the data segmentation strategy, wherein the data segmentation strategy comprises the following steps:

determining an effective segmentation position and an invalid segmentation position according to the operation information, the operation starting time information and the operation ending time information which are contained in the operation information, and the data characteristics corresponding to each sub-data sequence, the segmentation starting time information and the segmentation ending time information which correspond to the sub-data sequence;

outputting parameters for updating a data segmentation strategy according to the effective segmentation position and the ineffective segmentation position;

and learning the required data segmentation strategy according to the parameters for updating the data segmentation strategy so as to improve the data segmentation strategy.

3. The data processing method according to claim 2, wherein outputting parameters for updating a data partitioning policy according to the valid partitioning position and the invalid partitioning position comprises: and outputting parameters for updating the data segmentation strategy according to the effective segmentation position and the ineffective segmentation position, wherein the parameters for updating the data segmentation strategy comprise target segmentation interval duration corresponding to different features.

4. The data processing method of claim 1, further comprising, prior to the acquiring the sequence of data:

acquiring data acquired by the electronic equipment within a time interval;

5. The data processing method of claim 1, wherein the obtaining the data partitioning policy comprises: acquiring a data segmentation strategy, wherein the acquired data segmentation strategy comprises segmentation interval duration;

the dividing the data sequence into a plurality of subdata sequences according to the obtained data division strategy includes: and adjusting the used segmentation interval duration by using a greedy algorithm when performing data segmentation each time according to the obtained data segmentation strategy, and segmenting the data sequence into a plurality of sub-data sequences.

6. A data processing device applied to an electronic device, comprising:

7. The data processing apparatus of claim 6, wherein the second obtaining module is further configured to: acquiring segmentation start time information and segmentation end time information corresponding to each subdata sequence;

the third obtaining module is configured to: acquiring operation information of a user on the electronic equipment, wherein the operation information further comprises operation starting time information and operation ending time information;

the learning module is to: determining an effective segmentation position and an invalid segmentation position according to the operation information, the operation starting time information and the operation ending time information which are contained in the operation information, and the data characteristics corresponding to each sub-data sequence, the segmentation starting time information and the segmentation ending time information which correspond to the sub-data sequence; outputting parameters for updating a data segmentation strategy according to the effective segmentation position and the ineffective segmentation position; and learning the required data segmentation strategy according to the parameters for updating the data segmentation strategy so as to improve the data segmentation strategy.

8. The data processing apparatus of claim 7, wherein the learning module is configured to: and outputting parameters for updating the data segmentation strategy according to the effective segmentation position and the ineffective segmentation position, wherein the parameters for updating the data segmentation strategy comprise target segmentation interval duration corresponding to different features.

9. A storage medium having stored thereon a computer program, characterized in that the computer program, when executed on a computer, causes the computer to execute the method according to any of claims 1 to 5.

10. An electronic device comprising a memory, a processor, wherein the processor is configured to perform the method of any one of claims 1 to 5 by invoking a computer program stored in the memory.