Card display method and related equipment

Abstract

The embodiment of the invention relates to the technical field of intelligent terminals, and provides a card display method and related equipment, and the card display method comprises the steps: obtaining the current position information of electronic equipment; determining the intention level of the user to use the riding card under the condition that the electronic equipment is determined to enter the geo-fence based on the current position information; displaying the riding card by adopting a card popping strategy corresponding to the intention level; wherein the riding card is used for triggering and displaying a riding code page. According to the card display method, the intention level of the user using the riding card can be identified, and different card display modes can be adopted based on different intention levels, so that the user can conveniently use the riding code page to carry out entrance code scanning or exit code scanning.

Description

Technical Field

[0001] This application relates to the field of intelligent terminals, and particularly to a card display method and related devices. Background Art

[0002] Geofencing is to use a virtual fence to enclose a geographical area with boundaries. The closer the geographical area indicated by the geofence is to the location area of the real scene, the more accurate the indication of the real scene is.

[0003] Currently, the geofences in electronic devices such as mobile phones are pre-set by application developers or mobile service providers. When a user brings a mobile phone into a geographical area indicated by certain geofences, the mobile phone will automatically display certain messages. For example, when the user arrives at a subway station, the mobile phone will automatically pop up a subway card, and the user can quickly scan the code based on the subway card and enter the station or take the train, thus improving the user's riding efficiency.

[0004] However, the existing form of card pop-up is fixed and cannot meet the usage requirements of different users, affecting the user experience. Summary of the Invention

[0005] This application provides a card display method and related devices, which solves the problem of the fixed display method of the displayed card and improves the user experience.

[0006] In a first aspect, an embodiment of this application provides a card display method, which is applied to an electronic device. The card display method includes: in the case where the electronic device enters a first geofence, displaying a first riding card on the desktop interface; in the case where the electronic device enters a second geofence, displaying a second riding card on the desktop interface; wherein, both the first riding card and the second riding card are used to trigger the display of a riding code page, the area of the second riding card is larger than that of the first riding card, the first geofence corresponds to a first riding station, the second geofence corresponds to a second riding station, and the number of rides of the electronic device at the first riding station is less than the number of rides at the second riding station.

[0007] By adopting the above technical solution, different riding stations can adopt different card display methods. For example, as the number of rides of the user at a certain riding station increases, the electronic device can adopt a card display method with a higher degree of visibility, such as increasing the display area of the riding card, so that the user can intuitively find the riding card and quickly use the riding card.

[0008] In a possible implementation, when the electronic device enters the second geofence, a second ride card is displayed on the desktop interface. It further includes: when the electronic device enters the second geofence and the number of rides at the second boarding station within a preset period is greater than a preset number, a second ride card is displayed on the desktop interface; when the electronic device enters the second geofence and the number of rides at the second boarding station within a preset period is less than the preset number, a first ride card is displayed on the desktop interface.

[0009] With the above technical solution, if the number of rides at the second boarding station within a preset period is greater than the preset number, it indicates that the second boarding station is a station with relatively regular rides. By adopting a card display method with a higher visibility level, it is convenient for users to use the ride card. If the number of rides at the second boarding station within a preset period is less than the preset number, it indicates that the second boarding station is a station with irregular rides, and users may not necessarily take the vehicle at this second boarding station. A card display method with a lower visibility level can still be adopted to reduce the accidental disturbance to users caused by the popping up of the card.

[0010] In a possible implementation, when the electronic device enters the second geofence, a second ride card is displayed on the desktop interface. It further includes: when the electronic device enters the second geofence, a first ride card or a second ride card is displayed on the desktop interface, and a third interface is opened to display a third ride card, where the third ride card is used to trigger the display of the ride code page, and the third interface is a floating interface or an interface displayed in an interface with a global function display area.

[0011] With the above technical solution, as the number of rides of the user at a certain boarding station increases, the electronic device can adopt a card display method with a higher visibility level. For example, the display area of the ride card can be increased and / or quick access entries can be added to facilitate the user's use of the ride card. For example, the floating interface can be a floating window or a floating ball, and having a global function display area can refer to implementing the display of the ride card in the buried hole area at the top of the screen of the notch screen using the intelligent capsule solution of Honor Company, so that the ride code page can be opened without returning to the desktop interface.

[0012] In a possible implementation, the display of the first ride card on the desktop interface, the display of the second ride card on the desktop interface, and the opening of the third interface to display the third ride card are all obtained based on the prediction of a preset model.

[0013] With the above technical solution, after the electronic device enters the geofence, a preset model (which can also be called an intention level prediction model) trained by the electronic device can be used to determine which ride card display method to adopt. For example, a preset model can be trained using historical ride behavior information.

[0014] In a possible implementation manner, when the preset model becomes effective, the electronic device generates a model file corresponding to the preset model.

[0015] By adopting the above technical solution, it is possible to determine whether the preset model becomes effective by detecting whether a model file corresponding to the preset model is generated. The preset model becoming effective may mean that the preset model has been trained for a preset number of iterations.

[0016] In a possible implementation manner, the input of the preset model includes the time information, location information, running application information, and motion state of the electronic device when entering a geofence, and the output of the preset model includes identification information for characterizing the intention level.

[0017] By adopting the above technical solution, the electronic device can train the preset model using historical riding behavior information. The historical riding behavior information may include the historical location information, historical time information, historical running application information, and historical motion state of the electronic device when a historical riding behavior event occurs. After training the preset model, the time information, location information, running application information, and motion state of the electronic device obtained when entering the geofence can be input into the preset model, and the output of the preset model can be identification information for characterizing the intention level, so as to realize different forms of card popping based on the intention level of the user's ride.

[0018] In a possible implementation manner, before displaying the first riding card on the desktop interface, the card display method further includes: obtaining first identification information based on the preset model; before displaying the second riding card on the desktop interface, the card display method further includes: obtaining second identification information based on the preset model; wherein, the intention level characterized by the second identification information is higher than the intention level characterized by the first identification information.

[0019] By adopting the above technical solution, different boarding stations can adopt different card display methods. For example, as the intention level of the user boarding at the station increases, the electronic device can adopt a card display method with a higher visibility, such as increasing the display area of the riding card, so that the user can intuitively discover the riding card and quickly use the riding card.

[0020] In a possible implementation manner, the output of the preset model further includes identification information for characterizing whether to pop a card.

[0021] With the above technical solution, the output of the intention level prediction model may include identification information on whether to pop up the card. In the case where the identification information indicates card popping, the output of the intention level prediction model may further include another identification information representing the intention level. If the identification information indicates no card popping, it means that the user has no intention of using the ride card under the current geofence, and then there is no need to display the card, thus avoiding the accidental popping of the card. If the identification information indicates card popping, different forms of card popping can be performed based on different intention levels.

[0022] In a possible implementation manner, the card display method further includes: when the preset model is not in effect and the electronic device enters the geofence corresponding to any station, displaying a fourth ride card on the negative first screen.

[0023] With the above technical solution, in the case where the preset model is not in effect, since the intention level of the user using the ride code at the station cannot be predicted, it can be set that when the electronic device enters the geofence corresponding to any station, a fourth ride card is displayed on the negative first screen to reduce the accidental disturbance of the card popping on the user.

[0024] In a second aspect, the present application provides a card display method applied to an electronic device. The card display method includes: obtaining the current location information of the electronic device; when it is determined based on the current location information that the electronic device enters a geofence, determining the intention level of the user using the ride card; and displaying the ride card using a card popping strategy corresponding to the intention level; wherein the ride card is used to trigger the display of the ride code page.

[0025] With the above technical solution, when the electronic device triggers the geofence, by predicting the intention level of the user using the ride card currently, different intention levels can correspond to different card popping strategies, realizing different forms of card popping based on the intention level of the user. In this way, not only can the accidental popping of the card when the user has no intention of using the ride card be avoided, but also the accidental disturbance of the card popping to the user can be minimized to the greatest extent, and the user can use the card conveniently and quickly, improving the accuracy of the card popping on the electronic device and the user experience.

[0026] In a possible implementation manner, when it is determined based on the current location information that the electronic device enters a geofence, determining the intention level of the user using the ride card includes: when it is determined based on the current location information that the electronic device enters a geofence, obtaining ride intention information, where the ride intention information includes the current time information, current location information, currently running application information, and current motion state of the electronic device; and determining the intention level of the user using the ride card based on the ride intention information.

[0027] Adopting the above technical solution, the intention information includes, but is not limited to, the current time information, current location information, currently running application information, and current motion state of the electronic device. Based on the information such as the current time information, current location information, currently running application information, and current motion state of the electronic device, the intention level of the user's current use of the ride card can be accurately identified, so as to perform different forms of card pop-up based on the user's intention level.

[0028] In a possible implementation manner, the higher the intention level, the greater the card visibility of the card pop-up strategy corresponding to the intention level. The card visibility includes at least one of the card area, the number of quick access entries, and the display position.

[0029] Adopting the above technical solution, the higher the intention level, the greater the card visibility of the card pop-up strategy corresponding to the intention level. For example, the larger the card area, or the more quick access entries, or the global display position (for example, as the intention level increases, the card is displayed in a global manner such as a floating window / intelligent capsule instead of a specified area), ensuring that users with a high intention level can use the card conveniently and quickly, while users with a low intention level can also use the card, thereby minimizing the accidental disturbance of the card pop-up to the user and improving the accuracy of the electronic device to pop up the card and the user experience.

[0030] In a possible implementation manner, based on the intention information, determining the intention level of the user's use of the ride card includes: constructing a user profile corresponding to the geographical fence based on the intention information; comparing the user profile with a preset intention recognition rule set to obtain the intention level of the user's use of the ride card; wherein, the intention recognition rule set includes multiple intention levels and a feature set mapped to each intention level in the multiple intention levels, and the features included in the user profile are determined based on the feature set.

[0031] Adopting the above technical solution, by constructing an intention recognition rule set including multiple intention levels, the features of the user profile constructed based on the intention information can be the same as the features corresponding to the intention levels in the intention recognition rule set. Furthermore, the user profile constructed when the geographical fence is triggered can be compared with the preset intention recognition rule set to determine the intention level of the user's use of the ride card, so as to perform different forms of card pop-up based on the user's intention level.

[0032] In a possible implementation manner, the feature set includes a frequency feature and a geographical fence feature. The frequency feature is used to indicate the frequency of the user using the ride card within a preset time period, and the geographical fence feature is used to indicate the accuracy of the geographical fence.

[0033] By adopting the above technical solution, an intention recognition rule set can be constructed based on the frequency of the user using the ride card and the accuracy of the triggered geofence. For example, the frequency of the user using the ride card can be divided into low frequency, medium frequency, and high frequency, and the accuracy of the geofence can be divided into low accuracy, medium accuracy, and high accuracy. After the geofence is triggered, the frequency feature of the user and the feature of the currently triggered geofence can be compared with the intention recognition rule set to determine the intention level of the user using the ride card, so as to perform different forms of card pop-up based on the intention level of the user.

[0034] In a possible implementation manner, based on the intention information, determining the intention level of the user using the ride card includes: inputting the intention information into a preset model to obtain an output result, and the output result includes first identification information for characterizing the intention level.

[0035] By adopting the above technical solution, a preset model can be trained to predict the intention level of the user using the ride card, so as to perform different forms of card pop-up based on the intention level of the user. For example, the preset model can be trained using historical ride behavior information. After the preset model is trained, the obtained intention information can be input into the preset model, and the output of the preset model is the first identification information for characterizing the intention level, realizing the prediction of the intention level.

[0036] In a possible implementation manner, the output result further includes second identification information for characterizing whether to pop up a card, and the card display method further includes: if the second identification information indicates not to pop up a card, determining not to display the ride card.

[0037] By adopting the above technical solution, the output of the intention level prediction model can include identification information on whether to pop up a card. And in the case where the identification information indicates to pop up a card, the output of the intention level prediction model can further include another identification information for characterizing the intention level. If the identification information indicates not to pop up a card, it means that the user has no intention of using the ride card under the current geofence, then there is no need to display the ride card, thus avoiding the accidental pop-up of the card.

[0038] In a possible implementation manner, displaying the ride card by adopting a card pop-up strategy corresponding to the intention level includes: if the second identification information indicates to pop up a card, displaying the ride card by adopting a card pop-up strategy corresponding to the intention level.

[0039] By adopting the above technical solution, in the case where the identification information indicates to pop up a card, it means that the user has the intention of using the ride card under the current geofence. The card can be popped up by adopting a card pop-up strategy corresponding to the intention level determined by the intention level prediction model, realizing different forms of card pop-up based on the intention level of the user.

[0040] In a possible implementation manner, the preset model includes a first preset model and a second preset model. The first preset model is trained based on the historical riding behavior information on weekdays, and the second preset model is trained based on the historical riding behavior information on non-weekdays. Inputting the intention information into the preset model to obtain an output result includes: obtaining the current time information of the electronic device; in the case where it is determined to be a weekday based on the current time information, inputting the intention information into the first preset model to obtain an output result; in the case where it is determined to be a non-weekday based on the current time information, inputting the intention information into the second preset model to obtain an output result.

[0041] By adopting the above technical solution, since the habits of users using the riding card on weekdays and non-weekdays are quite different, by dividing the historical riding behavior information into the historical riding behavior information on weekdays and the historical riding behavior information on non-weekdays, and respectively training the first preset model for predicting the intention level of riding on weekdays and the second preset model for predicting the intention level of riding on non-weekdays, the accuracy of intention level prediction can be improved, and thus the electronic device can achieve accurate card popping.

[0042] In a possible implementation manner, the card display method further includes: dividing the historical riding behavior information into multiple behavior information units according to a preset time window; training the first preset model or the second preset model based on the multiple behavior information units and the weight of each behavior information unit in the multiple behavior information units; the earlier the behavior information unit is from the current training time of the first preset model or the second preset model, the lower the weight.

[0043] By adopting the above technical solution, different weight values are given according to the distance from the current model training time. For example, the earlier the historical time corresponding to the training sample is, the smaller the weight value of the training sample, and the smaller the influence degree of the training sample in this sample unit on the future intention of using the riding card. The later the historical time corresponding to the training sample is, the greater the influence degree of the training sample on the future intention of using the riding card. By the above method, it is beneficial to improve the prediction accuracy of the intention level. For example, it can more accurately predict the riding level of the user after the change of the workplace / residence, and achieve accurate card popping.

[0044] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor. The memory is used to store computer-readable instructions; the processor is used to read the computer-readable instructions and implement the method provided in the first aspect and its optional implementation manners, or implement the method provided in the second aspect and its optional implementation manners.

[0045] Fourthly, an embodiment of the present application provides a computer storage medium storing computer-readable instructions, and when the computer-readable instructions are executed by a processor, the method provided in the first aspect and its optional implementation manners is implemented, or the method provided in the second aspect and its optional implementation manners is implemented.

[0046] Fifthly, an embodiment of the present application provides a computer program product, which includes computer-readable instructions, and when the computer-readable instructions are executed by a processor, the method provided in the first aspect and its optional implementation manners is implemented, or the method provided in the second aspect and its optional implementation manners is implemented.

[0047] Sixthly, an embodiment of the present application provides a chip, which is coupled to a memory, and the chip is configured to read and execute a computer program stored in the memory to implement the method provided in the first aspect and its optional implementation manners, or the method provided in the second aspect and its optional implementation manners.

[0048] The technical effects obtained in the second, third, fourth, and fifth aspects are similar to those obtained by the corresponding technical means in the first or second aspect, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

[0051] Figure 2 It is a schematic software structure diagram of an electronic device provided by an embodiment of the present application;

[0052] Figure 3 A schematic diagram of a sensing hub provided by an embodiment of the present application;

[0053] Figure 4 It is a schematic diagram of a training process of an intention level prediction model provided by an embodiment of the present application;

[0054] Figure 5a And Figure 5b It is a schematic diagram of an electronic device provided by an embodiment of the present application displaying a card on the negative first screen;

[0055] Figure 5c It is a schematic diagram of a feedback window provided by an embodiment of the present application;

[0056] Figure 5d Schematic diagram of the ride code display interface provided by the embodiment of the present application;

[0057] Figure 5e Schematic diagram of the electronic device provided by the embodiment of the present application displaying a card in the APP suggestion area on the desktop;

[0058] Figure 5f Schematic diagram of the electronic device provided by the embodiment of the present application displaying a card in the YOYO suggestion area on the desktop;

[0059] Figure 5g Schematic diagram of the electronic device provided by the embodiment of the present application displaying a card using a floating window;

[0060] Figure 6 Schematic diagram of the training process of the pop-up card decision model provided by the embodiment of the present application;

[0061] Figure 7a Schematic diagram of the training process of the pop-up card decision model in the training stage provided by the embodiment of the present application;

[0062] Figure 7b Schematic diagram of the inference process of the pop-up card decision model in the inference stage provided by the embodiment of the present application;

[0063] Figure 8 Schematic diagram of the architecture of the pop-up card decision system provided by the embodiment of the present application;

[0064] Figure 9 Schematic diagram of the software framework for the electronic device provided by the embodiment of the present application to implement the pop-up card function;

[0065] Figure 10 Schematic diagram of the terminal device provided by the embodiment of the present application adjusting the display size of the ride code icon;

[0066] Figure 11a Schematic diagram of the interface of the terminal device provided by the embodiment of the present application obtaining the subway ride code service in response to a user instruction;

[0067] Figure 11b Schematic diagram of the interface of the terminal device provided by the embodiment of the present application specifying the ride code service in response to a user instruction;

[0068] Figure 11c Schematic diagram of the interface of the terminal device provided by the embodiment of the present application initiating a query for a quick entry to add a ride code service;

[0069] Figure 12 Schematic diagram of the step flow of the card display method provided by the embodiment of the present application;

[0070] Figure 13Schematic diagram of the scenario of the user operation card provided by the embodiment of the present application;

[0071] Figure 14 Schematic flow chart of the steps of another card display method provided by the embodiment of the present application;

[0072] Figure 15 Schematic flow chart of the steps of yet another card display method provided by the embodiment of the present application;

[0073] Figure 16 Schematic interaction flow chart of the card display method provided by the embodiment of the present application;

[0074] Figure 17 Schematic interaction flow chart of another card display method provided by the embodiment of the present application. Detailed implementation manners

[0075] Next, the technical solutions in the embodiments of the present application will be described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0076] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, words such as "exemplary", "or", and "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary", "or", and "for example" is intended to present related concepts in a specific manner.

[0077] The reference to "an embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in combination with the embodiment is included in one or more embodiments of the present application. Thus, the statements "in an embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0078] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used in the description of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. It should be understood that unless otherwise stated in this application, " / " means "or". For example, A / B can mean A or B. The "and / or" in this application is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone, these three situations. "At least one" means one or more. "Multiple" means two or more than two. For example, at least one of a, b, or c can mean: a, b, c, a and b, a and c, b and c, a, b, and c, these seven situations. It should be understood that the order of the steps shown in the flowcharts herein can be changed and some can also be omitted.

[0079] It should be noted that the icons of the applications shown in the drawings of the specification are only examples given for clearly illustrating the embodiments of this application, and are only for illustration purposes. The embodiments of this application do not limit this.

[0080] To facilitate the understanding of the embodiments of this application, some nouns or terms involved in this application are first explained.

[0081] A fence refers to a trigger condition. When the fence meets the trigger condition, the electronic device starts to execute a specific service or provide a specific service, such as displaying, refreshing, or closing notification messages, warning messages, or cards, etc.

[0082] Generally, fences include multiple types, such as geographical fences, time fences, and associated event fences.

[0083] A geographical fence is used to represent a trigger condition related to a location. A geographical fence can identify the geographical range corresponding to the geographical fence through a geographical location (such as determining the geographical location through GPS positioning, etc.), or can also identify the geographical range corresponding to the geographical fence through the signal fingerprint within this geographical range (such as the base station information, wifi information, Bluetooth information, etc. that can be detected within this geographical range). A geographical fence can use a virtual fence to enclose a geographical area with a virtual boundary, that is, this virtual boundary defines a specific geographical area. The closer the geographical area indicated by the geographical fence is to the location area of the real scene, the more accurate the indication of the real scene. The geographical fence can be circular, polygonal, or irregularly shaped, and the embodiments of this application do not make limitations.

[0084] In some embodiments, the electronic device can listen in real time to the location where the electronic device is currently located. When the current location of the electronic device is within the geofence, the electronic device automatically pops up a card. Taking the subway ride scenario as an example, the geofence can be a geographical area centered on a subway station, or a geographical area centered on the turnstile of a subway station, or a geographical area that includes a subway station. The subway station can be the subway station where the user starts taking the train, or the subway station where the user ends taking the train.

[0085] The geofence can be divided into multiple types. For example, a low-precision geofence, a medium-precision geofence, and a high-precision geofence. Taking the subway ride scenario as an example, a low-precision geofence can be a geofence that can identify the approximate geographical range of the subway station. If the user carries the electronic device into the geographical range of the subway station, the low-precision geofence can be triggered; a medium-precision geofence can be a geofence that refers to the geographical range of the entrance of the subway station. If the user carries the electronic device into the geographical range of the entrance of the subway station, the medium-precision geofence can be triggered; a high-precision geofence can be a geofence that refers to the geographical range of the code-scanning turnstile in the subway station. If the user carries the electronic device into the geographical range of the code-scanning turnstile in the subway station, the high-precision geofence can be triggered.

[0086] In some embodiments, it is also possible to use the code-scanning turnstile / entrance as the center point to construct fences with different radius ranges, corresponding to the low-precision geofence, the medium-precision geofence, and the high-precision geofence respectively.

[0087] The time fence is used to represent the trigger condition related to time. For example, set the historical time when the user enters and exits the subway station (such as 7:00 every day) as the time fence. On the premise that the electronic device enters the geofence, if the system time of the electronic device meets the time set by the time fence, the electronic device automatically pops up a card.

[0088] The associated event fence is used to represent the trigger condition related to a specific event. The specific event is the trigger event for entering the geofence. For example, every day before entering the subway, the user will use the electronic device to buy breakfast. When the user enters the subway area indicated by the geofence, the electronic device can obtain whether the user has used the electronic device to buy breakfast before entering the geofence. If so, the associated event fence is triggered and the electronic device automatically pops up a card.

[0089] Currently, the geofences in electronic devices such as mobile phones are preset in the mobile phones by application developers or mobile service providers. When a user carries a mobile phone into the geographical areas indicated by certain geofences, the mobile phone will automatically display certain messages. For example, when the user enters the subway station, a subway card will pop up. The user can quickly scan the code to enter the station based on the subway card. However, in some cases, users located within the geofence may not need to take the train, but the subway card will still pop up by mistake, thus affecting the user experience.

[0090] In view of the above problems, the embodiments of the present application provide a card display solution. When a user carries an electronic device into the range of a geofence, the electronic device can predict the intention level of the user using the two-dimensional code based on the user's historical behavior information and the user's current status. Different intention levels can correspond to different card pop-up strategies, realizing different forms of card pop-up based on the user's intention level. In this way, not only can the accidental pop-up of the card be avoided when the user has no intention of using the two-dimensional code, but also the accidental disturbance to the user caused by the pop-up of the card can be minimized to the greatest extent, and the user can conveniently and quickly use the card, improving the accuracy of the electronic device to pop up the card and the user experience. The user's current status may include one or more of the location status, movement status, device status, etc.

[0091] The card display solution provided by the embodiments of the present application can be applied to various riding scenarios. For example, when a user enters the subway station to take the train, the scenario of scanning the code to enter the station is required; when the user finishes taking the train and leaves the subway station, the scenario of scanning the code to leave the station is required; when the user takes the bus, the scenario of scanning the code to get on the bus is required; when the user takes the light rail, the scenario of scanning the code to enter the station is required; and when the user takes the light rail, the scenario of scanning the code to leave the station is required, etc.

[0092] It should be noted that the embodiments of the present application are all described by taking the riding scenario as an example, which does not form a limitation on the embodiments of the present application. It can be understood that the card display solution provided by the embodiments of the present application can also be adopted for other travel scenarios that require code scanning.

[0093] The two-dimensional code in the embodiments of the present application can be used to represent the user's identity. When a user carries an electronic device into different geofences, the electronic device can display a card corresponding to the geofence, so that the user can use the two-dimensional code corresponding to the card. For example, use the riding code to enter and leave the subway station, and use the riding code to scan the code to take the bus on the bus, etc.

[0094] In addition, the card display solution provided by the embodiments of the present application can be applied to various electronic devices. In some embodiments, the electronic device can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) device, a virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a smart screen, or other terminal devices with a display function, or can also be other devices or apparatuses capable of displaying cards. The specific type of the electronic device is not limited in the embodiments of the present application.

[0095] Taking the electronic device as a mobile phone as an example, Figure 1 FIG. shows a schematic diagram of the hardware structure of the mobile phone provided by the embodiments of the present application.

[0096] As Figure 1 shown, the mobile phone may include: a processor 110, an external memory interface 120, an internal memory 121, a USB interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. Among them, the sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, and a bone conduction sensor 180M, etc.

[0097] The processor 110 may include one or more processing units. For example, the processor 110 may include a central processing unit (CPU), an image signal processor (ISP), a digital signal processor (DSP), a video codec, a neural-network processing unit (NPU), a graphics processing unit (GPU), an application processor (AP), and / or a modem processor, etc. In some embodiments, different processing units may be independent devices or integrated in one or more processors.

[0098] Among them, the CPU is the final execution unit for information processing and program running. Its main tasks include processing instructions, executing operations, controlling time, and processing data, etc. The CPU may include a controller, an arithmetic unit, a cache memory, and a bus for connecting these components. The controller may be the nerve center and command center of the mobile phone. The controller may generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching and executing instructions.

[0099] 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. This memory can save the instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0100] In some embodiments, the NPU may be used to train an intent level prediction model based on the user's behavior information, such as the subway stations entered and exited every day, the time of entering and exiting the subway stations every day, the code scanning events when entering the subway station each time, and the code scanning events when leaving the subway station each time, etc., and compare the output prediction result of the intent level prediction model with the expected result, and adjust the parameters of the intent level prediction model according to the comparison result to obtain an optimized intent level prediction model.

[0101] The wireless communication function of the mobile phone can be implemented by antenna 1, antenna 2, a mobile communication module 150, a wireless communication module 160, a modem processor, and a baseband processor, etc. Among them, antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals.

[0102] The mobile communication module 150 can provide solutions for wireless communications such as 2G / 3G / 4G / 5G applied to mobile phones. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. In some embodiments, the mobile communication module 150 can receive electromagnetic waves from other devices by the antenna 1, and perform processing such as filtering and amplifying the electromagnetic waves, and then transmit them to the modulation and demodulation processor for demodulation.

[0103] The modulation and demodulation processor may include a modulator and a demodulator. Among them, the modulator can be used to modulate the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator can be used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. Subsequently, the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After being processed by the baseband processor, the low-frequency baseband signal is transmitted to the application processor. The application processor outputs a sound signal through the audio device, or displays an image or video through the display screen 194.

[0104] The wireless communication module 160 can provide solutions for wireless communications such as wireless local area networks (WLAN) (such as Wi-Fi networks), Bluetooth, global navigation satellite system (GNSS), FM, NFC, infrared technology (IR), etc. applied to mobile phones. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. In some embodiments, based on GNSS, the wireless communication module 160 receives electromagnetic waves from communication devices via the antenna 2, and performs frequency modulation and filtering processing on the electromagnetic wave signals to obtain the location information of the mobile phone.

[0105] In some embodiments, antenna 1 of the mobile phone is coupled to the mobile communication module 150, and antenna 2 is coupled to the wireless communication module 160, enabling the mobile phone to communicate with the network and other devices through wireless communication technologies. The wireless communication technologies may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology, etc. GNSS may include global positioning system (GPS), global navigation satellite system (GLONASS), beidou navigation satellite system (BDS), quasi-zenith satellite system (QZSS), and / or satellite based augmentation systems (SBAS).

[0106] The mobile phone realizes the display function through the GPU, the display screen 194, and the application processor, etc. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs, which execute program instructions to generate or change the display information.

[0107] The display screen 194 is used to display images, videos, etc., such as display cards, two-dimensional codes, etc. The display screen 194 includes a display panel. The display panel can adopt a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a Miniled, a MicroLed, a Micro-oLed, a quantum dot light-emitting diode (QLED), etc.

[0108] In some embodiments, the mobile phone may include one or N display screens 194, where N is a positive integer greater than 1.

[0109] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the mobile phone. The external memory card communicates with the processor 110 through the external memory interface 120 to implement the data storage function. For example, the user's behavior data is saved in the external memory card.

[0110] The internal memory 121 can be used to store computer-executable program code, and the executable program code includes instructions. The processor 110 executes various functional applications and data processing of the mobile phone by running the instructions stored in the internal memory 121. The internal memory 121 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system, at least one application program (APP) required for functions (such as a desktop APP and a payment APP), etc. The data storage area can store the data created during the use of the mobile phone (such as audio data, phone book, etc.). In addition, the internal memory 121 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0111] In some embodiments, the external memory interface 120 or the internal memory 121 may store the following information for training and generating the intent level prediction model: the historical geographical location and historical time of the mobile phone when entering the geofence; the historical geographical location and historical time of the mobile phone when displaying the QR code; the historical geographical location and historical time of the mobile phone when the user holds the QR code for scanning; the historical geographical location and historical time of the mobile phone when the user starts a ride; the historical geographical location and historical time of the mobile phone when the user ends a ride. This information can be used to train and generate the intent level prediction model.

[0112] In addition, the external memory interface 120 or the internal memory 121 may also be used to store the trained intent level prediction model.

[0113] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the mobile phone. In other embodiments, the mobile phone may include more or fewer components than those illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0114] The software system of the electronic device may adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservices architecture, or a cloud architecture. In the embodiments of the present application, taking the Android system with a layered architecture as an example, the software structure of the electronic device is exemplarily described.

[0115] Figure 2 It is a schematic diagram of the software structure of the electronic device in the embodiments of the present application. The layered architecture divides the software into several layers, and each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the software layers of the Android system are sequentially divided from top to bottom into: the application layer (application), the framework layer (framework, FWK), the library layer (FWK LIB), and the kernel layer (Kernal).

[0116] The application layer may include a series of application packages, such as desktop applications, payment applications, emotion perception modules, business logic processing modules, and business presentation modules. When these application packages are run, they can access various service modules provided by the application framework layer through the application programming interface (API) and execute corresponding intelligent services.

[0117] Among them, the desktop application can be used to implement the display of the desktop, such as the display of application icons, the desktop background, the status bar, the notification bar, etc. In addition, the desktop application can also be used to display or cancel cards according to the instructions of the business presentation module.

[0118] The context awareness module runs in the foreground or in a low-power mode, and has the ability to perceive external facts or the environment. When the card reminder service is enabled, the context awareness module monitors the capabilities or events registered by the service logic processing module (such as specific times, specific locations, or specific events, etc.). If the user triggers one of the capabilities or events, the context awareness module sends a notification to the service logic processing module. In addition, the context awareness module can also detect relevant events and obtain the status of events through the API from other applications in the application layer, or the application framework layer, or the system layer, or the kernel layer, such as detecting Bluetooth connections, network connections, monitoring user text messages, customizing timers, etc.

[0119] Exemplarily, the functions of the context awareness module include perceiving whether the user enters a geofence. For example, the context awareness module can detect whether the electronic device enters the area of a certain subway station based on the Wi-Fi network detected by the electronic device, as well as the mapping relationship between the Wi-Fi network identifier, the Wi-Fi network signal strength, and the subway station. For another example, the context awareness module can detect whether the electronic device enters the area of a certain subway station based on the searched satellite status. In addition, the context awareness module can also detect the display interface of the electronic device, such as detecting whether a QR code is included in the current interface.

[0120] The service logic processing module, which can also be referred to as the computing engine or the brain, has the service logic processing ability and is used to implement the logic of the display and disappearance of various cards. For example, when the service logic processing module receives a notification sent by the context awareness module indicating that a certain event is detected (such as the subway entrance fence is triggered), it can send a command to the service presentation module (such as YOYO suggestion) according to the logic to display the card. Among them, the command can carry the link of a certain third-party APP or mini-program. When the user clicks on the card, it will jump to the third-party APP or mini-program according to the link. In addition, the service logic processing module can also control the cancellation of the displayed card by receiving a notification sent by the context awareness module indicating that the user has used the QR code.

[0121] The service presentation module, which can also be referred to as YOYO suggestion, is used to display or disappear the determined cards on the screen of the electronic device. For example, the service presentation module can receive the command to display the reminder card passed by the service logic processing module and display the reminder card to the user. When the user clicks on the card, it will link to a certain page of an APP. In some embodiments, when the user clicks on the subway card, the QR code page of the payment APP used by the user last time will be displayed, so that the user can directly scan the code to enter and exit the subway station. Correspondingly, if the service presentation module receives the command to disappear the card sent by the service logic processing module, the service presentation module will immediately disappear the already displayed card.

[0122] The framework layer provides the AP and programming frameworks for the applications in the application layer. The application framework layer includes some predefined functions. For example, the framework layer may include a window manager and a sensing management service, etc.

[0123] Among them, the window manager can be used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc. The sensing management service can be used to provide APIs related to the processing functions of time information and location information for the application layer, such as obtaining the time information and location information of the electronic device, and providing APIs related to the processing function of geographical fences for the context awareness module, such as determining whether the electronic device enters or leaves a geographical fence.

[0124] The library layer includes system libraries and Android runtime. The system libraries can include multiple functional modules, such as a surface manager, etc. The Android runtime is responsible for the scheduling and management of the Android system, including core libraries and a virtual machine. The core libraries contain two parts: one part is the functional functions that need to be called by the Java language, and the other part is the core libraries of Android. The application layer and the application framework layer run in the virtual machine. The virtual machine executes the Java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.

[0125] The kernel layer is the interface layer between hardware and software. The kernel layer may include a mobile communication driver, a Wi-Fi driver, a GNSS driver, a display driver, and a sensor driver, etc.

[0126] To reduce the occupancy of the processor and thus reduce the power consumption of the electronic device, in combination with Figure 2 the software structure block diagram shown, a sensor hub, that is, a coprocessor, may also be configured in the hardware layer of the electronic device in the embodiments of the present application. The sensor hub is a chip with certain processing capabilities and low power consumption, and can be used to process simple tasks.

[0127] In some embodiments, the sensor hub can be connected to the hardware layer of the electronic device and connected to, such as Figure 1 the mobile communication module 150 and the wireless communication module 160 shown, etc.

[0128] Exemplarily, Figure 3 is a schematic diagram of the sensor hub provided by the embodiments of the present application. As Figure 3As shown in the figure, the sensing hub can obtain base station signals (such as 5G signals), Bluetooth signals, Wi-Fi signals, GPS signals, NFC signals, etc. from the mobile communication module 150 and the wireless communication module 160 (such as Bluetooth module, Wi-Fi module, GPS module, NFC module). The sensing hub can also be used to receive and store established geographical fences, for example, Wi-Fi fences, cell fences, and fences containing multiple types of fence features. In some embodiments, when preset conditions are met, the sensing hub obtains location information and determines whether the electronic device is within the established geographical fence based on the location information. Among them, the preset conditions can be that the electronic device scans a specific electromagnetic wave, such as a specific FM radio frequency signal, Bluetooth signal, Wi-Fi signal, or base station signal, etc.

[0129] It should be noted that although the embodiments of this application are described by taking the Android system as an example, its basic principles also apply to electronic devices based on operating systems such as iOS or Windows.

[0130] The following takes the scenario of a user taking the subway as an example for illustration.

[0131] When the user brings the electronic device into the range of the geographical fence of the subway station, the electronic device can predict the intention level of the user using the ride QR code according to the user's historical behavior information and the user's current status. Different intention levels can correspond to different card popping strategies.

[0132] For example, the intention level can include 10 levels (the intention level ranges from low to high as intention level 1 to intention level 10). As shown in Table 1 below, different intention levels can correspond to different / same card popping strategies, where "×" means no card popping and "√" means card popping.

[0133] Table 1

[0134]

[0135] The card popping strategies corresponding to the intention levels shown in Table 1 are only an example of the embodiments of this application and can be adjusted according to the actual card popping requirements and the devices actually used. The embodiments of this application do not limit this.

[0136] In some embodiments, the card popping strategies corresponding to different intention levels can be set before the device leaves the factory or customized by the device user. The embodiments of this application do not limit this.

[0137] In some embodiments, when the user brings the electronic device into the range of the subway station's geofence, the user's current intention level of using the ride QR code can be determined by a pre-trained model or a pre-set intention recognition rule set in the electronic device.

[0138] Taking the determination of the intention level by a pre-set intention recognition rule set as an example, the intention recognition rule set can include multiple dimensions, such as the user profile dimension, the perception dimension, the decision-making dimension, etc. Each dimension can include one or more features, and rules for determining the intention level are constructed through the combination of these features. The electronic device can determine the intention level of the user using the ride QR code by comparing the user's ride intention information with the features in the intention recognition rule set. The user's ride intention information can refer to the current time information, current location information, currently running application information, motion state (i.e., the user's current motion state), etc. of the electronic device when the subway station's geofence is triggered.

[0139] For example, the user profile dimension can include frequency features and city features. The frequency feature can refer to the frequency of the user taking the subway within a period of time (week / month / quarter, etc.). For example, defining 0 times / 3 months as a non-riding user, no more than 3 times / month as a low-frequency riding user, no more than 14 times / week as a medium-frequency riding user, and no less than 15 times / week as a high-frequency riding user.

[0140] In some embodiments, the riding frequency ranges corresponding to low-frequency riding users, medium-frequency riding users, and high-frequency riding users for subway stations in a certain city can be dynamically set according to the distribution of the number of times users in that city take the subway. The embodiments of the present application do not limit this.

[0141] The city feature can include the usual residence (i.e., the subway station belongs to the station of the usual residence) and the non-usual residence (i.e., the subway station belongs to the station of the non-usual residence).

[0142] The perception dimension can include subway fence features. For example, the subway fence features can include low-precision geofences, medium-precision geofences, and high-precision geofences. Generally speaking, the ride intention of triggering a high-precision geofence is greater than that of triggering a medium-precision geofence, and the ride intention of triggering a medium-precision geofence is greater than that of triggering a low-precision geofence.

[0143] The decision-making dimensions may include payment method characteristics, station characteristics, date characteristics, time characteristics, motion state characteristics, location state characteristics, and device state characteristics. The payment method characteristics may include payment by ride code, NFC payment, etc. The station characteristics may include familiar stations, general stations, unfamiliar stations, special stations, etc. For example, a familiar station is a station where the user has boarded the train at least 3 times, a general station is a station where the user has boarded the train 1 or 2 times, an unfamiliar station is a station where the user has boarded the train 0 times, etc. Special stations may include stations with a large semantic association with the user (e.g., stations near the place of residence, stations near the workplace) and public transportation hub stations (e.g., stations at airports, railway stations). The date characteristics may include holidays, weekdays, restricted driving days, non-restricted driving days, etc. The time characteristics may include regular riding periods, non-regular riding periods, etc. The motion state characteristics include walking, cycling, driving / taking a vehicle, etc. The location state characteristics include indoor, outdoor, etc. The device state characteristics may include the application information currently running on the electronic device. Based on this device state characteristic, it can be determined whether the electronic device has launched other transportation software that does not use the ride code (e.g., taxi software, cycling software, etc.).

[0144] For example, Table 2 below shows some of the features corresponding to the intent levels in the intent recognition rule set. Among them, "No" in the device state in Table 2 indicates that other transportation software that does not use the ride code has not been launched.

[0145] Table 2

[0146]

[0147]

[0148] In some embodiments, one or more of the features shown in Table 2 for determining the intent level may also be omitted. For example, the electronic device may also determine the intent level only based on the frequency feature and the subway fence feature.

[0149] In some embodiments, the card display frame is set with a reach level. The card display frame is used to pop up corresponding cards according to the reach level. Different reach levels may correspond to different / same card pop-up strategies. After determining the intent level of the user's current use of the ride QR code, the intent level can be mapped to the reach level under the card display frame according to the preset rules, so that the card display frame can pop up cards with different strategies based on the reach level.

[0150] In some embodiments, after the popped-up card is displayed for a first preset time, the card display frame may also close the card, or after detecting the user's operation on the card, the card display frame may close the card. The first preset time can be set according to actual needs, and the embodiments of the present application do not limit this. For example, the first preset time is 5 minutes.

[0151] Taking the example of determining the intention level of the user using the ride QR code by a pre-trained model, the following is an example to illustrate the process of training an intention level prediction model for an electronic device. Figure 4

[0152] (1) Obtain the historical behavior information of the user. The historical behavior information may include the location information, time information, running application information, user's motion state, etc. of the electronic device when the historical behavior event occurs.

[0153] Among them, the historical behavior event may refer to an event associated with using the ride QR code that occurred before the electronic device currently enters the geofence. In the embodiment of the intention level prediction model of the present application, the geofence may refer to the above-mentioned low-precision geofence, or medium-precision geofence, or high-precision geofence. Taking the historical behavior event as an event that the electronic device triggers the low-precision geofence as an example, the subsequent prediction of the intention level by the trained intention level prediction model may refer to the prediction made when the electronic device triggers the low-precision geofence.

[0154] Exemplarily, the historical behavior event may include an event that the user enters the geofence, an event that the user triggers the display of the ride QR code, an event that the user holds the QR code for scanning, an event that the user ends the ride, etc.

[0155] Exemplarily, the event that the user enters the geofence can be determined according to the location information collected by the electronic device.

[0156] Exemplarily, before the user uses the ride QR code, usually a click operation is performed on the travel control, card package control, transportation card control, travel card, etc., so that the electronic device responds to the user operation and displays the ride QR code. Therefore, the electronic device can define the received trigger operation on these controls as an event that the user triggers the display of the ride QR code.

[0157] Exemplarily, when the electronic device responds to the user operation and displays the ride QR code, the electronic device can detect the displayed ride QR code. Therefore, the electronic device can also define the event of detecting the ride QR code as an event that the user triggers the display of the ride QR code.

[0158] Exemplarily, after the ride QR code is displayed, when the user holds the ride QR code for scanning, the user's wrist will flip to face and align the ride QR code with the scanning device. The electronic device can detect whether the flip angle of the electronic device exceeds a preset angle threshold through a sensor. If the flip angle of the electronic device exceeds the preset angle threshold, then it can be defined as an event that the user holds the ride QR code for scanning.

[0159] ​Exemplarily, after the user ends a ride and scans the ride QR code to exit the station, the electronic device will receive a notice of the deducted amount sent by the server. If the electronic device receives the notice of the deducted amount sent by the server, then it can be defined as an event that the user ends the ride.

[0160] (2) Process the historical behavior information to generate training samples.

[0161] In some embodiments, the operation of processing the historical behavior information may be: deleting the duplicate behavior information in the historical behavior information. At the same geographical location and during the same time period, the user may perform duplicate actions, such as opening the QR code multiple times. The historical behavior data corresponding to these duplicate actions may result in a large number of duplicate or similar training samples. By deleting the duplicate behavior information, the data processing volume for sample learning can be reduced, and the efficiency of sample learning can be improved.

[0162] In some embodiments, the operation of processing the historical behavior information may also be: dividing each station according to the station information indicated by the historical behavior information. When the user takes the subway from the starting station to the terminal station, one or more intermediate stations will be passed along the way. These intermediate stations respectively correspond to their own geographical fences. When the electronic device enters the geographical fence of an intermediate station, it may mistakenly think that the user has the intention to take a ride, resulting in the card popping up by mistake. To avoid this situation, the electronic device can divide each station according to the station information indicated by the historical behavior information and remove the behavior information of the intermediate stations, thereby improving the accuracy of sample learning.

[0163] In some embodiments, the operation of processing the historical behavior information may also be: performing user behavior enhancement processing on the historical behavior information, and the user behavior enhancement processing is used to obtain the behavior information related to the historical behavior event. For example, obtaining the behavior information at a time associated with the time when the historical behavior event occurs. The associated time may be a period of time before the time when the historical behavior event occurs, and / or a period of time after the time when the historical behavior event occurs. It should be understood that by performing enhancement processing on the historical behavior information, more behavior information related to the historical behavior event can be obtained, the training effect of the intention level prediction model is improved, and thus the accuracy of predicting the user's intention is improved.

[0164] After processing the historical behavior information, the electronic device can also convert the samples into a unified format, and then perform processing such as training, verification, and test set splitting, so as to generate training samples.

[0165] (3) Train the intention level prediction model according to the training samples.

[0166] The embodiments of the present application can adopt any possible algorithms, such as the Follow-the-Regularized-Leader (FTRL) algorithm, the Logistic Regression (LR) algorithm, the Factorization Machines (FM) algorithm, etc., to train the intention level prediction model. The algorithm can be determined according to actual usage requirements, and the embodiments of the present application do not make any limitations.

[0167] Each time the intention level prediction model is trained, the constructed intention level prediction model can be initialized first, and then according to the best learning rate searched, the training samples are input into the intention level prediction model to obtain the prediction result. The prediction result is compared with the expected result. Then, according to the comparison result, the parameters of the intention level prediction model are adjusted to obtain the trained intention level prediction model.

[0168] Exemplarily, labels are added to each training sample. For example, each training sample can include time information, location information, running application information, the user's motion state, etc. Label 1 is marked for training sample a, and label 2 is marked for training sample b. Then, training sample a and training sample b are used as the input of the intention level prediction model, and label 1 and label 2 are used as the expected results. Initial values are assigned to the connection weights between the neurons of each layer of the neural network. According to the connection weights between the neurons of each layer, the neural network algorithm is used to obtain the actual output result corresponding to the training sample. After the error function is used to process the expected result and the actual output result, the connection weights between the neurons of each layer are adjusted according to the processing result to obtain the adjusted connection weights between the neurons of each layer. The above training process is repeated, and after multiple rounds of iterative training, the trained intention level prediction model can be obtained.

[0169] In some embodiments, in order to improve the accuracy of intention level prediction, the historical behavior information can also be divided into historical behavior information on weekdays and historical behavior information on non-weekdays, and the first intention level prediction model for predicting the riding intention level on weekdays and the second intention level prediction model for predicting the riding intention level on non-weekdays are trained respectively.

[0170] In some embodiments, after the intention level prediction model is trained on the electronic device, the electronic device can generate a model file corresponding to the intention level prediction model (for example, a model file in JSON format), and this model file can represent that the electronic device has trained an available intention level prediction model.

[0171] In the embodiments of the present application, the electronic device can train the intent level prediction model on a daily, weekly, or monthly basis. For example, the electronic device can schedule the historical behavior information of the previous day / the previous N (N is greater than or equal to 2) days every day, generate training samples based on the historical behavior information of the previous day / the previous N days, and then train the intent level prediction model using the historical behavior information of the previous day / the previous N days. For example, the electronic device can schedule the historical behavior information of the previous week every Monday, generate training samples based on the historical behavior information of the previous week, and then train the intent level prediction model using the historical behavior information of the previous week. After training the intent level prediction model, the target information can be input into the intent level prediction model, and the output result of the intent level prediction model represents the information of the intent level corresponding to the target information, or the exception case information.

[0172] For example, after the electronic device triggers a geofence, the electronic device can obtain features such as the current location information, the current time information, the running application information, and the user's motion state, input the features into the intent level prediction model, and output a prediction result, which is the information for representing the intent level of the user using the ride QR code at this site, or the information for representing what kind of exception case the pop-up card strategy of this site belongs to.

[0173] For example, the labels annotated on the training samples include the confidence level for indicating the user's use of the ride QR code, and different confidence levels can be mapped to different intent levels. Suppose the range of the confidence level is between 0 and 1, the confidence level corresponding to intent level 1 can be set as [0, 0.1], the confidence level corresponding to intent level 2 can be set as (0.1, 0.2], the confidence level corresponding to intent level 3 can be set as (0.2, 0.3], and the confidence level corresponding to intent level 10 can be set as (0.9, 1].

[0174] For example, the labels annotated on the training samples also include exception case labels, and different exception cases can correspond to different pop-up card strategies. For the geofence that triggers an exception case, the result output by the intent level prediction model can include the exception case label information, rather than the intent level information.

[0175] In some embodiments, the pop-up card strategies shown in Table 1 above can also store the pop-up card strategies corresponding to each exception case, and the intent recognition rule sets shown in Table 2 above can also store the features corresponding to each exception case, so as to enable pop-up cards when an exception case is determined.

[0176] In some embodiments, since the user's riding intentions on weekdays and non-weekdays differ significantly, to improve the prediction accuracy of the intention level, the user's historical behavior information can also be divided into historical behavior information on weekdays and historical behavior information on non-weekdays. A first intention level prediction model for predicting the intention level of riding on weekdays is trained based on the historical behavior information on weekdays, and a second intention level prediction model for predicting the intention level of riding on non-weekdays is trained based on the historical behavior information on non-weekdays.

[0177] In some embodiments, the training samples can also be assigned different weight values according to their proximity to the current model training time. For example, the earlier the historical time (sample collection time) corresponding to the training sample, the smaller the weight value of the training sample. For example, the training samples can be divided into multiple sample units according to a preset time window, and the preset time window can be set according to actual needs. For example, the preset time window can be 10 days, half a month, 1 month, etc. The earlier the historical time corresponding to the sample unit, the smaller the influence of the training samples in this sample unit on the future riding intention. The later the historical time corresponding to the training sample (i.e., the closer it is to the current model training time), the greater the influence of this training sample on the future riding intention. Therefore, the above method is beneficial to improving the prediction accuracy of the riding intention level. For example, by assigning different weight values according to the proximity of the training samples to the current model training time, it is possible to accurately predict the user's riding intention after the change at the workplace / residence.

[0178] In some embodiments, taking the division of the user's historical behavior information into historical behavior information on weekdays and historical behavior information on non-weekdays as an example. For the training sample set, it is divided into a first sample set and a second sample set according to weekdays and non-weekdays. The first sample set is the training sample set on weekdays, and the second sample set is the training sample set on non-weekdays.

[0179] For example, after data cleaning and extraction of target events (events where the user enters a geofence, events where the user triggers the display of a ride QR code, events where the user scans a QR code with the QR code in hand, events where the user ends a ride), the first sample set can be divided into two sample units (long-term data and short-term data) for offline training to obtain a first intent level prediction model. Similarly, after data cleaning and extraction of target events, the second sample set can be divided into long-term sample data and short-term sample data for offline training to obtain a second intent level prediction model. The offline training referred to in the embodiments of this application may mean that model training is performed when the electronic device is locked or during a specified period (for example, from 1 to 5 am) to reduce the interference of model training on users. The long-term and short-term involved in the embodiments of this application are relative concepts and can be set according to actual model training requirements. The embodiments of this application do not limit this. For example, the long-term and short-term are bounded by 10 days. The long-term sample data is sample data for more than 10 days, and the short-term sample data is sample data within 10 days.

[0180] In some embodiments, both the first intent level prediction model and the second intent level prediction model can be characterized by the following formula ①:

[0181] P = Weight1 long *Factor1 long + Weight short *Factor short… ①;

[0182] Where P is the ride intent value. The ride intent value can be mapped to the ride intent level and exceptional situations. The specific mapping rules between the ride intent value and the ride intent level and exceptional situations can be predefined. The embodiments of this application do not limit this. Weight long is the weight of long-term rides, Factor long is the influence factor of long-term rides, Weight short is the weight of short-term rides, Factor short is the influence factor of short-term rides. The influence factor and the number of influence factors can be set according to actual prediction requirements. Weight long and Weight short can be obtained through model training, and Weight long + Weight short = 1.

[0183] That is, the process of training the first intent level prediction model / second intent level prediction model with training samples is the process of training to determine Weight long and Weight short .

[0184] Taking the impact factors including rides at a station and rides during a time period as an example, the rides during a time period can be rides in units of hours. For example, rides from 7:00 to 8:00, 8:00 to 9:00, etc. Equation ① can be rewritten as Equation ② shown below:

[0185] P = Weight long *(C * Long-term proportion of rides at this station + D * Long-term proportion of rides during this time period) + Weight short *(E * Short-term proportion of rides at this station + F * Short-term proportion of rides during this time period) … ②;

[0186] Among them, C is the number of times the fence at this station is triggered in the long term, D is the number of times the fence is triggered during this time period in the long term, E is the number of times the fence at this station is triggered in the short term, and F is the number of times the fence is triggered during this time period in the short term. The long-term proportion of rides at this station = the number of days of rides at this station in the long term / the number of days the fence at this station is triggered in the long term, the long-term proportion of rides during this time period = the number of days of rides during this time period in the long term / the number of days the fence is triggered during this time period in the long term, the short-term proportion of rides at this station = the number of days of rides at this station in the short term / the number of days the fence at this station is triggered in the short term, and the short-term proportion of rides during this time period = the number of days of rides during this time period in the short term / the number of days the fence is triggered during this time period in the short term.

[0187] In some embodiments, in order to improve the accuracy of model prediction, before counting the number of fence triggers, the long-term and short-term fence trigger data can be cleaned. For example, data cleaning can be consecutive fence triggers at the same station within a short period of time, and only the first fence trigger data needs to be retained.

[0188] Next, taking the example of predicting the intention level of a user using a ride QR code through an intention level prediction model after an electronic device triggers a geofence, the pop-up card strategy of the electronic device will be illustrated through the following several examples.

[0189] The intention level prediction model includes a cold start state and a hot start state. The cold start state can refer to the state where the intention level prediction model is not in effect, and the hot start state can refer to the state where the intention level prediction model is in effect. For example, if the sample data of the user's rides is small and not enough to train the intention level prediction model for X1 rounds, the value of X1 can be set according to actual training requirements, and this application embodiment does not limit this. In this case, the intention level prediction model is in an ungenerated / ineffective state and cannot be used to predict the intention level of the user using the ride QR code. If the sample data of the user's rides is sufficient to train the intention level prediction model for X1 rounds or more than X1 rounds, in this case, the intention level prediction model is in an effective state and can be used to predict the intention level of the user using the ride QR code.

[0190] The stations can also be divided into cold start stations and hot start stations. A cold start station can refer to a station where the user's riding record is less than X2 times, and a hot start station can refer to a station where the user's riding record is greater than or equal to X2 times. The value of X2 can be set according to actual needs, and the embodiments of the present application do not limit this. For example, the value of X2 can be set to 2.

[0191] Example 1, in the case where the intent level prediction model is in a cold start state, the electronic device can perform card popping based on the default card popping strategy.

[0192] For example, for users who rarely use the ride QR code to take the subway, or for users who use an electronic device that has just been purchased not long ago, since the sample data of the user's rides collected by the electronic device is small and an available intent level prediction model cannot be trained, in such a case, the electronic device can perform card popping based on the default card popping strategy.

[0193] For example, in the case where the intent level prediction model is in a cold start state, when the electronic device triggers the geofence of subway station A1, the electronic device can perform card popping based on the default card popping strategy.

[0194] In some embodiments, since the intent level of the user using the ride QR code cannot be determined when the intent level prediction model is in a cold start state, in order to reduce the interference to the user caused by card popping, the default card popping strategy can be set to a card popping strategy with less interference to the user. For example, the default card popping strategy is a tentative card popping. As Figure 5a or Figure 5b shown, after the electronic device triggers the geofence, it can perform card popping in the form of a nearby service card 11 on the negative first screen to prompt that there is a subway station nearby and to ask the user whether they need to use the ride QR code. After the electronic device triggers the geofence, the electronic device can also perform card popping in the form of a nearby service card on the desktop to prompt that there is a subway station nearby.

[0195] In some embodiments, it can also be set that when a preset precondition is met and the electronic device triggers the geofence, card popping is performed in the form of a nearby service card 11 on the negative first screen. For example, the preset precondition can be that the user has opened the ride code interface, or the user has used the ride code to scan the code to take the train.

[0196] In some embodiments, Figure 5a or Figure 5b the nearby service card 11 shown may also include a feedback control, and the user can enter by clicking the feedback control (such as Figure 5a or Figure 5b the "No, click to give feedback" control shown) to enter Figure 5cThe feedback window shown is used for recommending feedback on nearby services, enabling the electronic device to adjust the display content of the nearby service card 11 according to the user's feedback.

[0197] For example, after the user selects "not taking the subway" in the feedback window and clicks the "Stop Recommending" control, if the electronic device is in the cold start state of the intent level prediction model and the geofence of the subway station is triggered, the "Ride Code" will not be displayed in the nearby service card 11. If the electronic device detects that the user has used the ride code to take the subway, the "Ride Code" can be redisplayed in the nearby service card 11 when the intent level prediction model is in the cold start state and the geofence of the subway station is triggered.

[0198] For example, after the user clicks the "Not Needed for Now" control in the feedback window, the card will not be popped up within the second preset time when the geofence of the subway station is triggered. The second preset time can be set according to actual needs. For example, the second preset time is half an hour, one hour, etc.

[0199] For example, after the user clicks the "Take the Subway Using NFC / Physical Transit Card" control in the feedback window, the card will not be popped up. After that, if the electronic device detects that the user has used the ride code to take the subway or the user's permanent residence has changed, the "Ride Code" can be redisplayed in the nearby service card 11.

[0200] In some embodiments, the nearby service card 11 may at least include the "Ride Code" icon, and the user can click the "Ride Code" icon in the card to enter Figure 5d the "Ride Code" display interface shown to scan the code for taking the subway. In other embodiments, the nearby service card 11 may also include function service icons such as "Real-time Bus" and "Shared Bicycle".

[0201] Example 2, when the intent level prediction model is in the hot start state and the triggered geofence site is a cold start site, the intent level of the user using the ride QR code recognized by the intent level prediction model is generally between 1 and 3 levels.

[0202] For example, the number of sample data of the user's subway rides collected by the electronic device is sufficient to train the intent level prediction model. However, due to the irregularity of the user's boarding stations, some stations with historical ride records belong to cold start sites. In the case of triggering the geofences of these cold start sites, the intent level of the user using the ride QR code recognized by the intent level prediction model is generally between 1 and 3 levels. Or when the user arrives near a strange station and the geofence of the strange station is triggered, the intent level of the user using the ride QR code recognized by the intent level prediction model is generally between 1 and 3 levels.

[0203] The pop-up card strategy for intention level 1 can generally be set to not pop up a card, indicating that the user currently has no intention of using the ride QR code to swipe for a ride. The pop-up card strategies for intention levels 2 to 3 are generally exploratory pop-up cards. For example, the "Ride Code" icon can be displayed on the negative first screen, or in the APP suggestion area on the desktop, or in the YOYO suggestion area on the desktop to prompt that there is a subway station nearby and to ask the user if they need to use the ride QR code.

[0204] In some embodiments, for the pop-up card strategy with intention levels 2 to 3, the reason for the pop-up card can also be displayed near the "Ride Code" icon to reduce the user's aversion to the pop-up card. For example, the reason for the pop-up card can be "It is found that you are near XX Subway Station".

[0205] In some embodiments, intention level 2 and intention level 3 can be set to have the same pop-up card strategy or different pop-up card strategies, and the embodiments of the present application do not limit this. Generally speaking, as the intention level increases, the dominance degree of the corresponding pop-up card strategy is greater. A greater dominance degree can mean that the area of the popped-up card is larger, or the card is displayed in other ways that are more easily noticed by the user.

[0206] For example, the user is near Subway Station A2, and Subway Station A2 is a cold start station. When the intention level prediction model is in a hot start state, the electronic device triggers the geographical fence of Subway Station A2. The electronic device can determine the intention level of the user using the ride QR code based on the intention level prediction model. If it is determined based on the intention level prediction model that the user's current intention level of using the ride QR code is level 3, the electronic device can perform a pop-up card using the pop-up card strategy corresponding to intention level 3.

[0207] Suppose the pop-up card strategy corresponding to intention level 3 is to display the "Ride Code" icon on the negative first screen and in the APP suggestion area on the desktop. That is, after the electronic device triggers the geographical fence of Subway Station A2, it can display the "Ride Code" icon on the negative first screen and in the APP suggestion area on the desktop.

[0208] As Figure 5e shown, it schematically shows the "Ride Code" icon 122 being displayed in the APP suggestion area 12 on the desktop of the electronic device.

[0209] Example 3, when the intention level prediction model is in a hot start state and the site triggering the geographical fence is a hot start site, the intention level of the user using the ride QR code recognized by the intention level prediction model is generally between 4 and 10 levels.

[0210] For the pop-up card strategies with intention levels from 4 to 10, they are generally pop-up card strategies based on user convenience. If it is determined that the intention level of the user using the ride QR code is between 4 and 10, the pop-up card strategies corresponding to each intention level may include multiple pop-up card methods. The multiple pop-up card methods may include: displaying the "Ride Code" icon on the negative first screen, displaying the "Ride Code" icon in the APP suggestion area on the desktop, displaying the "Ride Code" icon in the YOYO display area on the desktop, displaying the "Ride Code" information / icon in the buried hole area at the top of the screen of the notch screen (for example, the intelligent capsule display solution of Honor Company) (the user can click on the intelligent capsule to display the "Ride Code" information and open the ride QR code interface), opening a floating interface (floating window / floating ball) that displays the "Ride Code" icon, displaying the "Ride Code" information / icon in the lock screen notification bar (the user can click on the "Ride Code" information / icon displayed in the lock screen notification bar to open the ride QR code interface), etc. Since the content displayed in the top area of the notch screen may not change with the change of the content displayed on the main interface, the interface displayed in the buried hole area at the top of the notch screen can also be called a global interface, and this top area of the screen can also be called an area with global function display.

[0211] For the pop-up card strategies with intention levels from 4 to 10, generally speaking, as the intention level increases, the dominance of the corresponding pop-up card strategy becomes greater. For example, as the intention level increases, the more card pop-up methods it contains, and / or the larger the area of the popped-up card (for example, small area - small card display, large area - large card display), and / or the display method of the card changes from fixed-position display (display on the negative first screen, in the APP suggestion area on the desktop, or in the YOYO display area on the desktop) to global display (intelligent capsule display, floating window / floating ball display, notification bar display).

[0212] For example, the pop-up card strategy corresponding to the intention level 8 is to display the "Ride Code" icon on the negative first screen and in the YOYO suggestion area on the desktop, and in the case of the electronic device being locked, display the "Ride Code" information / icon in the lock screen notification bar. The pop-up card strategy corresponding to the intention level 9 is to display the "Ride Code" icon on the negative first screen and in the YOYO suggestion area on the desktop, open a floating window that displays the "Ride Code" icon, and in the case of the electronic device being locked, display the "Ride Code" information / icon in the lock screen notification bar.

[0213] Suppose the user is near Subway Station A3, which is a hot start station. When the intent level prediction model is in the hot start state, the electronic device triggers the geofence of Subway Station A3. The electronic device can determine the intent level of the user's use of the ride QR code based on the intent level prediction model. If it is determined based on the intent level prediction model that the intent level of the user's current use of the ride QR code is level 8, the electronic device can use the pop-up card strategy corresponding to intent level 8 for pop-up card, that is, display the "Ride Code" icon in the YOYO suggestion area on the negative first screen and the desktop, and when the electronic device is locked, display the "Ride Code" information / icon in the lock screen notification bar. If it is determined based on the intent level prediction model that the intent level of the user's current use of the ride QR code is level 9, the electronic device can use the pop-up card strategy corresponding to intent level 9 for pop-up card, that is, display the "Ride Code" icon in the YOYO suggestion area on the negative first screen and the desktop, open the floating window displaying the "Ride Code" icon, and when the electronic device is locked, display the "Ride Code" information / icon in the lock screen notification bar.

[0214] As Figure 5f shown, it shows the display of the "Ride Code" icon 131 in the YOYO suggestion area 13 on the desktop of the electronic device. As Figure 5g shown, it shows the opening of the floating window 132 displaying the "Ride Code" icon on the electronic device.

[0215] For example, it can be defined that Figure 5a , 5e , as shown in 5f and 5g, the intent levels corresponding to the pop-up card methods are from low to high, Figure 5a the intent level corresponding to the pop-up card method shown is the lowest, Figure 5g the intent level corresponding to the pop-up card method shown is the highest, Figure 5f the intent level corresponding to the pop-up card method shown is less than Figure 5g the intent level corresponding to the pop-up card method shown, Figure 5e the intent level corresponding to the pop-up card method shown is less than Figure 5f the intent level corresponding to the pop-up card method shown.

[0216] The following uses the following several examples to illustrate the pop-up card strategy for exceptional situations. The pop-up card strategy for each exceptional situation can be preset.

[0217] Example 4. When the intention level prediction model is in the hot start state, and the site where the geofence is triggered is a regularly unboarded station and does not belong to a special site, the pop-up card strategy for this site can be identified as Exception Case 1 by the intention level prediction model. For example, the intention level prediction model outputs the identification information of Exception Case 1. Here, the regularly unboarded station may refer to a situation where there are n records of triggering the geofence of this site, but the user has never swiped the code to take the subway at this site. n is a positive integer, and its value can be set according to time requirements. This application embodiment does not limit this, for example, n can be set to 10.

[0218] In some embodiments, the pop-up card strategy corresponding to Exception Case 1 can be not to pop up the card. For example, when the user is near Subway Station A4, Subway Station A4 is a regularly unboarded station for the user and does not belong to a special site, and when the intention level prediction model is in the hot start state, the electronic device triggers the geofence of Subway Station A2. The electronic device can determine that the pop-up card strategy of Subway Station A4 belongs to Exception Case 1 based on the intention level prediction model, and the electronic device does not pop up the ride QR code.

[0219] Example 5. When the intention level prediction model is in the hot start state, and the site where the geofence is triggered is a regularly unboarded station and belongs to a special site, the pop-up card strategy for this site can be identified as Exception Case 2 by the intention level prediction model. For example, the intention level prediction model outputs the identification information of Exception Case 2.

[0220] The pop-up card strategy corresponding to Exception Case 2 can be to display the "Ride QR Code" icon in the negative one-screen or the APP suggestion area on the desktop to prompt that there is a subway station nearby and to ask the user whether they need to use the ride QR code.

[0221] For example, when the user is near Subway Station A5, Subway Station A5 is a regularly unboarded station for the user and is a transportation hub site. When the intention level prediction model is in the hot start state, the electronic device triggers the geofence of Subway Station A5. The electronic device can determine that the pop-up card strategy of Subway Station A5 belongs to Exception Case 2 based on the intention level prediction model, and the electronic device displays the "Ride QR Code" icon in the negative one-screen or the APP suggestion area on the desktop.

[0222] In some embodiments, in order to reduce the user's aversion to pop-up cards, for the pop-up card strategy of Exception Case 2, the reason for the pop-up card can also be displayed near the popped-up "Ride QR Code" icon, for example, "It is found that you are near XX Subway Station" is displayed.

[0223] Example 6. When the intent level prediction model is in the hot start state, the site where the geofence is triggered is a regular non-boarding station, and this site belongs to a special site, and the current day belongs to a special semantic day, the pop-up card strategy for this site can be identified as Exception Case 3 by the intent level prediction model. For example, the intent level prediction model outputs the identification information of Exception Case 3.

[0224] The pop-up card strategy corresponding to Exception Case 3 can be to display the "Ride Code" icon in the negative first screen and / or the APP recommendation area on the desktop to prompt that there is a subway station nearby and to ask the user whether they need to use the ride QR code.

[0225] In some embodiments, in order to reduce the user's aversion to pop-up cards, for the pop-up card strategy of Exception Case 3, the reason for the pop-up card can also be displayed near the "Ride Code" icon. For example, it is displayed as "It is found that you are near XX Subway Station and today is YY Day".

[0226] In some embodiments, the special semantic day can refer to a date when it is not regular to take a ride on weekdays, but there is a greater possibility of taking a ride on the special semantic day. The special semantic day can be set according to actual needs, and the embodiments of the present application do not limit this. For example, the special semantic day can include the restricted driving day of the user's vehicle, the day when the weather is too bad to drive, etc.

[0227] After the electronic device triggers the geofence of the subway station, although it can predict the intent level of the user using the ride QR code through the intent level prediction model, and can perform pop-up card using the corresponding pop-up card strategy according to the intent level output by the intent level prediction model, so as to facilitate the user to use the ride QR code to swipe the card for riding and reduce the accidental disturbance of the device's pop-up card to the user. However, due to different device users having different device usage habits, when performing pop-up card based on the intent level output by the intent level prediction model, there is a situation of unifying the usage habits and ride intentions of all device users, and there may still be a relatively high possibility of accidental disturbance pop-up cards.

[0228] To solve this problem, the embodiments of the present application also provide a card display solution, which predicts the intent level of the user using the ride QR code through the intent level prediction model, and makes a comprehensive decision on whether to perform a pop-up card or not based on the pop-up card decision model fed back by the user, so as to perform pop-up card following the user's usage habits and further reduce the accidental disturbance of the device's pop-up card to the user.

[0229] In some embodiments, any possible algorithm such as a supervised learning algorithm or a reinforcement learning algorithm can be used to train and obtain the pop-up card decision model. The algorithm can be determined according to actual usage needs, and the embodiments of the present application do not limit this. The following takes the pop-up card decision model trained by the reinforcement learning algorithm as an example for illustration.

[0230] Due to the limited software and hardware resources of the electronic device, and in order to minimize the impact of training and deploying the card popping decision model on the performance of the electronic device, the Q-Learning algorithm that occupies less device resources can be selected for reinforcement learning to obtain the card popping decision model. Moreover, since the environmental states and actions involved in the ride QR code scenario are relatively few, using the Q-Learning algorithm is sufficient to obtain a good card popping decision effect.

[0231] The following combines Figure 6 to illustrate the process of training the card popping decision model for the electronic device by way of example.

[0232] (1) Obtain historical intent trigger association information. The historical intent trigger association information may include information associated with the user's use of the ride QR code when a historical ride intent trigger event occurs.

[0233] For example, the historical intent trigger association information may include the intent trigger time, the intent end time, the intent level, the actual card popping strategy, and the detected usage feedback information. The intent trigger time may be the time when the geofence is triggered or the time when the intent level is generated. The intent end time may be the time when the card disappears, or for the case of no card popping, the intent end time may be the time after a preset duration from the intent trigger time. The preset duration can be set according to actual needs, and this application embodiment does not limit it. For example, the preset duration is 10 minutes. The actual card popping strategy may be the card popping behavior based on the intent level output by the intent level prediction model by the card display framework before the card popping decision model becomes effective, or the card popping behavior based on the decision results of the intent level prediction model and the card popping decision model by the card display framework after the card popping decision model becomes effective.

[0234] The usage feedback information may include the detected card operation information and ride behavior information after the card display framework pops a card, or the detected ride behavior information in the case where the card display framework does not pop a card. For example, the card operation information may include clicking on the card, removing the card, not clicking, etc., and the ride behavior information may include not taking a ride, swiping the ride QR code to take a ride, taking a ride without using the ride QR code, etc.

[0235] (2) Process the historical intent trigger association information to generate training samples.

[0236] In some embodiments, the processing operation on the historical intent trigger association information may be: deleting duplicate information in the historical intent trigger association information. For example, after a certain card popping, the user may perform repeated actions, such as clicking on the card multiple times. The historical data corresponding to these repeated actions may result in a large number of repeated or similar training samples. By deleting the duplicate information, the data processing volume for sample learning can be reduced, and the efficiency of sample learning can be improved.

[0237] In some embodiments, the processing operation on the historical intent trigger association information may also be: constructing the reward for each training sample. For example, each training sample may correspond to a complete intent trigger process, and a complete intent trigger process includes from intent trigger to intent end, as well as the usage feedback information detected during this period. The construction method of the reward for the training sample may include: initializing the reward for the training sample (that is, the training sample has an initial reward), and adjusting the initial reward based on the usage feedback information of the training sample and the preset reward adjustment rule to obtain the true reward of the training sample.

[0238] For example, as shown in Table 3 below, some of the reward adjustment rules in the preset reward adjustment rule are illustrated.

[0239] Table 3

[0240]

[0241] In some embodiments, each training sample may include: intent trigger time, intent end time, intent level, true card popping strategy, usage feedback information, and true reward.

[0242] After processing the historical behavior information, the electronic device may also convert the samples into a unified format, and then perform processing such as training, validation, and test set splitting, so as to generate training samples.

[0243] (3) Train the card popping decision model according to the training samples.

[0244] After generating the training samples, the card popping decision model may be trained based on the training samples to update the Q table of the card popping decision model. The state recorded in the Q table is the intent level, and the actions recorded in the Q table are card popping or not card popping. Assume that card popping corresponds to action a1 and not card popping corresponds to action a2. The Q table of the card popping decision model may be as shown in Table 4 below, and Q(s,a) represents the Q function value of action a in state s.

[0245] Table 4

[0246]

[0247] As Figure 7a shown, in the training stage of the card popping decision model, for each training sample, the intent level (state sj), true card popping strategy (action ai), and usage feedback information (determining the reward based on the usage feedback information) of the training sample can be obtained. i is equal to 1 or 2, and j is a positive integer. Training the card popping decision model according to one training sample can be equivalent to: calculating the Q function value Q(sj,ai) of action ai in state sj and updating it to the Q table. The update of Q(sj,ai) can be characterized by the following formula:

[0248] Q(sj, ai) ← Q’(sj, ai) + α[R + γ max ai ’Q(sj’, ai’) - Q’(sj, ai)];

[0249] Where Q(sj, ai) is the updated Q value of action ai in state sj (the value updated to the Q-table), Q’(sj, ai) is the value recorded in the Q-table for Q(sj, ai) before the update, R is the actual reward for executing action ai, γ is the learning parameter, α is the learning efficiency, and the values of γ and α can be preset, with 0 ≤ α ≤ 1 and 0 ≤ γ ≤ 1, and max ai ’Q(sj’, ai’) is the maximum Q value among all actions ai’ in the next state sj’ of state sj.

[0250] During the training process of the pop-up card decision model, if the read Q-table is empty, the Q-table can be initialized first to generate an initial Q-table, and then the initial Q-table can be updated based on the Q function values calculated for each training sample in the current training stage. For example, all Q(s, a) in the initial Q-table are set to 0. If the Q-table is not empty (i.e., the pop-up card decision model has been trained with training samples), the read Q-table is updated based on the Q function values calculated for each training sample in the current training stage.

[0251] In the embodiments of the present application, the electronic device can train the pop-up card decision model in dimensions such as daily, weekly, and monthly. For example, the electronic device can schedule the historical intent trigger association information of the previous day every day, generate training samples based on the historical intent trigger association information of the previous day, and then train the pop-up card decision model based on the training samples, that is, update the Q-table. For example, the electronic device can schedule the historical intent trigger association information of the previous week every Monday, generate training samples based on the historical intent trigger association information of the previous week, and then train the pop-up card decision model with the training samples of the previous week, that is, update the Q-table.

[0252] After obtaining the effective pop-up card decision model, it is possible to determine whether to perform a pop-up card based on the intent level input by the intent level prediction model. For example, in the case where the pop-up card decision model determines that a pop-up card is required, it can output pop-up card identification information to the card display framework, and the card display framework can perform a pop-up card using the pop-up card strategy corresponding to the intent level based on the pop-up card identification information; in the case where the pop-up card decision model determines that a pop-up card is not required, it can output non-pop-up card identification information to the card display framework, or not output identification information to the card display framework, so that the card display framework does not perform a pop-up card.

[0253] For example, it can be set that after the X3 - round iterative training of the pop - up card decision model or after the training with X4 sample data, the pop - up card decision model becomes effective; otherwise, the pop - up card decision model is not effective. The values of X3 and X4 can be set according to actual requirements, and the embodiments of this application do not limit this.

[0254] In some embodiments, in the case where the pop - up card decision model is not effective, the card display framework can directly adopt the pop - up card strategy corresponding to the intention level based on the intention level output by the intention level prediction model for pop - up card.

[0255] For example, the user is near subway station A6, and subway station A6 is a hot - start site. When the intention level prediction model is in the hot - start state, the electronic device triggers the geofence of subway station A6. Suppose the electronic device determines that the intention level of the user's current use of the ride - sharing QR code is level 5 based on the intention level prediction model. If the decision result after passing through the pop - up card decision model is that no pop - up card is needed, then the card display framework will not perform a pop - up card. If the decision result after passing through the pop - up card decision model is that a pop - up card is needed, the card display framework adopts the pop - up card strategy corresponding to intention level 5 for pop - up card.

[0256] In some embodiments, for the exceptional cases output by the intention level prediction model, the judgment of whether to perform a pop - up card or not does not need to pass through the pop - up card decision model. The card display framework can directly adopt the corresponding pop - up card strategy based on the label of the exceptional case for pop - up card.

[0257] In some embodiments, for the exceptional cases output by the intention level prediction model, training samples can also be constructed to train the pop - up card decision model, so that the pop - up card decision model can make decisions on whether to perform a pop - up card or not based on the exceptional cases output by the intention level prediction model.

[0258] In the case where the pop - up card decision model is effective, the pop - up card decision model can obtain the optimal decision based on the Q - function values recorded in the Q - table. For example, the optimal decision is the action with the largest Q - function value. As Figure 7b shown, in the inference stage of the pop - up card decision model, the pop - up card decision model can select an action (pop - up card or not) based on the intention level output by the intention level prediction model and the Q - table.

[0259] For example, in the inference stage, if the Q - table read by the pop - up card decision model is not empty, the pop - up card decision model can select an action (pop - up card or not) at this intention level (state) based on the read Q - table. After the card display framework executes the action selected by the pop - up card decision model, it can record the usage feedback information to facilitate the construction of training samples.

[0260] In the inference stage, if the Q-table read by the card popping decision model is empty (for example, there is a storage anomaly in the Q-table), the card popping decision model does not make a decision and can only save the data input to the model. The card display framework can directly adopt the card popping strategy corresponding to the intention level based on the intention level predicted by the intention level prediction model for card popping.

[0261] In some embodiments, since the present solution relates to the subway riding scenario, for multiple inputs of the same intention level, the card popping decision model may make variable action selections within a day, which will reduce the user experience. To ensure the stability of the subway riding card popping service, within a day, the card popping decision model can perform an inference (action selection) based on each piece of input data (intention level), but the card display framework can use the first inference result received on the same day as the shared inference result for the same day, that is, for multiple inputs of the same intention level, it is considered that the actions selected within a day are the same, so that the card display framework keeps the card popping method for the same intention level consistent within a day.

[0262] Please refer to Figure 8 , which is the architecture diagram of the card popping decision system provided by the embodiments of the present application.

[0263] The card popping decision system includes an intention understanding module 101, a card popping decision module 102, and a service operation and maintenance module 103. The intention understanding module 101 may include an intention level prediction model or an intention recognition rule set (constructed based on dimensions such as user portrait dimension, perception dimension, and decision dimension). Figure 8 Taking the case where the intention understanding module 101 includes an intention level prediction model as an example for illustration. The card popping decision module 102 may include a card popping decision model, and the service operation and maintenance module 103 may include a card display framework. The card display framework may define multiple card popping strategies, and each card popping strategy can be associated with an intention level. The modules referred to in the embodiments of the present application may refer to a series of computer program instruction segments capable of completing specific functions, or may be functional modules formed by the cooperation of computer program instruction segments and hardware. The division of the modules is a logical function division, and there may be other division methods in actual implementation. The present application does not make any limitations in this regard.

[0264] For example, after an electronic device triggers the geofence of a certain subway station, the intent understanding module 101 can determine the intent level corresponding to the user's current behavior information (current location information, current time information, application information running on the device, user's motion state, etc.) based on the intent level prediction model / intent recognition rule set. The intent level can be transmitted to the card popping decision module 102 for card popping decision-making. After receiving the intent level, the card popping decision module 102 can confirm whether the card popping decision model is effective. If the card popping decision model is not effective, the card popping decision module 102 can directly notify the default decision result to the service operation and maintenance module 103. For example, the default decision result is to pop a card, that is, the card display framework pops a card using the card popping strategy corresponding to this intent level.

[0265] If the card popping decision model is effective, the card popping decision model in the card popping decision module 102 can read the Q-table and select an action (pop a card or not pop a card) at this intent level (state) based on the Q-table, and notify the decision result to the service operation and maintenance module 103. For example, if the action selected at this intent level (state) based on the Q-table is not to pop a card, the card display framework does not pop a card; if the action selected at this intent level (state) based on the Q-table is to pop a card, the card display framework pops a card using the card popping strategy corresponding to this intent level.

[0266] In some embodiments, the card popping decision module 102 can also monitor the usage feedback information after selecting to pop a card or not pop a card, which is convenient for constructing training samples. The training samples can be stored in the local database of the terminal side (local to the electronic device). The constructed training samples can iteratively update the Q-table during the training phase. For example, the electronic device can iteratively update the Q-table based on the constructed training samples on a daily, weekly, monthly, etc. basis.

[0267] In some embodiments, the information input to the card popping decision module 102 can include the intent level and the station information. The station information can be used to represent whether the currently triggered geofence is the geofence of a subway station or the fence of other types of stations or regions. After receiving the intent level and the station information, the card popping decision module 102 can verify the station information and confirm whether the current intent level is the intent level for the user to take the subway using the ride code. For example, if the station information includes the subway station identifier, it indicates that the received intent level is the intent level for the user to take the subway using the ride code. The card popping decision module 102 then confirms whether the card popping decision model is effective. If it is confirmed that the current intent level is not the intent level for the user to take the subway using the ride code, the card popping decision for this intent level can be skipped without using the card popping decision model.

[0268] In some embodiments, when it is confirmed that the current intention level is not the intention level for the user to take the subway using the ride QR code, the pop-up card decision module 102 may also directly notify the default decision result (for example, the default decision result is to pop up a card) to the service operation and maintenance module 103. For example, if the intention understanding module 101 also supports intention recognition scenarios for other non-ride QR codes (such as when setting to show other non-ride QR codes when entering or leaving places such as communities, companies, schools, and commercial buildings), in the case where the pop-up card decision module 102 determines that the current intention level is not the intention level for the user to take the subway using the ride QR code, it may directly notify the default decision result to the service operation and maintenance module 103, so that the card display framework in the service operation and maintenance module 103 can pop up a card based on the pop-up card policy corresponding to this intention level.

[0269] In some embodiments, the pop-up card decision module 102 may also be omitted. The card display framework in the service operation and maintenance module 103 can directly pop up a card based on the intention level determined by the intention understanding module 101, using the pop-up card policy corresponding to this intention level.

[0270] Please refer to Figure 9 , which is a schematic diagram of the software framework for the electronic device provided in the embodiments of the present application to implement popping up a card in accordance with the user's usage habits. The software framework can be divided into three layers: the first layer is the service layer, the second layer is the decision layer, and the third layer is the data layer.

[0271] An application program associated with the ride-scanning service can run in the service layer. Taking the subway ride service as an example, in the service layer, subway ride intention subscription can be performed and usage feedback information can be recorded (such as clicking on the card, removing the card, swiping the ride QR code to take the subway, taking the subway without using the ride QR code, not taking the subway, etc.). By subscribing to the subway ride intention in the service layer, the decision layer can subsequently notify the intention level and the pop-up card decision result (pop up a card / do not pop up a card) to the service layer, and then the service layer can adopt the corresponding pop-up card policy to pop up a card.

[0272] The decision layer can identify the intention level and make a pop-up card decision. For example, after subscribing to the subway ride intention in the service layer, the decision layer can subscribe to the station geographical fence, so that subsequent to the electronic device triggering the geographical fence of a certain subway station, the intention level or exceptional situation can be identified. For example, the decision layer can determine the user's current intention level of using the ride QR code or determine what kind of exceptional situation it belongs to based on the intention level prediction model or the intention recognition rule set.

[0273] After the decision layer completes the identification of the intention level or exceptional situation, it can make a pop-up card decision based on the pop-up card decision model and notify the intention level and the pop-up card decision result (pop up a card / do not pop up a card) to the service layer.

[0274] The decision-making layer can also iteratively train the pop-up card decision-making model based on the training samples constructed using the usage feedback information to update the Q-table of the pop-up card decision-making model.

[0275] The data layer may include a perception middle platform, a learning middle platform, and a data middle platform. The perception middle platform may store the subway station geographic fence information and may determine whether the electronic device triggers the geographic fence of the subway station according to the obtained location information of the electronic device. The learning middle platform can perform learning on the user's QR code usage habits for taking the subway, user portraits, station portraits, etc. The data middle platform can be used to store the usage feedback information recorded by the service layer and the data used for training the models (intention level prediction model, pop-up card decision-making model).

[0276] After the electronic device triggers the geographic fence of the subway station, although it can pop up cards in accordance with the user's usage habits through the intention level prediction model and the pop-up card decision-making model, since the pop-up card strategy corresponding to each intention level is preset, different users have different device usage habits and preferences, and their acceptance levels of the pop-up card method and the card entry are different. For example, some users are more inclusive of a certain pop-up card method, while some users are more sensitive to a certain pop-up card method. The same user may also have variable card usage preferences.

[0277] To solve this problem, the embodiment of the present application also provides a card display solution, which can perform personalized pop-up cards in accordance with the user's card usage preferences, not only enabling the user to conveniently and quickly use the card, but also making the pop-up card method match the user's usage habits, and further reducing the accidental disturbance of the device's pop-up card to the user.

[0278] In some embodiments, for the pop-up card strategy corresponding to each intention level, the electronic device can adjust the pop-up card strategy based on the user's card operation information for the quick entry. For example, if a certain intention level corresponds to multiple quick entries, and after the first preset number of pop-up card times, it is detected that a certain quick entry among the multiple quick entries has not been used by the user, when the electronic device performs a pop-up card based on the pop-up card strategy corresponding to this intention level next time, this quick entry can be removed, that is, the pop-up card strategy corresponding to this intention level is modified to not include this quick entry. The first preset number of times can be set according to actual needs, and the embodiment of the present application does not limit this.

[0279] For example, the pop-up card strategy corresponding to intention level 9 includes: displaying the "Ride Code" icon in the negative first screen and the YOYO suggestion area on the desktop, and enabling the floating window for displaying the "Ride Code" icon. In addition, when the electronic device is locked, the "Ride Code" information / icon can be displayed in the lock screen notification bar. If, after a period of time (which can be set according to actual needs, for example, half a month) when the electronic device executes the pop-up card strategy corresponding to intention level 9, it is detected that the user has not used the quick access in the negative first screen (the "Ride Code" icon is displayed in the YOYO suggestion area on the negative first screen), while there are usage records for other quick accesses, the electronic device can remove the quick access in the negative first screen. That is, when the electronic device subsequently determines that the user's intention level for using the ride QR code is intention level 9, the pop-up card strategy corresponding to intention level 9 that it executes includes: displaying the "Ride Code" icon in the YOYO suggestion area on the desktop, and enabling the floating window for displaying the "Ride Code" icon. In addition, when the electronic device is locked, the "Ride Code" information / icon can be displayed in the lock screen notification bar.

[0280] In some embodiments, for the pop-up card strategy corresponding to each intention level, the electronic device can also adjust the display size of the card based on the user's card operation information for the quick access.

[0281] For example, the pop-up card strategy corresponding to intention level 5 includes: displaying the "Ride Code" icon in the negative first screen and the YOYO suggestion area on the desktop. If, after the electronic device executes the pop-up card strategy corresponding to intention level 5 for a second preset number of times, it is detected that the number of times the user opens the ride code interface from the quick access in the YOYO suggestion area is basically equal to the second preset number of times (for example, basically equal can mean that the difference is less than a preset difference), the electronic device can increase the display size of the "Ride Code" icon displayed in the YOYO suggestion area. For example, increasing the display size of the "Ride Code" icon displayed in the YOYO suggestion area can be to adjust the "Ride Code" icon 122 displayed in the YOYO suggestion area shown in (a) of Figure 10 to the "Ride Code" icon 131 displayed in the YOYO suggestion area shown in (b) of Figure 10 . The second preset number of times can be set according to actual needs, and the embodiments of the present application do not limit this.

[0282] In some embodiments, the electronic device may also perform a pop-up of the ride code service based on the user's reservation / rescheduling event, or simultaneously perform a pop-up of the ride code service and the taxi-hailing service. The reservation / rescheduling event may be a reservation / rescheduling event based on the APP installed on the electronic device. For example, the electronic device may perform an initial pop-up of the ride code service based on the user's reservation / rescheduling event, and subsequently the electronic device may adjust the pop-up strategy according to the user's usage behavior, so that the next trip with the same reservation / rescheduling event can be popped up based on the updated pop-up strategy. Since the user's travel choices are difficult to predict and changeable, the geofence associated with the user's travel plan is generally a geofence that is not frequently entered. Performing an initial pop-up of the ride code service based on the user's reservation / rescheduling event can adopt a tentative pop-up strategy to reduce the accidental interruption to the user. For example, the tentative pop-up strategy may be to pop up on the negative first screen, or in the APP suggestion area on the desktop, or in the YOYO suggestion area on the desktop, or pop up on the negative first screen and the APP suggestion area on the desktop, or pop up on the negative first screen and the YOYO suggestion area on the desktop.

[0283] For example, in the case where the geofence entered by the electronic device is a geofence associated with the user's travel plan, a tentative pop-up strategy is adopted for popping up to reduce the accidental interruption to the user.

[0284] For example, the electronic device can obtain the starting point and destination of the user's travel from the user's reservation / rescheduling event. If there is a subway station near the starting point and / or destination (for example, within a range of 1 kilometer), the electronic device can perform a pop-up of the ride code service based on the time of the user's reservation / rescheduling event. For example, if the reservation event is a train ticket order, the departure station of the train ticket order can be defined as the destination of a section of the journey, and the arrival station of the train ticket order can be defined as the starting point of another section of the journey. If there is a subway station near the departure station, a pop-up of the ride code service can be performed based on the departure time of the train ticket order to remind the user whether they need to take the subway to the train station. For example, in the case where the time is 2 hours before the departure time of the train ticket order, a pop-up of the ride code service is performed. If there is a subway station near the arrival station, the electronic device can also perform a pop-up of the ride code service based on the arrival time of the train ticket order to remind the user whether they need to take the subway to leave the train station.

[0285] For example, if the reservation event is a movie ticket order, the cinema corresponding to the movie ticket order is the destination for going to watch the movie and the starting point for ending the movie watching. If there is a subway station near the cinema, a pop-up of the ride code service can be performed based on the start time and end time of the movie ticket order to remind the user whether they need to take the subway to the cinema, or whether they need to take the subway to leave the cinema after the movie watching.

[0286] In some implementations, if there is a subway station near the destination, for the pop-up card for going to the destination, the electronic device can also make a decision on whether to pop up the card in combination with the user's current location. For example, when the electronic device makes a decision on popping up the card for the ride code service, it obtains the user's current location. If there is no subway station near the user's current location, indicating that it is inconvenient for the user to take the subway to the destination, the electronic device may not pop up the card for the ride code service.

[0287] In some embodiments, if there is a subway station near the starting point / destination, the electronic device can also determine whether to pop up the card for the ride code service based on the travel portrait of the starting point / destination. For example, if there is a subway station near the starting point, and the travel portrait of the starting point indicates that a relatively large number of users (e.g., more than 50% of the users) choose to take the subway to leave the starting point after arriving at the starting point, the electronic device can pop up the card for the ride code service. If there is a subway station near the starting point, and the travel portrait of the starting point indicates that a relatively small number of users (e.g., less than 20% of the users) choose to take the subway to leave the starting point after arriving at the starting point, the electronic device may not pop up the card for the ride code service.

[0288] In some embodiments, after the electronic device makes a decision on popping up the card for the ride code service based on the user's reservation / appointment event, it can also adjust the card popping strategy according to the user's usage behavior, so that the next trip with the same starting point or destination can pop up the card based on the updated card popping strategy.

[0289] For example, if the electronic device decides not to pop up the card for the ride code service based on a certain reservation event of the user, but subsequently detects that the user has a record of swiping the ride QR code to take the train, the electronic device can modify the card popping strategy corresponding to the reservation event from not popping up the card to popping up the card, so that the next time the user is detected to have the same reservation event, the card can be popped up based on the reservation event.

[0290] For example, a certain reservation event of the user occurs multiple times. The electronic device decides to pop up the card for the ride code service based on the reservation event, but subsequently does not detect that the user has a record of swiping the ride QR code to take the train. The electronic device can reduce the number of quick access entries included in the card popping strategy until it does not pop up the card. Suppose the card popping strategy corresponding to the reservation event includes two quick access entries. If it is detected for the first time that the user does not have a record of swiping the ride QR code to take the train, the electronic device can modify the card popping strategy corresponding to the reservation event from two quick access entries to one quick access entry. If it is detected for the second time that the user still does not have a record of swiping the ride QR code to take the train, the electronic device can modify the card popping strategy corresponding to the reservation event from popping up the card to not popping up the card.

[0291] For example, if a certain reservation event of a user occurs multiple times, based on this reservation event, the electronic device decides to pop up a card for the ride code service. Subsequently, if it is detected that the user has multiple records of swiping the ride QR code to take the bus, the electronic device can increase the quick access entry for the card popping strategy corresponding to this reservation event, so that the next time the same reservation event of the user is detected, the card can be popped up based on the modified card popping strategy, enabling the user to quickly open the ride code and making it more and more convenient to use.

[0292] As shown in Table 5 below, it illustrates the possible reservation / rescheduling events of the user.

[0293] Table 5

[0294] Reservation Event Location Associated with the Event Appointment Event Location Associated with the Event Air Ticket Reservation Airport Visiting Appointment Office Building / Industrial Park Train Ticket Reservation Train Station Food Appointment Restaurant Movie Ticket Reservation Movie Theater Exhibition Appointment Exhibition Hall … … Scenic Spot Appointment Scenic Spot / Scenic Area Vehicle Maintenance Appointment 4S Store Beauty and Maintenance Appointment Beauty Salon Registration Appointment Hospital Physical Examination Appointment Physical Examination Center Fitness Appointment Gym Government Affairs Handling Appointment Government Affairs Center … …

[0295] In some embodiments, for scenarios where the user's ride intention cannot be predicted or the ride code service is not recommended due to an anomaly, the electronic device can also support the user to actively ask the intelligent assistant (e.g., YOYO intelligent assistant) to provide the ride code service. For the case where the quick access entry is not the one preferred by the user, the electronic device can also support the user to actively ask the intelligent assistant to specify the desired quick access entry.

[0296] As Figure 11a shown, the user can actively wake up the YOYO intelligent assistant and send an instruction to the YOYO intelligent assistant to obtain the ride QR code service, enabling the YOYO intelligent assistant to open Figure 5c the "Ride Code" display interface as shown.

[0297] As Figure 11b shown, in the case where the user finds that the ride code service recommended by the electronic device is not the one preferred by the user, the user can wake up the YOYO intelligent assistant and specify the desired ride code service to the YOYO intelligent assistant. For example, specify the desired ride code service to be the ride code of.

[0298] In some embodiments, in the case where the user finds that the quick access entry for the ride code service recommended by the electronic device is not the one the user usually uses, the user can also wake up the YOYO intelligent assistant and specify the desired quick access entry to the YOYO intelligent assistant, or specify the desired quick access entry to the YOYO intelligent assistant and remove other quick access entries.

[0299] For example, send "The ride code card in the desktop YOYO suggestion area is what I usually use" to the YOYO intelligent assistant to specify that the desired quick access entry includes the ride code card in the desktop YOYO suggestion area. Subsequently, the electronic device can modify the card popping strategy corresponding to each intention level to include popping the card in the desktop YOYO suggestion area.

[0300] For example, send the following instruction to the YOYO intelligent assistant: "The QR code card for taking the bus that I usually use is the floating window one. Don't recommend any other ones in the future." This can achieve that the specified required quick access only includes the QR code card for taking the bus in the floating window, and other quick accesses are removed. Subsequently, when the electronic device determines that it needs to provide the QR code service for taking the bus, only the QR code card in the floating window is displayed. That is, the pop-up card strategy corresponding to different intention levels is the floating window pop-up card.

[0301] As Figure 11c shown, the YOYO intelligent assistant can also actively initiate an inquiry about adding a quick access to the QR code service for taking the bus. The user can set the quick access to the QR code service they need by interacting with the YOYO intelligent assistant.

[0302] In some embodiments, when the electronic device detects that the number of times the user uses the QR code to take the bus reaches the third preset number of times, it can actively initiate an inquiry about adding a quick access to the QR code service for taking the bus through the YOYO intelligent assistant. The third preset number of times can be set according to actual needs, and the embodiments of the present application do not limit this.

[0303] In some embodiments, the electronic device can also divide users into high-frequency bus-riding users, medium-frequency bus-riding users, and low-frequency bus-riding users according to the number of times the user uses the QR code to take the bus within a period of time. For each frequency of users, basic quick accesses can be correspondingly set, and then the quick accesses can be upgraded or additional quick accesses can be added based on the intention level, or it can be set that only for high-frequency bus-riding users and medium-frequency bus-riding users, the quick accesses can be upgraded or additional quick accesses can be added based on the intention level. Upgrading the quick access can refer to increasing the card size of the quick access.

[0304] For example, the basic quick access corresponding to low-frequency bus-riding users is the quick access on the negative first screen, the basic quick access corresponding to medium-frequency bus-riding users is the quick access in the desktop APP suggestion area, and the basic quick access corresponding to high-frequency bus-riding users is the quick access in the YOYO suggestion area on the desktop.

[0305] For example, for high-frequency bus-riding users, when it is determined that the intention level of the user using the bus QR code is greater than the first intention level, an additional quick access is added. For example, a quick access in the floating window is added. When it is determined that the intention level of the user using the bus QR code is greater than the second intention level, two additional quick accesses are added. For example, a quick access in the floating window and a quick access in the lock screen notification bar are added. The second intention level is greater than the first intention level, and the level values of the first intention level and the second intention level can be set according to actual needs, and the embodiments of the present application do not limit this.

[0306] In some embodiments, for the station where the user takes the first ride (for example, whether it is the station of the first ride can be determined based on the number of times the geofence of the station triggered by the electronic device), in order to reduce the false disturbance of the pop-up card to the user, the electronic device can adopt a tentative pop-up card strategy. As the number of times the user takes the ride at this station increases, for example, when the number of rides reaches a certain number, the electronic device can upgrade the corresponding quick entry for this station or add a quick entry for this station.

[0307] The following Figure 12 introduces the card display method provided by the embodiments of the present application. The execution subject of the card display method can be the above-mentioned electronic device, or a functional module and / or functional entity (such as a processor) in the electronic device that can implement the card display method, and the solution of the present application can be implemented in a hardware and / or software manner, and the present application does not make any limitation in this regard. The following takes the scenario of the user taking the subway as an example, and Figure 12 is used to exemplarily illustrate the card display method provided by the embodiments of the present application.

[0308] S121. Obtain the location information of the electronic device.

[0309] The electronic device can collect the location information of the electronic device based on a preset period. This location information can be used to indicate the geographical location where the electronic device is located or to determine the location of the electronic device.

[0310] In some embodiments, the location information of the electronic device may include the signal type and signal strength of the positioning signal.

[0311] For example, the signal type of the positioning signal may include one or more of the following: GPS signal, Bluetooth signal, Cell ID signal, Wi-Fi signal, NFC signal, and FM signal, etc. The positioning signals of different signal types correspond to different positioning accuracies. The electronic device can select one or more of these signals according to the actual situation of being on the ground or underground and whether there is a wireless access point (AP) installed in the area where it is located to determine the current location of the electronic device.

[0312] Taking the positioning signal as the GPS signal as an example. When the GPS function of the electronic device is turned on, the electronic device can update the coordinate information of the current location of the electronic device in real time according to the obtained GPS signal. Among them, the coordinate information may include longitude information and latitude information.

[0313] Take the positioning signal as the Cell ID signal as an example. As the geographical location of the electronic device changes, the base station connected to the electronic device may change. When the electronic device has enabled the function of the mobile communication module, the electronic device can receive the Cell ID of the current cell and the Cell IDs of neighboring cells, and monitor in real time whether the connected base station has changed through the Cell ID of the current cell and the Cell IDs of neighboring cells.

[0314] S122. According to the acquired location information, determine whether the electronic device enters a preset geographical fence.

[0315] Different application scenarios can correspond to different preset geographical fences. Take the scenario where the user takes the subway as an example. The preset geographical fence can refer to the geographical fence of the subway station.

[0316] When the electronic device does not enter the preset geographical fence, the electronic device can continue to acquire the location information of the electronic device and re-determine whether the electronic device enters the preset geographical fence.

[0317] In some embodiments, the fence information of the geographical fence may include one or more of a fence label, a fence type, and a fence range, etc. Among them, the fence label can be represented by characters such as numbers, letters, and symbols, and is used to uniquely characterize the geographical fence. The fence type corresponds to the signal type, such as any one type or any combination of types such as Wi-Fi type, Cell type, and GPS type. The fence range is used to characterize the location and size, etc. of the geographical area surrounded by the virtual fence.

[0318] It should be noted that the geographical fence can be of a single type, such as a single Wi-Fi type, a single Cell type, or a single GPS type. In some other embodiments, the geographical fence can also be a combined type of multiple single types. For example, a geographical fence of Wi-Fi type combined with Cell type, or a geographical fence of Cell type combined with GPS type, or a geographical fence of Wi-Fi type combined with Cell type and GPS type, etc. The embodiments of the present application do not make limitations.

[0319] Next, an exemplary description will be given with the geographical fence being a Cell fence.

[0320] The Cell fence is delimited according to the signal coverage range of the base station. The mapping relationship between the base station and the subway station can be pre-configured. Specifically, the mapping relationship between the base station and the subway station can be: a mapping relationship table between the Cell ID and the subway station name. In some embodiments, the mobile phone pre-stores the software development kit (SDK) of a third-party application. The third-party application can be used to query the mapping relationship table between the Cell ID and the subway station name to determine whether there is a subway station that matches the base station where the electronic device is currently located. When there is a subway station that matches the base station where the electronic device is currently located, it can be determined that the electronic device enters the geographical fence corresponding to the matching station.

[0321] Exemplarily, Table 6 is a mapping relationship table between the Cell ID and the subway station name provided by an embodiment of the present application. In Table 1, the signal of base station A covers cell Cell 1, and there is no subway station set in cell Cell 1. The signal of base station B covers cell Cell 2, and subway station x is set in cell Cell 2. The signal of base station C covers cell Cell 3, and subway station y is set in cell Cell 3.

[0322] Table 6

[0323] Cell ID Subway Station Name Cell 1 None Cell 2 Subway Station x Cell 3 Subway Station y

[0324] For example, when the base station currently connected to the mobile communication module of the electronic device is base station A, when the user carries the electronic device into the area range of subway station x, or when the user carries the electronic device passes through the area range of subway station x, the base station A connected to the mobile communication module of the electronic device switches to base station B. The electronic device obtains the cell identifier Cell 2 corresponding to base station B. The electronic device queries the mapping relationship table, such as Table 6 above, through the pre-stored third-party application. Since the cell identifier Cell 2 matches subway station x, the electronic device determines that the user has entered the geographical fence corresponding to subway station x.

[0325] S123. In the case of determining that the preset geographical fence is entered, obtain ride intention information.

[0326] The ride intention information can be used to indicate the intention level of the user to use the ride QR code within the preset geographical fence. The ride intention information can include the current time information, current location information, currently running application information, current user's motion state, etc. of the electronic device.

[0327] When the electronic device enters the geofence of a certain subway station, the user may or may not have the need to use the ride QR code to scan and board the train within the geofence. The electronic device can obtain the user's ride intention information to determine the intention level of the user to use the ride QR code based on the ride intention information.

[0328] In some embodiments, the current time information can have two meanings:

[0329] One meaning is that the current time information is used to indicate: the time when the electronic device enters the geofence. For example, when the electronic device collects the location information of the electronic device based on a preset period, a timestamp indicating the collection moment of the location information is marked for each location information. When the electronic device determines that the electronic device enters the geofence corresponding to the location information according to a certain location information, the electronic device can use the timestamp marked for the location information as the time when the user enters the geofence.

[0330] Another meaning is that the current time information is used to indicate: the time determined in real time by the electronic device based on a preset period after the electronic device enters the geofence. For example, assume that the preset periods for the electronic device to collect location information and time information are both 1 second. The electronic device can collect location information every 1 second. When the electronic device determines that the electronic device enters the geofence corresponding to the collected location information, the electronic device can obtain the system time from the clock application of the electronic device every 1 second and use the obtained system time as the current time.

[0331] In some embodiments, the current location information can be used to indicate the geographical location where the electronic device is located at the current time. Specifically, if the current time information is used to indicate the time when the electronic device enters the geofence, then the current location information is used to indicate the geographical location when the electronic device enters the geofence. Another possibility is that if the current time information is used to indicate the time determined in real time by the electronic device based on a preset period after the electronic device enters the geofence, then the current location information is used to indicate the location information re - collected by the electronic device according to the preset period after the electronic device enters the geofence. In this case, the electronic device can use the re - collected location information as the geographical location where it is located at the current time.

[0332] In some embodiments, the information of the currently running application can be used to indicate the information of the application running on the electronic device at the current time. For example, based on the information of the currently running application, it can be determined whether the electronic device has launched other transportation software that does not use the ride code (such as, taxi software, cycling software, etc.) at the current time.

[0333] In some embodiments, the current user's motion state can be used to indicate the user's motion state at the current time. For example, whether the user is in a walking state, a cycling state, or a driving / sitting state, etc.

[0334] S124. Based on the ride intention information, determine the intention level of the user to use the ride QR code.

[0335] In some embodiments, after the electronic device obtains the ride intention information, it can determine the intention level of the user to use the ride QR code through an intention level prediction model or an intention recognition rule set.

[0336] The first method is to determine the intention level of the user to use the ride QR code based on the intention recognition rule set and the ride intention information. The electronic device can first construct a user ride profile for the current station based on the ride intention information, and then compare the user ride profile for the current station with the intention recognition rule set to determine the intention level of the user to use the ride QR code. The user ride profile can include frequency characteristics (the user belongs to a low / medium / high-frequency rider), city characteristics (the current station belongs to the permanent residence / non-permanent residence station), subway fence characteristics (the entered geographical fence belongs to a low / medium / high-precision fence), station characteristics (the current station belongs to a familiar / strange station, etc.), date characteristics (the current time belongs to a weekday / holiday), time characteristics (the current time belongs to the regular riding period / non-regular riding period), motion state characteristics (walking / cycling / driving), device state characteristics (whether the cycling software / taxi software is turned on), etc.

[0337] The second method is to determine the intention level of the user to use the ride QR code based on the intention level prediction model and the ride intention information. For example, the ride intention information can be input into the intention level prediction model, and the output result of the intention level prediction model includes information for characterizing the intention level.

[0338] S125. Display the target card using a pop-up card strategy corresponding to the determined intention level. The target card is associated with the ride QR code for characterizing the user identity.

[0339] In some embodiments, the target card can be used to trigger the display of the ride QR code so that the user can use the electronic device to scan the code for taking a ride.

[0340] In some embodiments, each intention level can correspond to a different pop-up card strategy. The pop-up card strategy initially corresponding to each intention level can be set before the electronic device leaves the factory. Generally speaking, as the intention level increases, the dominance degree of the corresponding pop-up card strategy becomes greater. A greater dominance degree can mean that the area of the popped-up card is larger, or the card is displayed in other ways that are more easily noticed by the user.

[0341] For example, the intent level includes 10 levels (the intent levels range from the lowest, intent level 1, to the highest, intent level 10), and the pop-up card strategy corresponding to each intent level can be as shown in Table 1 above.

[0342] In some embodiments, the pop-up card strategy corresponding to each intent level can also be adjusted according to the user's usage habits / feedback.

[0343] Exemplarily, as Figure 13 shown in (a) of, if it is determined based on the ride intent information that the intent level of the user using the ride QR code is intent level 2, the electronic device can display the card 06 of "Ride Code" on the negative first screen. When the user clicks on card 06, the electronic device runs the payment application and directly jumps to the ride code page as shown in Figure 13 (b) of. The ride code page includes a QR code 07. If the user aligns the QR code 07 with the scanning device of the entrance turnstile, then the gate of the entrance turnstile opens and the user can enter the subway station. Or, if the user aligns the QR code 07 with the scanning device of the exit turnstile, then the gate of the exit turnstile opens and the user can leave the subway station. The ride code page can also include travel discount controls, ride record controls, and venue code scanning controls, etc. Among them, the travel discount control can be used to query discount information, the ride record control is used to view ride records, and the venue code scanning control is used to trigger the execution of the scanning operation.

[0344] In some embodiments, after the electronic device displays the target card, the electronic device can start a timer and detect whether a trigger operation on the target card is received within a preset duration. If a user operation on the target card is received within the preset duration, or, if an operation to cancel / delete the target card is received by the user within the preset duration, the electronic device can cancel the display of the target card in response to the user operation. If no user operation on the target card is received within the preset duration, or, if no operation to cancel / delete the target card is received by the user within the preset duration, then the electronic device keeps displaying the target card within the preset duration. After the preset duration is reached, the electronic device cancels the display of the target card.

[0345] In some embodiments, after the electronic device displays the target card, if it is determined based on the re-acquired location information of the electronic device that the electronic device has left the preset geographical fence, the display of the target card is cancelled.

[0346] Next, in combination with Figure 14 introduce the card display method provided by another embodiment of this application. Still taking the scenario of the user taking the subway as an example, in combination with Figure 14 , an example is given to illustrate the card display method provided by another embodiment of this application.

[0347] S141. Obtain the location information of the electronic device.

[0348] Step S141 of the embodiment of the present application is similar to step S121 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0349] S142. Determine whether the electronic device enters a preset geographical fence according to the obtained location information.

[0350] Step S142 of the embodiment of the present application is similar to step S122 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0351] S143. In the case of determining that the electronic device enters the preset geographical fence, obtain the intention information of taking a vehicle.

[0352] Step S143 of the embodiment of the present application is similar to step S123 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0353] S144. Based on the intention information of taking a vehicle, determine the intention level of the user to use the ride QR code.

[0354] Step S144 of the embodiment of the present application is similar to step S124 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0355] S145. Obtain the historical usage feedback information of the target card, and determine the card popping decision result based on the historical usage feedback information of the target card and the intention level.

[0356] In some embodiments, the historical usage feedback information of the target card may refer to the card operation information, ride behavior information detected after the target card is displayed based on the card popping strategy corresponding to the intention level at a historical time, or the ride behavior information detected in the case where the target card display is not performed based on the intention level decision. For example, the card operation information may include clicking the card, removing the card, not clicking the card, etc., and the ride behavior information may include not taking a vehicle, taking a vehicle by swiping the ride QR code, taking a vehicle without using the ride QR code, etc.

[0357] The electronic device can train a card popping decision model according to the historical usage feedback information. Then, input the intention level obtained in step S144 into the card popping decision model, and the card popping decision result output by the card popping decision model includes the identification information of whether to pop the card.

[0358] S146. If the card popping decision result is to pop the card, display the target card by using the card popping strategy corresponding to the determined intention level.

[0359] If the card popping decision result is to pop the card, it is considered that the user does have the intention to use the ride QR code. The electronic device can display the target card by using the card popping strategy corresponding to the determined intention level.

[0360] S147. If the card popping decision result is not to pop the card, the target card is not displayed.

[0361] If the card popping decision result is not to pop the card, it is considered that the user does not have the intention to use the ride QR code, and the electronic device does not display the target card. That is, the electronic device does not pop the card according to the card popping strategy corresponding to the intention level.

[0362] The following combines Figure 15 to introduce the card display method provided by another embodiment of the present application. Similarly, taking the scenario of a user taking the subway as an example, in combination with Figure 15 , an example is given to illustrate the card display method provided by another embodiment of the present application.

[0363] S151. Obtain the location information of the electronic device.

[0364] Step S151 of the embodiment of the present application is similar to step S121 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0365] S152. According to the obtained location information, determine whether the electronic device enters a preset geographical fence.

[0366] Step S152 of the embodiment of the present application is similar to step S122 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0367] S153. In the case of determining that the electronic device enters the preset geographical fence, obtain the ride intention information.

[0368] Step S153 of the embodiment of the present application is similar to step S123 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0369] S154. Based on the ride intention information, determine the intention level of the user to use the ride QR code.

[0370] Step S154 of the embodiment of the present application is similar to step S124 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0371] S155. Obtain the historical usage feedback information of the target card, and determine the card popping decision result based on the historical usage feedback information of the target card and the intention level.

[0372] Step S155 of the embodiment of the present application is similar to step S145 of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0373] S156. If the card popping decision result is to pop the card, display the target card by using the card popping strategy corresponding to the determined intention level.

[0374] Step S156 of the embodiment of the present application is similar to step S146 of the foregoing embodiment. To avoid repetition, it will not be described in detail here.

[0375] S157. Record the card operation information of the target card.

[0376] After the target card is displayed based on the pop-up card strategy corresponding to the intention level, the electronic device may record the card operation information of the target card. If the pop-up card strategy corresponding to the intention level includes multiple quick access entries, the electronic device may record the card operation information of each quick access entry.

[0377] S158. Adjust the pop-up card strategy of the first intention level based on the card operation information corresponding to the first intention level among multiple intention levels.

[0378] In some embodiments, for the pop-up card strategy corresponding to each intention level, the pop-up card strategy can be adjusted according to the associated card operation information, so as to realize personalized pop-up cards following the user's card usage preferences, and further reduce the accidental interruption of the device's pop-up cards to the user. For example, the pop-up card strategy corresponding to the first intention level among multiple intention levels is the first pop-up card strategy. After the electronic device displays the target card based on the first pop-up card strategy, the card operation information of the target card (i.e., the card operation information associated with the first pop-up card strategy) can be recorded. The electronic device may adjust the first pop-up card strategy based on the card operation information associated with the first pop-up card strategy recorded multiple times. Adjusting the first pop-up card strategy may refer to adjusting the quick access entries included in the first pop-up card strategy (for example, removing the quick access entries that the user has not used) or adjusting the size of the target card.

[0379] After the electronic device adjusts the first pop-up card strategy, if the first pop-up card strategy is triggered to display the target card subsequently, the electronic device may display the target card using the updated first pop-up card strategy.

[0380] S159. If the pop-up card decision result is not to pop up the card, the target card is not displayed.

[0381] Step S159 of the embodiment of the present application is similar to step S147 of the foregoing embodiment. To avoid repetition, it will not be described in detail here.

[0382] The above Figure 12 、 Figure 14 and Figure 15 introduce the solution provided by the embodiment of the present application from the perspective of the execution subject being the electronic device. It can be understood that in order for the electronic device to implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. The following will be combined with Figure 16, from the perspectives of the desktop application, algorithm module, emotion perception module, service logic processing module, and service presentation module included in the electronic device, the card display method is described in detail. The algorithm module can be deployed in the NPU and can be used to implement the logic of the intent recognition rule set or the intent level prediction model. The following also takes the scenario of a user taking the subway as an example.

[0383] S160. The service logic processing module sends a query message to the service presentation module. The query message is used to query whether the ride card reminder service is in an enabled state. The service presentation module returns a query result to the service logic processing module, such as the ride card reminder service being in an enabled state or a disabled state.

[0384] In some embodiments, when the ride card reminder service is in an enabled state, the electronic device can pop up the ride code service. When the ride card reminder service is in a disabled state, the electronic device will not pop up the ride code service.

[0385] S161. When the ride card reminder service is in an enabled state, the service logic processing module sends a request registration message to the emotion perception module. The request registration message is used to request the registration of the geographical fence of the subway station to monitor the registered geographical fence of the subway station.

[0386] S162. The context awareness module obtains the location information of the electronic device in response to the request message.

[0387] The context awareness module runs in a resident form or in a low-power form. When the ride card reminder service is in an enabled state, the context awareness module monitors the geographical fences of each subway station registered according to the service logic processing module. In addition, the context awareness module can also obtain the location information of the electronic device through the API from other application programs in the application layer, or the application framework layer, or the system layer, or the kernel layer, or the hardware layer, such as obtaining the GPS signal for determining the location signal from the GPS module, and obtaining the Cell ID signal for determining the location signal from the mobile communication module, etc.

[0388] S163. The context awareness module determines whether the electronic device enters the geographical fence of the subway station according to the location information of the electronic device.

[0389] S164. When the electronic device enters the geographical fence of a certain subway station, the context awareness module sends a notification message to the service logic processing module. It should be understood that when the electronic device does not enter the geographical fence of any subway station, the context awareness module can continue to obtain the location information of the electronic device and re-determine whether the electronic device enters the geographical fence of the subway station.

[0390] S165. The service logic processing module inputs the current ride intention information into the algorithm module in response to the notification message. The algorithm module can predict the intention level of the user's current use of the ride QR code according to the current ride intention information.

[0391] For example, the algorithm module can determine the intention level corresponding to the current ride intention information based on the intention recognition rule set or the intention level prediction model.

[0392] The ride intention information may include the current time information of the electronic device, the current location information, the currently running application information, the current user's motion state, etc. When the electronic device enters the geographical fence of a certain subway station, the service logic processing module can obtain the current time information of the electronic device from the clock application, obtain the current location information of the electronic device from the mobile communication module, the wireless communication module, etc., obtain the currently running application information from the application management, and obtain the current user's motion state data from the gyroscope sensor 180B and the acceleration sensor 180E.

[0393] S166. The service logic processing module obtains the predicted intention level from the algorithm module.

[0394] S167. The service logic processing module sends the pop-up card policy corresponding to the predicted intention level to the service presentation module, and the service presentation module constructs the target card based on the pop-up card policy.

[0395] S168. The service presentation module sends a notification to the desktop application, and the desktop application displays the target card. Among them, the target card is associated with the QR code used to represent the user identity.

[0396] For example, the target card is used to trigger the display of the ride QR code, or the target card includes the ride QR code.

[0397] S169. The service logic processing module obtains the card operation information of the target card, and adjusts the pop-up card policy of the intention level associated with the card operation information based on the card operation information.

[0398] For the pop-up card policy corresponding to each intention level, the pop-up card policy can be adjusted according to the associated card operation information. For example, the pop-up card policy corresponding to the first intention level among multiple intention levels is the first pop-up card policy. After the service presentation module constructs the target card based on the first pop-up card policy, the service logic processing module can obtain the card operation information of the target card displayed by the desktop application (i.e., the card operation information associated with the first pop-up card policy). The electronic device can adjust the first pop-up card policy based on the repeatedly recorded card operation information associated with the first pop-up card policy.

[0399] Please refer to Figure 17, assuming that the algorithm module can be used to implement the logic of the pop-up card decision model and the intention recognition rule set / intention level prediction model. The following will combine Figure 17 , and once again, from the perspectives of the desktop application, algorithm module, emotion perception module, business logic processing module, and business presentation module included in the electronic device, the card display method will be described in detail.

[0400] S170. The business logic processing module sends a query message to the business presentation module, and this query message is used to query whether the ride card reminder service is in an enabled state. The business presentation module returns a query result to the business logic processing module, such as the ride card reminder service is in an enabled state or a disabled state.

[0401] S171. When the ride card reminder service is in an enabled state, the business logic processing module sends a request registration message to the emotion perception module. This request registration message is used to request the registration of the geographical fence of the subway station to monitor the registered geographical fence of the subway station.

[0402] S172. The context awareness module obtains the location information of the electronic device in response to the request message.

[0403] S173. The context awareness module determines whether the electronic device enters the geographical fence of the subway station according to the location information of the electronic device.

[0404] S174. When the electronic device enters the geographical fence of a certain subway station, the context awareness module sends a notification message to the business logic processing module. It should be understood that when the electronic device does not enter the geographical fence of any subway station, the context awareness module can continue to obtain the location information of the electronic device and re-determine whether the electronic device enters the geographical fence of the subway station.

[0405] S175. The business logic processing module inputs the current ride intention information into the algorithm module in response to the notification message. The algorithm module can predict the intention level of the user's current use of the ride QR code and the pop-up card decision result according to the current ride intention information.

[0406] For example, the algorithm module can determine the intention level corresponding to the current ride intention information based on the intention recognition rule set or the intention level prediction model. After obtaining the intention level, the intention level can be input into the pop-up card decision model to obtain the pop-up card decision result of this time.

[0407] S176. The business logic processing module obtains the predicted intention level and the pop-up card decision result from the algorithm module.

[0408] S177. If the pop-up card decision result is to pop up the card, the service logic processing module sends a pop-up card policy corresponding to the predicted intention level to the service presentation module, and the service presentation module constructs a target card based on the pop-up card policy.

[0409] S178. The service presentation module sends a notification to the desktop application, and the desktop application displays the target card. Among them, the target card is associated with a two-dimensional code for characterizing the user identity.

[0410] S179. The service logic processing module obtains the card operation information of the target card, and adjusts the pop-up card policy associated with the card operation information based on the card operation information.

[0411] S180. If the pop-up card decision result is not to pop up the card, the service logic processing module determines not to display the target card. That is, the service logic processing module does not send a pop-up card policy corresponding to the predicted intention level to the service presentation module, and thus the service presentation module does not construct a target card either.

[0412] The above mainly introduces the solution provided in the embodiments of the present application from the perspective of the electronic device. It can be understood that in order to implement the above functions, the electronic device includes the corresponding hardware structure or software module for executing each function, or a combination of both. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0413] The embodiments of the present application can divide the functional modules of the electronic device according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the division of modules in the embodiments of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0414] The embodiments of the present application also provide an electronic device, including a processor, the processor is coupled with a memory, and the processor is used to execute the computer program or instructions stored in the memory so that the electronic device implements the methods in the above embodiments.

[0415] The embodiments of the present application also provide a computer-readable storage medium, in which computer instructions are stored; when the computer-readable storage medium runs on an electronic device, the electronic device is caused to execute the method as shown above. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that incorporates one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium, or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0416] The embodiments of the present application also provide a computer program product, which includes computer program code. When the computer program code runs on a computer, the computer is caused to execute the methods in the above embodiments.

[0417] The embodiments of the present application also provide a chip, which is coupled to a memory. The chip is used to read and execute the computer program or instructions stored in the memory to execute the methods in the above embodiments. The chip can be a general-purpose processor or a special-purpose processor.

[0418] It should be noted that the chip can be implemented using the following circuits or devices: one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0419] The electronic device, computer-readable storage medium, computer program product, and chip provided in the embodiments of the present application above are all used to execute the method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects corresponding to the method provided above, and will not be elaborated here.

[0420] It should be understood that the above is only to help those skilled in the art better understand the embodiments of the present application, rather than to limit the scope of the embodiments of the present application. Based on the above examples given, those skilled in the art can obviously make various equivalent modifications or changes. For example, in each of the embodiments of the above detection method, some steps may not be necessary, or some steps may be newly added, etc. Or any combination of any two or any more of the above embodiments. The solutions after such modifications, changes or combinations also fall within the scope of the embodiments of the present application.

[0421] It should also be understood that the above description of the embodiments of the present application focuses on emphasizing the differences between the embodiments. The same or similar parts not mentioned can be referred to each other. For the sake of brevity, they will not be elaborated here.

[0422] It should also be understood that the magnitude of the serial numbers of the above processes does not mean the sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0423] It should also be understood that in the embodiments of the present application, "pre-set" and "pre-defined" can be implemented by pre-saving the corresponding codes, tables or other means that can be used to indicate relevant information in a device (for example, including an electronic device). The present application does not limit its specific implementation manner.

[0424] It should also be understood that the division of the manners, situations, categories and embodiments in the embodiments of the present application is only for the convenience of description and should not constitute a special limitation. The features in various manners, categories, situations and embodiments can be combined without contradiction.

[0425] It should also be understood that in each of the embodiments of the present application, if there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be cited from each other. The technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0426] Finally, it should be noted that the above description content is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any change or replacement within the technical scope disclosed in the present application should be covered by the protection scope of the present application.

Claims

1. A card display method, characterized in that, Applied to an electronic device, the method includes: When the electronic device enters the first geographical fence, display a first ride card on the desktop interface; When the electronic device enters the second geographical fence, display a second ride card on the desktop interface; Wherein, both the first ride card and the second ride card are used to trigger the display of the ride code page, the area of the second ride card is larger than that of the first ride card, the first geographical fence corresponds to the first boarding station, the second geographical fence corresponds to the second boarding station, and the number of rides of the electronic device at the first boarding station is less than that at the second boarding station.

2. The method according to claim 1, wherein The step of, when the electronic device enters the second geographical fence, displaying a second ride card on the desktop interface further includes: When the electronic device enters the second geographical fence and the number of rides of the electronic device at the second boarding station within a preset time period is greater than a preset number, display the second ride card on the desktop interface; When the electronic device enters the second geographical fence and the number of rides of the electronic device at the second boarding station within the preset time period is less than the preset number, display the first ride card on the desktop interface.

3. The method according to claim 1, characterized in that, The step of, when the electronic device enters the second geographical fence, displaying a second ride card on the desktop interface further includes: When the electronic device enters the second geographical fence, display the first ride card or the second ride card on the desktop interface, and open a third interface to display a third ride card, wherein the third ride card is used to trigger the display of the ride code page, and the third interface is a floating interface or an interface displayed in an interface with a global function display area.

4. The method according to claim 3, wherein The steps of displaying the first ride card on the desktop interface, displaying the second ride card on the desktop interface, and opening the third interface to display the third ride card are all obtained by predicting based on a preset model.

5. The method according to claim 4, wherein When the preset model becomes effective, the electronic device generates a model file corresponding to the preset model.

6. The method according to claim 4, wherein The input of the preset model includes the time information, location information, running application information, and motion state of the electronic device when it enters the geographical fence, and the output of the preset model includes identification information for characterizing the intention level.

7. The method according to claim 6, wherein Before displaying the first ride card on the desktop interface, the method further includes: Obtaining first identification information based on the preset model; Before displaying the second ride card on the desktop interface, the method further includes: Obtaining second identification information based on the preset model; Wherein, the intention level characterized by the second identification information is higher than that characterized by the first identification information.

8. The method according to claim 6, wherein The output of the preset model further includes identification information for characterizing whether to pop up a card.

9. The method according to any one of claims 4 to 8, characterized in that The method further includes: When the preset model is not effective and the electronic device enters the geographical fence corresponding to any station, display a fourth ride card on the negative first screen.

10. A method for card display, characterized in that, The method includes: Obtain the current location information of the electronic device; When it is determined that the electronic device enters the geofence based on the current location information, determine the intention level of the user to use the ride card; Display the ride card by using a pop-up card strategy corresponding to the intention level; wherein, the ride card is used to trigger the display of the ride code page.

11. The method according to claim 10, characterized in that, The determining the intention level of the user to use the ride card when it is determined that the electronic device enters the geofence based on the current location information includes: When it is determined that the electronic device enters the geofence based on the current location information, obtain ride intention information, where the ride intention information includes the current time information, current location information, currently running application information, and current motion state of the electronic device; Based on the ride intention information, determine the intention level of the user to use the ride card.

12. The method according to claim 10 or 11, characterized in that, The higher the intention level, the greater the card visibility of the pop-up card strategy corresponding to the intention level, and the card visibility includes at least one of card area, number of quick access entries, and display location.

13. The method according to claim 11, wherein The determining the intention level of the user to use the ride card based on the intention information includes: Construct a user portrait corresponding to the geofence based on the intention information; Compare the user portrait with a preset intention recognition rule set to obtain the intention level of the user to use the ride card; wherein, the intention recognition rule set includes multiple intention levels and a feature set mapped to each intention level in the multiple intention levels, and the features included in the user portrait are determined based on the feature set.

14. The method according to claim 13, wherein The feature set includes a frequency feature and a geofence feature, the frequency feature is used to indicate the frequency of the user using the ride card within a preset period, and the geofence feature is used to indicate the accuracy of the geofence.

15. The method according to claim 11, wherein The determining the intention level of the user to use the ride card based on the intention information includes: Input the intention information into a preset model to obtain an output result, where the output result includes first identification information for characterizing the intention level.

16. The method according to claim 15, wherein The output result further includes second identification information for characterizing whether to pop up a card, and the method further includes: If the second identification information indicates not to pop up a card, determine not to display the ride card.

17. The method according to claim 16, wherein The displaying the ride card by using a pop-up card strategy corresponding to the intention level includes: If the second identification information indicates to pop up a card, display the ride card by using a pop-up card strategy corresponding to the intention level.

18. The method according to claim 15, wherein The preset model includes a first preset model and a second preset model, the first preset model is trained according to the historical ride behavior information on weekdays, the second preset model is trained according to the historical ride behavior information on non-weekdays, and the inputting the intention information into the preset model to obtain the output result includes: Obtain the current time information of the electronic device; When it is determined to be a weekday based on the current time information, input the intention information into the first preset model to obtain the output result; When it is determined to be a non-weekday based on the current time information, input the intention information into the second preset model to obtain the output result.

19. The method according to claim 18, wherein The method further includes: Divide the historical riding behavior information into multiple behavior information units according to a preset time window; Train the first preset model or the second preset model based on the multiple behavior information units and the weight of each behavior information unit in the multiple behavior information units; the earlier the behavior information unit is from the current training time of the first preset model or the second preset model, the lower the weight.

20. An electronic device, characterized in that, It includes a memory and a processor. Among them, the memory is used to store computer-readable instructions; the processor is used to read the computer-readable instructions and implement the card display method according to any one of claims 1 to 9, or implement the card display method according to any one of claims 10 to 19.

21. A computer storage medium, characterized in that, Store computer-readable instructions, and the computer-readable instructions, when executed by a processor, implement the card display method according to any one of claims 1 to 9, or implement the card display method according to any one of claims 10 to 19.

Images