WO2022161325A1 - 提示方法和电子设备 - Google Patents

提示方法和电子设备 Download PDF

Info

Publication number
WO2022161325A1
WO2022161325A1 PCT/CN2022/073583 CN2022073583W WO2022161325A1 WO 2022161325 A1 WO2022161325 A1 WO 2022161325A1 CN 2022073583 W CN2022073583 W CN 2022073583W WO 2022161325 A1 WO2022161325 A1 WO 2022161325A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
power consumption
time
feature vector
electronic device
Prior art date
Application number
PCT/CN2022/073583
Other languages
English (en)
French (fr)
Inventor
刘琛峰
Original Assignee
维沃移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2022161325A1 publication Critical patent/WO2022161325A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
    • G06F1/3212—Monitoring battery levels, e.g. power saving mode being initiated when battery voltage goes below a certain level
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting

Definitions

  • the present application belongs to the field of electronic technology, and specifically relates to a prompting method and an electronic device.
  • the usage of battery power is predicted according to voltage and current, or according to the historical average power consumption of electronic equipment.
  • the purpose of the embodiments of the present application is to provide a prompting method, which can solve the problem of low accuracy in predicting battery power usage in the related art because the interference of man-made, environmental and other variable factors is not considered.
  • an embodiment of the present application provides a prompting method, the method includes: acquiring a first feature vector, where the first feature vector is used to represent first feature information of a first application, and the first application is a history record
  • the application program running within the target period associated with the determine the average power consumption speed of the electronic device in the target period; output the power prompt information according to the target period and the average power consumption rate.
  • an embodiment of the present application provides an electronic device, the device includes a first acquisition module configured to acquire a first feature vector, the first feature vector is used to reflect the first feature information of the first application, and the first feature vector
  • An application program is an application program running in the target period associated in the historical record; the second acquisition module is used to acquire a second feature vector, and the second feature vector is used to represent the second power consumption associated with the start time of the target period feature information; a power consumption speed determination module for determining the average power consumption speed of the electronic device within the target period according to the first feature vector and the second feature vector; a prompt module for outputting according to the target period and the average power consumption speed Battery information.
  • an embodiment of the present application provides an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor.
  • the program or instruction is executed by the processor, the The steps of the method of the first aspect.
  • an embodiment of the present application provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the method of the first aspect are implemented.
  • an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement the method of the first aspect.
  • the first application running in the target period associated in the historical record is obtained, and the An application program may be the first application program recorded in the history record that the user uses more frequently in the target period, so as to obtain the first feature vector corresponding to the first application program.
  • the second feature vector is obtained.
  • the second power consumption feature information embodied by the second feature vector is associated with the start time of the target period, and the start moment of the target period (such as the current moment) is associated with the actual operation of the user and the actual environment.
  • the second power consumption The feature information is information generated based on the actual operation of the device by the user and the actual environment in which it is located.
  • the second power consumption characteristic information includes some information related to real-time power consumption, such as the battery power information at the start of the target period, the temperature of the environment, and the like.
  • the two sets of feature vectors are integrated, and the average power consumption speed in the target period is calculated through the pre-trained regression tree model.
  • the battery power usage in the target period is predicted. Further, the period from the current time to the time when the power is exhausted is divided into multiple periods, and the above process is repeated to predict the usage of battery power in all periods, thereby completing the prediction of the usage of battery power.
  • this embodiment not only combines the user's historical usage habits, but also considers the user's actual operating conditions and the environment in which he is located, thus combining the man-made, environmental and other variable factors in the actual operation to improve the predicted battery power. Usage accuracy.
  • FIG. 1 is a schematic flowchart of an embodiment of a prompting method of the present application
  • FIGS. 2 to 6 are schematic diagrams illustrating data involved in the prompting method according to an embodiment of the present application.
  • FIG. 7 is a block diagram of an electronic device according to an embodiment of the present application.
  • FIG. 9 is the second schematic diagram of the hardware structure of the electronic device according to the embodiment of the present application.
  • first, second and the like in the description and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and distinguish between “first”, “second”, etc.
  • the objects are usually of one type, and the number of objects is not limited.
  • the first object may be one or more than one.
  • “and/or” in the description and claims indicates at least one of the connected objects, and the character “/" generally indicates that the contextual objects are in an "or” relationship.
  • FIG. 1 shows a flowchart of a prompting method according to an embodiment of the present application, which is applied to an electronic device. As shown in FIG. 1 , the prompting method includes steps S1 to S4:
  • Step S1 Obtain a first feature vector.
  • the first feature vector is used to represent the first feature information of the first application, and the first application is an application running within the target time period associated in the history record.
  • the target time period may be any time period from the current moment to the time when the power is exhausted.
  • the time when the battery is exhausted is the predicted time.
  • one or more time periods can be divided from the current time to the time when the battery is exhausted, and each time period can be used as the target time period in this embodiment.
  • one or more time periods may be divided according to the time interval T.
  • t1 represents the current moment
  • time interval T as the unit
  • time periods t1 to t2 and t2 to t3 are divided, and each time period can be used as the target time period of this embodiment.
  • the application program running in the target period may be acquired in the history record as the first application program, so as to acquire the first feature vector of the first application program.
  • the first application running within the target period may be an application frequently used by the user within the target period.
  • the first application frequently used by the user during the target period in this step can reflect the user's historical usage habits, so that this embodiment can predict the usage of battery power in combination with the user's historical usage habits.
  • Step S2 Obtain a second feature vector.
  • the second feature vector is used to represent the second power consumption feature information associated with the start time of the target period.
  • the second power consumption characteristic information is associated with the start time of the target period, and the power consumption at the start time of the target period can at least reflect the actual operation of the device by the user, so that this embodiment can be combined with the user Actual operation of the device to predict battery usage.
  • the second power consumption characteristic information includes: based on the start time of the target period, information related to real-time power consumption is generated in the electronic device.
  • the second power consumption characteristic information includes information directly related to user operations, such as power consumption, power consumption speed, processor occupancy rate, etc.; the second power consumption characteristic information may also include, for example, network type, signal strength, time, geographic location, Environment-related information such as temperature. Based on the information listed above, it can be seen that the second power consumption feature information includes at least device state information and environment state information.
  • the second power consumption feature information can also reflect the current environmental factors, so that this embodiment can also predict the usage of battery power in combination with the real-time environmental factors.
  • the network signal is poor and the device responds slowly to the server, so the power consumption is accelerated, which can be reflected in the power consumption speed in the second power consumption feature information.
  • the user is usually in a rest state from 2:00 pm to 3:00 pm every day, there are fewer applications running in the electronic device, and the power consumption speed is slow.
  • the user does not have a rest, but uses video software to watch movies and TV series. This operation of the user leads to faster power consumption, so that at the beginning of the target period to be predicted, the calculated instantaneous The power consumption speed can reflect this operation of the user. Therefore, when the second power consumption characteristic information includes the instantaneous power consumption speed, the second power consumption characteristic information may reflect the real-time operation of the user.
  • the start time of the target period is not earlier than the current time.
  • Step S3 Determine the average power consumption speed of the electronic device within the target period according to the first feature vector and the second feature vector.
  • the preset processing method is a pre-trained regression tree model.
  • the first feature vector and the second feature vector are input into the regression tree model, so that the average power consumption speed of the electronic device within the target period is calculated based on the regression tree model.
  • the data used to reflect the user's historical usage habits, as well as the data used to reflect the user's actual operation, and environmental data are all expressed in the form of unified feature vectors, and then unified and integrated into the regression tree.
  • the model through the input of the vector and the calculation of the model, the average power consumption speed in the target period is obtained.
  • the regression tree model is, for example, a Gradient Boost Regression Tree (GBRT), an extreme gradient boosting (eXtreme Gradient Boosting, XgBoos), a Light Gradient Boosting Machine (Light GBM), and the like.
  • GBRT Gradient Boost Regression Tree
  • eXtreme Gradient Boosting extreme gradient boosting
  • XgBoos extreme gradient boosting
  • Light GBM Light Gradient Boosting Machine
  • step S1 obtains the first feature vector in the period from t1 to t2
  • step S2 obtains the second feature vector in the period from t1 to t2
  • the two sets of feature vectors are integrated and input into the regression tree
  • the average power consumption speed v1 in the time period from t1 to t2 can be predicted.
  • Step S4 According to the target period and the average power consumption speed, output power prompt information.
  • the power consumption of at least one period of time can be predicted to output a prompt message for the user's reference.
  • steps S1 to S3 in this embodiment may be cyclically repeated steps, so as to predict the average power consumption speed of each time period in the future starting from the current moment, thereby As of the time when the power is exhausted, the power consumption of all periods during the period can be predicted, and a prompt message can be output for the user's reference.
  • the time when the battery is exhausted is the predicted time.
  • the first application running in the target period associated in the historical record is obtained, and the An application program may be the first application program recorded in the history record that the user uses more frequently in the target period, so as to obtain the first feature vector corresponding to the first application program.
  • the second feature vector is obtained.
  • the second power consumption feature information embodied by the second feature vector is associated with the start time of the target period, and the start moment of the target period (such as the current moment) is associated with the actual operation of the user and the actual environment.
  • the second power consumption The feature information is information generated based on the actual operation of the device by the user and the actual environment in which it is located.
  • the second power consumption feature information includes some information related to real-time power consumption, such as battery power information at the start of the target period, the temperature of the environment where it is located, and the like. Then, the two sets of feature vectors are integrated, and the average power consumption speed in the target period is calculated through the pre-trained regression tree model. Finally, according to the target period and the average power consumption rate, the battery power usage in the target period is predicted.
  • this embodiment not only combines the user's historical usage habits, but also considers the user's actual operating conditions and the environment in which he is located, thus combining the man-made, environmental and other variable factors in the actual operation to improve the predicted battery power. Usage accuracy.
  • the second power consumption characteristic information includes at least the first battery power information at the start time of the target period
  • step S4 includes sub-step A1 and sub-step A2:
  • Sub-step A1 Determine the second battery power information at the end time of the target period according to the first battery power information and the average power consumption rate.
  • the end time of the target period can be predicted, that is, the battery power at the start time t2 of the next to-be-predicted period is x1-v1*T.
  • x1 represents the first battery power information, that is, the battery power at the start time t1 of the target period.
  • Sub-step A2 When the second battery power information is less than or equal to zero, output power prompt information according to all time periods from the current time to the end time of the target time period and the average power consumption rate corresponding to each time period.
  • the sum of all predicted time periods is the predicted time period during which the battery power is predicted to be usable.
  • the first line of data represents the second power consumption feature information at time t1 and the first feature vector from t1 to t2.
  • the second row of data represents the second power consumption feature information at time t2 and the first feature vector from t2 to t3.
  • the prediction can be re-predicted, so that the prediction result can be updated in real time, so as to improve the accuracy of the prediction result.
  • a prediction process of repeatedly executing steps S1 to S3 is provided to obtain a final prediction result.
  • steps S1 to S3 are performed to obtain the average power consumption speed v1 of the target period, and the power consumption function x1-v1*T of the adjacent next period can be obtained.
  • the steps are repeated, and the next time period adjacent to the target time period is used as the time period to be predicted, the historical application program of the user in this time period, and the power consumption feature information related to the start time of this time period are obtained, and the corresponding feature vector is updated.
  • this embodiment adopts the method of forecasting by time periods, respectively considering the historical usage habits and environmental influences of the users associated with each time period, and each time period is related to the actual operation of the user at the current moment and the environment at the current moment, thereby Further improve the accuracy of battery usage predictions.
  • step S4 includes at least any one of the following:
  • Sub-step B1 Output the estimated power consumption curve graph of the electronic device.
  • the output power prompt information may be in the form of an expected power consumption curve graph of the electronic device.
  • the abscissa of the predicted power consumption curve of the electronic device represents time
  • the ordinate of the predicted power consumption curve of the electronic device represents the battery level
  • the predicted usage of battery power is displayed in the form of a graph, so as to provide an intuitive prompting method from a visual point of view.
  • Sub-step B2 Output the estimated remaining usage time of the electronic device.
  • the output power prompt information may be in the form of the estimated remaining usage time of the electronic device.
  • the predicted usage of battery power is displayed in the form of estimated available time, so as to provide an intuitive prompt method from the perspective of time.
  • two methods for outputting prompt information are provided.
  • One is output in the form of a graph, so that the user can intuitively see the predicted power consumption trend, and then the user can adjust the actual usage of the electronic device according to the graph; the other is output in the form of the remaining available time. Therefore, it is convenient for the user to intuitively see the predicted time when the power is exhausted, and then the user can reasonably arrange the charging plan, the usage plan, etc. according to the remaining available time.
  • step S1 before step S1, it further includes steps C1-step C3:
  • Step C1 Record the characteristic information of each application program.
  • the feature information includes at least identification information, usage time information, usage duration information and usage location information.
  • the purpose is to collect the user's application history usage data.
  • the identification information includes an application name
  • the usage time information includes time and duration
  • the usage location information includes a geographic location
  • information such as the application name, time, duration, and geographic location of each time the user uses the application is recorded, and stored in a local database in chronological order to ensure user privacy and data security. Eliminate some applications that have been used for a short time, reduce the scale of data storage, and improve the retrieval speed of subsequent habit mining.
  • Step C2 According to the recorded characteristic information of each application program, determine the application program that runs in each time period and satisfies the preset condition.
  • the purpose is to mine the user's historical usage habits.
  • time periods are divided according to the daily routine of the user.
  • Table 1 a plurality of time ranges are divided, and each time range is regarded as a time period.
  • the preset condition is: the frequency of use is greater than the preset degree. That is, the applications that satisfy the preset conditions are the applications that are used more frequently in a certain period of time every day.
  • Method 1 Based on frequent pattern mining (Frequent PatternTree, FP-Growth) or association rule algorithm (Apriori), the usage records of the application in the same period of a period of time are used as a transaction database, and iteratively generates the data that meets the conditions. Larger frequent items to build frequent set items, and finally output the frequently used applications for each period.
  • Method 2 Based on statistical mining, count the usage records of the application within the same period of time within a certain date, and assign weights by the frequency and duration of the application. application used.
  • the application programs running in various locations and meeting the preset conditions may also be determined according to the recorded usage location information of each application program.
  • the historical data may be obtained, and the applications running at the current location and meeting the preset conditions can be obtained.
  • Step C3 Map the application programs that run in each time period and meet the preset conditions to a vector space.
  • the purpose of this step is to vectorize the acquired data of the user's historical usage habits.
  • the representation method based on the above-mentioned vectors can show the vector relationship that applications of the same kind are similar and applications of different categories are far away.
  • step S1 includes:
  • Sub-step C4 Based on the vector space, obtain the first feature vector of the first application program running within the target time period and satisfying the preset condition.
  • the first application program that is, the application program that is used more frequently by the user in the target period of time every day.
  • the first feature vector may be a vector of an application program, or may be a vector set of multiple application programs.
  • the historical usage habits of the user are recorded in real time, and the recorded historical usage habits include but are not limited to: the name of the application, the usage time, the usage time, the usage location, etc.
  • the applications that are used more frequently by users in each period are obtained, and then the applications that are used more frequently by users in each period are unified by means of feature vectors.
  • the first feature vector of the first application program that is frequently used in the target period can be determined from the recorded historical usage habits to input into the regression tree model.
  • the first feature vector can reflect the characteristics of the first application, so that the input into the regression tree model can reflect the power consumption of the first application, so that this embodiment can predict the battery according to the user's historical usage habits.
  • the usage of electricity, and the prediction of each time period corresponds to the usage habits of each time period, so that the accuracy of the prediction is high.
  • step S2 before step S2, it further includes step D1 and step D2:
  • Step D1 Acquire second power consumption feature information.
  • the second power consumption feature information includes battery power information, time information, target location information, network status information, device power consumption duration information, and device power consumption speed information, and the first battery power information, time information, target position information, The network status information, the device power consumption duration information, and the device power consumption speed information are all associated with the start time of the target period.
  • the user's behavior is random. For example, a user uses chat software to chat at 2 pm, and suddenly wants to open the video software to watch TV series at 3 o'clock in the afternoon. In this case, if you only rely on the applications mined from historical habits, and then make predictions based on the historical power consumption of these applications, it will be very different from the actual usage of the user. The remaining battery usage time is also inaccurate. Therefore, not only the historical habits of users, but also the real-time power consumption feature information in electronic devices must be integrated to dynamically adjust the prediction results in combination with user operations and environmental factors.
  • the second power consumption characteristic information associated with the start time of the target period is acquired.
  • the battery level information is the battery level information at the start of the target period.
  • it is processed into the following features: battery percentage.
  • the power at the current moment is obtained through the interface of the operating system of the electronic device as the battery power information; when the starting moment of the target period is not the current moment, Based on the power at the current time, the power at the start of the target period can be predicted as the battery power information.
  • the time information includes time information of the start time of the target period.
  • it is processed into the following features: day of the week, minutes relative to 00:00 of the day.
  • the current moment is obtained through the interface of the operating system of the electronic device as time information; when the starting moment of the target period is not the current moment, the current moment can be time, the start time of the target period is estimated as time information.
  • the target location information and the network state information include the target location information and the network state information at the start time of the target period.
  • a clustering method such as Density-Based Spatial Clustering of Applications with Noise (DB-SCAN) is used to set the geo-fence to 1 km, and the user can be obtained.
  • DB-SCAN Density-Based Spatial Clustering of Applications with Noise
  • the geographic location and network status at the current moment are obtained through the interface of the operating system of the electronic device, as target position information and network status information; at the beginning of the target period If the time is not the current time, the geographic location and network state at the current time can be used as the target location information and network state information.
  • the device power consumption duration information includes the device power consumption duration information from the start time of the target period to the latest full power time.
  • it is treated as the following feature: the duration relative to the moment of full charge (100% charge).
  • the start time of the target period is the current time.
  • the time t 100 corresponding to the latest fully charged state can be retrieved, and combined with the current time t 1 , the duration relative to the fully charged time can be obtained as t 1 -t 100 .
  • the start time of the target time period is not the current time
  • the duration of the start time of the target time period relative to the full power time may be determined based on the current time and the duration of the current time relative to the full power time, as the power consumption of the device duration information.
  • the device power consumption rate information includes an instantaneous power consumption rate and a long-term power consumption rate at the start of the target period.
  • the start time of the target period is the current time.
  • the instantaneous power consumption rate is used to represent the current power consumption rate of the electronic device.
  • the current moment is the power amount x 1
  • the power amount 5 minutes ago is x 2
  • the instantaneous power consumption rate can be expressed as (x 2 -x 1 )/5.
  • the long-term power consumption speed is used to characterize the average power consumption speed of the electronic device in the recent period of time.
  • the current time t 1 is the power amount x 1 .
  • the monotonically decreasing sequence of , the power consumption time interval t from the moment of full power to the current moment can be obtained, and the long-term power consumption speed can be expressed as (100-x 1 )/t.
  • the start time of the target time period is not the current time
  • the power consumption speed information of the electronic device can be obtained based on the power consumption speed information of the electronic device at the current time and in combination with the relationship between the target time period and the current time.
  • the second power consumption feature information corresponding to each time period and the first feature vector corresponding to each time period are shown.
  • Step D2 Generate a second feature vector corresponding to the second power consumption feature information according to the second power consumption feature information.
  • the corresponding second power consumption feature information is acquired for each time period, and vectorized according to a preset rule to generate a second feature vector corresponding to each time period.
  • Exemplarily first retrieve the applications of historical usage habits, then vectorize these applications, and then vectorize the acquired second power consumption feature information, and connect the vectorized application sequence and power consumption feature together to form a feature. vector.
  • a feature vector formed by the first feature vector and the second feature vector together is shown in a certain period of time.
  • the second power consumption feature information generated in the electronic device may be obtained in combination with the start time of the target time period.
  • the second power consumption feature information includes but is not limited to the above mentioned in this embodiment. specific feature information.
  • the obtained feature data is vectorized, and then integrated with the first feature vector of the corresponding period to form the feature vector to be input, So that the prediction of the usage of the battery power in the target period can be successfully completed.
  • this embodiment in addition to considering the influence of the user's daily habits of using electronic devices on power consumption; it also considers that the user's behavior of using electronic devices is changing all the time, and the environment where the electronic device is located is always changing. All are changing, and the predicted results are not static. Therefore, this embodiment can dynamically predict the future power change according to the actual usage of the user and the environment.
  • the embodiment of the present application predicts the future usage of the user's remaining power by using the user's daily usage habits, the current real-time device state, and the current real-time environment state, and can provide the user with a dynamic remaining power usage time in real time.
  • the execution subject may be an electronic device, or a control module in the electronic device for executing the prompting method.
  • an electronic device for the prompt method provided by the embodiment of the present application is described by taking the electronic device executing the prompt method as an example.
  • FIG. 7 shows a block diagram of an electronic device according to an embodiment of the present application, as shown in FIG. 7 , including:
  • the first acquisition module 10 is used to acquire a first feature vector, the first feature vector is used to reflect the first feature information of the first application program, and the first application program is the application program running in the target time period associated in the historical record;
  • the second obtaining module 20 is configured to obtain a second feature vector, where the second feature vector is used to represent the second power consumption feature information associated with the start time of the target period;
  • a power consumption speed determination module 30, configured to determine the average power consumption speed of the electronic device within the target period according to the first feature vector and the second feature vector;
  • the prompt module 40 is configured to output power prompt information according to the target period and the average power consumption speed.
  • the first application running in the target period associated in the historical record is obtained, and the An application program may be the first application program recorded in the history record that the user uses more frequently in the target period, so as to obtain the first feature vector corresponding to the first application program.
  • the second feature vector is obtained.
  • the second power consumption feature information embodied by the second feature vector is associated with the start time of the target period, and the start moment of the target period (such as the current moment) is associated with the actual operation of the user and the actual environment.
  • the second power consumption The feature information is information generated based on the actual operation of the device by the user and the actual environment in which it is located.
  • the second power consumption feature information includes some information related to real-time power consumption, such as battery power information at the start of the target period, the temperature of the environment where it is located, and the like. Then, the two sets of feature vectors are integrated, and the average power consumption speed in the target period is calculated through the pre-trained regression tree model. Finally, according to the target period and the average power consumption speed, the battery power usage in the target period is predicted.
  • this embodiment not only combines the user's historical usage habits, but also considers the user's actual operating conditions and the environment in which he is located, thus combining the man-made, environmental and other variable factors in the actual operation to improve the predicted battery power. Usage accuracy.
  • the second power consumption characteristic information includes at least the first battery power information at the start time of the target period
  • the prompting module 40 includes:
  • a power information determining unit configured to determine the second battery power information at the end time of the target period according to the first battery power information and the average power consumption speed
  • the first output unit is configured to output power prompt information according to all time periods from the current time to the end time of the target time period and the average power consumption speed corresponding to each time period when the second battery power information is less than or equal to zero .
  • the prompting module 40 includes at least any one of the following:
  • a second output unit configured to output an estimated power consumption curve diagram of the electronic device
  • the third output unit is used for outputting the estimated remaining usage time of the electronic device.
  • the device further includes:
  • the recording module is used to record the characteristic information of each application program, and the characteristic information includes at least identification information, usage time information, usage duration information and usage location information;
  • a first processing module configured to determine, according to the recorded feature information of each application program, the application program that runs in each time period and satisfies the preset condition
  • the second processing module is used to map the application programs that run in each time period and meet the preset conditions to a vector space through the vectorization model;
  • the first acquisition module 10 includes:
  • the vector obtaining unit is configured to obtain, based on the vector space, the first feature vector of the first application program running within the target time period and satisfying the preset condition.
  • the device further includes:
  • a third obtaining module configured to obtain the second power consumption characteristic information
  • a generating module configured to generate a second feature vector corresponding to the second power consumption feature information according to the second power consumption feature information
  • the second power consumption feature information includes battery power information, time information, target location information, network status information, device power consumption duration information and device power consumption speed information, and battery power information, time information, target position information, network status information
  • the information, the device power consumption duration information, and the device power consumption speed information are all associated with the start time of the target period.
  • the electronic device in this embodiment of the present application may be a device, or may be a component, an integrated circuit, or a chip in a terminal.
  • the device may be a mobile electronic device or a non-mobile electronic device.
  • the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palmtop computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (personal digital assistant).
  • UMPC ultra-mobile personal computer
  • PDA personal digital assistant
  • non-mobile electronic devices can be servers, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (television, TV), teller machine or self-service machine, etc., this application Examples are not specifically limited.
  • the electronic device in this embodiment of the present application may be a device with an operating system.
  • the operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.
  • the electronic device provided in the embodiment of the present application can implement each process implemented by the foregoing method embodiment, which is not repeated here to avoid repetition.
  • FIG. 8 is a schematic diagram of a hardware structure of an example of an electronic device provided by an embodiment of the present application.
  • the electronic device 100 includes a processor 101 and a memory 102, which are stored in the memory 102 and can be processed in the The program or instruction running on the processor 101, when the program or instruction is executed by the processor 101, implements each process of any of the above-mentioned prompting method embodiments, and can achieve the same technical effect. To avoid repetition, it is not repeated here.
  • the electronic devices in the embodiments of the present application include the aforementioned mobile electronic devices and non-mobile electronic devices.
  • FIG. 9 is a schematic diagram of a hardware structure of another example of an electronic device provided by an embodiment of the present application.
  • the electronic device 1000 includes but is not limited to: a radio frequency unit 1001 , a network module 1002 , an audio output unit 1003 , an input unit 1004 , a sensor 1005 , a display unit 1006 , a user input unit 1007 , an interface unit 1008 , and a memory 1009 , the processor 1010 and other components.
  • the electronic device 1000 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 1010 through a power management system, so that the power management system can manage charging, discharging, and power functions. consumption management and other functions.
  • a power source such as a battery
  • the structure of the electronic device shown in FIG. 9 does not constitute a limitation to the electronic device.
  • the electronic device may include more or less components than the one shown, or combine some components, or arrange different components, which will not be repeated here. .
  • the processor 1010 is used for obtaining the first feature vector, the first feature vector is used to reflect the first feature information of the first application program, and the first application program is the application program running in the target time period associated in the historical record; Obtain a second feature vector, where the second feature vector is used to represent the second power consumption feature information associated with the start time of the target period; according to the first feature vector and the second feature vector, determine the average value of the electronic device 1000 within the target period Power consumption speed; output power prompt information according to the target period and average power consumption speed.
  • the first application running in the target period associated in the historical record is obtained, and the An application program may be the first application program recorded in the history record that the user uses more frequently in the target period, so as to obtain the first feature vector corresponding to the first application program.
  • the second feature vector is obtained.
  • the second power consumption feature information embodied by the second feature vector is associated with the start time of the target period, and the start moment of the target period (such as the current moment) is associated with the actual operation of the user and the actual environment.
  • the second power consumption The feature information is information generated based on the actual operation of the device by the user and the actual environment in which it is located.
  • the second power consumption feature information includes some information related to real-time power consumption, such as battery power information at the start of the target period, the temperature of the environment where it is located, and the like. Then, the two sets of feature vectors are integrated, and the average power consumption speed in the target period is calculated through the pre-trained regression tree model. Finally, according to the target period and the average power consumption speed, the battery power usage in the target period is predicted.
  • this embodiment not only combines the user's historical usage habits, but also considers the user's actual operating conditions and the environment in which he is located, thus combining the man-made, environmental and other variable factors in the actual operation to improve the predicted battery power. Usage accuracy.
  • the second power consumption characteristic information includes at least the first battery power information at the start time of the target time period
  • the processor 1010 is further configured to determine, according to the first battery power information and the average power consumption speed, the first battery power level at the end time of the target time period.
  • Second battery power information when the second battery power information is less than or equal to zero, output power prompt information according to all time periods from the current time to the end time of the target time period and the average power consumption rate corresponding to each time period.
  • the processor 1010 is further configured to output an estimated power consumption curve of the electronic device 1000, or output an estimated remaining usage time of the electronic device 1000.
  • the processor 1010 is further configured to record feature information of each application program, and the feature information includes at least identification information, usage time information, usage duration information and usage location information; Applications that run in each time period and meet the preset conditions; through the vectorization model, the application programs that run in each time period and meet the preset conditions are mapped to a vector space; and the first feature vector of the first application program that satisfies the preset condition.
  • the processor 1010 is further configured to acquire second power consumption feature information; generate a second feature vector corresponding to the second power consumption feature information according to the second power consumption feature information; wherein the second power consumption feature information Including first battery power information, time information, target location information, network status information, device power consumption duration information and device power consumption speed information, and first battery power information, time information, target position information, network status information, device power consumption information Both the power duration information and the device power consumption speed information are associated with the start time of the target period.
  • the input unit 1004 may include a graphics processor (Graphics Processing Unit, GPU) 10041 and a microphone 10042. Such as camera) to obtain still pictures or video image data for processing.
  • the display unit 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 1007 includes a touch panel 10071 and other input devices 10072 .
  • the touch panel 10071 is also called a touch screen.
  • the touch panel 10071 may include two parts, a touch detection device and a touch controller.
  • Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.
  • Memory 1009 may be used to store software programs as well as various data, including but not limited to application programs and operating systems.
  • the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the like, and the modem processor mainly processes wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 1010.
  • the embodiments of the present application further provide a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, each process of any of the foregoing prompting method embodiments is implemented, and can To achieve the same technical effect, in order to avoid repetition, details are not repeated here.
  • the processor is the processor in the electronic device described in the foregoing embodiments.
  • the readable storage medium includes a computer-readable storage medium, and examples of the computer-readable storage medium include non-transitory computer-readable storage media, such as computer read-only memory (Read-Only Memory, ROM), random access memory ( Random Access Memory, RAM), disk or CD, etc.
  • An embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or an instruction to implement any of the above prompting methods In order to avoid repetition, the details are not repeated here.
  • the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip, or the like.
  • processors may be, but are not limited to, general purpose processors, special purpose processors, application specific processors, or field programmable logic circuits. It will also be understood that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can also be implemented by special purpose hardware for performing the specified functions or actions, or by special purpose hardware and/or A combination of computer instructions is implemented.
  • the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation.
  • the technical solution of the present application can be embodied in the form of a software product in essence or in a part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of this application.
  • a storage medium such as ROM/RAM, magnetic disk, CD-ROM

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Power Sources (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

一种提示方法及电子设备，属于电子技术领域，所述提示方法包括：获取第一特征向量，第一特征向量用于体现第一应用程序的第一特征信息，且第一应用程序为历史记录中关联的目标时段内运行的应用程序（S1）；获取第二特征向量，第二特征向量用于体现与目标时段的开始时刻相关联的第二耗电特征信息（S2）；根据第一特征向量和第二特征向量，确定电子设备在目标时段内的平均耗电速度（S3）；根据目标时段和平均耗电速度，输出电量提示信息（S4）。

Description

提示方法和电子设备
相关申请的交叉引用
本申请主张2021年1月28日在中国提交的中国专利申请号202110120865.1的优先权，其全部内容通过引用包含于此。
技术领域
本申请属于电子技术领域，具体涉及一种提示方法和电子设备。
背景技术
随着电子技术的发展，手机等电子设备逐渐成为人们生活的一部分。在日常生活中，用户需要使用电子设备进行导航、支付、通信、娱乐等，从而导致电子设备的耗电速度也逐渐加快。特别是在一些不方便充电的场景中，用户需实时关注电子设备的电池电量或者被迫减少使用，以避免因电池电量意外耗尽而带来损失。
为了避免因电池电量意外耗尽而带来损失，可通过预测电池电量的使用情况，来让用户更直观地了解剩余电池电量。在相关技术中，依据电压和电流，或者依据电子设备的历史平均耗电情况，来预测电池电量的使用情况。
可见，在相关技术中，因没有考虑到人为、环境等多方面可变化因素的干扰，导致预测电池电量使用情况的准确率较低。
发明内容
本申请实施例的目的是提供一种提示方法，能够解决在相关技术中，因没有考虑到人为、环境等多方面可变化因素的干扰，导致预测电池电量使用情况的准确率较低的问题。
第一方面，本申请实施例提供了一种提示方法，该方法包括：获取第一特 征向量，第一特征向量用于体现第一应用程序的第一特征信息，且第一应用程序为历史记录中关联的目标时段内运行的应用程序；获取第二特征向量，第二特征向量用于体现与目标时段的开始时刻相关联的第二耗电特征信息；根据第一特征向量和第二特征向量，确定电子设备在目标时段内的平均耗电速度；根据目标时段和平均耗电速度，输出电量提示信息。
第二方面，本申请实施例提供了一种电子设备，该设备包括第一获取模块，用于获取第一特征向量，第一特征向量用于体现第一应用程序的第一特征信息，且第一应用程序为历史记录中关联的目标时段内运行的应用程序；第二获取模块，用于获取第二特征向量，第二特征向量用于体现与目标时段的开始时刻相关联的第二耗电特征信息；耗电速度确定模块，用于根据第一特征向量和第二特征向量，确定电子设备在目标时段内的平均耗电速度；提示模块，用于根据目标时段和平均耗电速度，输出电量提示信息。
第三方面，本申请实施例提供了一种电子设备，该电子设备包括处理器、存储器及存储在存储器上并可在处理器上运行的程序或指令，程序或指令被处理器执行时实现如第一方面的方法的步骤。
第四方面，本申请实施例提供了一种可读存储介质，可读存储介质上存储程序或指令，程序或指令被处理器执行时实现如第一方面的方法的步骤。
第五方面，本申请实施例提供了一种芯片，芯片包括处理器和通信接口，通信接口和处理器耦合，处理器用于运行程序或指令，实现如第一方面的方法。
这样，在本申请的实施例中，对目标时段的电池电量的使用情况进行预测时，一方面，基于用户的历史使用习惯，获取历史记录中关联的目标时段内运行的第一应用程序，第一应用程序可以是历史记录中记录的用户在目标时段内使用较为频繁的第一应用程序，从而获取第一应用程序对应的第一特征向量。另一方面，获取第二特征向量。第二特征向量所体现的第二耗电特征信息，与目标时段的开始时刻相关联，而目标时段的开始时刻(如当前时刻)与用户实际操作、实际环境相关联，因此，第二耗电特征信息是基于用户对设备的实际操作、以及所处实际环境而产生的信息。例如第二耗电特征信息包括目标时段 开始时刻的电池电量信息、所处环境的温度等与实时耗电相关的一些信息。然后，整合两组特征向量，通过预先训练的回归树模型，计算出目标时段内的平均耗电速度。最后，根据目标时段，以及平均耗电速度，预测出目标时段的电池电量的使用情况。进一步地，将当前时刻至电量耗尽时刻之间的时段，划分为多个时段，重复上述过程，可预测出所有时段内的电池电量的使用情况，从而完成对电池电量的使用情况的预测。可见，本实施例在结合用户的历史使用习惯的同时，还考虑了用户实际操作情况和所处环境情况，从而结合了实际操作中的人为、环境等多方面可变化因素，提高了预测电池电量使用情况的准确率。
附图说明
图1是本申请的提示方法的实施例的流程示意图；
图2～图6是本申请实施例的提示方法中涉及的数据说明示意图；
图7是本申请实施例的电子设备的框图；
图8是本申请实施例的电子设备的硬件结构示意图之一；
图9是本申请实施例的电子设备的硬件结构示意图之二。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象，而不用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施，且“第一”、“第二”等所区分的对象通常为一类，并不限定对象的个数，例如第一对象可以是一个，也可以是多个。此外，说明书 以及权利要求中“和/或”表示所连接对象的至少其中之一，字符“/”，一般表示前后关联对象是一种“或”的关系。
下面结合附图，通过具体的实施例及其应用场景对本申请实施例提供的提示方法进行详细地说明。
图1示出了本申请一个实施例的提示方法的流程图，应用于电子设备，如图1所示，该提示方法包括步骤S1-步骤S4：
步骤S1：获取第一特征向量。
其中，第一特征向量用于体现第一应用程序的第一特征信息，且第一应用程序为历史记录中关联的目标时段内运行的应用程序。
可选地，本实施例应用于对电池电量的使用情况的预测场景中，因此，目标时段可以是：从当前时刻至电量耗尽时刻的时间段内的任意时段。
其中，电量耗尽时刻为预测出来的时刻。
可参考地，从当前时刻至电量耗尽时刻，可划分出一个或者多个时段，每个时段均可作为本实施例中的目标时段。
示例性地，可按照时间间隔T来划分出一个或者多个时段。
参见图2，例如，t1表示当前时刻，以时间间隔T为单位，至少划分出t1～t2、t2～t3等时段，每个时段均可作为本实施例的目标时段。
对应地，在该步骤中，可在历史记录中，获取目标时段内运行的应用程序，作为第一应用程序，从而获取第一应用程序的第一特征向量。
可选地，目标时段内运行的第一应用程序，可以是用户在目标时段内使用频繁的应用程序。
其中，该步骤中的目标时段内，用户使用频繁的第一应用程序，可体现出用户的历史使用习惯，从而使得本实施例可结合用户的历史使用习惯来预测电池电量的使用情况。
步骤S2：获取第二特征向量。
其中，第二特征向量用于体现与目标时段的开始时刻相关联的第二耗电特征信息。
在该步骤中，第二耗电特征信息与目标时段的开始时刻相关联，而目标时段的开始时刻的耗电情况至少可体现出用户对设备的实际操作情况，从而使得本实施例可结合用户对设备的实际操作来预测电池电量的使用情况。
可参考地，第二耗电特征信息包括：基于目标时段的开始时刻，在电子设备中产生与实时耗电相关的信息。
其中，第二耗电特征信息包括如电量、耗电速度、处理器占用率等与用户操作直接关联的信息；第二耗电特征信息还可以包括如网络类型、信号强度、时间、地理位置、温度等与环境相关的信息。基于以上列举的信息，可以看出第二耗电特征信息至少包括设备状态信息和环境状态信息。
因此，第二耗电特征信息还可体现出当前存在环境因素，从而使得本实施例还可结合实时的环境因素来预测电池电量的使用情况。
例如，在目标时段的开始时刻，网络信号不佳，设备响应服务器较慢，因此耗电加快，从而可在第二耗电特征信息中的耗电速度中体现。
又如，用户在每天下午两点到三点的时段，通常处于休息状态，电子设备中运行的应用程序较少，耗电速度较慢。而某一天的下午两点到三点的时段，用户没有休息，而是使用视频软件观看影视剧，用户的这一操作导致耗电加快，从而在待预测的目标时段的开始时刻，计算的瞬时耗电速度可以体现出用户的这一操作。因此，在第二耗电特征信息中包括瞬时耗电速度的情况下，第二耗电特征信息可体现出用户的实时操作。
其中，目标时段的开始时刻不早于当前时刻。
步骤S3：根据第一特征向量和第二特征向量，确定电子设备在目标时段内的平均耗电速度。
可选地，预设的处理方式为预先训练的回归树模型。
对应地，在该步骤中，将第一特征向量和第二特征向量输入回归树模型，从而基于回归树模型，计算得到电子设备在目标时段内的平均耗电速度。
在本实施例中，首先将用于体现用户的历史使用习惯的数据，以及用于体现用户实际操作的数据、环境数据，均以统一的特征向量的形式表现出来，再 统一整合后输入回归树模型中，从而通过向量的输入，以及模型的计算，得到目标时段内的平均耗电速度。
可选地，回归树模型如，渐进梯度回归树(Gradient BoostRegression Tree，GBRT)、极端梯度提升(eXtreme Gradient Boosting，XgBoos)、轻度梯度提升机(Light Gradient Boosting Machine，LightGBM)等。
结合图2，具体地，首先由步骤S1获取t1～t2时段的第一特征向量，以及由步骤S2获取t1～t2时段的第二特征向量，然后将这两组特征向量整合后输入到回归树模型中，则可预测出t1～t2时段内的平均耗电速度v1。
步骤S4：根据目标时段和平均耗电速度，输出电量提示信息。
在该步骤中，可预测出至少一个时段的耗电情况，以输出提示消息，供用户参考。
进一步地，为了提高预测结果的准确性，本实施例中的步骤S1～步骤S3，可以是循环重复执行的步骤，从而从当前时刻开始，依次预测出未来每个时段的平均耗电速度，从而截止电量耗尽时刻，可预测出期间所有时段的耗电情况，以输出提示消息，供用户参考。
其中，电量耗尽时刻为预测出来的时刻。
这样，在本申请的实施例中，对目标时段的电池电量的使用情况进行预测时，一方面，基于用户的历史使用习惯，获取历史记录中关联的目标时段内运行的第一应用程序，第一应用程序可以是历史记录中记录的用户在目标时段内使用较为频繁的第一应用程序，从而获取第一应用程序对应的第一特征向量。另一方面，获取第二特征向量。第二特征向量所体现的第二耗电特征信息，与目标时段的开始时刻相关联，而目标时段的开始时刻(如当前时刻)与用户实际操作、实际环境相关联，因此，第二耗电特征信息是基于用户对设备的实际操作、以及所处实际环境而产生的信息。例如第二耗电特征信息包括目标时段开始时刻的电池电量信息、所处环境的温度等与实时耗电相关的一些信息。然后，整合两组特征向量，并通过预先训练的回归树模型，计算出目标时段内的平均耗电速度。最后，根据目标时段，以及平均耗电速度，预测出目标时段的 电池电量的使用情况。进一步地，将当前时刻至电量耗尽时刻之间的时段，划分为多个时段，重复上述过程，可预测出所有时段内的电池电量的使用情况，从而完成对电池电量的使用情况的预测。可见，本实施例在结合用户的历史使用习惯的同时，还考虑了用户实际操作情况和所处环境情况，从而结合了实际操作中的人为、环境等多方面可变化因素，提高了预测电池电量使用情况的准确率。
在本申请另一个实施例的提示方法的流程中，第二耗电特征信息至少包括目标时段的开始时刻的第一电池电量信息，步骤S4，包括子步骤A1和子步骤A2：
子步骤A1：根据第一电池电量信息和平均耗电速度，确定目标时段的结束时刻的第二电池电量信息。
结合图2，例如，由平均耗电速度v1，可以预测出目标时段的结束时刻，即下一个待预测时段的开始时刻t2的电池电量为x1-v1*T。其中，x1表示第一电池电量信息，即目标时段的开始时刻t1的电池电量。
子步骤A2：在第二电池电量信息小于或者等于零的情况下，根据当前时刻至目标时段的结束时刻之内的所有时段，以及每个时段对应的平均耗电速度，输出电量提示信息。
在该步骤中，若目标时段的结束时刻的第二电池电量信息小于或者等于零，则说明在预测结果中，在目标时段的结束时刻时，电池电量已耗尽。因此，完成本次对电池电量的使用情况的预测。
进一步地，在一次对电池电量的使用情况的预测中，从当前时刻至目标时段的结束时刻，预测过的所有时段的总和，即预测出来电池电量预计可使用的时段。
因此，将预测过的所有时段，结合每个时段对应得到的平均耗电速度，进行分析，输出电量提示信息。
可参考地，在当前的t1时刻进行电池电量的使用情况的预测。参见图3所示的表格。
首先，将t1～t2作为目标时段，根据t1～t2的第一特征向量和第二特征向量，得到t1～t2的预测结果。其中，第一行数据表示t1时刻的第二耗电特征信息和t1～t2的第一特征向量。
然后，将t2～t3作为目标时段，将预测出来的t2时刻关联的耗电特征信息作为t2～t3的第二特征向量，同时获取t2～t3对应的第一特征向量，得到t2～t3的预测结果。其中，第二行数据表示t2时刻的第二耗电特征信息和t2～t3的第一特征向量。
以此类推，直至预测出来的某一时段的结束时刻的电池电量为零，完成本次预测。
可见，图3所示表格中的数据，都将用于在t1时刻对电池电量的预测。
进一步地，在t1时刻对电池电量的预测结束后，在下一时刻，可重新预测，从而实时更新预测结果，以提高预测结果的准确性。
在本实施例中，提供一种重复执行步骤S1～步骤S3的预测过程，以得到最终的预测结果。首先，基于当前待预测的目标时段，执行步骤S1～步骤S3，得到目标时段的平均耗电速度v1，并可以得到相邻下一时段的耗电函数x1-v1*T。进一步地，重复执行步骤，将与目标时段相邻的下一时段作为待预测时段，得到用户在该时段的历史应用程序，以及该时段开始时刻相关的耗电特征信息，并更新对应的特征向量，将更新得到的特征向量输入到回归树模型中即可得到该时段的平均耗电速度v2，以及该时段相邻的下一时段的耗电函数。重复以上步骤，更新特征向量，并将特征向量输入到回归树模型，得到耗电速度，以及相邻下一时段的耗电函数。如此循环步骤，直到电池电量为零，结束本次预测，从而可基于当前时刻得到剩余电池电量未来的使用情况。可见，本实施例采用分时段预测的方法，分别考虑了每个时段关联的用户历史使用习惯和环境影响，而且每个时段均关联于当前时刻的用户实际操作以及当前时刻的所处环境，从而进一步提高对电池电量的使用情况预测的准确率。
在本申请另一个实施例的提示方法的流程中，步骤S4，至少包括以下任一项：
子步骤B1：输出电子设备的预计耗电曲线图。
在该步骤中，输出的电量提示信息可以是电子设备的预计耗电曲线图的形式。
可参考地，电子设备的预计耗电曲线图的横坐标表示时间，电子设备的预计耗电曲线图的纵坐标表示电池电量。
在本实施例的一种方案中，通过曲线图的形式展示预测出来的电池电量的使用情况，从而从视觉的角度考虑，提供了一种直观的提示方法。
子步骤B2：输出电子设备的预计剩余使用时长。
在该步骤中，输出的电量提示信息可以是电子设备的预计剩余使用时长的形式。
可参考地，在预测出来某一时段的结束时刻的电池电量小于或者等于零的情况下，将预测过的所有时段相加，得到电子设备的预计剩余使用时长。
在本实施例的另一种方案中，通过预计可用时长的形式展示预测出来的电池电量的使用情况，从而从时间的角度考虑，提供了一种直观的提示方法。
另外，本实施例提供的两种方案可单一实现，也可结合实现。
在本实施例中，提供了两种输出提示信息的方法。一种是以曲线图的形式输出，从而便于用户直观看到预测出来的耗电走势，进而用户可根据曲线图调整对电子设备的实际使用情况；另一种是以剩余可用时长的形式输出，从而便于用户直观看到预测出来的电量耗尽的时刻，进而用户可以根据剩余可用时长，合理安排充电计划、使用计划等。
在本申请另一个实施例的提示方法的流程中，在步骤S1之前，还包括步骤C1-步骤C3：
步骤C1：记录各个应用程序的特征信息。
其中，特征信息至少包括识别信息、使用时间信息、使用时长信息和使用位置信息。
在该步骤中，其目的在于：收集用户的应用历史使用数据。
可选地，识别信息包括应用名称，使用时间信息包括时间、时长，使用位 置信息包括地理位置。
示例性地，记录用户每次使用应用程序的应用名称、时间、时长和地理位置等信息，按时间顺序存入本地数据库，保证用户隐私和数据安全。对一些使用时间较短的应用程序进行剔除，减少数据存储的规模，提高后续习惯挖掘的检索速度。
步骤C2：根据记录的各个应用程序的特征信息，确定在各个时段内运行、且满足预设条件的应用程序。
在该步骤中，其目的在于：挖掘用户的历史使用习惯。
在本实施例中，考虑到用户很难以准确的时间点为单位，来形成使用习惯，因此以准确的时间点挖掘用户的历史使用习惯较难，从而以模糊的时间段为单位，挖掘用户的历史使用习惯。
可选地，根据用户的日常作息规律来划分出多个时段。例如，在下表1中，划分出多个时间范围，每个时间范围作为一个时段。
时段名称 时间范围
早餐 7：00～9：00
上午 9：00～12：00
午饭 12：00～14：00
下午 14：00～18：00
晚餐 18：00～20：00
晚上 20：00～23：00
深夜 23：00～(第二天)2：00
睡眠 2：00～7：00
表1
进一步地，通过检索前述记录用户历史使用习惯的本地数据库，在限定的一段日期内，可以挖掘到用户每天在某个时段内使用的、满足预设条件的应用程序。
可选地，预设条件为：使用的频繁程度大于预设程度。即，满足预设条件的应用程序为每天在某个时段内的使用较为频繁的应用程序。
可参考地，频繁应用的挖掘方式主要有以下两种：
方式一：基于频繁模式树(Frequent PatternTree，FP-Growth)或关联规则算法(Apriori)的频繁模式挖掘，把一段日期内相同时段内应用程序的使用记录作为一个事务数据库，通过迭代生成满足条件的更大频繁项来建立频繁集项，最终输出每个时段的频繁使用的应用程序。
方式二：基于统计的挖掘，统计一段日期内相同时段内的应用程序的使用记录，由应用程序出现的频次和使用时长来赋予权重，统计上述记录中权重较大的应用程序即为输出的频繁使用的应用程序。
在更多的实施例中，还可根据记录的各个应用程序的使用位置信息，确定在各个位置运行、且满足预设条件的应用程序。
进一步地，在预测场景中，可获取历史数据中，在当前位置运行、且满足预设条件的应用程序。
步骤C3：将在各个时段内运行、且满足预设条件的应用程序映射至一个向量空间。
该步骤中的目的在于，将获取的用户的历史使用习惯的数据向量化。
通常，应用程序和耗电情况是强相关的，不同种类的应用程序的耗电情况差别很大，比如游戏类和通讯类，二者的耗电情况差别很大。同类型的应用程序的耗电情况(如耗电速度)是相似的。为了刻画这种相对关系，使用了应用程序向量化模型，将所有应用程序映射到一个向量空间，实现了同类应用相近，不同类应用较远。
示例性地，任意应用程序的特征向量可以表示为：X i＝{x i1，x i2，x i3...x im}。
而基于上述向量的表示方法，可以表现出同类应用相近，不同类应用较远的向量关系。
对应地，步骤S1，包括：
子步骤C4：基于向量空间，获取目标时段内运行、且满足预设条件的第一应用程序的第一特征向量。
第一应用程序，即挖掘到用户每天在目标时段内的使用较为频繁的应用程序。
其中，第一特征向量可以是一个应用程序的向量，还可以是多个应用程序的向量集合。
例如，基于某时段，第一特征向量中集合了n个应用程序，因此，第一特征向量可由向量相加而来，表示为：X＝{x 1，x 2，x 3...x m}＝X 1+X 2+X 3+…+X n。
在本实施例中，在用户的使用过程中，实时记录用户的历史使用习惯，记录的历史使用习惯包括但不限于：应用程序的名称、使用时长、使用时间、使用位置等，从而可基于用户的作息时间，得到各个时段用户使用较为频繁的应用程序，进而将获取的各个时段用户使用较为频繁的应用程序，通过特征向量的方式统一化。在预测目标时段的电池电量的使用情况时，可在记录的历史使用习惯中，确定目标时段使用频繁的第一应用程序的第一特征向量，以输入回归树模型中。其中，第一特征向量可体现出第一应用程序的特征，从而输入回归树模型中，可体现出第一应用程序的耗电情况，使得本实施例可根据用户的历史使用习惯，预测出电池电量的使用情况，且各个时段的预测对应各个时段的使用习惯，使得预测的准确性较高。
在本申请另一个实施例的提示方法的流程中，在步骤S2之前，还包括步骤D1和步骤D2：
步骤D1：获取第二耗电特征信息。
其中，第二耗电特征信息包括电池电量信息、时间信息、目标位置信息、网络状态信息、设备耗电时长信息和设备耗电速度信息，且第一电池电量信息、时间信息、目标位置信息、网络状态信息、设备耗电时长信息和设备耗电速度信息均关联于目标时段的开始时刻。
通常，用户的行为具有随机性，比如某个用户下午2点的时候在使用聊天软件进行聊天，3点的时候用户突然就想打开视频软件观看电视剧。如果在这种情况下，仅依靠历史习惯挖掘出来的那些应用程序，然后再依据这些应用程序的历史耗电情况进行预测，那就会和用户的实际使用情况有很大差别，最终预测出的剩余电量使用时间也是不准确的。所以不仅要根据用户的历史习惯，也要融合电子设备中实时的耗电特征信息，以结合用户操作和环境因素，动态 调整预测结果。
因此，在该步骤中，基于待预测的目标时段，获取与目标时段的开始时刻关联的第二耗电特征信息。
在一个实施例中，电池电量信息为目标时段的开始时刻的电池电量信息。可选地，将其处理成以下的特征：电量百分比。
可选地，在目标时段的开始时刻为当前时刻的情况下，通过电子设备的操作系统的接口获取到当前时刻的电量，作为电池电量信息；在目标时段的开始时刻非当前时刻的情况下，可基于当前时刻的电量，预测出目标时段的开始时刻的电量，作为电池电量信息。
在一个实施例中，时间信息包括目标时段的开始时刻的时间信息。可选地，将其处理成以下的特征：星期几、相对于当天0点00分的分钟数。
可选地，在目标时段的开始时刻为当前时刻的情况下，通过电子设备的操作系统的接口获取到当前时刻，作为时间信息；在目标时段的开始时刻非当前时刻的情况下，可基于当前时刻，推算出目标时段的开始时刻，作为时间信息。
在一个实施例中，目标位置信息和网络状态信息包括目标时段的开始时刻的目标位置信息和网络状态信息。
可选地，根据用户历史地理位置信息使用具有噪声的基于密度的聚类方法(Density-Based Spatial Clustering of Applications with Noise，DB-SCAN)等聚类的方法设置地理围栏为1km，即可得到用户的一些常驻地，将这些常住地标记为：家里1，常住地2，常住地3等，即得到地理位置标签，作为位置信息，以在特征处理时为方便计算，处理为1、2、3…等类别标签。
可选地，在目标时段的开始时刻为当前时刻的情况下，通过电子设备的操作系统的接口获取到当前时刻的地理位置和网络状态，作为目标位置信息和网络状态信息；在目标时段的开始时刻非当前时刻的情况下，可将当前时刻的地理位置和网络状态，作为目标位置信息和网络状态信息。
在一个实施例中，设备耗电时长信息包括目标时段的开始时刻至最近满电时刻的设备耗电时长信息。可选地，将其处理成以下的特征：相对于满电(100％ 电量)时刻的时长。
在一个实施例中，目标时段的开始时刻为当前时刻。
在电子设备从充满电开始就再未连接过电源适配器进行充电的情况下，可以检索出最近的满电状态对应的t 100时刻，结合当前的t 1时刻，得到相对于满电时刻的时长为t 1-t 100。
在电子设备从充满电之后，消耗电量又继续充电的情况下，按时间正序查询的视图中从当前是t 1时刻的电量x 1开始，向前查找比当前电量高的最近的电量下降序列seq 1＝{(t k，x k)，(t k-1，x k-1)，(t k-2，x k-2)，...(t 1，x 1)}，再向前查找比t k时刻电量x k高的最近的电量下降序列seq2＝{(t k+p，x k+p)，(t k+p-1，x k+p-1)，(t k+p-2，x k+p-2)，...(t k+1，x k+1)}，重复以上步骤直至查询到100％电量为止，得到所有序列seq 1、seq 2、seq 3、...seq m(图4所示)，然后将这些序列头尾拼接，减去间隔时间，即可得到从满电状态对应的t 100时刻到当前的t 1时刻的单调下降的完整耗电序列(图5所示)，则相对于满电的时间为t 1-t 100。
在另一个实施例中，目标时段的开始时刻非当前时刻，可基于当前时刻，以及当前时刻相对于满电时刻的时长，确定目标时段的开始时刻相对于满电时刻的时长，作为设备耗电时长信息。
在一个实施例中，设备耗电速度信息包括目标时段的开始时刻的瞬时耗电速度和长时耗电速度。
在一个实施例中，目标时段的开始时刻为当前时刻。
瞬时耗电速度用于表征电子设备当前的耗电速度，当前时刻为电量为x 1，5分钟之前的电量为x 2，则瞬时耗电速度可表示为(x 2-x 1)/5。
长时耗电速度用于表征电子设备在最近一段时间内的平均耗电速度，当前的t 1时刻为电量为x 1，与设备耗电时长信息的计算步骤类似，得到满电时刻到当前时刻的单调下降序列，即可得到从满电时刻到当前时刻的耗电时间间隔t，则长时耗电速度可表示为(100-x 1)/t。
在另一个实施例中，目标时段的开始时刻非当前时刻，可基于当前时刻的 电子设备耗电速度信息，结合目标时段与当前时刻的关系，得到电子设备耗电速度信息。
进一步地，参见图3，示出了一次预测过程中，与各个时段对应的第二耗电特征信息，以及每个时段对应的第一特征向量。
步骤D2：根据第二耗电特征信息，生成与第二耗电特征信息对应的第二特征向量。
将每个时段获取对应的第二耗电特征信息，按照预设规则，进行向量化，生成与每个时段对应的第二特征向量。
示例性地，首先检索历史使用习惯的应用程序，再将这些应用程序向量化，然后将获取到的第二耗电特征信息向量化，将向量化的应用序列和耗电特征连接在一起形成特征向量。参见图6，示出了某一时段，第一特征向量和第二特征向量一起形成的特征向量。
在本实施例中，基于待预测的目标时段，可结合目标时段的开始时刻，获取电子设备中产生的第二耗电特征信息，第二耗电特征信息包括但不限于本实施例所述以上具体特征信息。进一步地，为了将第二耗电特征信息输入回归树模型中进行计算，将获取的特征数据，进行向量化，再与对应时段的第一特征向量整合在在一起，形成待输入的特征向量，以使得对目标时段的电池电量的使用情况的预测可顺利完成。
综上，在本申请的实施例中，除了考虑到用户日常使用电子设备的习惯对耗电造成的影响；还考虑到用户使用电子设备的行为时刻都在发生变化，电子设备所处的环境时刻都在发生变化，预测的结果不是一成不变的这一现象。因此，本实施例可动态地随用户的实际使用情况、以及环境情况，来预测未来电量变化情况。
可见，本申请的实施例通过用户日常的使用习惯、当前的实时设备状态，以及当前的实时环境状态，预测用户剩余电量未来的使用情况，可以实时为用户提供一个动态的剩余电量使用时间。
需要说明的是，本申请实施例提供的提示方法，执行主体可以为电子设备， 或者该电子设备中的用于执行提示方法的控制模块。本申请实施例中以电子设备执行提示方法为例，说明本申请实施例提供的提示方法的电子设备。
图7示出了本申请实施例的电子设备的框图，如图7所示，包括：
第一获取模块10，用于获取第一特征向量，第一特征向量用于体现第一应用程序的第一特征信息，且第一应用程序为历史记录中关联的目标时段内运行的应用程序；
第二获取模块20，用于获取第二特征向量，第二特征向量用于体现与目标时段的开始时刻相关联的第二耗电特征信息；
耗电速度确定模块30，用于根据第一特征向量和第二特征向量，确定电子设备在所述目标时段内的平均耗电速度；
提示模块40，用于根据目标时段和平均耗电速度，输出电量提示信息。
这样，在本申请的实施例中，对目标时段的电池电量的使用情况进行预测时，一方面，基于用户的历史使用习惯，获取历史记录中关联的目标时段内运行的第一应用程序，第一应用程序可以是历史记录中记录的用户在目标时段内使用较为频繁的第一应用程序，从而获取第一应用程序对应的第一特征向量。另一方面，获取第二特征向量。第二特征向量所体现的第二耗电特征信息，与目标时段的开始时刻相关联，而目标时段的开始时刻(如当前时刻)与用户实际操作、实际环境相关联，因此，第二耗电特征信息是基于用户对设备的实际操作、以及所处实际环境而产生的信息。例如第二耗电特征信息包括目标时段开始时刻的电池电量信息、所处环境的温度等与实时耗电相关的一些信息。然后，整合两组特征向量，并通过预先训练的回归树模型，计算出目标时段内的平均耗电速度。最后，根据目标时段，以及平均耗电速度，预测出目标时段的电池电量的使用情况。进一步地，将当前时刻至电量耗尽时刻之间的时段，划分为多个时段，重复上述过程，可预测出所有时段内的电池电量的使用情况，从而完成对电池电量的使用情况的预测。可见，本实施例在结合用户的历史使用习惯的同时，还考虑了用户实际操作情况和所处环境情况，从而结合了实际操作中的人为、环境等多方面可变化因素，提高了预测电池电量使用情况的准 确率。
可选地，第二耗电特征信息至少包括目标时段的开始时刻的第一电池电量信息，提示模块40，包括：
电量信息确定单元，用于根据第一电池电量信息和平均耗电速度，确定目标时段的结束时刻的第二电池电量信息；
第一输出单元，用于在第二电池电量信息小于或者等于零的情况下，根据当前时刻至目标时段的结束时刻之内的所有时段，以及每个时段对应的平均耗电速度，输出电量提示信息。
可选地，提示模块40，至少包括以下任一项：
第二输出单元，用于输出电子设备的预计耗电曲线图；
第三输出单元，用于输出电子设备的预计剩余使用时长。
可选地，该设备还包括：
记录模块，用于记录各个应用程序的特征信息，特征信息至少包括识别信息、使用时间信息、使用时长信息和使用位置信息；
第一处理模块，用于根据记录的各个应用程序的特征信息，确定在各个时段内运行、且满足预设条件的应用程序；
第二处理模块，用于通过向量化模型，将在各个时段内运行、且满足预设条件的应用程序映射至一个向量空间；
第一获取模块10，包括：
向量获取单元，用于基于向量空间，获取目标时段内运行、且满足预设条件的第一应用程序的第一特征向量。
可选地，该设备还包括：
第三获取模块，用于获取第二耗电特征信息；
生成模块，用于根据第二耗电特征信息，生成与第二耗电特征信息对应的第二特征向量；
其中，第二耗电特征信息包括电池电量信息、时间信息、目标位置信息、网络状态信息、设备耗电时长信息和设备耗电速度信息，且电池电量信息、时 间信息、目标位置信息、网络状态信息、设备耗电时长信息和设备耗电速度信息均关联于目标时段的开始时刻。
本申请实施例中的电子设备可以是设备，也可以是终端中的部件、集成电路、或芯片。该设备可以是移动电子设备，也可以为非移动电子设备。示例性的，移动电子设备可以为手机、平板电脑、笔记本电脑、掌上电脑、车载电子设备、可穿戴设备、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本或者个人数字助理(personal digital assistant，PDA)等，非移动电子设备可以为服务器、网络附属存储器(Network Attached Storage，NAS)、个人计算机(personal computer，PC)、电视机(television，TV)、柜员机或者自助机等，本申请实施例不作具体限定。
本申请实施例中的电子设备可以为具有操作系统的设备。该操作系统可以为安卓(Android)操作系统，可以为ios操作系统，还可以为其他可能的操作系统，本申请实施例不作具体限定。
本申请实施例提供的电子设备能够实现上述方法实施例实现的各个过程，为避免重复，这里不再赘述。
可选地，图8为本申请实施例提供的电子设备的示例的硬件结构示意图，如图8所示，电子设备100包括处理器101，存储器102，存储在存储器102上并可在所述处理器101上运行的程序或指令，该程序或指令被处理器101执行时实现上述任一种提示方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
需要说明的是，本申请实施例中的电子设备包括上述所述的移动电子设备和非移动电子设备。
可选地，图9为本申请实施例提供的电子设备的另一示例的硬件结构示意图。
如图9所示，该电子设备1000包括但不限于：射频单元1001、网络模块1002、音频输出单元1003、输入单元1004、传感器1005、显示单元1006、用户输入单元1007、接口单元1008、存储器1009、处理器1010等部件。
本领域技术人员可以理解，电子设备1000还可以包括给各个部件供电的电源(比如电池)，电源可以通过电源管理系统与处理器1010逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。图9中示出的电子设备结构并不构成对电子设备的限定，电子设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置，在此不再赘述。
其中，处理器1010，用于获取第一特征向量，第一特征向量用于体现第一应用程序的第一特征信息，且第一应用程序为历史记录中关联的目标时段内运行的应用程序；获取第二特征向量，第二特征向量用于体现与目标时段的开始时刻相关联的第二耗电特征信息；根据第一特征向量和第二特征向量，确定电子设备1000在目标时段内的平均耗电速度；根据目标时段和平均耗电速度，输出电量提示信息。
这样，在本申请的实施例中，对目标时段的电池电量的使用情况进行预测时，一方面，基于用户的历史使用习惯，获取历史记录中关联的目标时段内运行的第一应用程序，第一应用程序可以是历史记录中记录的用户在目标时段内使用较为频繁的第一应用程序，从而获取第一应用程序对应的第一特征向量。另一方面，获取第二特征向量。第二特征向量所体现的第二耗电特征信息，与目标时段的开始时刻相关联，而目标时段的开始时刻(如当前时刻)与用户实际操作、实际环境相关联，因此，第二耗电特征信息是基于用户对设备的实际操作、以及所处实际环境而产生的信息。例如第二耗电特征信息包括目标时段开始时刻的电池电量信息、所处环境的温度等与实时耗电相关的一些信息。然后，整合两组特征向量，并通过预先训练的回归树模型，计算出目标时段内的平均耗电速度。最后，根据目标时段，以及平均耗电速度，预测出目标时段的电池电量的使用情况。进一步地，将当前时刻至电量耗尽时刻之间的时段，划分为多个时段，重复上述过程，可预测出所有时段内的电池电量的使用情况，从而完成对电池电量的使用情况的预测。可见，本实施例在结合用户的历史使用习惯的同时，还考虑了用户实际操作情况和所处环境情况，从而结合了实际操作中的人为、环境等多方面可变化因素，提高了预测电池电量使用情况的准 确率。
可选地，第二耗电特征信息至少包括目标时段的开始时刻的第一电池电量信息，处理器1010，还用于根据第一电池电量信息和平均耗电速度，确定目标时段的结束时刻的第二电池电量信息；在第二电池电量信息小于或者等于零的情况下，根据当前时刻至目标时段的结束时刻之内的所有时段，以及每个时段对应的平均耗电速度，输出电量提示信息。
可选地，处理器1010，还用于输出电子设备1000的预计耗电曲线图，或者输出电子设备1000的预计剩余使用时长。
可选地，处理器1010，还用于记录各个应用程序的特征信息，特征信息至少包括识别信息、使用时间信息、使用时长信息和使用位置信息；根据记录的各个应用程序的特征信息，确定在各个时段内运行、且满足预设条件的应用程序；通过向量化模型，将在各个时段内运行、且满足预设条件的应用程序映射至一个向量空间；基于向量空间，获取目标时段内运行、且满足预设条件的第一应用程序的第一特征向量。
可选地，处理器1010，还用于获取第二耗电特征信息；根据第二耗电特征信息，生成与第二耗电特征信息对应的第二特征向量；其中，第二耗电特征信息包括第一电池电量信息、时间信息、目标位置信息、网络状态信息、设备耗电时长信息和设备耗电速度信息，且第一电池电量信息、时间信息、目标位置信息、网络状态信息、设备耗电时长信息和设备耗电速度信息均关联于目标时段的开始时刻。
应理解的是，本申请实施例中，输入单元1004可以包括图形处理器(Graphics Processing Unit，GPU)10041和麦克风10042，图形处理器10041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元1006可包括显示面板10061，可以采用液晶显示器、有机发光二极管等形式来配置显示面板10061。用户输入单元1007包括触控面板10071以及其他输入设备10072。触控面板10071，也称为触摸屏。触控面板10071可包括触摸检测装置和触摸控制器两个部分。其他 输入设备10072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆，在此不再赘述。存储器1009可用于存储软件程序以及各种数据，包括但不限于应用程序和操作系统。处理器1010可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器1010中。
本申请实施例还提供一种可读存储介质，所述可读存储介质上存储有程序或指令，该程序或指令被处理器执行时实现上述任一种提示方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
其中，所述处理器为上述实施例中所述的电子设备中的处理器。所述可读存储介质，包括计算机可读存储介质，计算机可读存储介质的示例包括非暂态计算机可读存储介质，如计算机只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等。
本申请实施例另提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现上述任一种提示方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
应理解，本申请实施例提到的芯片还可以称为系统级芯片、系统芯片、芯片系统或片上系统芯片等。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外，需要指出的是，本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能，还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能，例如，可以按不 同于所描述的次序来执行所描述的方法，并且还可以添加、省去、或组合各种步骤。另外，参照某些示例所描述的特征可在其他示例中被组合。
上面参考根据本申请的实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本申请的各方面。应当理解，流程图和/或框图中的每个方框以及流程图和/或框图中各方框的组合可以由计算机程序指令实现。这些计算机程序指令可被提供给通用计算机、专用计算机、或其它可编程数据处理装置的处理器，以产生一种机器，使得经由计算机或其它可编程数据处理装置的处理器执行的这些指令使能对流程图和/或框图的一个或多个方框中指定的功能/动作的实现。这种处理器可以是但不限于是通用处理器、专用处理器、特殊应用处理器或者现场可编程逻辑电路。还可理解，框图和/或流程图中的每个方框以及框图和/或流程图中的方框的组合，也可以由执行指定的功能或动作的专用硬件来实现，或可由专用硬件和计算机指令的组合来实现。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述，但是本申请并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本申请的启示下，在不脱离本申请宗旨和权利要求所保护的范围情况下，还可做出很多形式，均属于本申请的保护之内。

Claims (15)

  1. 一种提示方法，包括：
    获取第一特征向量，所述第一特征向量用于体现第一应用程序的第一特征信息，且所述第一应用程序为历史记录中关联的目标时段内运行的应用程序；
    获取第二特征向量，所述第二特征向量用于体现与所述目标时段的开始时刻相关联的第二耗电特征信息；
    根据所述第一特征向量和所述第二特征向量，确定电子设备在所述目标时段内的平均耗电速度；
    根据所述目标时段和所述平均耗电速度，输出电量提示信息。
  2. 根据权利要求1所述的方法，其中，所述第二耗电特征信息至少包括所述目标时段的开始时刻的第一电池电量信息，所述根据所述目标时段和所述平均耗电速度，输出电量提示信息，包括：
    根据所述第一电池电量信息和所述平均耗电速度，确定所述目标时段的结束时刻的第二电池电量信息；
    在所述第二电池电量信息小于或者等于零的情况下，根据当前时刻至所述目标时段的结束时刻之内的所有时段，以及每个时段对应的平均耗电速度，输出电量提示信息。
  3. 根据权利要求1所述的方法，其中，所述输出电量提示信息，至少包括以下任一项：
    输出所述电子设备的预计耗电曲线图；
    输出所述电子设备的预计剩余使用时长。
  4. 根据权利要求1所述的方法，在所述获取第一特征向量之前，还包括：
    记录各个应用程序的特征信息，所述特征信息至少包括识别信息、使用时间信息、使用时长信息和使用位置信息；
    根据记录的各个应用程序的特征信息，确定在各个时段内运行、且满足预设条件的应用程序；
    通过向量化模型，将所述在各个时段内运行、且满足预设条件的应用程序 映射至一个向量空间；
    所述获取第一特征向量，包括：
    基于所述向量空间，获取所述目标时段内运行、且满足所述预设条件的第一应用程序的第一特征向量。
  5. 根据权利要求1所述的方法，在所述获取第二特征向量之前，还包括：
    获取第二耗电特征信息；
    根据所述第二耗电特征信息，生成与所述第二耗电特征信息对应的第二特征向量；
    其中，所述第二耗电特征信息包括第一电池电量信息、时间信息、目标位置信息、网络状态信息、电子设备耗电时长信息和电子设备耗电速度信息，且所述第一电池电量信息、所述时间信息、所述目标位置信息、所述网络状态信息、所述电子设备耗电时长信息和所述电子设备耗电速度信息均关联于所述目标时段的开始时刻。
  6. 一种电子设备，包括：
    第一获取模块，用于获取第一特征向量，所述第一特征向量用于体现第一应用程序的第一特征信息，且所述第一应用程序为历史记录中关联的目标时段内运行的应用程序；
    第二获取模块，用于获取第二特征向量，所述第二特征向量用于体现与所述目标时段的开始时刻相关联的第二耗电特征信息；
    耗电速度确定模块，用于根据所述第一特征向量和所述第二特征向量，确定所述电子设备在所述目标时段内的平均耗电速度；
    提示模块，用于根据所述目标时段和所述平均耗电速度，输出电量提示信息。
  7. 根据权利要求6所述的设备，其中，所述第二耗电特征信息至少包括所述目标时段的开始时刻的第一电池电量信息，所述提示模块，包括：
    电量信息确定单元，用于根据所述第一电池电量信息和所述平均耗电速度，确定所述目标时段的结束时刻的第二电池电量信息；
    第一输出单元，用于在所述第二电池电量信息小于或者等于零的情况下，根据当前时刻至所述目标时段的结束时刻之内的所有时段，以及每个时段对应的平均耗电速度，输出电量提示信息。
  8. 根据权利要求6所述的设备，其中，所述提示模块，至少包括以下任一项：
    第二输出单元，用于输出所述电子设备的预计耗电曲线图；
    第三输出单元，用于输出所述电子设备的预计剩余使用时长。
  9. 根据权利要求6所述的设备，还包括：
    记录模块，用于记录各个应用程序的特征信息；所述特征信息至少包括识别信息、使用时间信息、使用时长信息和使用位置信息；
    第一处理模块，用于根据记录的各个应用程序的特征信息，确定在各个时段内运行、且满足预设条件的应用程序；
    第二处理模块，用于通过向量化模型，将所述在各个时段内运行、且满足预设条件的应用程序映射至一个向量空间；
    所述第一获取模块，包括：
    向量获取单元，用于基于所述向量空间，获取所述目标时段内运行、且满足所述预设条件的第一应用程序的第一特征向量。
  10. 根据权利要求6所述的设备，还包括：
    第三获取模块，用于获取第二耗电特征信息；
    生成模块，用于根据所述第二耗电特征信息，生成与所述第二耗电特征信息对应的第二特征向量；
    其中，所述第二耗电特征信息包括电池电量信息、时间信息、目标位置信息、网络状态信息、设备耗电时长信息和设备耗电速度信息，且所述电池电量信息、所述时间信息、所述目标位置信息、所述网络状态信息、所述电子设备耗电时长信息和所述电子设备耗电速度信息均关联于所述目标时段的开始时刻。
  11. 一种电子设备，包括处理器，存储器及存储在所述存储器上并可在所 述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求1-5任一项所述的提示方法的步骤。
  12. 一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如权利要求1-5任一项所述的提示方法的步骤。
  13. 一种计算机程序产品，所述程序产品被存储在非易失的存储介质中，所述程序产品被至少一个处理器执行以实现如权利要求1-5任一项所述的提示方法的步骤。
  14. 一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如权利要求1-5任一项所述的提示方法的步骤。
  15. 一种电子设备，用于执行如权利要求1-5任一项所述的提示方法的步骤。
PCT/CN2022/073583 2021-01-28 2022-01-24 提示方法和电子设备 WO2022161325A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110120865.1 2021-01-28
CN202110120865.1A CN112764513A (zh) 2021-01-28 2021-01-28 提示方法和电子设备

Publications (1)

Publication Number Publication Date
WO2022161325A1 true WO2022161325A1 (zh) 2022-08-04

Family

ID=75706505

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/073583 WO2022161325A1 (zh) 2021-01-28 2022-01-24 提示方法和电子设备

Country Status (2)

Country Link
CN (1) CN112764513A (zh)
WO (1) WO2022161325A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117496677A (zh) * 2023-12-29 2024-02-02 深圳市明心数智科技有限公司 车辆实时预警方法及相关装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112764513A (zh) * 2021-01-28 2021-05-07 维沃移动通信有限公司 提示方法和电子设备
CN113220106B (zh) * 2021-05-10 2024-05-14 维沃移动通信有限公司 省电控制方法和省电控制装置
CN113873083A (zh) * 2021-09-24 2021-12-31 杭州逗酷软件科技有限公司 续航时长确定方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107370877A (zh) * 2017-06-30 2017-11-21 广东欧珀移动通信有限公司 应用程序的推送方法、装置、存储介质及电子设备
US20180188331A1 (en) * 2014-05-20 2018-07-05 Samsung Electronics Co., Ltd. Method for managing battery of electronic device and electronic device performing the same
CN108732502A (zh) * 2017-04-20 2018-11-02 深圳市理邦精密仪器股份有限公司 设备可使用的剩余时长的获取方法及装置
CN110554945A (zh) * 2018-06-01 2019-12-10 中兴通讯股份有限公司 一种电量控制方法、电子设备及计算机可读存储介质
CN112053011A (zh) * 2020-10-14 2020-12-08 腾讯科技（深圳）有限公司 电源优化管理方法、装置、电子设备和存储介质
CN112764513A (zh) * 2021-01-28 2021-05-07 维沃移动通信有限公司 提示方法和电子设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108810226A (zh) * 2018-06-22 2018-11-13 维沃移动通信有限公司 一种电量预警方法及移动终端
CN110022403A (zh) * 2019-03-06 2019-07-16 华为技术有限公司 终端充电提醒方法、装置、设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180188331A1 (en) * 2014-05-20 2018-07-05 Samsung Electronics Co., Ltd. Method for managing battery of electronic device and electronic device performing the same
CN108732502A (zh) * 2017-04-20 2018-11-02 深圳市理邦精密仪器股份有限公司 设备可使用的剩余时长的获取方法及装置
CN107370877A (zh) * 2017-06-30 2017-11-21 广东欧珀移动通信有限公司 应用程序的推送方法、装置、存储介质及电子设备
CN110554945A (zh) * 2018-06-01 2019-12-10 中兴通讯股份有限公司 一种电量控制方法、电子设备及计算机可读存储介质
CN112053011A (zh) * 2020-10-14 2020-12-08 腾讯科技（深圳）有限公司 电源优化管理方法、装置、电子设备和存储介质
CN112764513A (zh) * 2021-01-28 2021-05-07 维沃移动通信有限公司 提示方法和电子设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117496677A (zh) * 2023-12-29 2024-02-02 深圳市明心数智科技有限公司 车辆实时预警方法及相关装置
CN117496677B (zh) * 2023-12-29 2024-03-26 深圳市明心数智科技有限公司 车辆实时预警方法及相关装置

Also Published As

Publication number Publication date
CN112764513A (zh) 2021-05-07

Similar Documents

Publication Publication Date Title
WO2022161325A1 (zh) 提示方法和电子设备
EP3502880B1 (en) Method for preloading application, storage medium, and terminal device
US11481231B2 (en) Systems and methods for intelligent application instantiation
CN104520815B (zh) 一种任务调度的方法及装置
US10097973B2 (en) Systems and methods for proactively identifying and surfacing relevant content on a touch-sensitive device
KR102318884B1 (ko) 터치 감응형 디바이스 상의 관련 콘텐츠를 사전행동적으로 식별 및 표면화하기 위한 시스템 및 방법
US20150100621A1 (en) User Interface for a System Including Smart Phone and Smart Watch
US20130110992A1 (en) Electronic device management using interdomain profile-based inferences
CN108733825A (zh) 一种对象触发事件预测方法及装置
WO2019062418A1 (zh) 应用清理方法、装置、存储介质及电子设备
CN108965389A (zh) 用于展示信息的方法
US20150241519A1 (en) Method for managing power of electronic device and electronic device thereof
CN107943582B (zh) 特征处理方法、装置、存储介质及电子设备
CN107402808B (zh) 进程管理方法、装置、存储介质及电子设备
WO2017124874A1 (zh) 一种网络资源推荐方法及计算机设备
CN109587328B (zh) 消息管理方法和装置、存储介质及电子设备
CN107193718A (zh) 一种充电提醒方法、系统及终端设备
CN107748697B (zh) 应用关闭方法、装置、存储介质及电子设备
WO2019085754A1 (zh) 应用清理方法、装置、存储介质及电子设备
US9946427B1 (en) Dynamic home screen
WO2021115481A1 (zh) 终端控制方法、装置、终端和存储介质
CN108038050B (zh) 性能调整方法、装置、存储介质及电子设备
JP7204903B2 (ja) 情報プッシュ方法、装置、機器及び記憶媒体
WO2021093472A1 (zh) 数据处理方法、电子设备及可读存储介质
US9143178B1 (en) Activity-based remaining battery life

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22745200

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22745200

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 17.01.2024)