Behavior Prediction Method, Apparatus, Storage Medium, and Electronic Device

Abstract

The present application discloses a behavior prediction method, apparatus, storage medium and electronic device. The method includes: determining a current base station to which the electronic device is connected; determining a target base station set to which the current base station belongs, wherein the target base station set is obtained according to the jump frequency of the electronic device jumping between historical base stations, and the jump frequency of the electronic device jumping between the base stations in the target base station set is greater than or equal to the jump frequency of the electronic device jumping between the base stations in the target base station set and the base stations outside the target base station set; performing user behavior prediction according to the target base station set to obtain a prediction result. The present application can determine the user's permanent residence where the electronic device is currently located based on the current base station to which the electronic device is connected.

Description

Technical Field

[0001] This application belongs to the field of electronic technology, and particularly relates to a behavior prediction method, apparatus, computer-readable storage medium, and electronic device. Background Art

[0002] User behavior understanding is the core of end-side intelligent decision-making. Through related technologies, user behavior can be learned, and then the user's frequent residence can be determined. By associating the user behavior with the user's frequent residence, when the electronic device is at the corresponding user's frequent residence subsequently, the user behavior at that user's frequent residence can be predicted, and appropriate suggestions or services can be provided to the user for the predicted user behavior, thereby enhancing the user experience. That is to say, based on learning the user's behavior, it is also necessary to determine the user's frequent residence, associate the user behavior with the user's frequent residence, and when the electronic device is at the corresponding user's frequent residence subsequently, the user behavior at that user's frequent residence can be predicted. Summary of the Invention

[0003] Embodiments of this application provide a behavior prediction method, apparatus, computer-readable storage medium, and electronic device, which can determine the user's frequent residence where the electronic device is currently located based on the current base station connected to the electronic device.

[0004] In a first aspect, embodiments of this application provide a behavior prediction method, including:

[0005] Determine the current base station connected to the electronic device;

[0006] Determine a target base station set to which the current base station belongs, where the target base station set is obtained according to the hopping frequency of the electronic device between historical base stations, and the hopping frequency of the electronic device between the base stations in the target base station set is greater than or equal to the hopping frequency of the electronic device between the base stations in the target base station set and the base stations outside the target base station set;

[0007] Perform user behavior prediction according to the target base station set to obtain a prediction result.

[0008] In a second aspect, embodiments of this application provide a behavior prediction apparatus, including:

[0009] A base station determination module, configured to determine the current base station connected to the electronic device;

[0010] A set determination module, configured to determine a target base station set to which the current base station belongs, where the target base station set is obtained according to the hopping frequency of the electronic device hopping between historical base stations, and the hopping frequency of the electronic device hopping between the base stations in the target base station set is greater than or equal to the hopping frequency of the electronic device hopping between the base stations in the target base station set and the base stations outside the target base station set;

[0011] A behavior prediction module, configured to perform user behavior prediction according to the target base station set to obtain a prediction result.

[0012] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed on a computer, the computer is enabled to execute the behavior prediction method provided by the embodiment of the present application.

[0013] In a fourth aspect, an embodiment of the present application further provides an electronic device, including a memory and a processor. The processor is configured to execute the behavior prediction method provided by the embodiment of the present application by calling the computer program stored in the memory.

[0014] In the embodiment of the present application, since the user moves relatively frequently within the user's usual residence and moves relatively infrequently outside the user's usual residence, therefore, the hopping frequency of the electronic device hopping between the base stations within the user's usual residence is greater than or equal to the hopping frequency of the electronic device hopping between the base stations within the user's usual residence and the base stations outside the user's usual residence. Based on this, the electronic device can determine a base station set in which the hopping frequency of the corresponding electronic device hopping between the internal base stations is greater than or equal to the hopping frequency of the electronic device hopping between the internal and external base stations of the electronic device, and use the determined base station set to represent the user's usual residence. Subsequently, by determining the target base station set to which the current base station connected by the electronic device belongs, the user's current usual residence where the electronic device is located is determined. By performing user behavior prediction according to the target base station set to obtain a prediction result, the user behavior in the user's usual residence can be predicted. Description of the Drawings

[0015] The following will make the technical solutions and their beneficial effects of the present application obvious by describing the specific embodiments of the present application in detail in conjunction with the drawings.

[0016] Figure 1 is the first flow diagram of the behavior prediction method provided by the embodiment of the present application.

[0017] Figure 2 is a schematic diagram of the base station directed graph provided by the embodiment of the present application.

[0018] Figure 3 is the second flow diagram of the behavior prediction method provided by the embodiment of the present application.

[0019] Figure 4 It is a schematic structural diagram of the behavior prediction device provided by an embodiment of the present application.

[0020] Figure 5 It is a schematic structural diagram of the electronic device provided by an embodiment of the present application. Specific embodiments

[0021] It should be noted that the terms "include" and "have" in this application and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the listed steps or modules, but some embodiments also include steps or modules not listed, or some embodiments also include other steps or modules inherent to these processes, methods, products, or devices.

[0022] Referring to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The phrase appears at various positions in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0023] An embodiment of the present application provides a behavior prediction method, a behavior prediction device, a storage medium, and an electronic device. Among them, the behavior prediction method can be applied to neural network behavior prediction in any field and any structure such as images, sounds, natural languages, and controls. The execution subject of the behavior prediction method can be the behavior prediction device provided by an embodiment of the present application, or an electronic device integrated with the behavior prediction device, where the behavior prediction device can be implemented in a hardware or software manner. Among them, the electronic device can be a device with a processor and having behavior prediction capabilities such as a smart phone, a tablet computer, a palm computer, a notebook computer, etc.

[0024] Please refer to Figure 2 , Figure 2 It is the first flowchart of the behavior prediction method provided by an embodiment of the present application, and the process may include:

[0025] In 101, determine the current base station to which the electronic device is connected.

[0026] Among them, different base stations exist in different geographical locations. When the electronic device is in different geographical regions, the base stations to which it is connected are also different. For example, when the electronic device is at the user's residence, the base station to which the electronic device is connected is the base station within the user's residence; when the electronic device is at the user's workplace, the base station to which the electronic device is connected is the base station within the user's workplace.

[0027] In this embodiment, the current base station connected to the electronic device can be determined. Specifically, the base station identifier of the current base station connected to the electronic device can be obtained, and the current base station connected to the electronic device can be determined according to the base station identifier of the current base station to which the electronic device is currently connected. Among them, the base station identifier of a certain base station uniquely identifies the base station.

[0028] In 102, a target base station set to which the current base station belongs is determined. Among them, the target base station set is obtained according to the hopping frequency of the electronic device hopping between historical base stations. The hopping frequency of the electronic device hopping between the base stations in the target base station set is greater than or equal to the hopping frequency of the electronic device hopping between the base stations in the target base station set and the base stations outside the target base station set.

[0029] Generally speaking, users usually move frequently within a certain fixed range, such as within the user's place of residence or within the user's place of work, etc. These ranges can be regarded as the user's permanent residence. As the user moves frequently, the electronic device will hop between different base stations within this fixed range, and the hopping frequency is relatively high compared to the hopping frequency between the base stations within this range and the base stations outside this range. Based on this, the electronic device can pre-determine different candidate base station sets according to the hopping frequency of the electronic device hopping between different historical base stations to which it is connected. Among them, the hopping frequency of the electronic device hopping between the base stations in the candidate base station set is greater than or equal to the hopping frequency of the electronic device hopping between the base stations in the candidate base station set and the base stations outside the candidate base station set. Then, after determining the current base station connected to the electronic device, the electronic device can determine the candidate base station set to which the current base station connected to the electronic device belongs from the previously determined candidate base station sets, and use this candidate base station set as the target base station set.

[0030] For example, assume that the determined candidate base station sets include candidate base station set M1 and candidate base station set M2. Among them, candidate base station set M1 includes base stations S1, S2, S3, and S4, and candidate base station set M2 includes base stations S11, S12, S13, and S14. If the current base station connected to the electronic device is base station S1, then the target base station set is candidate base station set M1; if the current base station connected to the electronic device is base station S11, then the target base station set is candidate base station set M2.

[0031] Optionally, when the current base station does not belong to any candidate base station set, the electronic device can do nothing, or it can perform destination prediction based on the base station sequence including the current base station. For the specific method of performing destination prediction based on the base station sequence including the current base station, reference can be made to other embodiments, which will not be elaborated here.

[0032] In 103, user behavior prediction is performed according to the target base station set to obtain a prediction result.

[0033] It can be understood that when a user is in different usual residence locations of the user, such as when the user is at the user's residence, the user's workplace, the user's dining place, or a subway station near the user's workplace, etc., the user's behavior is different. For example, when the user is at the user's residence, the user will perform behaviors such as watching videos or playing games. When the user is at the user's workplace, the user will perform behaviors such as video conferencing or ordering takeout. Different base station sets can represent different usual residence locations of the user. Then, after determining the target base station set, the electronic device can perform user behavior prediction based on the target base station set to obtain a prediction result.

[0034] For example, assume that when the electronic device is connected to the base stations in the target base station set, the user usually uses the electronic device to watch videos or play games. Then, when the current base station belongs to the target base station set, the electronic device can predict that the user's behavior is watching videos or playing games. That is to say, when the current base station belongs to the target base station set, the prediction result obtained by the electronic device performing user behavior prediction based on the target base station set is: watching videos or playing games.

[0035] In this embodiment, since the user is more frequently active within the user's usual residence location and less frequently active outside the user's usual residence location, therefore, the switching frequency of the electronic device between the base stations within the user's usual residence location is greater than or equal to the switching frequency of the electronic device between the base stations within the user's usual residence location and the base stations outside the user's usual residence location. Based on this, the electronic device can determine a base station set in which the switching frequency of the electronic device between the internal base stations is greater than or equal to the switching frequency of the electronic device between the internal and external base stations, and use the determined base station set to represent the user's usual residence location. Subsequently, after determining the target base station set to which the current base station connected by the electronic device belongs, the user's current usual residence location is determined, and user behavior prediction is performed based on the target base station set to obtain a prediction result, so that the user behavior at this user's usual residence location can be predicted.

[0036] In an optional embodiment, before determining the target base station set to which the current base station belongs, it further includes:

[0037] Obtain a candidate base station set;

[0038] Determining the target base station set to which the current base station belongs includes:

[0039] If there is a matching base station in the candidate base station set that matches the current base station, then determine the candidate base station set with the matching base station as the target base station set to which the current base station belongs.

[0040] In this embodiment, after obtaining the current base station and the candidate base station set, the electronic device can detect whether there is a matching base station in the candidate base station set that matches the current base station. If there is a matching base station in the candidate base station set that matches the current base station, it means that the electronic device is at the user's usual residence. Then, the electronic device can determine the candidate base station set where the matching base station exists as the target base station set to which the current base station belongs, and perform user behavior prediction based on the target base station set.

[0041] For example, assume that the candidate base station set includes candidate base station set M1 and candidate base station set M2. Among them, candidate base station set M1 includes base stations S1, S2, S3, and S4, and candidate base station set M2 includes base stations S11, S12, S13, and S14. If the current base station connected by the electronic device is base station S1, since there is also base station S1 in the candidate base station set, the electronic device can determine that there is a matching base station in candidate base station set M1 that matches the current base station. Then, the electronic device can determine candidate base station set M1 as the target base station set.

[0042] In an optional embodiment, before obtaining the candidate base station set, it further includes:

[0043] (1) Determine the historical base stations connected by the electronic device, and the jump frequency of the electronic device jumping between the connected historical base stations;

[0044] (2) Obtain a base station directed graph according to the historical base stations and the jump frequency of the electronic device jumping between the connected historical base stations. The base station directed graph includes vertices, edges, and the weights of the edges. Among them, the vertices represent the historical base stations connected by the electronic device, the edges represent that there is a jump relationship between the two historical base stations it connects, and the weights of the edges represent the jump frequency of the electronic device jumping between the two historical base stations connected by the edge;

[0045] (3) Obtain a candidate base station set according to the base station directed graph, where the jump frequency of the electronic device jumping between the base stations in the candidate base station set is greater than or equal to the jump frequency of the electronic device jumping between the base stations in the candidate base station set and the base stations outside the candidate base station set.

[0046] For example, as Figure 2As shown, it is assumed that the historical base stations connected to the electronic device include base stations S1 to S18. Among them, there is a jump relationship between base station S1 and base station S2, and the jump frequency of the electronic device between base station S1 and base station S2 is 11. There is a jump relationship between base station S2 and base station S3, and the jump frequency of the electronic device between base station S2 and base station S3 is 12. There is a jump relationship between base station S3 and base station S4, and the jump frequency of the electronic device between base station S3 and base station S4 is 2. There is a jump relationship between base station S2 and base station S4, and the jump frequency of the electronic device between base station S2 and base station S4 is 11. There is a jump relationship between base station S4 and base station S5, and the jump frequency of the electronic device between base station S4 and base station S5 is 1. There is a jump relationship between base station S5 and base station S6, and the jump frequency of the electronic device between base station S5 and base station S6 is 1. There is a jump relationship between base station S6 and base station S7, and the jump frequency of the electronic device between base station S6 and base station S7 is 1. There is a jump relationship between base station S7 and base station S8, and the jump frequency of the electronic device between base station S7 and base station S8 is 1. There is a jump relationship between base station S8 and base station S9, and the jump frequency of the electronic device between base station S8 and base station S9 is 1. There is a jump relationship between base station S9 and base station S10, and the jump frequency of the electronic device between base station S9 and base station S10 is 1. There is a jump relationship between base station S10 and base station S11, and the jump frequency of the electronic device between base station S10 and base station S11 is 10. There is a jump relationship between base station S11 and base station S12, and the jump frequency of the electronic device between base station S11 and base station S12 is 11. There is a jump relationship between base station S12 and base station S13, and the jump frequency of the electronic device between base station S12 and base station S13 is 12. There is a jump relationship between base station S10 and base station S13, and the jump frequency of the electronic device between base station S10 and base station S13 is 1. There is a jump relationship between base station S11 and base station S13, and the jump frequency of the electronic device between base station S11 and base station S13 is 2. There is a jump relationship between base station S8 and base station S14, and the jump frequency of the electronic device between base station S8 and base station S14 is 1. There is a jump relationship between base station S14 and base station S15, and the jump frequency of the electronic device between base station S14 and base station S15 is 6. There is a jump relationship between base station S14 and base station S17, and the jump frequency of the electronic device between base station S14 and base station S17 is 12. There is a jump relationship between base station S14 and base station S18, and the jump frequency of the electronic device between base station S14 and base station S18 is 11. There is a jump relationship between base station S15 and base station S18, and the jump frequency of the electronic device between base station S15 and base station S18 is 5. There is a jump relationship between base station S16 and base station S17,Moreover, the switching frequency of the electronic device between base station S16 and base station S17 is 1. There is a switching relationship between base station S17 and base station S18, and the switching frequency of the electronic device between base station S17 and base station S18 is 10. Then the obtained directed graph of base stations is as follows. Figure 2 As shown.

[0047] Through the directed graph of base stations as shown. Figure 2 It can be determined that the maximum switching frequency between any two base stations with a switching relationship among base stations S1, S2, S3, and S4 of the electronic device is 12 and the minimum is 1. Among base stations S1, S2, S3, and S4 of the electronic device, the maximum switching frequency between any two base stations with a switching relationship with base stations S5 to S18 is 1 and the minimum is also 1. For example, the switching frequency of the electronic device between base station S4 and base station S5 is 1. Then S1, S2, S3, and S4 can be used as the candidate base station set M1.

[0048] Similarly, base stations S10, S11, S12, and S13 can be used as the candidate base station set M2, and base stations S14, S15, S17, and S18 can be used as the candidate base station set M3, thus obtaining three candidate base station sets. If the current base station connected by the electronic device is base station S11, it can be determined that the target base station set to which base station S11 belongs is the candidate base station set M2; if the current base station connected by the electronic device is base station S17, it can be determined that the target base station set to which base station S17 belongs is the candidate base station set M3.

[0049] In an optional embodiment, different candidate base station sets can be determined according to the switching frequency of the electronic device between different historical base stations through the community discovery strategy.

[0050] In an optional embodiment, the behavior prediction method further includes:

[0051] During the process of the electronic device establishing a connection with each historical base station until the electronic device disconnects from each historical base station, obtain historical user behavior information to obtain the historical user behavior information corresponding to each historical base station.

[0052] After obtaining the candidate base station set according to the directed graph of base stations, it further includes:

[0053] Statistical historical user behavior information corresponding to each historical base station in the candidate base station set to obtain the historical user behavior information corresponding to the candidate base station set.

[0054] Predict user behavior according to the target base station set to obtain a prediction result, including:

[0055] (1) Determine the target user behavior information corresponding to the target base station set from the historical user behavior information corresponding to the candidate base station set;

[0056] (2) Perform user behavior prediction based on the target user behavior information to obtain a prediction result.

[0057] For example, during the process from when the electronic device establishes a connection with the historical base station S1 to when the electronic device disconnects from the historical base station S1, the electronic device obtains user behavior information as the historical user behavior information. Among them, the user behavior information may include user behavior and the time of user behavior, such as having a video conference at 11 am. Then, after obtaining the candidate base station set, the electronic device can count the historical user behavior information corresponding to the historical base stations in the candidate base station set to obtain the historical user behavior information corresponding to the candidate base station set.

[0058] For example, assume the candidate base station set is M1. The electronic device can count the historical user behavior information corresponding to the historical base station S1, the historical user behavior information corresponding to the historical base station S2, the historical user behavior information corresponding to the historical base station S3, and the historical user behavior information corresponding to the historical base station S4 to obtain the historical user behavior information corresponding to the candidate base station set M1. Assume the target base station set is the candidate base station set M1. Then, user behavior prediction can be performed based on the historical user behavior information corresponding to the candidate base station set M1 to obtain a prediction result. For example, assume the historical user behavior information corresponding to the candidate base station set M1 includes watching videos and playing games. Then, the prediction result can be: watching videos and playing games.

[0059] In an optional embodiment, counting the historical user behavior information corresponding to each historical base station in the candidate base station set to obtain the historical user behavior information corresponding to the candidate base station set includes:

[0060] Count the historical user behavior information corresponding to each historical base station in the candidate base station set for each time interval to obtain the historical user behavior information corresponding to the candidate base station set for each time interval;

[0061] Determining the target user behavior information corresponding to the target base station set from the historical user behavior information corresponding to the candidate base station set includes:

[0062] Determine the target user behavior information corresponding to the target base station set for each time interval from the historical user behavior information corresponding to the candidate base station set for each time interval;

[0063] Performing user behavior prediction based on the target user behavior information to obtain a prediction result includes:

[0064] Perform user behavior prediction based on the target user behavior information corresponding to the target base station set for each time interval to obtain a prediction result.

[0065] For example, during the process of the electronic device establishing a connection with the historical base station S1 until the electronic device disconnects from the historical base station S1, the electronic device obtains user behavior information as historical user behavior information. Among them, the user behavior information may include user behavior and the user behavior time, such as having a video conference at 11:00 am. Then, after obtaining the candidate base station set, the electronic device can count the historical user behavior information corresponding to the historical base station in the candidate base station set for each time interval, and obtain the historical user behavior information corresponding to the candidate base station set for each time interval.

[0066] For example, assuming the candidate base station set is M1, the electronic device can count the historical user behavior information corresponding to the historical base station S1 for each time interval, the historical user behavior information corresponding to the historical base station S2 for each time interval, the historical user behavior information corresponding to the historical base station S3 for each time interval, and the historical user behavior information corresponding to the historical base station S4 for each time interval, and obtain the historical user behavior information corresponding to the candidate base station set M1 for each time interval. For example, assuming that at 19:00, the electronic device establishes a connection with the historical base station S1, and at 20:00, the electronic device disconnects from the historical base station S1. During this period, the obtained user behaviors are: watching videos through a certain video application, swiping videos through a certain short video application, and playing games through a certain game application. Assuming that at 20:00, the electronic device establishes a connection with the historical base station S2, and at 21:00, the electronic device establishes a connection with the historical base station S2. During this period, the obtained user behavior is: playing games through a certain game application. Assuming that at 21:00, the electronic device establishes a connection with the historical base station S3, and at 22:00, the electronic device establishes a connection with the historical base station S3. During this period, the obtained user behavior is: playing games through a certain game application. Assuming that at 22:00, the electronic device establishes a connection with the historical base station S4, and at 23:00, the electronic device establishes a connection with the historical base station S4. During this period, the obtained user behavior is: playing games through a certain game application.

[0067] Then, it can be determined that the historical user behavior information corresponding to the candidate base station set M1 for each time interval includes: from 19:00 to 20:00, watching videos through a certain video application, swiping videos through a certain short video application, and playing games through a certain game application; from 20:00 to 21:00, playing games through a certain game application; from 21:00 to 22:00, playing games through a certain game application, and from 22:00 to 23:00, playing games through a certain game application. Assuming that the target base station set is the candidate base station set M1 and the current time is 21:00, then the obtained prediction result may be: playing games through a certain game application.

[0068] In an optional embodiment, after obtaining the candidate base station set, it further includes:

[0069] (1) If there is no such matching base station in the set of candidate base stations, obtain the current base station sequence to which the electronic device is connected, where the current base station sequence includes the current base station;

[0070] (2) Obtain the historical base station sequence to which the electronic device is connected;

[0071] (3) Determine a target base station sequence that matches the current base station sequence from the historical base station sequence;

[0072] (4) Perform destination prediction based on the target base station sequence and the current base station sequence.

[0073] If there is no matching base station in the set of candidate base stations that matches the current base station, it means that the electronic device is not in the user's usual residence. Then, the electronic device can detect whether the user carrying the electronic device is going to a certain user's usual residence, such as the user's place of residence. That is, the electronic device can obtain the current base station sequence including the current base station to which the electronic device is connected, and perform destination prediction based on this current base station sequence to predict whether the user carrying the electronic device is going to a certain user's usual residence, such as the user's place of residence.

[0074] Generally speaking, under the same path, the base station sequences to which the electronic device is connected will be relatively similar. Then, we can obtain the historical base station sequence in advance and set the corresponding destination for the same historical base station sequence. For example, set the area where the corresponding set of candidate base stations is located as the destination corresponding to the historical base station sequence. When the current base station sequence to which the electronic device is connected matches the historical base station sequence, the electronic device can predict the area where the corresponding set of candidate base stations of this historical base station sequence is located as the destination corresponding to the current base station sequence to which the electronic device is connected.

[0075] Among them, when the matching degree between the current base station sequence to which the electronic device is connected and the historical base station sequence is greater than or equal to the preset matching degree, it is determined that the current base station sequence to which the electronic device is connected matches the historical base station sequence. The matching degree between the current base station sequence to which the electronic device is connected and the historical base station sequence is determined by calculating the percentage of the same base stations in the current base station sequence and the historical base station sequence in all the base stations included in the base station sequence with more base stations in the current base station sequence or the historical base station sequence. The preset matching degree can be set by those skilled in the art according to actual needs, or can be set by the electronic device based on certain rules.

[0076] For example, Figure 2As shown, the area where the candidate base station set M2 is located can be set as the destination corresponding to the historical base station sequences S5, S6, S7, S8, and S9. Assuming the matching degree is 80%, when the current base station sequence is S5, S6, S7, S8, it is determined that the matching degree between the current base station sequence and the historical base station sequence is 80%. The electronic device can predict that the destination is the area where the candidate base station set M2 is located. If the candidate base station set M2 represents the user's residence, then the electronic device can predict that the destination is the user's residence.

[0077] In an optional embodiment, after predicting the user behavior according to the target base station set and obtaining the prediction result, it further includes:

[0078] (1) Determine the task to be executed according to the prediction result;

[0079] (2) Execute the task to be executed.

[0080] Among them, the task to be executed may include at least one of controlling the corresponding smart home device, starting the corresponding application, and turning on the corresponding operating mode. The smart furniture device may include a smart air conditioner, a smart refrigerator, or a smart curtain, etc. The operating mode may include a power-saving mode (power saving first), a performance mode (performance first), or a balanced mode (balancing power saving and performance), etc.

[0081] For example, assume the prediction result is: turn on the smart air conditioner and adjust the temperature to 23 degrees. That is to say, when the current base station connected to the electronic device belongs to the target base station set, the electronic device predicts the user behavior as: turn on the smart air conditioner and adjust the temperature to 23 degrees. Then, when the smart air conditioner is not turned on, the electronic device can automatically start the smart air conditioner and automatically adjust the temperature to 23 degrees. When the smart air conditioner is already turned on, the electronic device can do nothing.

[0082] Another example, assume the prediction result is: start a certain game application. That is to say, when the current base station connected to the electronic device belongs to the target base station set, the electronic device predicts the user behavior as: start a certain game application. Then, when the game application is not started, the electronic device can automatically start a certain game application. When the game application has already been started, the electronic device can do nothing.

[0083] Another example, assume the prediction result is: turn on the power-saving mode. That is to say, when the current base station connected to the electronic device belongs to the target base station set, the electronic device predicts the user behavior as: turn on the power-saving mode. Then, when the power-saving mode is not turned on, the electronic device can turn on the power-saving mode. When the power-saving mode has already been turned on, the electronic device can do nothing.

[0084] In an optional embodiment, after predicting the user behavior according to the target base station set and obtaining the prediction result, it further includes:

[0085] (1) Generate corresponding reminder information according to the prediction result;

[0086] (2) Output the reminder information.

[0087] Among them, the reminder information includes at least one of the reminder information for reminding to control the corresponding smart home device, the reminder information for reminding to start the corresponding application, and the reminder information for reminding to turn on the corresponding operation mode.

[0088] To avoid the situation of automatically executing tasks that the user does not want to execute, after obtaining the prediction result, corresponding reminder information can be generated according to the prediction result, and the reminder information can be output.

[0089] For example, assume that the prediction result is: turn on the smart air conditioner and adjust the temperature to 23 degrees. Then, when the smart air conditioner is not turned on, the electronic device can generate and output the prompt information "Do you need to turn on the smart air conditioner and adjust the temperature to 23 degrees"; if the user selects yes, the electronic device can turn on the smart air conditioner and adjust the temperature to 23 degrees; if the user selects no, the electronic device can do nothing. When the smart air conditioner is already turned on, the electronic device can do nothing.

[0090] Another example, assume that the prediction result is: start a certain game application. When the game application is not started, the electronic device can generate and output the prompt information "Do you want to start the game application"; if the user selects yes, the electronic device can automatically start the game application; if the user selects no, the electronic device can do nothing. When the game application is already started, the electronic device can do nothing.

[0091] Another example, assume that the prediction result is: turn on the performance mode. When the performance mode is not turned on, the electronic device can generate and output the prompt information "Do you want to turn on the performance mode"; if the user selects yes, the electronic device can automatically turn on the performance mode; if the user selects no, the electronic device can do nothing. When the performance mode is already turned on, the electronic device can do nothing.

[0092] Please refer to Figure 3 , Figure 3 which is the second process schematic diagram of the behavior prediction method provided by the embodiment of the present application. The process may include:

[0093] In 201, determine the historical base stations connected by the electronic device and the jump frequency of the electronic device jumping between the connected historical base stations.

[0094] In 202, a base station directed graph is obtained according to historical base stations and the hopping frequency of the electronic device hopping between the connected historical base stations. The base station directed graph includes vertices, edges, and weights of the edges. Among them, the vertices represent the historical base stations connected by the electronic device, the edges represent that there is a hopping relationship between the two historical base stations it connects, and the weight of the edge represents the hopping frequency of the electronic device hopping between the two historical base stations connected by the edge.

[0095] In 203, a candidate base station set is obtained according to the base station directed graph. Among them, the hopping frequency of the electronic device hopping between the base stations in the candidate base station set is greater than or equal to the hopping frequency of the electronic device hopping between the base stations in the candidate base station set and the base stations outside the candidate base station set.

[0096] In 204, during the process of the electronic device establishing a connection with each historical base station to disconnecting from each historical base station, historical user behavior information is obtained, and the historical user behavior information corresponding to each historical base station is obtained.

[0097] In 205, the historical user behavior information corresponding to each historical base station in the candidate base station set for each time interval is counted, and the historical user behavior information corresponding to the candidate base station set for each time interval is obtained.

[0098] In 206, the current base station connected by the electronic device is determined.

[0099] In 207, the candidate base station set is obtained.

[0100] In 208, if there is a matching base station in the candidate base station set that matches the current base station, the candidate base station set with the matching base station is determined as the target base station set to which the current base station belongs.

[0101] In 209, the target user behavior information corresponding to the target base station set for each time interval is determined from the historical user behavior information corresponding to the candidate base station set for each time interval.

[0102] In 210, user behavior prediction is performed according to the target user behavior information corresponding to the target base station set for each time interval, and a prediction result is obtained.

[0103] In 211, if there is no matching base station in the candidate base station set, the current base station sequence connected by the electronic device is obtained, and the current base station sequence includes the current base station.

[0104] In 212, the historical base station sequence connected by the electronic device is obtained.

[0105] In 213, a target base station sequence that matches the current base station sequence is determined from the historical base station sequence.

[0106] In 214, destination prediction is performed according to the target base station sequence and the current base station sequence.

[0107] It can be understood that for the specific implementation of steps 201 to 214, reference can be made to the previous embodiments, which will not be elaborated here.

[0108] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of the behavior prediction device provided by the embodiment of the present application. The behavior prediction device 300 includes: a base station determination module 301, a set determination module 302, and a behavior prediction module 303.

[0109] The base station determination module 301 is used to determine the current base station to which the electronic device is connected.

[0110] The set determination module 302 is used to determine the target base station set to which the current base station belongs, where the target base station set is obtained according to the jump frequency of the electronic device jumping between historical base stations, and the jump frequency of the electronic device jumping between the base stations in the target base station set is greater than or equal to the jump frequency of the electronic device jumping between the base stations in the target base station set and the base stations outside the target base station set.

[0111] The behavior prediction module 303 is used to perform user behavior prediction according to the target base station set to obtain a prediction result.

[0112] In an optional embodiment, the behavior prediction device further includes a set acquisition module, and the set acquisition module can be used to: acquire a candidate base station set;

[0113] The set determination module 302 can be used to: if there is a matching base station in the candidate base station set that matches the current base station, then determine the candidate base station set where the matching base station exists as the target base station set to which the current base station belongs

[0114] In an optional embodiment, the set determination module 302 may be configured to: determine the historical base stations to which the electronic device is connected, and the number of times the electronic device jumps between the connected historical base stations; obtain a base station directed graph according to the historical base stations and the number of times the electronic device jumps between the connected historical base stations, where the base station directed graph includes vertices, edges, and weights of the edges, wherein the vertices represent the historical base stations to which the electronic device is connected, the edges represent that there is a jump relationship between two historical base stations to which it is connected, and the weights of the edges represent the number of times the electronic device jumps between the two historical base stations connected by the edge; obtain a candidate base station set according to the base station directed graph, wherein the number of times the electronic device jumps between the base stations in the candidate base station set is greater than or equal to the number of times the electronic device jumps between the base stations in the candidate base station set and the base stations outside the candidate base station set; determine the target base station set to which the current base station belongs from the candidate base station set.

[0115] In an optional embodiment, the behavior prediction device 300 may further include an information acquisition module, and the information acquisition module may be configured to: during the process of the electronic device establishing a connection with each historical base station to the electronic device disconnecting from each historical base station, acquire historical user behavior information to obtain historical user behavior information corresponding to each historical base station; count the historical user behavior information corresponding to each historical base station in the candidate base station set to obtain historical user behavior information corresponding to the candidate base station set; the behavior prediction module 303 may be configured to: determine the target user behavior information corresponding to the target base station set from the historical user behavior information corresponding to the candidate base station set; perform user behavior prediction according to the target user behavior information to obtain a prediction result.

[0116] In an optional embodiment, the information acquisition module may be configured to: count the historical user behavior information corresponding to each historical base station in the candidate base station set for each time interval to obtain historical user behavior information corresponding to the candidate base station set for each time interval; the behavior prediction module 303 may be configured to: determine the target user behavior information corresponding to the target base station set for each time interval from the historical user behavior information corresponding to the candidate base station set for each time interval; perform user behavior prediction according to the target user behavior information corresponding to the target base station set for each time interval to obtain a prediction result.

[0117] In an optional embodiment, the behavior prediction device 300 may further include a destination prediction module, and the destination prediction module may be used to: if there is no such matching base station in the candidate base station set, obtain the current base station sequence to which the electronic device is connected, where the current base station sequence includes the current base station; obtain the historical base station sequence to which the electronic device is connected; determine a target base station sequence matching the current base station sequence from the historical base station sequence; and perform destination prediction according to the target base station sequence and the current base station sequence.

[0118] In an optional embodiment, the behavior prediction device 300 may further include a task execution module, and the task execution module may be used to: determine a task to be executed according to the prediction result; and execute the task to be executed.

[0119] In an optional embodiment, the task to be executed includes at least one of: controlling a corresponding smart home device, starting a corresponding application, and enabling a corresponding operation mode.

[0120] In an optional embodiment, the behavior prediction device 300 may further include an information output module, and the information output module may be used to: generate a corresponding reminder message according to the prediction result; and output the reminder message.

[0121] In an optional embodiment, the reminder message includes at least one of: a reminder message for reminding to control a corresponding smart home device, a reminder message for reminding to start a corresponding application, and a reminder message for reminding to enable a corresponding operation mode.

[0122] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed on a computer, the computer is enabled to execute the behavior prediction method provided in this embodiment.

[0123] The embodiment of the present application further provides an electronic device, including a memory and a processor. The processor is configured to execute the behavior prediction method provided in this embodiment by calling the computer program stored in the memory.

[0124] For example, the above-mentioned electronic device may be a mobile terminal such as a tablet computer or a smart phone. Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of the electronic device provided in the embodiment of the present application.

[0125] The electronic device 400 may include components such as a processor 401 and a memory 402. Those skilled in the art can understand that Figure 5 the structural diagram of the electronic device shown in does not constitute a limitation on the electronic device, and it may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements. For example, the electronic device 400 may further include a screen.

[0126] The processor 401 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines. By running or executing the application programs stored in the memory 402 and calling the data stored in the memory 402, it executes various functions of the electronic device and processes data, thereby monitoring the entire electronic device.

[0127] The memory 402 can be used to store application programs and data. The application programs stored in the memory 402 contain executable codes. The application programs can form various functional modules. The processor 401 executes various functional applications and data processing by running the application programs stored in the memory 402.

[0128] In this embodiment, the processor 401 in the electronic device will, according to the following instructions, load the executable codes corresponding to the processes of one or more application programs into the memory 402, and the processor 401 will run the application programs stored in the memory 402, so as to achieve:

[0129] Determine the current base station to which the electronic device is connected;

[0130] Determine the target base station set to which the current base station belongs, where the target base station set is obtained according to the hopping frequency of the electronic device hopping between historical base stations, and the hopping frequency of the electronic device hopping between the base stations in the target base station set is greater than or equal to the hopping frequency of the electronic device hopping between the base stations in the target base station set and the base stations outside the target base station set;

[0131] Perform user behavior prediction according to the target base station set to obtain a prediction result.

[0132] In an optional embodiment, before the processor 401 executes determining the target base station set to which the current base station belongs, it may also execute: obtaining a candidate base station set; when the processor 401 executes determining the target base station set to which the current base station belongs, it may execute: if there is a matching base station in the candidate base station set that matches the current base station, then determine the candidate base station set where the matching base station exists as the target base station set to which the current base station belongs.

[0133] In an alternative embodiment, before the processor 401 executes the determination of the current base station to which the electronic device is connected, it further includes: determining the historical base stations to which the electronic device is connected, and the number of jump frequencies of the electronic device jumping between the connected historical base stations; obtaining a base station directed graph according to the historical base stations and the number of jump frequencies of the electronic device jumping between the connected historical base stations, where the base station directed graph includes vertices, edges, and weights of the edges. Among them, the vertices represent the historical base stations to which the electronic device is connected, the edges represent that there is a jump relationship between two historical base stations to which it is connected, and the weight of the edge represents the number of jump frequencies of the electronic device jumping between the two historical base stations connected by the edge; obtaining a candidate base station set according to the base station directed graph, where the number of jump frequencies of the electronic device jumping between the base stations in the candidate base station set is greater than or equal to the number of jump frequencies of the electronic device jumping between the base stations in the candidate base station set and the base stations outside the candidate base station set; when the processor 401 executes the determination of the target base station set to which the current base station belongs, it may execute: determining the target base station set to which the current base station belongs from the candidate base station set.

[0134] In an alternative embodiment, the processor 401 may further execute: during the process of the electronic device establishing a connection with each historical base station to the electronic device disconnecting from each historical base station, obtaining historical user behavior information to obtain historical user behavior information corresponding to each historical base station; after the processor 401 executes obtaining the candidate base station set according to the base station directed graph, it may further execute: counting the historical user behavior information corresponding to each historical base station in the candidate base station set to obtain historical user behavior information corresponding to the candidate base station set; when the processor 401 executes the user behavior prediction according to the target base station set to obtain a prediction result, it may execute: determining the target user behavior information corresponding to the target base station set from the historical user behavior information corresponding to the candidate base station set; performing user behavior prediction according to the target user behavior information to obtain a prediction result.

[0135] In an optional embodiment, when the processor 401 executes to obtain the historical user behavior information corresponding to each historical base station in the candidate base station set, and obtains the historical user behavior information corresponding to the candidate base station set, the following operations may be performed: counting the historical user behavior information corresponding to each historical base station in the candidate base station set for each time interval, to obtain the historical user behavior information corresponding to the candidate base station set for each time interval; when the processor 401 executes to determine the target user behavior information corresponding to the target base station set from the historical user behavior information corresponding to the candidate base station set, the following operations may be performed: determining the target user behavior information corresponding to the target base station set for each time interval from the historical user behavior information corresponding to the candidate base station set for each time interval; when the processor 401 executes to perform user behavior prediction based on the target user behavior information to obtain a prediction result, the following operations may be performed: performing user behavior prediction based on the target user behavior information corresponding to the target base station set for each time interval to obtain a prediction result.

[0136] In an optional embodiment, after the processor 401 executes to obtain the candidate base station set, the following operations may further be performed: if the matching base station does not exist in the candidate base station set, obtaining the current base station sequence to which the electronic device is connected, where the current base station sequence includes the current base station; obtaining the historical base station sequence to which the electronic device is connected; determining a target base station sequence that matches the current base station sequence from the historical base station sequence; and performing destination prediction based on the target base station sequence and the current base station sequence.

[0137] In an optional embodiment, after the processor 401 executes to perform user behavior prediction based on the target base station set to obtain a prediction result, the following operations may further be performed: determining a task to be executed according to the prediction result; and executing the task to be executed.

[0138] In an optional embodiment, the task to be executed includes at least one of: controlling corresponding smart home devices, starting corresponding applications, and enabling corresponding operation modes.

[0139] In an optional embodiment, after the processor 401 executes to perform user behavior prediction based on the target base station set to obtain a prediction result, the following operations may further be performed: generating corresponding reminder information according to the prediction result; and outputting the reminder information.

[0140] In an optional embodiment, the reminder information includes at least one of: reminder information for reminding to control corresponding smart home devices, reminder information for reminding to start corresponding applications, and reminder information for reminding to enable corresponding operation modes.

[0141] In the above embodiments, the descriptions of the various embodiments each have their own focuses. For the parts not detailed in a certain embodiment, reference may be made to the detailed description of the behavior prediction method above, and details will not be repeated here.

[0142] The behavior prediction device provided in the embodiments of the present application and the behavior prediction method in the above embodiments belong to the same concept. Any method provided in the embodiments of the behavior prediction method can be run on the behavior prediction device. The specific implementation process is detailed in the embodiments of the behavior prediction method, and details will not be repeated here.

[0143] It should be noted that for the behavior prediction method in the embodiments of the present application, those of ordinary skill in the art can understand that all or part of the process of implementing the behavior prediction method in the embodiments of the present application can be completed by controlling related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, such as stored in a memory and executed by at least one processor. During the execution process, it can include the process of the embodiments of the behavior prediction method. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), etc.

[0144] It can be understood that in the specific implementation of the present application, user information is involved, such as data related to application usage behavior data, logs, etc. When the above embodiments of the present application are applied to specific products or technologies, user authorization, permission or consent is required, and the collection, use and processing of related data need to comply with the relevant laws, regulations and standards of relevant countries and regions.

[0145] For the behavior prediction device in the embodiments of the present application, its various functional modules can be integrated in a processing chip, or each module can exist physically separately, or two or more modules can be integrated in one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk or an optical disk.

[0146] The above has introduced in detail a behavior prediction method, device, storage medium and electronic device provided in the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A behavior prediction method, characterized in that, Including: Determine the current base station to which the electronic device is connected; Determine the historical base stations to which the electronic device is connected, and the jump frequency of the electronic device jumping between the connected historical base stations; Obtain a base station directed graph according to the historical base stations and the jump frequency of the electronic device jumping between the connected historical base stations. The base station directed graph includes vertices, edges, and weights of the edges. Among them, the vertices represent the historical base stations to which the electronic device is connected, the edges represent that there is a jump relationship between two connected historical base stations, and the weights of the edges represent the jump frequency of the electronic device jumping between the two historical base stations connected by the edge; Obtain a candidate base station set according to the base station directed graph, where the jump frequency of the electronic device jumping between the base stations in the candidate base station set is greater than or equal to the jump frequency of the electronic device jumping between the base stations in the candidate base station set and the base stations outside the candidate base station set; Obtain the candidate base station set; If there is a matching base station in the candidate base station set that matches the current base station, determine the candidate base station set where the matching base station exists as the target base station set to which the current base station belongs. The target base station set is obtained according to the jump frequency of the electronic device jumping between historical base stations. The jump frequency of the electronic device jumping between the base stations in the target base station set is greater than or equal to the jump frequency of the electronic device jumping between the base stations in the target base station set and the base stations outside the target base station set; Perform user behavior prediction according to the target base station set to obtain a prediction result.

2. The behavior prediction method according to claim 1, wherein The method further includes: During the process of the electronic device establishing a connection with each historical base station to disconnecting from each historical base station, obtain historical user behavior information to obtain historical user behavior information corresponding to each historical base station; After obtaining the candidate base station set according to the base station directed graph, it further includes: Count the historical user behavior information corresponding to each historical base station in the candidate base station set to obtain the historical user behavior information corresponding to the candidate base station set; The performing user behavior prediction according to the target base station set to obtain a prediction result includes: Determine the target user behavior information corresponding to the target base station set from the historical user behavior information corresponding to the candidate base station set; Perform user behavior prediction according to the target user behavior information to obtain a prediction result.

3. The behavior prediction method according to claim 2, wherein The counting the historical user behavior information corresponding to each historical base station in the candidate base station set to obtain the historical user behavior information corresponding to the candidate base station set includes: Count the historical user behavior information corresponding to each historical base station in the candidate base station set for each time interval to obtain the historical user behavior information corresponding to the candidate base station set for each time interval; The determining the target user behavior information corresponding to the target base station set from the historical user behavior information corresponding to the candidate base station set includes: Determine the target user behavior information corresponding to the target base station set for each time interval from the historical user behavior information corresponding to the candidate base station set for each time interval; Performing user behavior prediction based on the target user behavior information to obtain a prediction result, including: Performing user behavior prediction based on the target user behavior information corresponding to the target base station set in each time interval to obtain a prediction result.

4. The behavior prediction method according to claim 1, wherein After obtaining the candidate base station set, further including: If the matching base station does not exist in the candidate base station set, obtaining the current base station sequence to which the electronic device is connected, where the current base station sequence includes the current base station; Obtaining the historical base station sequence to which the electronic device is connected; Determining a target base station sequence matching the current base station sequence from the historical base station sequence; Performing destination prediction based on the target base station sequence and the current base station sequence.

5. The behavior prediction method according to claim 1, wherein After performing user behavior prediction based on the target base station set to obtain a prediction result, further including: Determining a task to be executed according to the prediction result; Executing the task to be executed.

6. The behavior prediction method according to claim 5, wherein The task to be executed includes at least one of controlling corresponding smart home devices, starting corresponding applications, and enabling corresponding operation modes.

7. The behavior prediction method according to claim 1, wherein After performing user behavior prediction based on the target base station set to obtain a prediction result, further including: Generating a corresponding reminder message according to the prediction result; Outputting the reminder message.

8. The behavior prediction method according to claim 7, wherein The reminder message includes at least one of a reminder message for reminding to control corresponding smart home devices, a reminder message for reminding to start corresponding applications, and a reminder message for reminding to enable corresponding operation modes.

9. A behavior prediction device, characterized in that, Including: A base station determination module for determining the current base station to which the electronic device is connected; A set determination module for determining the historical base stations to which the electronic device is connected and the jump frequency of the electronic device between the connected historical base stations; Obtaining a base station directed graph according to the historical base stations and the jump frequency of the electronic device between the connected historical base stations, where the base station directed graph includes vertices, edges, and weights of the edges. The vertices represent the historical base stations to which the electronic device is connected, the edges represent that there is a jump relationship between two connected historical base stations, and the weights of the edges represent the jump frequency of the electronic device between the two historical base stations connected by the edge. Obtaining a candidate base station set according to the base station directed graph, where the jump frequency of the electronic device between the base stations in the candidate base station set is greater than or equal to the jump frequency of the electronic device between the base stations in the candidate base station set and the base stations outside the candidate base station set. Determining the target base station set to which the current base station belongs from the candidate base station set; A set acquisition module for acquiring the candidate base station set; The set determination module is further configured to, if there is a matching base station in the candidate base station set that matches the current base station, determine the candidate base station set where the matching base station exists as the target base station set to which the current base station belongs, where the target base station set is obtained according to the jump frequency of the electronic device jumping between historical base stations, and the jump frequency of the electronic device jumping between the base stations in the target base station set is greater than or equal to the jump frequency of the electronic device jumping between the base stations in the target base station set and the base stations outside the target base station set; The behavior prediction module is configured to perform user behavior prediction based on the target base station set to obtain a prediction result.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program runs on a computer, the computer is caused to execute the behavior prediction method according to any one of claims 1 to 8.

11. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory stores a computer program, and the processor is configured to execute the behavior prediction method according to any one of claims 1 to 8 by calling the computer program stored in the memory.

Images