CN116561437A

CN116561437A - User behavior prediction method, terminal equipment and storage medium

Info

Publication number: CN116561437A
Application number: CN202310837975.9A
Authority: CN
Inventors: 赵杰; 孙铭椿
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2023-07-10
Filing date: 2023-07-10
Publication date: 2023-08-08

Abstract

The application provides a user behavior prediction method, terminal equipment and a storage medium, and relates to the technical field of communication. The terminal equipment can acquire target track information of the terminal equipment and reference track information corresponding to a preset time period where the current moment is located. The target track information indicates base stations which the terminal equipment passes through in time sequence within a first preset time before the current moment, and the target track information comprises base station identifications of at least one base station arranged in time sequence. And the terminal equipment obtains a prediction result of the target behavior through the similarity of the target track information and the reference track information. In this way, accuracy of end-side prediction of user behavior can be improved.

Description

User behavior prediction method, terminal equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of terminals, in particular to a user behavior prediction method, terminal equipment and a storage medium.

Background

With research and development of terminal technology, functions which can be realized by the terminal equipment are more and more widely implemented. The user behavior prediction is used as a new function of the terminal equipment, and can be used for predicting the user behavior. For example, through browsing data of the user on the shopping webpage, preference commodities of the user can be predicted, and accordingly relevant information of the preference commodities can be recommended to the user in the shopping webpage.

At present, the terminal equipment can predict the user behavior through the collected user data, so that personalized service is provided for the user, and user experience is improved. However, due to the limitation of the computing power and the power consumption of the terminal, the accuracy of the terminal device for some user behavior predictions needs to be improved, and the user experience needs to be improved.

Disclosure of Invention

The embodiment of the application provides a user behavior prediction method, terminal equipment and storage medium, which can improve the accuracy of the terminal equipment on the user behavior prediction and promote the user experience.

In order to achieve the above purpose, the embodiments of the present application adopt the following technical solutions:

in a first aspect, a method for predicting user behavior is provided, the method comprising: and acquiring target track information of the terminal equipment, wherein the target track information represents base stations which the terminal equipment passes by in time sequence in a first preset duration before the current moment, and the target track information comprises base station identifications of at least one base station arranged in time sequence. If the current time is within the preset time period, acquiring reference track information corresponding to the preset time period in which the current time is, wherein the reference track information is used for indicating a base station passing in a first preset time period before the occurrence of the target behavior. Further, the similarity of the target track information and the reference track information is determined, and the prediction result of the target behavior is determined according to the similarity of the target track information and the reference track information.

In the method, the terminal equipment can consider whether the latest target track information of the user is similar to the past reference track information of the user in the process of predicting the target behavior. The reference track information may represent a user's usual location within a period of time before the occurrence of the target behavior, and predict whether the user has a behavior intention of the target behavior according to the similarity between the target track information and the reference track information. Therefore, the nearest position track information of the user can be considered in the process of predicting the target behavior, so that the accuracy of predicting the target behavior by the terminal equipment can be improved, and the accurate prediction of the target behavior is realized. Meanwhile, the target track information of the user is represented by the base station identifier, so that the influence of the base station identifier on the power consumption of the terminal equipment is small, and the influence of accurately predicting the target behavior on the terminal equipment can be reduced.

In a possible implementation manner of the first aspect, after determining the prediction result of the target behavior, if the prediction result of the target behavior indicates that there is a behavior intention of the target behavior, displaying a function icon of the target application in the display interface; wherein the target application is for performing a target behavior.

In another possible implementation manner of the first aspect, in a case that the display interface displays the function icon of the target application for the second preset duration, the function icon of the target application is canceled in the display interface.

In another possible implementation manner of the first aspect, the reference track information includes n pieces of first track information arranged in time sequence. The terminal equipment can split target track information to obtain n sections of second track information, the time length of the ith section of second track information is matched with the time length of the ith section of first track information, i is a positive integer less than or equal to n, and n is a positive integer. And calculating the similarity between each piece of second track information and the corresponding first track information, and determining the similarity between the target track information and the reference track information according to the n similarities between the n pieces of second track information and the corresponding first track information. The similarity of the i-th section second track information and the i-th section first track information is the i-th similarity among n-th similarities.

In another possible implementation manner of the first aspect, the terminal device weights the n similarities according to preset weight parameters corresponding to the n similarities respectively, and determines the similarity between the target track information and the reference track information; wherein, the preset weight parameters corresponding to the n similarities are sequentially increased.

In another possible implementation manner of the first aspect, each piece of first sub-track information includes at least one base station identifier and a frequency corresponding to each base station identifier. The terminal equipment searches the same base station identification in the ith section second track information and the ith section first track information aiming at the ith section second track information in the n sections second track information. And obtaining the similarity of the second track information of the ith section and the first track information of the ith section according to the frequency corresponding to the same base station identifier.

In another possible implementation manner of the first aspect, the terminal device merges the same base station identifiers adjacently arranged in the target track information to obtain target track information after duplication removal, and further splits the target track information after duplication removal to obtain n segments of second track information.

In another possible implementation manner of the first aspect, one history track includes a plurality of base station identities arranged in time sequence before one target behavior. The terminal equipment splits a historical track into n sections of third track information, and counts the base station identifications of the i sections of third track information in the historical tracks to obtain the i sections of first track information of the reference track information. Wherein i is a positive integer less than or equal to n, and n is a positive integer.

In another possible implementation manner of the first aspect, for a plurality of ith segment of third track information in a plurality of historical tracks, the terminal device counts the frequency of each base station identifier to obtain the ith segment of first track information of the reference track information. The reference trajectory information includes a plurality of different base station identities and a frequency corresponding to each base station identity.

In another possible implementation manner of the first aspect, the terminal device generates a behavior feature for predicting the target behavior according to the similarity between the target track information and the reference track information, and inputs the behavior feature into a preset machine learning model to obtain a prediction result of the target behavior output by the preset machine learning model. The preset machine learning model is obtained by model training based on sample characteristics of training samples and sample labels of the training samples, the training samples comprise sample characteristics, the sample characteristics are obtained based on similarity of sample track information and reference track information of a user in a first historical preset duration, the sample track information comprises at least one base station identifier arranged according to a time sequence, and the sample labels of the training samples are used for indicating execution target behaviors or non-execution target behaviors.

In another possible implementation manner of the first aspect, the terminal device obtains the target track information of the terminal device if a preset condition is met, where the preset condition includes that the current time is within a preset time period, and the current display interface is one or more of desktop interfaces.

In a second aspect, the present application provides a terminal device, including: a memory and one or more processors, the memory coupled to the processors. The memory has stored therein computer program code comprising computer instructions. The computer instructions, when executed by the processor, cause the terminal to perform the steps of: acquiring target track information of terminal equipment; the target track information represents base stations which the terminal equipment passes through in time sequence in a first preset time before the current moment, and the target track information comprises base station identifiers of at least one base station arranged in time sequence; if the current moment is in the preset time period, acquiring reference track information corresponding to the preset time period in which the current moment is; the reference track information is used for indicating base stations passing by within a first preset duration before the occurrence of the target behavior; determining the similarity between the target track information and the reference track information; and determining a prediction result of the target behavior according to the similarity of the target track information and the reference track information.

In a possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: if the predicted result of the target behavior indicates that the behavior intention of the target behavior exists, displaying a functional icon of the target application in a display interface; wherein the target application is for performing a target behavior.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: and canceling the function icon of the display target application in the display interface under the condition that the function icon of the display interface displays the target application reaches the second preset time length.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: splitting target track information to obtain n sections of second track information; the time length of the second track information of the ith section is matched with the time length of the first track information of the ith section, i is a positive integer less than or equal to n, and n is a positive integer; calculating the similarity between each section of second track information and the corresponding first track information; according to n pieces of similarity between n pieces of second track information and corresponding first track information, determining the similarity between the target track information and the reference track information; the similarity between the ith section second track information and the ith section first track information is the ith similarity in n similarities.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: weighting the n similarities according to preset weight parameters corresponding to the n similarities respectively, and determining the similarity between the target track information and the reference track information; wherein, the preset weight parameters corresponding to the n similarities are sequentially increased.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: searching the same base station identifier in the ith section of second track information and the ith section of first track information aiming at the ith section of second track information in the n sections of second track information; and obtaining the similarity of the second track information of the ith section and the first track information of the ith section according to the frequency corresponding to the same base station identifier.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: merging the same base station identifiers adjacently arranged in the target track information to obtain target track information after duplication removal; splitting the target track information to obtain n sections of second track information, wherein the splitting comprises the following steps: splitting the target track information after the duplication removal to obtain n sections of second track information.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: acquiring a plurality of historical tracks in a preset time period; wherein, a history track comprises a plurality of base station identifications arranged in time sequence before one target behavior; splitting a historical track into n sections of third track information; counting base station identifiers of a plurality of ith section third track information in a plurality of historical tracks to obtain ith section first track information of reference track information; wherein i is a positive integer less than or equal to n, and n is a positive integer.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: counting the frequency of each base station mark aiming at a plurality of ith section third track information in a plurality of historical tracks to obtain ith section first track information of reference track information; the reference track information comprises a plurality of different base station identifications and frequencies corresponding to the base station identifications.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: generating behavior characteristics for predicting target behaviors according to the similarity of the target track information and the reference track information; inputting the behavior characteristics into a preset machine learning model to obtain a prediction result of target behaviors output by the preset machine learning model; the method comprises the steps that a preset machine learning model is obtained through model training based on sample characteristics of training samples and sample labels of the training samples, the training samples comprise sample characteristics, the sample characteristics are obtained based on similarity of sample track information and reference track information of a user in a first historical preset duration, the sample track information comprises at least one base station identifier arranged according to time sequence, and the sample labels of the training samples are used for indicating execution target behaviors or non-execution target behaviors.

In another possible implementation manner of the second aspect, the computer instructions, when executed by the processor, cause the terminal device to further perform the steps of: under the condition that the preset condition is met, the terminal equipment acquires target track information of the terminal equipment, wherein the preset condition comprises one or more of the current display interface and the desktop interface in a preset time period at the current moment.

In a third aspect, the present application provides a computer readable storage medium comprising computer instructions which, when run on a terminal device, cause the terminal device to perform the method of the first aspect and any one of its possible implementations.

In a fourth aspect, the present application provides a computer program product comprising program instructions which, when run on a computer, enable the computer to perform the method of the first aspect and any one of its possible implementations. For example, the computer may be the above-described terminal device.

In a fifth aspect, the present application provides a chip system, which is applied to the above terminal device. The system-on-chip includes an interface circuit and a processor. The interface circuit and the processor are interconnected by a wire. The interface circuit is for receiving signals from the memory and transmitting signals to the processor, the signals including computer instructions stored in the memory. When the processor executes the computer instructions, the terminal device performs the method of the first aspect and any possible implementation manner thereof.

Drawings

Fig. 1 is a schematic diagram of an example of a base station location indicated by a base station identifier according to an embodiment of the present application;

fig. 2 is a schematic diagram of a display interface of a terminal device according to an embodiment of the present application;

fig. 3 is a schematic diagram of an example of a base station identifier record collected by a terminal device according to an embodiment of the present application;

fig. 4 is a block diagram of a terminal device example mobile phone 100 according to an embodiment of the present application;

FIG. 5 is a flowchart of an example of a method for predicting user behavior according to an embodiment of the present application;

FIG. 6 is a flowchart of another example of a user behavior prediction method according to an embodiment of the present application;

fig. 7 is a flowchart of an example of determining similarity between target track information and reference track information according to an embodiment of the present application;

FIG. 8 is a flowchart of a training example of a preset machine learning model according to an embodiment of the present application;

fig. 9 is a flowchart of an example of determining reference track information according to an embodiment of the present application.

Detailed Description

The embodiment of the application provides a user behavior prediction method, which can predict user behaviors through terminal equipment, so that the user experience of a user using the terminal equipment can be improved through the predicted user behaviors.

User behavior may be understood as behavior that may trigger a response of the terminal device. For example, the user behavior may be a browsing behavior of a user browsing a web page, a clicking behavior of a user opening an application, a photographing behavior of a user using a photographing function, a payment behavior of a user paying using a terminal device, and the like.

The user data collected by the terminal device may include current time, wi-Fi data, movement data, etc. However, for some predictions of user behavior, such as payment behavior prediction and user travel prediction, there is a phenomenon that the accuracy of the prediction result is low. For example, the terminal device predicts a user behavior, which the user will not take place until a long time has elapsed. Or the predicted user behavior of the terminal device is not matched with the user behavior actually generated by the user. In order to improve the phenomenon that the accuracy of predicting the user behavior by the terminal device is not high, in some implementations, the terminal device may also acquire the user position, and consider the user position when predicting the user behavior, so as to improve the accuracy of predicting the user behavior. Some user location acquisition schemes are provided below.

In one possible implementation, the terminal device may determine the current user location by scanning a surrounding Wi-Fi Access Point (AP). Specifically, the terminal device may initiate Wi-Fi functionality to scan for nearby Wi-Fi access points and collect nearby Wi-Fi access point data. Each Wi-Fi access point has a corresponding media access control (Media Access Control, MAC) address, which in turn corresponds to the geographic location of the Wi-Fi access point. Wi-Fi access point data collected by the terminal device may include a MAC address and a received signal strength. The terminal equipment can calculate the current user position according to the acquired MAC address and the received signal strength of each Wi-Fi access point.

In this implementation, the terminal device may locate the user's location by way of Wi-Fi scanning. Because Wi-Fi coverage is smaller, the terminal equipment can accurately position the current user position by utilizing a Wi-Fi positioning mode. However, the terminal device needs to perform Wi-Fi scanning a plurality of times when predicting user behavior. Each Wi-Fi scan by the terminal device generates a significant amount of power consumption. The performance of the terminal equipment is seriously affected, the standby time of the terminal equipment is reduced, and the user experience is affected.

In another possible implementation, the terminal device may determine the current user location by using a positioning fence to implement positioning. Specifically, the terminal device may preset a base station identifier list as a static space fence. The static spatial fence corresponds to the base station location where a user may behave as a user. When the base station identifier of the base station to which the terminal device is currently connected is in the preset base station identifier list, the user can be considered to be located at the base station position of the static space fence. If the base station identifier of the base station to which the terminal device is currently connected is not in the preset base station identifier list, the user can be considered to be not in the base station position of the static space fence currently.

In this implementation, the terminal device considers the user to be about to take the user behavior regardless of the base station location to which the user is traversing the static space fence from any path. This can lead to misidentification of the terminal device, reducing the accuracy of the user behavior prediction.

The embodiment of the application provides a user behavior prediction method which can be applied to terminal equipment. The terminal device may obtain target track information passed by the user within a period of time (e.g., a first preset period of time) before the current time. The target track information includes at least one base station identifier arranged in time sequence, and can represent the base station position passed by the user in a period of time before the current moment. The terminal can also acquire reference track information corresponding to a preset time period where the current moment is located. The reference trajectory information may represent the base station locations that have passed over a period of time before the user has historically occurred the target behavior. Further, the terminal device can determine the similarity between the target track information and the reference track information, and predict the target behavior of the current user according to the similarity so as to obtain a prediction result of the target behavior.

In the method provided by the embodiment of the application, the terminal equipment can consider whether the latest target track information of the user is similar to the past reference track information of the user in the process of predicting the target behavior. The reference track information may represent a user's usual location within a period of time before the occurrence of the target behavior, and predict whether the user has a behavior intention of the target behavior according to the similarity between the target track information and the reference track information. Therefore, the nearest position track information of the user can be considered in the process of predicting the target behavior, so that the accuracy of predicting the target behavior by the terminal equipment can be improved, and the accurate prediction of the target behavior is realized. Meanwhile, the target track information of the user is represented by the base station identifier, so that the influence of the base station identifier on the power consumption of the terminal equipment is small, and the influence of accurately predicting the target behavior on the terminal equipment can be reduced.

It will be appreciated that the base station identity is a base station identity code of a base station to which the terminal device is connected, for indicating the location of the base station. The base station location may be understood as the area (also called cell) covered by a mobile communication network provided by a base station. The Cell may be a Primary Cell (PCell), a Secondary Cell (Scell), a Primary Secondary Cell (Primary Secondary Cell, PSCell), a special Cell (specell), or the like. The base station is configured to provide a mobile communication network to the terminal device. Different base station locations covered by a mobile communication network may be distinguished by a base station identification (Cell ID).

As shown in fig. 1, the route from the company to the mall passes through 6 base stations denoted as base station identities, base station 1, base station 2, base station 3, base station 4, base station 5 and base station 6, respectively. It can be seen that each base station identity indicates a geographic distinction. The base station locations indicated by the different base station identities may overlap. The terminal equipment accesses a base station, acquires the base station identification of the base station, and communicates through the mobile communication network provided by the base station. Even if the terminal device does not predict the target behavior of the user, the terminal device will acquire the base station identifier of the current access base station. Therefore, the target behavior is predicted by using the target track information represented by the base station identifier, and the requirement of the terminal equipment on the power consumption can be met.

The target track information before the user takes the target action tends to have regularity. For example, taking the example where the target behavior is a payment behavior, as shown in FIG. 1, the user may go from the company to a nearby mall via route 1 or route 2 before the payment behavior occurs. The target track information of the route 1 or the route 2 is reflected by a record that can be identified by the base station. The records of the base station identity may exhibit some similarity when the user moves on similar routes.

Taking the base station identifier collected by the terminal device before the user makes payment in 3 days as an example, the record of the base station identifier before the user makes payment in the evening every 3 days is shown in fig. 3. In fig. 3 (1), the payment moments of the payment action by the user in the evening of the current day are 18:15:15. Before the payment time, at least one base station identifier included in the target track information is arranged according to the time sequence, namely, a base station 1, a base station 3, a base station 4 and a base station 5. In fig. 3 (2), the time for payment to occur in the evening of the day is 18:18:13. Before the payment time, at least one base station identifier included in the target track information is arranged according to the time sequence, namely, a base station 1, a base station 2, a base station 3, a base station 4 and a base station 5. In (3) of fig. 3, the time for payment to occur in the evening of the day is 18:17:27. Before the payment time, at least one base station identifier included in the target track information is arranged according to the time sequence, namely, the base station 1, the base station 2, the base station 4, the base station 5 and the base station 5. It can be seen that the target track information before the payment action occurs in the 3 days is similar, and a certain regularity can be considered.

In view of this, in the method provided in the embodiment of the present application, the terminal device encodes the target track information passed by the user through the base station identifier, and calculates the similarity between the current target track information of the user and the reference track information commonly used by the user, so as to characterize whether the user passes the base station position frequently visited by the user. And further predicting the target behavior of the user by the terminal equipment according to the similarity.

The preset period may be a period in which the target track information before the target behavior of the user exhibits regularity. The user's target behavior may exhibit regularity over different regular time periods of 1 day. For example, taking the example that the target behavior is payment behavior, in the period of 18:00-19:00 in evening every day, the target track information before the user generates payment behavior is mostly from a company to a nearby market, and a certain regularity is shown. In this case, 18:00-19:00 a day may be a preset period of time.

Of course, the target track information may exhibit regularity for a plurality of preset time periods. For example, taking the example that the target behavior is a payment behavior, the target track information before the user takes place the payment behavior may exhibit regularity in three periods of 8:00-9:00, 12:00-13:00, 18:00-19:00 in 1 day, respectively. In this case, 8:00-9:00 is a preset time period, 12:00-13:00 is a preset time period, and 12:00-13:00 is a preset time period.

Here, the user behavior may be understood as a behavior in which the user triggers the terminal response. The target behavior may be any user behavior. For example, the target behavior may be any one of a browsing behavior of a user browsing a web page, a clicking behavior of a user opening an application, a photographing behavior of a user using a photographing function, a check-in behavior of a user checking in using a terminal, and a payment behavior of a user paying out using a terminal.

The user data may be data related to a target behavior. For example, taking the example that the target behavior is a payment behavior, the user data may include data of a current time, target track information, a workday or a rest day, a continuous state of the wireless network, a movement state of the user, and the like.

The predicted result of the target behavior may indicate whether the user has a behavior intention to perform the target behavior. If the prediction result indicates that the user has a behavior intention of the target behavior, the possibility that the target behavior is about to occur is high. If the prediction indicates that the user does not have a behavioral intention of the target behavior, it is less likely that the user is about to be about to occur the target behavior. For example, the target behavior is a browsing behavior of browsing a web page, and the predicted result may indicate whether the user has a browsing intention of the browsing behavior. As another example, the target behavior is a payment behavior, and the prediction result may indicate whether the user has a payment intention of the payment behavior.

The terminal equipment can collect user data, and predict user behaviors through the collected user data to obtain a prediction result of the user behaviors. In order to better provide convenience for users, after obtaining the predicted result of the user behavior, the terminal device may provide services corresponding to the predicted result for the users. For example, the terminal device may initiate or prompt a target application related to the user behavior in advance, such as initiating a check-in application, a map application, etc. Alternatively, the terminal device may present application icons of the target applications related to the user behavior in the display interface, such as functional icons of the map application in the display interface, or the like.

Illustratively, taking the terminal device as a mobile phone and the user behavior as a payment behavior as an example. Before the payment behavior of the user is predicted, the display interface of the mobile phone is shown as (1) in fig. 2. It can be seen that at this time, there is no application icon of the payment function in the display interface of the mobile phone. In the case where the mobile phone predicts that the user has an intention to pay, the display interface of the mobile phone is shown as (2) in fig. 2. It can be seen that at this time, the display interface of the mobile phone displays functional icons (such as "payment code", "swipe" icons) of the payment application. If the user wants to pay by using the mobile phone, the user can see the function icons of the payment application by operating the mobile phone to open the display interface. The mobile phone can provide quick payment service for the user through the function icons of the payment application, and provides convenience for the user.

By way of example, the terminal device described in the embodiments of the present application may be a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal digital assistant (personal digital assistant, PDA), an augmented reality (augmented reality, AR) \virtual reality (VR) device, a media player, a wearable device, or the like.

In this embodiment, taking the mobile phone 100 as shown in fig. 4 as an example, the hardware structure of the terminal device is described by the mobile phone 100. As shown in fig. 4, the mobile phone 100 may include: processor 110, external memory interface 120, internal memory 121, universal serial bus (universal serial bus, USB) interface 130, charge management module 140, power management module 141, battery 142, antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headset interface 170D, sensor module 180, keys 190, motor 191, indicator 192, camera 193, display 194, and subscriber identity module (subscriber identification module, SIM) card interface 195, etc.

The processor 110 may include one or more processing units, for example: the processor 110 may include an application processor (application processor, AP), a modem processor modem, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a memory, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and/or a neural-network processor (neural-network processing unit, NPU), a driver processor, etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors. The processor 110 may be a neural and command center of the cell phone 100. The processor 110 may generate operation control signals according to the instruction operation code and the timing signals to complete instruction fetching and instruction execution control.

A memory may also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may hold instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to reuse the instruction or data, it can be called directly from the memory. Repeated accesses are avoided and the latency of the processor 110 is reduced, thereby improving the efficiency of the system.

The external memory interface 120 may be used to connect an external memory card, such as a Micro SD card, to extend the memory capabilities of the handset 100. The external memory card communicates with the processor 110 through an external memory interface 120 to implement data storage functions. For example, files such as music, video, etc. are stored in an external memory card.

The internal memory 121 may be used to store computer executable program code including instructions. The processor 110 executes various functional applications of the cellular phone 100 and data processing by executing instructions stored in the internal memory 121. For example, in an embodiment of the present application, the processor 110 may include a storage program area and a storage data area by executing instructions stored in the internal memory 121, and the internal memory 121 may include a storage program area and a storage data area.

The storage program area may store, among other things, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function of the operating system, a configuration file of the motor 191, etc. The storage data area may store data (e.g., audio data, phonebook, etc.) created during use of the handset 100, etc. In addition, the internal memory 121 may include a high-speed random access memory, and may further include a nonvolatile memory such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (universal flash storage, UFS), and the like.

The charge management module 140 is configured to receive a charge input from a charger. The charger can be a wireless charger or a wired charger. The charging management module 140 may also supply power to the mobile phone 100 through the power management module 141 while charging the battery 142.

The power management module 141 is used for connecting the battery 142, and the charge management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and/or the charge management module 140 and provides power to the processor 110, the internal memory 121, the external memory, the display 194, the camera 193, the wireless communication module 160, and the like. In some embodiments, the power management module 141 and the charge management module 140 may also be provided in the same device.

The wireless communication function of the mobile phone 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, a modem processor, a baseband processor, and the like. In some embodiments, the antenna 1 and the mobile communication module 150 of the handset 100 are coupled, and the antenna 2 and the wireless communication module 160 are coupled, so that the handset 100 can communicate with a network and other devices through wireless communication technology.

The antennas 1 and 2 are used for transmitting and receiving electromagnetic wave signals. Each antenna in the handset 100 may be used to cover a single or multiple communication bands. Different antennas may also be multiplexed to improve the utilization of the antennas. For example: the antenna 1 may be multiplexed into a diversity antenna of a wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The mobile communication module 150 may provide a solution for wireless communication including 2G/3G/4G/5G, etc. applied to the handset 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA), etc. The mobile communication module 150 may receive electromagnetic waves from the antenna 1, perform processes such as filtering, amplifying, and the like on the received electromagnetic waves, and transmit the processed electromagnetic waves to the modem processor for demodulation.

The mobile communication module 150 can amplify the signal modulated by the modem processor, and convert the signal into electromagnetic waves through the antenna 1 to radiate. In some embodiments, at least some of the functional modules of the mobile communication module 150 may be disposed in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 may be provided in the same device as at least some of the modules of the processor 110.

In this embodiment, the mobile phone 100 may communicate with the base station through the mobile communication module 150 to obtain the base station identifier of the base station.

The wireless communication module 160 may provide solutions for wireless communication including wireless local area network (wireless local area networks, WLAN) (e.g., wi-Fi), bluetooth (BT), global navigation satellite system (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field wireless communication technology (near field communication, NFC), infrared technology (IR), etc. applied to the mobile phone 100.

The wireless communication module 160 may be one or more devices that integrate at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the electromagnetic wave signals, filters the electromagnetic wave signals, and transmits the processed signals to the processor 110. The wireless communication module 160 may also receive a signal to be transmitted from the processor 110, frequency modulate it, amplify it, and convert it to electromagnetic waves for radiation via the antenna 2.

The handset 100 may implement audio functions through an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, an application processor, and the like. Such as music playing, recording, etc.

The sensor module 180 may include sensors such as a pressure sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a hall sensor, a touch sensor, an ambient light sensor, and a bone conduction sensor. The cell phone 100 may collect various data through the sensor module 180.

The mobile phone 100 implements display functions through a GPU, a display 194, an application processor, and the like. The GPU is a microprocessor for image processing, and is connected to the display 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

The display screen 194 is used to display images, videos, and the like. The display 194 includes a display panel. The display panel may employ a liquid crystal display (liquid crystal display, LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED) or an active-matrix organic light-emitting diode (matrix organic light emitting diode), a flexible light-emitting diode (flex), miniLED, microLED, micro-OLED, a quantum dot light-emitting diode (quantum dot light emitting diodes, QLED), or the like.

The mobile phone 100 may implement photographing functions through an ISP, a camera 193, a video codec, a GPU, a display 194, an application processor, and the like. The ISP is used to process data fed back by the camera 193. The camera 193 is used to capture still images or video. In some embodiments, the cell phone 100 may include 1 or more cameras 193.

The keys 190 include a power-on key, a volume key, etc. The keys 190 may be mechanical keys. Or may be a touch key. The motor 191 may generate a vibration cue. The motor 191 may be used for incoming call vibration alerting as well as for touch vibration feedback. The indicator 192 may be an indicator light, may be used to indicate a state of charge, a change in charge, a message indicating a missed call, a notification, etc.

The SIM card interface 195 is used to connect a SIM card. The SIM card may be inserted into the SIM card interface 195 or removed from the SIM card interface 195 to enable contact and separation with the handset 100. The handset 100 may support 1 or more SIM card interfaces. The SIM card interface 195 may support Nano SIM cards, micro SIM cards, and the like.

It should be understood that the connection relationship between the modules illustrated in this embodiment is only illustrative, and does not limit the structure of the terminal device. In other embodiments, the terminal device may also include more or fewer modules than provided in the foregoing embodiments, and different interfaces or a combination of multiple interfaces may also be used between the modules in the foregoing embodiments.

The methods in the following embodiments may be implemented in a terminal device having the above-described hardware structure. In the following embodiments, the method of the embodiments of the present application is described by taking an example that the terminal device is a mobile phone and the target behavior is a payment behavior. As shown in fig. 5, the method provided in the embodiment of the present application may include the following steps:

s501, the mobile phone acquires target track information in a first preset time before the current moment.

Under the condition that the user uses the mobile phone, the mobile phone can acquire the user data of the current user. For example, the handset obtains user data every 30 milliseconds. The user data acquired by the handset may be data related to payment activity.

The user data acquired by the mobile phone may include target track information within a first preset duration before the current time. For example, the mobile phone may acquire target track information within 15 minutes before the current time. The target track information includes at least one base station identity arranged in a time sequence. The base station identity is used to indicate a base station location. The target track information may represent the location of the base station that the user has recently passed.

Here, the first preset duration may be set according to an actual application scenario or a requirement. For example, the first preset time period may be set to a value of 10 minutes, 15 minutes, or the like. The time sequence may be a time-from-first-to-last sequence.

The user data acquired by the user may include, in addition to the target track information, data such as a current time, a working day or a rest day, a continuous and disconnected state of the wireless network, a movement state of the user, and the like.

The connection and disconnection state of the wireless network may be a state in which the wireless network of the mobile phone is connected or disconnected. The disconnection state of the wireless network can reflect whether the mobile phone uses the wireless network when the payment occurs. The wireless network may include a wireless network (e.g., 4G, 5G, etc.) provided by the mobile communication module and a wireless network (e.g., wi-Fi, etc.) provided by the wireless communication module.

The motion state may be whether the user is in a traveling state or a stopped state. The movement state may reflect whether the user is in progress or relatively stationary before the payment action occurs.

In order to reduce the energy consumption consumed by the mobile phone to predict the payment behavior, in some implementations, the mobile phone may start the payment behavior prediction function to obtain the target track information when a preset condition is satisfied. The preset conditions can be set according to actual application scenes or requirements. For example, the preset conditions may include: the display interface of the mobile phone is one or more of desktop interfaces within a preset time period at the current moment.

In one example, the preset condition may be that the current time is within a preset period of time. The mobile phone can determine whether the current time is within a preset time period. If the current moment is within the preset time period, the mobile phone can start the function of predicting the payment behavior, and the target track information is obtained.

The preset time period may be a time period during which the user may have a payment action in the day. One or more preset time periods may be included in a day. The handset may estimate a time period during which the user may be paying for the day based on the user's historical data, and determine a preset time period. The historical data may be user data collected by the mobile phone before and after a user has performed a payment action in the past. The likelihood of payment by the user is greatest during a preset time period of the day. The mobile phone can start the function of predicting payment behavior within a preset time period every day, and target track information is obtained.

For example, the handset may count the historical time of multiple payment actions that have occurred in the past by the user. If the historical time of the multiple payment actions is within one or more time periods, the mobile phone can take the one or more time periods in which the historical time is located as the preset time period for predicting the payment action. If the preset time period is 11:00-13:00, the possibility that the user generates the payment behavior in the preset time period in 1 day is maximum, and the mobile phone can start the payment behavior prediction function at 11:00 every day to obtain the target track information and predict the payment behavior of the user. The handset may turn off the payment behavior prediction function after 13:00 a day, stopping predicting the user's payment behavior.

In other examples, the preset condition may be that the current time is within a preset period of time, and the display interface of the mobile phone is a desktop interface. If the current time is within the preset time period and the current display interface of the mobile phone is a desktop interface, the mobile phone can start the function of predicting the payment behavior, and the target track information is obtained.

For example, as shown in fig. 6, a cell phone may include a perception module, a business module, and a prediction module. The mobile phone can sense the user operation through the sensing module. And under the condition that the sensing module senses the user operation of switching the display interface to the desktop interface by the user, the sensing module can inform the service module of the user operation. The service module can be used for judging whether the preset condition is met. And under the condition that the current moment is in a preset time period, the service module responds to the user operation of switching the display interface to the desktop interface, notified by the perception module, and instructs the prediction module to start a prediction function of the payment behavior. And the prediction module responds to the indication of the service module, starts a prediction function of payment behavior, and acquires user data in the hotlist. The hotlist may be user data collected by the handset in the last period of time.

S502, if the current time is within the preset time period, the mobile phone acquires the reference track information corresponding to the preset time period where the current time is located.

As described above, the preset time period is a time period in which the user may take place a payment action in one day. The mobile phone stores reference track information corresponding to a preset time period. The reference track information is used for indicating the base station position where the user is before the payment action occurs historically, and can indicate the past common payment route of the user. The reference track information corresponding to different preset time periods may be different. The determination method of the reference track information will be described in detail later, and will not be described in detail here.

After the mobile phone starts the prediction function of the payment behavior, the reference track information corresponding to the preset time period where the current moment is located can be obtained. For example, the current time is 11:00, and the mobile phone can acquire the reference track information corresponding to the preset time period of 11:00-12:00.

It will be appreciated that in the case of starting the payment behavior prediction function, the mobile phone may execute S501 first and then execute this step. Alternatively, the mobile phone may execute the step first and then execute S501. Of course, the mobile phone may also perform S501 and this step at the same time. The embodiment of the present application does not limit the sequence of step S501 and the present step.

S503, the mobile phone determines the similarity between the target track information and the reference track information.

After the mobile phone acquires the target track information and the reference track information corresponding to the preset time period of the current moment, the mobile phone further calculates the similarity between the target track information and the reference track information. For example, the target track information may be represented as at least one base station identity arranged in time order. The reference trajectory information may also be represented as a plurality of base station identities arranged in time sequence. The mobile phone calculates the distance between the target track information and the reference track information, such as cosine distance or Euclidean distance, and takes the distance between the target track information and the reference track information as the similarity between the target track information and the reference track information. Or, the mobile phone can calculate a Jacrad similarity coefficient or a Pearson correlation coefficient between the target track information and the reference track information to obtain the similarity of the target track information and the reference track information.

To better discern whether the user's most recent target track information is similar to the reference track information, in some implementations, the reference track information may include n pieces of first track information arranged in a time sequence. The mobile phone can split the target track information into n sections of second track information, calculate the similarity between each section of second track information and the corresponding first track information, synthesize the similarity between n sections of second track information and the corresponding first track information, and determine the similarity between the target track information and the reference track information. Specifically, the mobile phone determines the similarity between the target track information and the reference track information, and may include the following steps:

S701, the mobile phone merges the same base station identifiers continuously arranged in the target track information to obtain merged target track information.

In order to reduce complexity of similarity calculation, after obtaining the target track information, the mobile phone may perform deduplication processing on a plurality of identical base station identifiers continuously arranged in the target track information, where the identical plurality of base station identifiers continuously repeatedly recorded in the target track information takes a first base station identifier to record. In the combined target track information, each base station identifier is different from the adjacent base station identifiers.

For example, as shown in fig. 7, the base station identifiers arranged in time sequence in the target track information are in order: base station 1, base station 2, base station 3, base station 4, base station 1, base station 5, base station 1. And combining the plurality of base station identifications continuously and repeatedly recorded in the mobile phone into one base station identification aiming at the target track information. The base station identifiers arranged according to the time sequence in the combined target track information are as follows: base station 1, base station 2, base station 3, base station 4, base station 1, base station 5, base station 1. It can be seen that in the target track information before the combination, the base station 2, the base station 3, and the base station 1 have two identical records, respectively. In the combined target track information, two base stations 2 that continuously appear are combined into 1 base station 2, base stations 3 that continuously appear are combined into 1 base station 3, and two base stations 1 that continuously appear are combined into 1 base station 1.

S702, splitting target track information by the mobile phone according to a time sequence to obtain n sections of second track information.

The reference track information may include n pieces of first track information arranged in the above-described time sequence. The n pieces of first track information included in the reference track information are arranged in order of time from first to last. The time information corresponding to the i-th section first track information is prior to the time information corresponding to the i+1th section first track information. The time information corresponding to the first track information may indicate a preset time interval corresponding to the current first track information, in addition to the sequence of the current first track information according to the time arrangement. The preset time interval is used for indicating the time interval for splitting the target track information. The preset time intervals corresponding to the different first track information may be the same or different. n is a positive integer. i is a positive integer less than or equal to n.

The mobile phone can split the target track information according to the time sequence and the preset time interval corresponding to the first track information to obtain n sections of second track information. The time information corresponding to the n pieces of second track information is sequentially increased. The time information corresponding to the second track information may be understood as a time period formed by the acquisition moments of the plurality of base station identifiers in the second track information. The i-th segment second track information corresponds to the i-th segment first track information. And the maximum time interval between the acquisition moments of the base station identifiers in the second track information of the ith section is equal to the preset time interval corresponding to the first track information of the ith section.

For example, the reference track information includes 3 pieces of first track information, and the preset time interval corresponding to each piece of first track information is 5 minutes. In the example shown in fig. 7, the base station identifiers arranged in time sequence in the combined target track information are in order: base station 1, base station 2, base station 3, base station 4, base station 1, base station 5, base station 1. The mobile phone can divide the target track information into 3 pieces of second track information according to the time sequence. The 3 pieces of second track information are respectively: segment 1 second track information: base station 1, base station 2; segment 2 second track information: a base station 3, a base station 4; segment 3 second track information: base station 1, base station 5, base station 1.

S703, the mobile phone calculates the similarity between each piece of second track information and the corresponding first track information.

The mobile phone can respectively calculate the similarity between each piece of second track information in the n pieces of second track information and the corresponding first track information. The i-th segment second track information corresponds to the i-th segment first track information. Aiming at the ith section of second track information in the n sections of second track information, the mobile phone can calculate the similarity between the ith section of second track information and the ith section of first track information to obtain the ith similarity.

For example, the mobile phone may calculate a distance, such as a cosine distance or a euclidean distance, between the ith second track information of the target track information and the ith first track information of the reference track information, and use the distance as a similarity between the ith second track information of the target track information and the ith first track information of the reference track information. Or the mobile phone can calculate a Jacrad similarity coefficient or a Pearson correlation coefficient between the ith second track information of the target track information and the ith first track information of the reference track information to obtain the similarity of the ith second track information of the target track information and the ith first track information of the reference track information.

To more intuitively represent the common payment route of the user before the payment action by the reference trajectory information, in some implementations, each piece of first trajectory information of the reference trajectory information may include at least one base station identification and a corresponding frequency of each base station identification. The frequency corresponding to each base station identifier represents the frequency with which the user history appears at the base station location indicated by the corresponding base station identifier. The higher the frequency corresponding to a base station identity, the more times a user passes the base station location corresponding to the base station identity before payment.

In the implementation manner, the mobile phone can search the same base station identifier in the ith section of second track information and the ith section of first track information aiming at the ith section of second track information in the n sections of second track information. And then the mobile phone can accumulate the frequencies corresponding to the same base station identifiers in the second track information of the ith section to obtain the similarity of the second track information of the ith section and the first track information of the ith section, wherein the similarity can be the ith similarity.

For example, as shown in fig. 7, the target track information includes 3 pieces of second track information, respectively: segment 1 second track information: base station 1, base station 2; segment 2 second track information: a base station 3, a base station 4; segment 3 second track information: base station 1, base station 5, base station 1. The reference track information includes 3 pieces of first track information. Wherein, the first track information of the 1 st segment is represented as { base station 1:10, base station 2:11, base station 3:5}; the first track information of the 2 nd segment is represented as { base station 3:10, base station 4:10, base station 5:10}; the 3 rd segment first track information is represented as { base station 1:20, base station 2:10, base station 5:10}.

Taking similarity between the second track information of the 1 st section and the first track information of the 1 st section as an example, the same base station identifiers in the second track information of the 1 st section and the first track information of the 1 st section are the base station 1 and the base station 2. In the first track information of paragraph 1, the frequency corresponding to the base station 1 is 10, and the frequency corresponding to the base station 2 is 11. The mobile phone adds up the frequency corresponding to the base station 1 and the frequency corresponding to the base station 2, so that the similarity between the 1 st section of second track information and the 1 st section of first track information can be obtained, and the similarity is 21 (1 st similarity). Through the same similarity calculation mode, the similarity (2 nd similarity) between the 2 nd section second track information and the 2 nd section first track information and the similarity (3 rd similarity) between the 3 rd section second track information and the 3 rd section first track information can be obtained.

S704, the mobile phone determines the similarity of the target track information and the reference track information according to the n similarities of the n sections of second track information and the corresponding first track information.

After calculating the similarity between each piece of second track information and the corresponding first track information, the mobile phone can obtain n similarities. The similarity of the ith second track information and the ith first track information may be the ith similarity of the n similarities. After the mobile phone obtains n similarities, the similarity between the target track information and the reference track information can be determined according to the n similarities. For example, the mobile phone may add the obtained n similarities to obtain the similarity between the target track information and the reference track information.

In order to calculate the similarity between the target track information and the reference track information more accurately, in some implementations, the mobile phone may perform weighting processing on the n similarities by using n preset weight parameters set in advance, so as to obtain the similarity between the target track information and the reference track information.

In this implementation manner, the mobile phone may set a preset weight parameter for the similarity between each piece of second track information and the corresponding first track information. The ith similarity between the ith section second track information and the ith section first track information corresponds to the ith preset weight parameter. The i-th preset weight parameter is smaller than the i+1-th preset weight parameter. The n preset weight parameters are sequentially increased, and the sum of the n preset weight parameters is 1.

For example, among 3 similarities in the example shown in fig. 7, the 1 st similarity corresponds to the 1 st preset weight parameter, the 2 nd similarity corresponds to the 2 nd preset weight parameter, and the 3 rd similarity corresponds to the 3 rd preset weight parameter. The similarity of the target track information and the reference track information can be calculated by the formula (1).

Formula (1);

wherein, the liquid crystal display device comprises a liquid crystal display device,and->。/>And the similarity of the target track information and the reference track information is represented. />The 1 st similarity between the 1 st piece of second track information and the 1 st piece of first track information is represented. />And the 2 nd similarity between the 2 nd section second track information and the 2 nd section first track information is represented. />And 3 rd similarity between the 3 rd section second track information and the 3 rd section first track information is represented. />Indicating that the 1 st similarity corresponds to the 1 st preset weight parameter. />Indicating that the 2 nd similarity corresponds to the 2 nd preset weight parameter. />Indicating that the 3 rd similarity corresponds to the 3 rd preset weight parameter.

It will be appreciated that the n pieces of second track information of the target track information are split in time order. The time information corresponding to the different second track information is different. The second track information with the time information can reflect the position of the base station which the user has recently passed. The mobile phone can allocate a larger preset weight parameter for the similarity between the second track information with the time information and the corresponding first track information, and allocate a smaller preset weight parameter for the similarity between the second track information with the time information and the corresponding first track information. The similarity between the calculated target track information and the reference track information can reflect whether the user passes through the common payment route indicated by the reference track information more accurately, so that the accuracy of payment behavior prediction is improved.

S504, the mobile phone predicts the payment behavior according to the similarity of the target track information and the reference track information, and obtains a prediction result of the payment behavior.

After obtaining the similarity between the target track information and the reference track information, the mobile phone can predict whether the user has the behavior intention of the payment behavior according to the similarity between the target track information and the reference track information.

For example, if the similarity between the target track information and the reference track information is greater than a preset similarity threshold (e.g., 80%), the target track information may be considered to be consistent with the reference track information, and the likelihood that the user will perform the payment is high, and the mobile phone may generate a prediction result that the user has a payment intention. If the similarity between the target track information and the reference track information is smaller than or equal to a preset similarity threshold value, the target track information and the reference track information can be considered to have larger difference, the probability that the user is about to execute the payment action is small, and the mobile phone can generate a prediction result that the user does not have the payment intention.

For example, the accuracy of predicting the payment behavior of the mobile phone is further improved, and the mobile phone can predict the payment behavior of the user by using a machine learning model. In some implementations, the mobile phone may generate behavior features for predicting payment behavior based on the similarity of the target trajectory information and the reference trajectory information. Further, the mobile phone can input the generated behavior characteristics into a preset machine learning model to obtain a prediction result of the payment behavior output by the preset machine learning model.

In this implementation, the mobile phone may generate the behavior feature according to the similarity between the target track information and the reference track information. For example, the mobile phone may directly use the similarity as a feature value of one dimension in the behavior feature. Or the mobile phone can code the similarity to obtain a feature value of one dimension in the behavior feature. The mobile phone can also generate behavior characteristics of the user according to the similarity of the target track information and the reference track information and other user data. Other user data may include the current time of day, workday or weekday, continuous disconnection status of the wireless network, etc. After the mobile phone generates the behavior characteristics for predicting the payment behavior, the generated behavior characteristics can be input into a preset machine learning model, and a prediction result of the payment behavior is obtained by using the preset machine learning model.

The predicted outcome of the payment action may indicate whether the user has a payment intention. For example, the prediction result may be the first identifier or the second identifier. The preset result is a first identifier, which can indicate that the user has a payment intention, and the probability that the user is about to take payment is high. The preset result is a second identifier, which can indicate that the user has no intention to pay, and the probability that the user will take the payment action is small. For another example, the prediction result may be a value between 0 and 1. If the predicted result is greater than a preset value (e.g., 80%), indicating that the user has a payment intention, the user is highly likely to be about to take payment. If the preset result is less than or equal to the preset value, it may indicate that the user does not have a payment intention, and the user is less likely to be about to take payment.

The handset may include a preset machine learning model that may be used to predict the user's payment behavior. The model structure of the preset machine learning model can be set according to actual application scenes or requirements. Considering limitations of the mobile phone side in terms of computing power and power consumption, in some implementations, the preset machine learning model may be a lightweight machine learning model with a simple model structure. For example, the preset machine learning model may be a tree model, a logistic regression (Logistic Regression, LR) model, a bi-classification model, or the like. Because the model structure of the preset machine learning model is simple, the related calculated amount is much less compared with the deep neural network model, so that the mobile phone predicts the payment behavior through the preset machine learning model and has less influence on the performance of the mobile phone. Of course, the preset machine learning model can be improved on the basis of a common machine learning model or a new model structure is adopted, and the model structure of the preset machine learning model is not limited in the application.

Here, the preset machine learning model may be model-trained based on a training sample and a sample tag of the training sample. Training the sample may include providing a sample feature based on historical data of the user. The historical data may include sample track information for the user over a first predetermined period of time of the history, the sample track information including at least one base station identification arranged in a time sequence. The sample characteristics may be derived based on the similarity of the sample trajectory information to the reference trajectory information. The sample tag of the training sample is used to indicate that a payment action is performed or not performed. The user's history data may include history, workday or rest day, continuous disconnection state of the wireless network, etc., in addition to the sample track information. The history data may be user data obtained in a cold table. The cold table may be used to store user data in the past of the user. The history data may also be referred to as cold table data.

Here, the sample feature is obtained based on the similarity of the sample trajectory information and the reference trajectory information. The similarity between the sample track information and the reference track information may refer to the calculation manner of the similarity between the target track information and the reference track information, which is not described herein. The sample feature may include a feature value corresponding to other data in addition to the feature value corresponding to the sample trajectory information. The mobile phone can respectively generate characteristic values corresponding to the similarity of the sample track information and the reference track information and characteristic values corresponding to other data, and then splice, screen and the like are carried out on the characteristic values corresponding to the similarity of the sample track information and the reference track information and the characteristic values corresponding to other data, so that the sample characteristics of the user history data are obtained.

As shown in fig. 8, the prediction module of the mobile phone may obtain cold table data in the cold table as the history data of the user. The historical data comprises a plurality of sample track information of the user in a plurality of historical first preset time periods. Further, the mobile phone performs a feature generation operation to generate a plurality of sample features based on the plurality of sample trajectory information. For one sample track information, the mobile phone calculates the similarity between the sample track information and the reference track information corresponding to the preset time period where the history is located, and generates a characteristic value corresponding to the sample track information in the sample characteristic according to the similarity. The handset may generate other data corresponding feature values in the history data. Then, the mobile phone performs operations such as splicing and screening on the characteristic value corresponding to the track information of one sample and the characteristic value corresponding to other data to obtain a training sample of the preset machine learning model.

Further, the mobile phone can perform model training on a preset machine model through a plurality of groups of training samples. In one round of model training of a preset machine learning model, the mobile phone can input a group of training samples into the preset machine learning model, and predict payment behaviors through the preset machine learning model to obtain a prediction result corresponding to each sample feature. Further, the mobile phone may bring the predicted result of the training sample and the sample label of the training sample into a preset loss function, and calculate a model loss of the preset machine learning model corresponding to the set of training samples. And the mobile phone adjusts model parameters of a preset machine learning model according to the calculated model loss. Through the multi-round model training, the model loss of the preset machine learning model can be continuously reduced, and the mobile phone can obtain the preset machine learning model for completing training. The mobile phone can infer the payment behavior of the user through a trained preset machine learning model.

The preset loss function used in the model training process of the preset machine learning model can be selected according to actual application scenes or requirements. For example, the preset loss function may be a maximum likelihood loss function, a binary cross entropy function, or the like. The embodiment of the application does not limit the preset loss function.

And S505, if the predicted result shows that the user has the payment intention, the mobile phone provides a function icon of the payment application in the display interface.

If the predicted result obtained by the mobile phone indicates that the user has a payment intention, the probability that the user will take the payment action is high. In order to facilitate the user to operate the mobile phone to realize payment, the mobile phone may then present a function icon of the payment application (an example of the target application) in the display interface. The payment application is for assisting a user in performing a payment action.

As in the example shown in fig. 6, the handset also includes a service module. And under the condition that the preset result obtained by the prediction module of the mobile phone indicates that the user has the payment intention, the service module of the mobile phone can instruct the service module to display the function icon of the payment application in the display interface.

For example, the handset may add a function icon for the payment application in the desktop interface. Alternatively, the handset may provide the function icons of the payment application in a recommendation card of the desktop interface. The recommendation card is used for recommending application programs possibly used by the user according to the preference of the user.

Here, the function icon of the payment application may be used to trigger the payment function of the payment application. For example, the function icons of the payment application may include at least one of a payment code icon and a swipe code icon of the payment application. When the user clicks the function icon of the payment application, the mobile phone can start the payment function of the payment application so that the user can complete payment.

As in the example shown in fig. 2, the desktop interface of the mobile phone is shown in fig. 2 (1) before the mobile phone obtains the predicted result of the payment behavior. It can be seen that calendar, email, video and application icons of the application mall are displayed in the recommended card provided by the desktop interface of the mobile phone. After obtaining the predicted result of the payment behavior, if the predicted result indicates that the user is about to execute the payment behavior, the desktop interface of the mobile phone is shown in fig. 2 (2). It can be seen that the recommended card on the desktop interface of the mobile phone has a payment code icon (labeled "payment code") and a swipe code icon (labeled "swipe"). If the user wants to operate the mobile phone to pay, the mobile phone can assist the user to quickly realize payment through a payment code or a sweep provided by a desktop interface, and user experience is improved.

In order to provide a more perfect user experience for the user, under the condition that the function icons of the payment application are displayed in the display interface of the mobile phone to reach the second preset duration, the mobile phone cancels the display of the function icons of the payment application in the display interface. For example, when the duration of displaying the function icon of the payment application reaches 10 minutes, the mobile phone changes the displayed function icon of the payment application to the function icon of another application, such as changing to the function icon of the application displayed before the payment application is displayed.

Here, the second preset duration of the function icon of the payment application displayed by the mobile phone may be set according to an actual application scenario or a requirement. For example, the second preset time period may be set to a time period of 10 minutes, 15 minutes, or the like.

In some implementations, the mobile phone may further set a second preset duration according to the historical payment behavior of the user. For example, the mobile phone may count information about the user's historical payment behavior (e.g., the behavior time of the historical payment behavior). If the statistics indicate that the user's historical payment behavior occurs within a period of time (e.g., within 5-10 minutes) after each predicted outcome, the handset may set the second preset period of time to the upper limit of the period of time (e.g., to 10 minutes).

In the embodiment of the application, the mobile phone can predict the payment behavior of the user by using the similarity between the target track information and the reference track information. The following describes a manner of determining the reference track information by the embodiment of the present application. The method provided by the embodiment of the application can further comprise the following steps:

s901, the mobile phone acquires a plurality of pieces of history track information in a preset time period.

The mobile phone can periodically collect the base station identification of the base station where the mobile phone is located. For example, taking the example that the acquisition period is 100 ms, the mobile phone may acquire the base station identifier of the base station at every 100 ms. The mobile phone can store the collected base station identifications according to the time sequence to form a base station identification record.

For at least one preset time period, the mobile phone can acquire a plurality of historical track information of the user in each preset time period from the base station identification record. The historical track information comprises a plurality of base station identifications which are arranged according to time sequence in a first preset duration before the user historical payment action occurs once. One payment action corresponds to one historical track information.

For example, for one payment action among a plurality of payment actions that the user has taken in the past within a preset time period of 18:00-19:00, the mobile phone may obtain a base station identification record 15 minutes (an example of the first preset duration) before the one payment action, and obtain historical track information of the one payment action.

In order to more intuitively reflect the base station positions passed by the user before each payment action, in some implementations, after acquiring multiple historical track information of the user, the mobile phone may perform deduplication processing on multiple identical base station identifiers continuously arranged in each historical track information. Specifically, the method provided in the embodiment of the present application may further include S902:

s902, the mobile phone merges the same base station identifiers continuously arranged in each piece of history track information to obtain each piece of merged history track information.

The mobile phone can combine the same base station identifications continuously arranged in each history track information according to each acquired history track information, and the same plurality of base station identifications continuously repeatedly recorded in each history track information take the first base station identification to record. In each combined historical track information, each base station identifier is different from the adjacent base station identifier.

For example, as shown in fig. 9, the base station identities arranged in time sequence in one history track information are in order: base station 1, base station 2, base station 3, base station 4, base station 1, base station 5, base station 1. For the historical track information, the mobile phone combines a plurality of base station identifications continuously and repeatedly recorded therein into one base station identification. The base station identifiers arranged according to the time sequence in the combined historical track information are as follows: base station 1, base station 2, base station 3, base station 4, base station 1, base station 5, base station 1. It can be seen that in this piece of history track information before merging, the base station 2, the base station 3, and the base station 1 have two identical records, respectively. In the combined piece of history track information, two base stations 2 that appear continuously are combined into 1 base station 2, base stations 3 that appear continuously are combined into 1 base station 3, and two base stations 1 that appear continuously are combined into 1 base station 1.

S903, the mobile phone splits one piece of history track information into n pieces of third track information.

After the mobile phone acquires a plurality of pieces of history track information in a preset time period, each piece of history track information can be split in the same splitting mode, and each piece of history track information is split into n pieces of third track information. The time information corresponding to the different third track information in one history track information is different. The time information corresponding to the third track information may be understood as a time period formed by the acquisition moments of the plurality of base station identifiers in the third track information.

In some implementations, the mobile phone may split the combined historical track information into n pieces of third track information. For example, in the example shown in fig. 9, the base station identifiers arranged in time sequence in the combined historical track information are in order: base station 1, base station 2, base station 3, base station 4, base station 1, base station 5, base station 1. The mobile phone can split the combined historical track information into 3 sections of third track information, and the 3 sections of third track information are respectively: third track information of paragraph 1: base station 1, base station 2; third track information of paragraph 2: a base station 3, a base station 4; third track information of 3 rd segment: base station 1, base station 5, base station 1.

In some examples, the mobile phone may divide each historical track information into n segments of third track information according to a time sequence, where a time interval between a collection time of the first base station identifier and a collection time of the last base station identifier in each third track information is equal to a preset time interval. The time information corresponding to the n sections of third track information is sequentially increased.

For example, a historical trajectory information includes a plurality of base station identifications in chronological order (i.e., time order) of the collection times within 15 minutes (e.g., 18:00-18:15 minutes) before a payment event occurs. The preset time interval may be 5 minutes. The mobile phone can split the historical track information into 3 sections of third track information according to the sequence of the acquisition time. The maximum time interval of the acquisition time of the plurality of base station identifiers in each section of third track information is 5 minutes. The time information of the 3 pieces of third track information is sequentially incremented. The time information of the third track information of the 1 st section is 18:00-18:05, the time information of the third track information of the 2 nd section is 18:05-18:10, and the time information of the third track information of the 3 rd section is 18:10-18:15.

In other examples, the mobile phone may split each historical track information into n segments of third track information according to a time sequence, and a maximum time interval of the acquisition time of the base station identifier in different third track information may be equal to a different preset time interval. The time information corresponding to the n sections of third track information is sequentially increased.

For example, a historical trajectory information includes a plurality of base station identifications in chronological order (i.e., time order) of the collection times within 15 minutes (e.g., 18:00-18:15 minutes) before a payment event occurs. The mobile phone can split the historical track information into 3 sections of third track information according to the sequence of the acquisition time. The preset time intervals corresponding to the 3 pieces of third track information are 6 minutes, 5 minutes and 4 minutes, respectively. The time information of the third track information of the 1 st section is 18:00-18:06, the time information of the third track information of the 2 nd section is 18:06-18:11, and the time information of the third track information of the 3 rd section is 18:11-18:15. It can be seen that the maximum time intervals of the acquisition moments of the plurality of base station identifications in the 3 pieces of third track information are 6 minutes, 5 minutes and 4 minutes, respectively, and the time information of the 3 pieces of third track information is sequentially increased.

S904, the mobile phone gathers a plurality of ith section of third track information in a plurality of historical track information to obtain ith section of first track information of the reference track information.

After splitting each piece of history track information of the preset time period, the mobile phone splits each piece of history track information of the preset time period into n pieces of third track information. The mobile phone gathers a plurality of ith section third track information in a plurality of history track information, and can obtain the ith section first track information of the reference track information.

Here, the reference track information may include n pieces of first track information. Each piece of first track information can be obtained by summarizing third track information corresponding to a plurality of pieces of historical track information. The first track information of the 1 st section is obtained by summarizing third track information of the 1 st section of a plurality of historical track information. The 2 nd section of first track information is obtained by summarizing the 2 nd section of third track information of a plurality of historical track information. … …, the nth piece of first track information is obtained by summarizing the nth piece of third track information of the plurality of historical track information.

For example, the user has 2 pieces of target track information, respectively target track information 1 and target track information 2, for a preset period of time. The history track information 1 includes 3 pieces of third track information, which are the 1 st piece of third track information, the 2 nd piece of third track information, and the 3 rd piece of third track information, respectively. The history track information 2 also includes 3 pieces of third track information, which are the 1 st piece of third track information, the 2 nd piece of third track information, and the 3 rd piece of third track information, respectively. The mobile phone gathers the 1 st section third track information of the historical track information 1 and the 1 st section third track information of the historical track information 2 to obtain the 1 st section first track information of the reference track information. The mobile phone gathers the 2 nd section third track information of the historical track information 1 and the 2 nd section third track information of the historical track information 2 to obtain the 2 nd section first track information of the reference track information. The mobile phone gathers the 3 rd section third track information of the historical track information 1 and the 3 rd section third track information of the historical track information 2 to obtain the 3 rd section first track information of the reference track information.

In order to more intuitively represent the reference track information, the common payment route of the user before the payment behavior is represented by the reference track information, and in some implementations, the mobile phone may represent the reference track information through the base station identifiers and the frequency corresponding to each base station identifier. The higher the frequency corresponding to a base station identity, the more times a user passes the base station location corresponding to the base station identity before payment.

Aiming at a plurality of ith section of third track information in a plurality of historical track information, the mobile phone can count the frequency of each base station mark to obtain the ith section of first track information of the reference track information. The ith section of first track information of the reference track information comprises at least one different base station identifier and a frequency corresponding to each base station identifier.

For example, as shown in fig. 9, 3 pieces of third track information of one history track information are respectively: third track information of paragraph 1: base station 1, base station 2; third track information of paragraph 2: a base station 3, a base station 4; third track information of 3 rd segment: base station 1, base station 5, base station 1. For each piece of third track information of the historical track information, the frequency of each base station identification of each piece of third track information can be counted. In the third track information of the 1 st segment, the base station 1 and the base station 2 appear once respectively, and the frequency of the base station 1 and the frequency of the base station 2 are both 1, which can be expressed as { base station 1:1, base station 2:1}. In the third track information of the 2 nd segment, the base station 3 and the base station 4 appear once respectively, and the frequency of the base station 3 and the frequency of the base station 4 are both 1, which can be expressed as { base station 3:1, base station 4:1}. In the third track information of the 3 rd segment, the base station 1 appears 2 times, the base station 5 appears once, the frequency of the base station 1 is 2, the frequency of the base station 5 is 1, and can be expressed as { base station 1:2, base station 5:1}.

Aiming at each section of third track information of a plurality of historical track information in a preset time period, the mobile phone independently gathers the frequencies of all base station identifications of each section of third track information, and accumulates the frequencies of the base station identifications of a plurality of ith sections of the plurality of historical track information to obtain each section of first track information of the reference track information. Taking the example that the reference track information includes 3 pieces of first track information, the 1 st piece of first track information of the reference track information may be expressed as { base station 1:10, base station 2:11, base station 3:5}. The 2 nd piece of first track information of the reference track information may be expressed as { base station 3:10, base station 4:10, base station 5:10}. The 3 rd piece of first track information of the reference track information may be expressed as { base station 1:20, base station 2:10, base station 5:10}.

It can be understood that, in the embodiment of the present application, taking reference track information corresponding to a preset time period as an example, a determination manner of the reference track information corresponding to the preset time period is described. In some embodiments, payment actions that have occurred in the past by the user may be regular for a number of preset time periods. In this case, the determination manner of the reference track information corresponding to each of the plurality of preset time periods is the same as the determination manner of the reference track information corresponding to the previous one of the preset time periods, and will not be described herein.

In the embodiment of the application, a mobile phone is taken as an example to introduce a user behavior prediction method. The similarity of the target track information and the reference track information is calculated through the mobile phone side, so that the payment behavior of the user is predicted, and the accuracy of the terminal side in predicting the payment behavior can be improved.

According to the method provided by the embodiment of the application, under the condition that the user is predicted to have the payment intention, the time length from recommending payment to actual payment of more than 50% of users is within 6 minutes, and the average time length from recommending payment to actual payment is about 12 minutes. The recommended payment to actual payment is shortened by 5.57 minutes on average compared to the scheme of introducing the target trajectory information.

Still further, in other embodiments of the present application, a terminal device is provided, including: a memory and one or more processors. The memory is coupled to the processor. The memory has stored therein computer program code comprising computer instructions. The terminal device, when executed by the processor, may perform the various functions or steps of the method embodiments described above. Of course, the terminal device may also include other hardware structures such as other antennas for receiving signals. For example, the terminal device further includes a sensor, a display screen, and other hardware structures. The structure of the terminal may refer to the structure of the mobile phone 100 shown in fig. 4.

The embodiment of the application also provides a chip system which is applied to the terminal equipment. The system-on-chip includes at least one processor and at least one interface circuit. The processors and interface circuits may be interconnected by wires. For example, the interface circuit may be used to receive signals from other devices (e.g., memory). For another example, the interface circuit may be used to send signals to other devices (e.g., processors). The interface circuit may, for example, read instructions stored in the memory and send the instructions to the processor. The instructions, when executed by the processor, may cause the terminal device to perform the steps of the above embodiments. Of course, the chip system may also include other discrete devices, which are not specifically limited in this embodiment of the present application.

The embodiments also provide a computer-readable storage medium including computer instructions which, when executed on the terminal device, cause the terminal device to perform the functions or steps of the method embodiments described above.

Embodiments of the present application also provide a computer program product which, when run on a computer, causes the computer to perform the functions or steps of the method embodiments described above. For example, the computer may be the above-described terminal device.

It will be apparent to those skilled in the art from this description that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another apparatus, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and the parts displayed as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed in a plurality of different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be essentially or a part contributing to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions for causing a device (may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely a specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for predicting user behavior, applied to a terminal device, the method comprising:

acquiring target track information of the terminal equipment; the target track information represents base stations which the terminal equipment passes through according to time sequence in a first preset duration before the current moment, and the target track information comprises base station identifications of at least one base station arranged according to the time sequence;

if the current moment is in the preset time period, acquiring reference track information corresponding to the preset time period in which the current moment is; the reference track information is used for representing base stations passing by within the first preset duration before the occurrence of the target behavior;

determining the similarity of the target track information and the reference track information;

and determining a prediction result of the target behavior according to the similarity of the target track information and the reference track information.

2. The method of claim 1, wherein after the determining the predicted outcome of the target behavior, the method further comprises:

if the predicted result of the target behavior indicates that the behavior intention of the target behavior exists, displaying a functional icon of the target application in a display interface; wherein the target application is for executing a target behavior.

3. The method according to claim 2, wherein the method further comprises:

and under the condition that the display interface displays the function icon of the target application for a second preset time period, canceling displaying the function icon of the target application in the display interface.

4. The method according to claim 1, wherein the reference trajectory information includes n pieces of first trajectory information arranged in the time order; the determining the similarity between the target track information and the reference track information includes:

splitting the target track information to obtain n sections of second track information; the time length of the second track information of the ith section is matched with the time length of the first track information of the ith section, i is a positive integer less than or equal to n, and n is a positive integer;

Calculating the similarity between each section of second track information and the corresponding first track information;

according to the n similarity between the n sections of second track information and the corresponding first track information, determining the similarity between the target track information and the reference track information; the similarity between the ith section second track information and the ith section first track information is the ith similarity in the n similarities.

5. The method of claim 4, wherein determining the similarity of the target track information and the reference track information according to the n similarities of the n pieces of second track information and the corresponding first track information, respectively, comprises:

weighting the n similarities according to preset weight parameters respectively corresponding to the n similarities, and determining the similarity between the target track information and the reference track information; the n similarity degrees respectively correspond to preset weight parameters and are sequentially increased.

6. The method of claim 4, wherein each piece of first sub-track information includes at least one base station identification and a corresponding frequency for each base station identification; the calculating the similarity between each section of second track information and the corresponding first track information comprises the following steps:

Searching the same base station identifier in the ith section of second track information and the ith section of first track information aiming at the ith section of second track information in the n sections of second track information;

and obtaining the similarity of the second track information of the ith section and the first track information of the ith section according to the frequency corresponding to the same base station identifier.

7. The method according to any one of claims 4-6, wherein before splitting the target track information to obtain n pieces of second track information, the method further comprises:

combining the same base station identifiers adjacently arranged in the target track information to obtain target track information after duplication removal;

the splitting the target track information to obtain n sections of second track information comprises the following steps: splitting the target track information after the duplication removal to obtain the n sections of second track information.

8. The method according to claim 1, wherein the method further comprises:

acquiring a plurality of historical tracks in the preset time period; wherein, a history track comprises a plurality of base station identifications arranged in time sequence before one target behavior;

splitting a historical track into n sections of third track information;

Counting the base station identifiers of a plurality of ith section of third track information in the plurality of historical tracks to obtain the ith section of first track information of the reference track information; wherein i is a positive integer less than or equal to n, and n is a positive integer.

9. The method of claim 8, wherein the counting base station identifiers of a plurality of i-th pieces of third track information in the plurality of historical tracks to obtain i-th pieces of first track information of the reference track information includes:

counting the frequency of each base station mark aiming at a plurality of ith section third track information in the plurality of historical tracks to obtain ith section first track information of the reference track information; the reference track information comprises a plurality of different base station identifiers and frequencies corresponding to the base station identifiers.

10. The method according to claim 1, wherein determining the predicted result of the target behavior according to the similarity between the target trajectory information and the reference trajectory information comprises:

generating behavior characteristics for predicting the target behavior according to the similarity of the target track information and the reference track information;

inputting the behavior characteristics into a preset machine learning model to obtain a prediction result of the target behavior output by the preset machine learning model; the preset machine learning model is obtained by model training based on sample characteristics of a training sample and sample labels of the training sample, the training sample comprises sample characteristics, the sample characteristics are obtained based on similarity of sample track information of a user in a first historical preset time period and the reference track information, the sample track information comprises at least one base station identifier arranged according to a time sequence, and the sample labels of the training sample are used for indicating execution of the target behavior or non-execution of the target behavior.

11. The method according to claim 1, wherein the obtaining the target track information of the terminal device includes:

and under the condition that a preset condition is met, acquiring target track information of the terminal equipment, wherein the preset condition comprises one or more of the current display interface and the desktop interface in the preset time period at the current moment.

12. A terminal device, comprising: a memory and one or more processors; the memory is coupled with the processor; wherein the memory has stored therein computer program code comprising computer instructions which, when executed by the processor, cause the terminal device to perform the method of any of claims 1-11.

13. A computer readable storage medium comprising computer instructions which, when run on a terminal device, cause the terminal device to perform the method of any of claims 1-11.