Download prompts, methods, devices, equipment, and readable storage media

Abstract

This application discloses a download prompt method, apparatus, device, and readable storage medium, belonging to the field of computer technology. The method includes: acquiring download information of a device to be prompted, the download information including download content information and device status information; determining the download location based on the download information and a trained regression algorithm; and sending download prompt information to the device to be prompted based on the download location.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computer, and particularly relates to a download prompting method, a download prompting device, an electronic device and a readable storage medium. BACKGROUND

[0002] With the development of economy and technology, smart phones have been more and more widely used.

[0003] At present, users often use smart phones to browse videos, news information and the like during the process of taking the subway or bus to work. However, when the subway or bus enters a weak signal coverage area or a signal-free area, the smart phone will not be able to smoothly play videos or display news information and the like to the user. In this way, the user can only temporarily interrupt the current use of the smart phone. For example, as shown in FIG. 1, Xiaoming takes the subway and uses a smart phone to browse news information on the subway. However, when the subway reaches position 1 located in a weak signal coverage area, Xiaoming's browsing is interrupted. Until the subway reaches position 2, the signal strength is restored. Therefore, Xiaoming cannot continue to browse news information between position 1 and position 2, and the user experience is low. In the figure, Figure 1 Figure 1 the arrow direction in the figure indicates the subway travel direction.

[0004] In view of the above situation, the user will usually determine, according to his own experience, that the signal strength is restored after the subway or bus passes a certain position, so that the smart phone can continue to play videos or display news information and the like. Then the user continues to use the smart phone at the position.

[0005] However, the user's own experience has a large error, and the interruption of the use of the smart phone leads to poor user experience. Therefore, how to make the smart phone smoothly play videos or information and the like to the user when the smart phone enters a weak signal coverage area or a signal-free area becomes a problem to be solved. SUMMARY

[0006] The purpose of the embodiments of the present application is to provide a download prompting method, which can solve the problem of how to make the smart phone smoothly play videos or information and the like to the user when the smart phone enters a weak signal coverage area or a signal-free area.

[0007] In a first aspect, the embodiments of the present application provide a download prompting method, which comprises:

[0008] obtaining download information of a to-be-prompted device, wherein the download information comprises download content information and device state information;

[0009] determining a download position according to the download information and a trained regression algorithm;

[0010] ​According to the download position, the download prompting information is sent to the device to be prompted.

[0011] In a second aspect, an embodiment of the present application provides a download prompting device, the device comprising:

[0012] a obtaining module, configured to obtain download information of a device to be prompted, the download information comprising download content information and device state information;

[0013] a determining module, configured to determine a download position according to the download information and a trained regression algorithm;

[0014] a sending module, configured to send download prompting information to the device to be prompted according to the download position.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions are executed by the processor to implement the steps of the method according to the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a readable storage medium, wherein the readable storage medium stores programs or instructions, and the programs or instructions are executed by a processor to implement the steps of the method according to the first aspect.

[0017] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute programs or instructions to implement the method according to the first aspect.

[0018] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the method according to the first aspect.

[0019] In the embodiment of the present application, a download prompting method is provided, comprising obtaining download information of a device to be prompted, the download information comprising download content information and device state information; determining a download position according to the download information and a trained regression algorithm; and sending download prompting information to the device to be prompted according to the download position. Through the embodiment, on the one hand, the user does not need to determine which position can continue to use the device to be prompted according to experience, and on the other hand, the user does not need to interrupt the use of the device to be prompted. Therefore, when the device to be prompted, such as a smart phone, enters a weak signal coverage area or a signal-free area, the device to be prompted can still display content, such as a video or information, that the user plans to browse to the user. This solves the problem of how to make the smart phone play a video or information smoothly to the user when the smart phone enters a weak signal coverage area or a signal-free area. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 A scene diagram is shown for a user using a smart phone to browse news information;

[0021] Figure 2 A download prompting method is shown for implementing an embodiment of the present application Figure 1 ;

[0022] Figure 3 A download prompting method is shown for implementing an embodiment of the present application Figure 2 ;

[0023] Figure 4 A download prompting method is shown for implementing an embodiment of the present application Figure 3 ;

[0024] Figure 5 A download prompting device is shown for implementing an embodiment of the present application

[0025] Figure 6 A hardware structure of an electronic device is shown for implementing an embodiment of the present application Figure 1 ;

[0026] Figure 7 A hardware structure of an electronic device is shown for implementing an embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be described clearly below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

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

[0029] The download prompting method, device, equipment and readable storage medium provided by the embodiments of the present application will be described in detail below in conjunction with the drawings and specific embodiments and their application scenarios.

[0030] The embodiment of the present application provides a download prompting method, as shown in the figure, the method comprises the following S2100-S2300: Figure 2

[0031] S2100, obtaining download information of a device to be prompted.

[0032] The download information comprises download content information and device state information.

[0033] In the embodiment of the present application, the device to be prompted is a device that needs to be prompted for download. For example, a terminal device such as a smart phone that still needs to be used when a user takes a subway or a bus and the subway or the bus will enter a signal coverage area or a signal-free area.

[0034] The download content information is related information of a content planned to be browsed by a user when the device to be prompted enters a weak signal coverage area or a signal-free area. For example, at least one of a time length of the content planned to be browsed, a power consumption of watching the content planned to be browsed, and a power consumption of downloading the content planned to be browsed.

[0035] The content planned to be browsed corresponds to a theme. The theme can be any one of a video, a game, information and social interaction.

[0036] In an example, the content planned to be browsed is a video A, and on this basis, the download content information is a time length of the video A, a power consumption of watching the video A and a power consumption of downloading the video A.

[0037] The device state information is related state information of the device to be prompted, for example, a current power, a current actual signal receiving power value, a theme of a currently displayed content, a current position, a starting position and the like.

[0038] In an embodiment of the present application, the specific implementation of S2100 can be that the device to be prompted actively reports the download information.

[0039] S2200, determining a download position according to the download information and a trained regression algorithm.

[0040] In the embodiment of the present application, the download position is a position at which downloading of download content corresponding to the download content information starts, and the downloading of the download content corresponding to the download content information starts at the download position, so that the user can directly watch the content corresponding to the pre-downloaded content information when the device to be prompted enters a weak signal coverage area or a signal-free area.

[0041] In the embodiment of the present application, the trained regression algorithm is a regression algorithm that has been trained and can output the download position according to the download information.

[0042] ​In an embodiment of the present application, the regression algorithm can be any one of Gradient Boosting Decision Tree (GBDT) algorithm, Logistic regression (LR) algorithm, Convolutional Neural Networks (CNN) algorithm, and Deep Neural Networks (DNN) algorithm.

[0043] In an embodiment of the present application, the implementation of S2200 can be as follows: establishing a database, the database storing a large number of data groups, each data group containing a download information and a corresponding test download position; for any download information, searching for the test download position matched with the download information in the database; and taking the searched test download position as the download position in S2200.

[0044] In another embodiment of the present application, S2200 can be implemented by S2210 and S2220 as follows:

[0045] S2210, obtaining a target position.

[0046] The target position is the position where the minimum signal receiving power value of the content of the theme to which the download content information belongs.

[0047] It should be noted that in the following content, the theme to which the download content information belongs is taken as a video for example to illustrate the download prompting method provided in the embodiments of the present application.

[0048] In an embodiment of the present application, the target position can be obtained by a technician using an electronic device to perform a large number of tests along the path where the device to be prompted is located. For example, when the theme to which the download content information belongs is a video, the specific test process can be as follows: repeatedly playing the video using the electronic device on the path where the device to be prompted is located to record the positions corresponding to the minimum signal receiving power values of the video respectively; and taking the average of the recorded positions as the target position. It should be noted that the way of recording the positions corresponding to the minimum signal receiving power values of the video is not limited in the embodiment.

[0049] In another embodiment of the present application, the target position can be obtained by S2211-S2214 as follows:

[0050] S2211, obtaining actual signal receiving power values of the content belonging to the theme (to which the download content information of the device to be prompted belongs) displayed by a plurality of first sample devices.

[0051] The first sample devices and the device to be prompted are located in the same path.

[0052] In an embodiment of the present application, the first sample device is the same as the operator to which the device to be prompted belongs.

[0053] In an embodiment of the present application, taking a video as an example of the theme, the implementation of S2211 can be as follows: the first sample device plays the video during the movement of the first sample device on the path where the device to be prompted is located; and the actual signal receiving power values of the first sample device at different positions are collected in the case that the first sample device plays the video smoothly. The collection can be achieved by the first sample device itself collecting and then reporting by the first sample device.

[0054] In an embodiment of the present application, the actual signal receiving power value of the content to which the download content information of the device to be prompted belongs is actively reported by the first sample device.

[0055] S2212, constructing a fitness function of a global search algorithm.

[0056] In an embodiment of the present application, the global search algorithm is an algorithm for searching the minimum actual receiving power value of the content to which the theme of the download content information of the device to be prompted belongs and which can be displayed smoothly on the path where the device to be prompted is located.

[0057] In an embodiment of the present application, the global search algorithm in S2212 can be any one of a particle swarm optimization (PSO) algorithm, a simplex algorithm, an ant colony algorithm and a genetic algorithm.

[0058] In an embodiment of the present application, taking the PSO algorithm as an example of the global search algorithm, the fitness function of the global search algorithm can be constructed as the following function:

[0059]

[0060] wherein i is the number of the particle;

[0061] n is the number of the particle;

[0062] w i is the weight value of the i-th particle, which can be a random number or the market share of the operator to which the device to be prompted belongs in an embodiment of the present application;

[0063] t i is the theoretical minimum signal receiving power value of the i-th particle when the content to which the theme of the download content information of the device to be prompted belongs is displayed smoothly, which can be an empirical value;

[0064] b iThe actual signal receiving power value of the ith particle in the case of smoothly displaying the content of the theme to which the download content information of the to-be-tipped device belongs.

[0065] It can be understood that in the embodiments of the present application, the particle refers to the device used to determine the minimum signal receiving power value of the content of the theme to which the download content information of the to-be-tipped device belongs.

[0066] S2213, determining the minimum signal receiving power value of the theme according to the plurality of actual signal receiving power values and the fitness function.

[0067] In the embodiments of the present application, the maximum value refers to the maximum actual receiving power value in the plurality of actual signal receiving power values obtained based on S2211, and the minimum value refers to the minimum actual receiving power value in the plurality of actual signal receiving power values obtained based on S2212.

[0068] In addition, the maximum difference value and the minimum difference value of the actual receiving power values collected at adjacent positions are determined according to the plurality of actual receiving power values.

[0069] In the embodiments of the present application, taking the fitness function as the above formula one, the specific implementation of S2213 is:

[0070] Step 1, randomly initialize the example group. Specifically, define the number of particles n, the initial position D m and the speed V m of each particle.

[0071] Wherein, m is the index of the particle, D m =(b1, b2, ……b i ……b n ); b i is the position of the ith particle, which is the actual signal receiving power value of the ith sample device in the case of smoothly displaying the content of the theme to which the download content information of the to-be-tipped device belongs.

[0072] V m =(v1, v2, ……v i ……v n ), v i is the moving speed of the ith particle, that is, the size of the change value of each particle based on the last position, which is the change value of the actual signal receiving power value of the ith sample device between adjacent two positions.

[0073] Wherein, b i is any value between the maximum value and the minimum value (including the maximum value and the minimum value).

[0074] v i It is any value between the maximum and minimum differences mentioned above (inclusive).

[0075] Step 2: Substitute the historical best solution of each particle into the fitness function to obtain the corresponding fitness error value.

[0076] When performing step 2 for the first time, D in step 1 will be... m The value of each particle in the solution is taken as the historical best solution P. m .

[0077] Step 3: Take the actual signal received power value corresponding to the smallest fitness Error value in Step 2 as the global optimal solution G.

[0078] Step 4: Update the particle's position D according to Formulas 2 and 3 below. m and speed V m ;

[0079] V m =αV m +β1γ1(P m -D m )+β2γ2(GD m (Formula 2);

[0080] D m =D m +V m (Formula 3)

[0081] For Formula 2 above, the first part is: inertial velocity, which is the previous velocity V. m The weighting coefficient is α, which is generally taken as 0.9-0.4;

[0082] Part Two: Memory Comparison, compare with the previous position, select the optimal tilt direction, β1 is generally taken as 2.0, and γ1 is a random number;

[0083] Part 3: Group collaboration method to find the optimal position in the group, tilting towards the group's optimal direction, β2 is generally taken as 2.0, and γ2 is a random number.

[0084] It should be noted that for Formula 2 above, V on the left side of the equal sign... m For the updated speed, V on the right side of the equals sign m The speed was before the update.

[0085] And, for Formula 3 above, D on the left side of the equal sign m The updated position is D on the right side of the equals sign. m This is the position before the update.

[0086] Step 6: For any updated particle, calculate the fitness error value; compare the calculated fitness error value with the fitness value corresponding to the particle's historical best value; if the calculated fitness error value is less than the fitness value corresponding to the historical best value, then update the particle's historical best value to the calculated fitness error value. Otherwise, do not update.

[0087] Furthermore, after all the historical best values ​​of all particles have been updated, the fitness error value is calculated based on all the updated historical best values; the historical best position of the particle corresponding to the minimum fitness error value is taken as the current global best solution.

[0088] Repeat step 4 above until the preset number of iterations is reached. The current globally optimal solution corresponding to the reached iteration number is taken as the minimum signal received power value for the corresponding topic. The preset number of iterations can be set empirically.

[0089] S2214. The location corresponding to the minimum signal received power value of the subject is taken as the target location.

[0090] In this embodiment, the closest actual signal received power value to the minimum signal received power value calculated based on S2213 is determined between the minimum signal received power value calculated based on S2213 and the actual signal received power value obtained based on S2211. The sampling position corresponding to the closest actual signal received power value is taken as the target position.

[0091] S2220. Determine the download location based on the download information, target location, and the trained regression algorithm.

[0092] In this embodiment, the input information to be input into the trained regression algorithm is determined based on the download information and the target location. The input information is then input into the trained regression algorithm to obtain the download location.

[0093] In one embodiment of this application, the download content information in the download information includes: the length of video A, the power consumption of watching video A, and the power consumption of downloading video A. The device status information in the download information includes: current battery level, current actual signal receiving power value, the theme of the currently displayed content, current position, and starting position. Based on this, the specific implementation of S2220 is as follows: based on the current position, determine the distance and direction of the current position relative to the target position, and the distance from the starting position; determine the input information as: the distance and direction of the current position relative to the target position, the position relative to the starting distance, the current battery level, the current actual signal receiving power value, the theme of the currently displayed content, the length of video A, the power consumption of watching video A, and the power consumption of downloading video A. Based on this, the input information can be exemplarily shown in Table 1 below.

[0094] Table 1

[0095]

[0096]

[0097] In Table 1 above, the 3km corresponding to the download location is the download location output by the trained regression algorithm. This download location is represented by its distance from the target location.

[0098] In this embodiment, since the target location is the location of the minimum signal received power value of the content of the topic to which the downloaded content information belongs, the relevant features of the target location (such as the distance and direction of the current location relative to the target location in Table 1 above) are more effective in determining the download location. Thus, the distance and direction of the current location relative to the target location, determined based on the target location, can replace several less effective features (such as device operating speed, device age, device size, etc.). Therefore, by using these two features—the distance and direction of the current location relative to the target location—the dimensionality of the input information for the regression algorithm can be reduced. This makes the regression algorithm lightweight, allowing its application and training to be completed on the terminal.

[0099] In one embodiment of this application, the download prompt method provided in this application further includes the following steps S2221 and S2222 before the above-described S2220:

[0100] S2221. Obtain a training sample set consisting of multiple sets of training samples.

[0101] The training sample set includes sample information of the second sample device and its corresponding download location. The sample information includes the download information of the second sample device and its relative distance and direction relative to the target location. The second sample device and the sample to be prompted are on the same path.

[0102] In one embodiment of this application, the second sample device belongs to the same operator as the device to be prompted.

[0103] In this embodiment, for any second sample device, while moving along the path of the device to be prompted, the second sample device is controlled to display any one of the following: video, news, social media, and games, and simultaneously download any video. Furthermore, the second sample device can proactively report its download information and corresponding download location. Based on this, combined with the target location, a training sample set is obtained.

[0104] S2222. Based on the second training sample set, determine the trained regression algorithm.

[0105] Step 1: Initialize the loss function:

[0106]

[0107] Where c represents the parameter to be estimated, i.e., the label value of the leaf node. In this embodiment, it represents the download location to be output by the regression algorithm. N is the number of training samples. j is the training sample number. y j This is the download location for the j-th training sample.

[0108] Based on Formula 4 above, the loss function is the squared loss function. The squared loss function is a convex function. Therefore, directly differentiating c with respect to it yields a derivative of 0, thus obtaining c. Specifically:

[0109]

[0110] Let the derivative equal to 0:

[0111] Right now

[0112] Based on the above, it can be seen that during initialization, c is the mean of all download locations in all training samples.

[0113] Step 2: For each training sample, calculate the negative gradient, i.e., the residual, using the following formula six;

[0114]

[0115] Where m is the number of the regression tree.

[0116] Step 3: Use the residuals calculated in the above steps as the new true values ​​for the training samples, i.e., the new download positions; update the download positions in each training sample with the new download positions, and then use them as training samples for the next tree. Repeat step 2 above to obtain M new regression trees.

[0117] Step 4: The weighted sum of the initial loss function and the residuals of the M regression trees is used as the final output value of the regression algorithm.

[0118] S2300: Based on the download location, send a download prompt message to the device to be prompted.

[0119] In one embodiment of this application, the specific implementation of S2300 can be as follows: the download location is used as download prompt information for the device to be prompted, and sent to the device. Based on this, after receiving the download prompt information, the device to be prompted, upon determining that its current location is at the download location, begins downloading the content, such as video A. Thus, when the device to be prompted enters an area with weak signal coverage or no signal, the user can directly watch video A. This eliminates the need for the user to rely on experience to determine which location is safe to continue using the device, and also eliminates the need for the user to interrupt their use of the device. Therefore, even when the device to be prompted, such as a smartphone, enters an area with weak signal coverage or no signal, it can still display content that the user plans to browse, such as videos or news. This solves the problem of how to ensure that a smartphone can smoothly play videos or news when it enters an area with weak signal coverage or no signal.

[0120] In another embodiment of this application, the specific implementation of S2300 above may further be as follows: determining the current speed of the device to be prompted, and the distance between the location where the device to be prompted was when it reported the download information and the download location; estimating the time it will take for the device to be prompted to reach the download location based on the ratio of the distance to the speed; determining the download prompt information as a prompt information that the download will start after the estimated time has elapsed; or, superimposing the estimated time on the current time of the device to be prompted to obtain the download time, determining the download prompt information as the download time; and sending the prompt information that the download will start at the download time to the device to be prompted.

[0121] It is understandable that, based on the above steps S2100-S2300, when the downloaded content is video A, the download prompt information for video A can be determined. When the downloaded content is news B, the download prompt information for news B can be determined. When the downloaded content is game C, the download prompt information for game C can be determined. When the downloaded content is social media D, the download prompt information for social media D can be determined.

[0122] Furthermore, if the first sample device and the second sample device belong to the same operator as the device to be prompted, taking operators including operator 1, operator 2 and operator 3 as an example, if the downloaded content is video A, then based on the above S2100-S2300, download prompt information for downloading video A by the devices to be prompted belonging to operator 1, operator 2 and operator 3 can be obtained respectively.

[0123] Based on the above, it can be seen that the download prompt method provided in this application embodiment can send download prompt information to the device to be prompted for download information of a single topic from a single operator. Furthermore, it can be understood that the download prompt method provided in this application embodiment can also send corresponding download prompt information to the corresponding device to be prompted for download information of each topic from each operator. Thus, it is only necessary to determine the operator of the device to be prompted and the topic to which the downloaded content belongs, and then determine the corresponding download prompt information. Specifically, as follows... Figure 3 As shown, the process includes: after entering the subway, the user inputs download content information on their electronic device, i.e., the device to be prompted, according to their own needs. The execution entity executing the download prompt method of this application embodiment receives the download content information input by the user on the device to be prompted, and obtains the device status information of the device to be prompted, so as to implement the above-mentioned S2100. The execution entity determines the topic to which the download content information belongs, and the operator of the device to be prompted. Further, the above-mentioned S2200 is executed to determine the download location for the following scenarios: for operator 1, the topic of the download content information is video or A, news B, game C or social D; for operator 2, the topic of the download content information is video or A, news B, game C or social D; for operator 3, the topic of the download content information is video A, news B, game C or social D; and the above-mentioned S2300 is executed to send a download prompt message, for example, indicating that the download will start at the download time, to the device to be prompted. Further, taking the download prompt message as the download time as an example, the device to be prompted will actively download after the download time arrives. Alternatively, a prompt to start the download can be displayed on the interface of the device to be prompted, allowing the user to indicate whether to start the download.

[0124] This application provides a download notification method, including obtaining download information of the device to be notified, the download information including download content information and device status information; determining the download location based on the download information and a trained regression algorithm; and sending download notification information to the device to be notified based on the download location. This embodiment eliminates the need for users to rely on experience to determine where they can continue using the device, and also eliminates the need for users to interrupt their use of the device. Therefore, even when the device to be notified, such as a smartphone, enters an area with weak signal coverage or no signal, it can still display content that the user plans to browse, such as videos or news. This solves the problem of how to ensure that a smartphone can smoothly play videos or news when it enters an area with weak signal coverage or no signal.

[0125] In one embodiment of this application, the download prompt method provided in this application further includes the following steps S2500 and S2600:

[0126] S2500: Obtain the download result from the device that is about to be prompted, in response to the download prompt information.

[0127] In this embodiment of the application, the device to be prompted performs a download operation based on the download prompt information, obtains the download result, and reports the download result.

[0128] In this embodiment of the application, the download result is: whether the downloaded content was successfully downloaded upon reaching the target location.

[0129] In this embodiment of the application, when the device reaches the target location, it checks whether the downloaded content has been successfully downloaded and reports the detection result.

[0130] S2600. Based on the download results, update the trained regression algorithm.

[0131] In this embodiment, when the download result indicates a successful download, the download location and the input information used to input that location into the regression algorithm are used as training samples for the trained regression algorithm. The trained regression algorithm is then further trained based on these training samples to update the algorithm. This allows the trained regression algorithm to obtain a more accurate download location in subsequent uses.

[0132] In light of the above, in one embodiment of this application, the entity executing the download prompt information provided in this application embodiment serves as a prompting device, such as... Figure 4 As shown, the download prompt method provided in this application embodiment can be specifically as follows:

[0133] Each of the first sample devices reports the actual received signal power value related to the topic content;

[0134] The device obtains multiple actual signal received power values ​​that belong to the topic content, constructs a fitness function for a global search algorithm, and determines the minimum signal received power value of the topic content based on the multiple actual signal received power values ​​and the fitness function; the position corresponding to the minimum signal received power value of the topic content is taken as the target position.

[0135] Any second sample device shall report the download information of the second sample, the corresponding download location, and the device status information of the second sample;

[0136] The device obtains a training sample set based on the target location, the download information of the second sample, and the corresponding download location and device status information of the second sample. Based on the training sample set, the trained regression algorithm is determined.

[0137] The device awaiting notification should report its download information.

[0138] The prompting device determines the download location based on the download information of the device to be prompted, the target location, and the trained regression algorithm, and sends download prompt information to the device to be prompted based on the download location;

[0139] The device to be prompted performs the download operation based on the download prompt information, obtains the download result, and reports the download result;

[0140] The device is prompted to update the trained regression algorithm based on the download results.

[0141] The download prompting method provided in this application can be executed by a download prompting device. This application uses a download prompting device executing the download prompting method as an example to illustrate the download prompting device provided in this application.

[0142] like Figure 5 As shown, the download prompt device 500 provided in this application embodiment includes the following acquisition module 510, determination module 520, and sending determination module 530, wherein:

[0143] The acquisition module 510 is used to acquire the download information of the device to be prompted, the download information including download content information and device status information;

[0144] The determination module 520 is used to determine the download location based on the download information and the trained regression algorithm;

[0145] The sending module 530 is used to send download prompt information to the device to be prompted according to the download location.

[0146] This application provides a download notification device, comprising: an acquisition module for acquiring download information of a device to be notified, the download information including download content information and device status information; a determination module for determining the download location based on the download information and a trained regression algorithm; and a sending module for sending download notification information to the device to be notified based on the download location. This embodiment eliminates the need for users to rely on experience to determine where they can continue using the device, and also eliminates the need for users to interrupt their use of the device. Therefore, even when the device to be notified, such as a smartphone, enters an area with weak signal coverage or no signal, it can still display content that the user plans to browse, such as videos or news. This solves the problem of how to ensure that a smartphone can smoothly play videos or news when it enters an area with weak signal coverage or no signal.

[0147] In one embodiment of this application, the determining module 520 includes:

[0148] An acquisition unit is used to acquire a target location, wherein the target location is the location of the minimum signal received power value of the content of the topic to which the downloaded content information belongs;

[0149] The first determining unit is used to determine the download location based on the download information, the target location, and the trained regression algorithm.

[0150] In one embodiment of this application, the acquisition unit is specifically used for:

[0151] Obtain the actual signal received power values ​​of multiple first sample devices displaying content belonging to the topic, wherein the first sample devices and the device to be prompted are located on the same path;

[0152] Construct the fitness function for the global search algorithm;

[0153] Based on the multiple actual signal received power values ​​and the fitness function, determine the minimum signal received power value of the content of the topic;

[0154] The location corresponding to the minimum signal reception power value of the content of the topic is taken as the target location.

[0155] In one embodiment of this application, the acquisition module 510 is further configured to:

[0156] Obtain a training sample set consisting of multiple training samples. The training samples include sample information of the second sample device and its corresponding download location. The sample information includes the download information of the second sample device and its relative distance and direction relative to the target location. The second sample device and the sample device to be prompted are on the same path.

[0157] The determination module 520 is further configured to determine the trained regression algorithm based on the training sample set.

[0158] In one embodiment of this application, the acquisition module 510 is further configured to:

[0159] Obtain the download result of the device to be prompted in response to the download prompt information;

[0160] In this embodiment of the application, the download notification device 500 further includes an update module, wherein:

[0161] An update module is used to update the trained regression algorithm based on the download results.

[0162] In one embodiment of this application, the regression algorithm is any one of gradient boosting decision tree algorithm, logistic regression algorithm, convolutional neural network algorithm, and deep neural network algorithm.

[0163] In one embodiment of this application, the global search algorithm is any one of particle swarm optimization, simplex algorithm, ant colony algorithm, and genetic algorithm.

[0164] The download prompt device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television set (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the specific device.

[0165] The download prompt device in this embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this embodiment does not specifically limit it.

[0166] The download notification device provided in this application embodiment can achieve... Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0167] Optionally, such as Figure 6 As shown, this application embodiment also provides an electronic device 600, including a processor 601 and a memory 602. The memory 602 stores a program or instructions that can run on the processor 601. When the program or instructions are executed by the processor 601, they implement the various steps of the above-described download prompt method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0168] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0169] Figure 7 A schematic diagram of the hardware structure of an electronic device according to an embodiment of this application.Figure 2 .

[0170] The electronic device 1000 includes, but is not limited to, components such as: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, and processor 1010.

[0171] Those skilled in the art will understand that the electronic device 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 7 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0172] The processor 1010 is used to obtain download information of the device to be prompted, the download information including download content information and device status information;

[0173] Based on the download information and the trained regression algorithm, the download location is determined;

[0174] Based on the download location, a download prompt message is sent to the device to be prompted.

[0175] In this embodiment, an electronic device is provided, wherein a processor is configured to: acquire download information of a device to be prompted, the download information including download content information and device status information; determine the download location based on the download information and a trained regression algorithm; and send download prompt information to the device to be prompted based on the download location. This embodiment eliminates the need for users to rely on experience to determine where they can continue using the device to be prompted, and also eliminates the need for users to interrupt their use of the device to be prompted. Therefore, even when the device to be prompted, such as a smartphone, enters an area with weak signal coverage or no signal, the device can still display content that the user plans to browse, such as videos or news. This solves the problem of how to ensure that a smartphone can smoothly play videos or news to the user when it enters an area with weak signal coverage or no signal.

[0176] Optionally, the processor 1010 is specifically used for:

[0177] Obtain the target location, which is the location of the minimum signal received power value of the content of the topic to which the downloaded content information belongs;

[0178] The download location is determined based on the download information, the target location, and the trained regression algorithm.

[0179] Optionally, the processor 1010 is specifically used for:

[0180] Obtain the actual signal received power values ​​of multiple first sample devices displaying content belonging to the topic, wherein the first sample devices and the device to be prompted are located on the same path;

[0181] Construct the fitness function for the global search algorithm;

[0182] Based on the multiple actual signal received power values ​​and the fitness function, determine the minimum signal received power value of the content of the topic;

[0183] The location corresponding to the minimum signal reception power value of the content of the topic is taken as the target location.

[0184] Optionally, the processor 1010 is also used for:

[0185] Obtain a training sample set consisting of multiple training samples. The training samples include sample information of the second sample device and its corresponding download location. The sample information includes the download information of the second sample device and its relative distance and direction relative to the target location. The second sample device and the sample device to be prompted are on the same path.

[0186] Based on the training sample set, the trained regression algorithm is determined.

[0187] Optionally, the processor 1010 is also used for:

[0188] Obtain the download result of the device to be prompted in response to the download prompt information;

[0189] Based on the download results, update the trained regression algorithm.

[0190] Optionally, the regression algorithm is any one of gradient boosting decision tree algorithm, logistic regression algorithm, convolutional neural network algorithm, and deep neural network algorithm.

[0191] Optionally, the global search algorithm is any one of particle swarm optimization, simplex algorithm, ant colony algorithm, and genetic algorithm.

[0192] It should be understood that, in this embodiment, the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042. The GPU 10041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. 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 at least one of other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include 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 buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0193] The memory 1009 can be used to store software programs and various data. The memory 1009 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1009 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1009 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0194] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor 1010.

[0195] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described download prompt method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0196] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0197] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described download prompt method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0198] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0199] This application provides a computer program product that is stored in a storage medium and executed by at least one processor to implement the various processes of the download prompt method embodiment described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0200] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0201] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0202] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A download prompting method, characterized by, The method comprises: obtaining download information of a device to be prompted, the download information comprising download content information and device state information; determining a download position according to the download information and a trained regression algorithm; sending download prompt information to the device to be prompted according to the download position; wherein the determining of the download position according to the download information and the trained regression algorithm comprises: obtaining a target position, the target position being a position of a minimum signal receiving power value of content of a theme to which the download content information belongs; determining the download position according to the download information, the target position and the trained regression algorithm; the obtaining of the target position comprises: obtaining actual signal receiving power values of content belonging to the theme displayed by a plurality of first sample devices, the first sample devices and the device to be prompted being located on the same path; constructing a fitness function of a global search algorithm; determining the minimum signal receiving power value of the content of the theme according to the actual signal receiving power values and the fitness function; and taking a position corresponding to the minimum signal receiving power value of the content of the theme as the target position.

2. The method of claim 1, wherein, The method further comprises, before the determining of the download position according to the download information, the target position and the trained regression algorithm: obtaining a training sample set composed of a plurality of training samples, the training samples comprising sample information of a second sample device and a corresponding download position, the sample information comprising download information of the second sample device and a relative distance and direction relative to the target position, the second sample device and the device to be prompted being located on the same path; determining the trained regression algorithm according to the training sample set.

3. The method of claim 1, wherein, The method further comprises, after the sending of the download prompt information to the device to be prompted according to the download position: obtaining a download result of the device to be prompted in response to the download prompt information; updating the trained regression algorithm according to the download result.

4. The method of claim 1, wherein, The regression algorithm is any one of a gradient boosting decision tree algorithm, a logistic regression algorithm, a convolutional neural network algorithm and a deep neural network algorithm.

5. The method of claim 1, wherein, The global search algorithm is any one of a particle swarm optimization algorithm, a simplex algorithm, an ant colony algorithm and a genetic algorithm.

6. A download prompting apparatus characterized by comprising: The apparatus comprises: an obtaining module configured to obtain download information of a device to be prompted, the download information comprising download content information and device state information; a determining module configured to determine a download position according to the download information and a trained regression algorithm; a sending module configured to send download prompt information to the device to be prompted according to the download position; wherein the determining module comprises: an obtaining unit configured to obtain a target position, the target position being a position of a minimum signal receiving power value of content of a theme to which the download content information belongs; a first determining unit configured to determine the download position according to the download information, the target position and the trained regression algorithm; the obtaining unit is specifically configured to obtain actual signal receiving power values of content belonging to the theme displayed by a plurality of first sample devices, the first sample devices and the device to be prompted being located on the same path; constructing a fitness function of the global search algorithm; determining a minimum signal receiving power value of the content of the topic according to the multiple actual signal receiving power values and the fitness function; taking the position corresponding to the minimum signal receiving power value of the content of the topic as the target position.

7. An electronic device, comprising: A computer program product, comprising a computer readable storage medium to store logically and / or physically a computer program or instructions, wherein the computer program or instructions are executable by a processor to implement the steps of the download prompting method according to any one of claims 1-5.

8. A readable storage medium, characterized by, A computer program product, comprising a computer readable storage medium to store logically and / or physically a computer program or instructions, wherein the computer program or instructions are executable by a processor to implement the steps of the download prompting method according to any one of claims 1-5.

Images