System and method for facilitating wireless token interaction across multiple device and / or token types

Abstract

In some embodiments, a system may obtain first feedback indicating one or more first signal strength related results corresponding to one or more first token interactions, the one or more first token interactions occur in relation to presentation of one or more first components at one or more first locations of a user interface of the user device. Based on the first feedback, the system may obtain one or more second locations of the user interface and cause presentation of one or more second components at the one or more second locations of the user interface. The system may obtain a second feedback indicating one or more second signal strength related results corresponding to the one or more second token interactions. Using the first feedback and the second feedback, the system may update a user interface presentation location within a profile associated with a user of the user device at which a component for token interaction is presented.

Description

[0001] Cross - Reference to Related Applications

[0002] This application claims the benefit of priority of U.S. Patent Application No. 17 / 933,964, filed on September 21, 2022. The content of the foregoing application is incorporated herein by reference in its entirety. Background Art

[0003] When a user attempts to connect a particular token to a particular device, the wide variety of available tokens and device types causes technical problems. These problems result in a poor user experience and inefficient or ineffective information transfer between the token and the device. As an example, a token can be implemented within an identification badge for wirelessly authorizing a user to open a door using a token reader device. When a user positions the token near the token reader device, the user may become frustrated if the token does not connect to the token reader device. As a further example, when a user is unfamiliar with or does not regularly use a particular token with a particular device, or the user has multiple different tokens for use with one or more different devices, due to the variations between the token and the device, the user's expectations for connecting the token and the device may be incorrect, resulting in a poor user experience and technical problems with connecting the token and the device. Summary of the Invention

[0004] Due to this diversity of token and device types, a user's expectations for how to facilitate interaction between a token and a device may be inaccurate, preventing or reducing the opportunity for proper interaction between the token and the device. Given the differences between different types of tokens and devices, a user may be unsure how to facilitate interaction between a token (e.g., a badge, a card, or another suitable token) and a device (e.g., an access device, a card reader device, or another suitable device), such as how to align a badge or card with the device to achieve proper interaction between them.

[0005] In view of the foregoing problems, systems and methods for improving wireless token interaction across one or more device types and token types are described herein. As an example, the methods and systems described herein can generate dynamic widgets for display on a device based on the device type of the device and the token type of the token. These widgets can guide or assist a user in properly facilitating interaction between the device and the token. For example, when a user attempts to use a token with a token reader device to facilitate a wireless payment, the widget generated for display on the token reader device can guide the user as to where to position the token relative to the token reader device and how to orient the token at that position.

[0006] As another example, when a user attempts to use a token with a device, the described systems and methods can obtain a profile associated with the user or other users. The profile can include information about previous interactions between the same or similar token types and device types. Specifically, the information can include the results of previous interactions between the same or similar token types and device types at known locations of the device. The described systems and methods can use this information to generate components for display on the device at locations known or predicted to achieve results that meet a specific threshold between the token and the device. When the user uses the token with the device at the displayed location within the generated component, the described systems and methods can record the achieved results and update the profile to improve future component generation when the user's request or another user's request is related to the same or similar token type and device type.

[0007] As another example, when a user attempts to use a token with a device, the described systems and methods can obtain a profile that includes information associated with the token type of the token, the device type of the device, and the user. The profile can also include information about regions (e.g., locations) on the display of the device, and the region information includes the results of previous interactions between the same or similar token and device types at each region. The described systems and methods can use the previous interactions from each region to identify one or more regions to generate for display components, where interactions may achieve results that meet a specific threshold when the user places the token at the component displayed on the device. Additionally, if the profile contains certain user information, the described systems and methods can adjust the identified regions to best conform to the user's previous interactions between the same or similar tokens and devices. When the user places the token at the component displayed on the device, the described systems and methods can record the results of the interaction and update the profile to improve future component generation when the user's request or another user's request is related to the same or similar token type and device type.

[0008] Various other aspects, features, and advantages of the systems and methods described herein will be apparent from the detailed description and the drawings. It should also be understood that the foregoing general description and the following detailed description are both examples and are not limitations on the scope of the systems and methods described herein. As used in the specification and the claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Additionally, unless the context clearly provides otherwise, as used in the specification and the claims, the term "or" means "and / or" and includes one, less than all, or all of the items in a list or phrase. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1Shows a system for facilitating wireless token interaction according to one or more embodiments.

[0010] Figure 2 Shows a depiction of a boot profile according to one or more embodiments.

[0011] Figures 3A - 3B Shows a depiction of components presented on a device according to one or more embodiments.

[0012] Figure 4 Shows a machine learning model configured to facilitate wireless token interaction according to one or more embodiments.

[0013] Figure 5 Shows a flowchart of a method for improving the signal strength of wireless token interaction according to one or more embodiments. Detailed Description

[0014] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the systems and methods described herein. However, one of ordinary skill in the art will understand that the embodiments may be practiced without these specific details or with equivalent arrangements. In other instances, well-known structures and devices are shown in block diagram form to avoid unnecessarily obscuring the embodiments.

[0015] Figure 1 Shows a system 100 for facilitating wireless token interaction according to one or more embodiments. As Figure 1As shown, system 100 may include computer system 102, client device 104 (or client devices 104a - 104n), or other components. Computer system 102 may include data analyzer subsystem 112, component generation subsystem 114, model subsystem 116, or other components. Each client device 104 may include any type of mobile terminal, fixed terminal, handheld device, stationary device, or other device. By way of example, client device 104 may include a desktop computer, laptop computer, tablet computer, point - of - sale device, smartphone, wearable device, or other client device. For example, a user may utilize one or more client devices 104 to interact with each other, with one or more servers, or with other components of system 100. It should be noted that although one or more operations are described herein as being performed by specific components of computer system 102, in some embodiments, those operations may be performed by other components of computer system 102 or by other components of system 100. By way of example, although one or more operations are described herein as being performed by components of computer system 102, in some embodiments, those operations may be performed by components of client device 104. It should be noted that although some embodiments are described herein with respect to machine - learning models, in other embodiments, other prediction models (e.g., statistical models or other analytical models) may be used instead of or in addition to machine - learning models (e.g., in one or more embodiments, a statistical model replaces a machine - learning model and a non - statistical model replaces a non - machine - learning model).

[0016] In some embodiments, system 100 may obtain a profile including device type and token type to generate components for display on client device 104, where client device 104 corresponds to the device type. The generated components may identify the location where the token interacts with client device 104, where the token corresponds to the token type. When the token and client device 104 interact at the generated components, system 100 may record feedback indicating the result between the token and client device 104 and associate the feedback and result with the location of the generated components. System 100 may update the profile based on the feedback and result associated with the location of the generated components to improve future - generated components. Additionally, system 100 may use the associated feedback and result to predict where to generate components for display: (i) on a different device type used with the token type, (ii) on different device types used with different token types, or (iii) on client device 104 used with different token types.

[0017] As a first example, a profile can correspond to a user of a financial service (“user”), such as a consumer using banking financial services, a retailer using payment processing financial services, a financial service provider facilitating the provision of financial services, or any similar user of a financial service. The device types included in the profile can correspond to one or more client devices 104 owned by the user, such as, for example, a cellular phone of the user having a token reader (e.g., having contactless Europay, Mastercard, and Visa (“EMV”) support). The token types can correspond to one or more transaction cards of the user, such as a primary transaction card having contactless EMV support. As a second example, the profile can alternatively correspond to a client device 104 for performing or facilitating a financial service, and as disclosed, the information stored in the profile is associated with any or all users of the client device 104. In these embodiments, the device types included in the profile correspond to the client device 104, and the token types can correspond to one or more transaction cards of a user interacting with the client device 104.

[0018] As another example, a user can access the system 100 on the user's cellular phone to use the user's transaction card with the cellular phone. When the user prompts (e.g., makes a request to) the system 100 that the user wishes to use the transaction card with the cellular phone, the system 100 can obtain the profile to identify the device type of the user's cellular phone and the token type of the user's transaction card. The system 100 can use the device type and the token type to generate a component (e.g., an icon) for display (e.g., presentation) on the user's cellular phone display (e.g., interface) that identifies the location for using the transaction card with the cellular phone. If the transaction card and the cellular phone have previously interacted via the user or a different user having a different profile, the system 100 can use the previous interaction, for example, at a location where the system 100 knows or predicts that a signal strength between the transaction card and the cellular phone that meets a specific threshold may be generated, to generate the component for display.

[0019] As another example, a user may access System 100 on a public device (e.g., a computer, a point-of-sale device, etc.) to use the user's transaction card with the public device. When the user prompts (e.g., makes a request to) System 100 that the user wishes to use the transaction card with the public device, System 100 may obtain a profile to identify the device type of the public device and the token type of the user's transaction card. System 100 may use the device type and the token type to generate a component (e.g., an icon) for display (e.g., rendering) on a display (e.g., an interface) of the public device, the component identifying a location for using the transaction card with the public device. If the transaction card and the public device have previously interacted via the user or a different user with a different transaction card, System 100 may use the previous interaction, for example, at a location where System 100 knows or predicts that a signal strength between the transaction card and the public device that meets a specific threshold may be generated, to generate the component for display.

[0020] If the transaction card has previously interacted with a cellular phone or a public device, but based on the previous interaction, System 100 identifies multiple component display locations or inconsistent component display locations that meet a specific threshold, then System 100 may generate a component for display that moves between multiple locations on the display, or moves in a circular or similar pattern between or around one or more locations on the display where a signal strength that meets a specific threshold may be generated. As another example, if the transaction card has previously interacted with a cellular phone or a public device, but based on the previous interaction, System 100 identifies that a specific threshold is met when a component is generated at a location offset from a location where other users' interactions, known to System 100 or predicted by System 100, meet a specific threshold, then System 100 may generate a component for display at a location offset from a location where other users may generate a signal strength that meets a specific threshold.

[0021] If the user has not previously used the transaction card with a cellular phone or a public device, System 100 may predict locations where a signal strength that meets a specific threshold may be generated, or common locations between client devices 104 that are typically used to generate a signal strength that meets a specific threshold. System 100 may use a profile, profiles of other users, a profile of the device type, or other data included in System 100 to predict the locations. In some scenarios, System 100 may generate a test component for display based on the predicted locations, or randomly generate a test component for display.

[0022] Once the generated component (or test component) is displayed, the user can position the transaction card near or on the display of the cellular phone or public device identified by the component, allowing the transaction card and the cellular phone or public device to interact via a contactless EMV, short-range radio frequency, or other similar wireless connection and exchange information. When the transaction card and the cellular phone or public device interact, system 100 can record feedback indicating the result, such as the presence of a wireless connection, signal strength, information exchange rate, information exchange efficiency, interaction time frame, or similar feedback information at the location of the generated component between the transaction card and the cellular phone or public device. System 100 can update the profile based on the feedback. When presenting test components, system 100 can generate or display one or more test components individually or sequentially, update the profile based on the feedback from each test component, and use the updated profile to generate subsequent test components.

[0023] In some embodiments, when the user accesses system 100 on the user's cellular phone or public device, the cellular phone or public device can perform locally one, more, or all of the following operations identified above and further disclosed below: (i) obtain a profile, (ii) identify or predict the location of the display to present the component, (iii) incorporate previous interaction information, motion assistance, or offset assistance when available, (iv) generate the component for display, (v) record feedback from the token interaction, or (vi) update the profile based on the feedback. The cellular phone or public device can similarly perform locally any additional operations that support these operations. In some embodiments, when the user accesses system 100 on the user's cellular phone or public device, computer system 102 can alternatively perform or assist the user's cellular phone or public device in performing one, more, or all of the above operations. For example, the cellular phone or public device can obtain feedback locally from a first token interaction, identify one or more locations for displaying one or more second components based on the first feedback, generate and display the components at the one or more second locations, obtain second feedback from the token interaction at the one or more second locations, and update the profile based on the first feedback and the second feedback.

[0024] Thus, when any user of system 100 wishes to use a particular token type and a particular device type together, whether the user has previously used the particular token type and the particular device type together or not, the user can be prompted with a generated component that identifies a location on the display of client device 104 where a signal strength, for example, meeting a particular threshold between the particular device type and the particular token type may be achieved. Additionally, even if the user has used the particular device type and the particular token type together, but is unable to consistently achieve a signal strength, for example, meeting a particular threshold, system 100 can compensate for the problem and animate or move the display location of the generated component to better allow the user to meet the particular threshold. Thus, regardless of the user's previous experience with any device type or any token type, system 100 allows the user to most likely achieve a signal strength, for example, meeting a particular threshold, thereby alleviating a poor user experience and technical problems associated with ineffective device and token interactions.

[0025] Subsystems 112 - 116

[0026] In some embodiments, the data analyzer subsystem 112 can obtain or update a profile associated with a user. The profile can include one or more client devices 104, one or more tokens, one or more user attributes, one or more bootstrap profiles, or other similar information associated with the user. Each of the one or more client devices 104 included can correspond to a device that the user owns, uses, or interacts with. Each client device 104 included in the profile can have a device type. The device type can include, for example, device identification information such as device manufacturer, device model, device operating system, device category (e.g., computer, tablet, cellular phone, consumer - facing point - of - sale, retailer - facing point - of - sale), or other similar device identification information. The device type can also include non - contact EMV support information (e.g., yes, no), device dimensions (e.g., display location, display size), token reader information (e.g., receiver location relative to the display, receiver signal range, or similar receiver information), or other similar device information. The information included with the device type can be based on a dataset of known device information from system 100, can be received from the client device 104 when interfacing with system 100, or can be derived by system 100 over time through an interface with multiple client devices 104.

[0027] One or more tokens included may correspond to tokens owned, used, or interacted with by the user, such as, for example, a contactless EMV-enabled transaction card with an antenna or other similar device that supports wireless communication with client device 104. Each token included in the profile may have a token type. The token type may include, for example, transaction card identification information such as a transaction card number, a user account identifier, a card type identifier, or other similar card identification information. The token type may also include card material (e.g., metal, plastic, or a specific variety thereof), card dimensions (e.g., thickness, height, or width), contactless EMV support (e.g., yes, no), token identification information, transmit antenna attributes (e.g., antenna length, antenna position), contactless EMV attributes (e.g., minimum required signal strength), or other similar token information. The information included with the token type may be based on a dataset of known token information from system 100, may be received from the token when interfacing with system 100, or may be derived by system 100 over time through interfacing with multiple tokens. As an example, system 100 may use vision recognition technology to identify token type information from an image collected by client device 104 of the token before, during, or after an interaction between the token and client device 104.

[0028] One or more user attributes included may correspond to the user associated with the profile. User attributes may include user accuracy or similar user information. User accuracy may include information identifying the user from the profile for meeting consistency of a specific threshold signal strength between the token and client device 104, the specific threshold signal strength being associated with the relevant token type, client device type, or location on client device 104. User accuracy may further include ancillary information such as, for example, motion assistance, offset assistance, or similar assistance information. Motion assistance information may, for example, identify that the user meets a specific threshold when a generated component moves between positions or around a specific position on the display of client device 104. Offset assistance information may, for example, identify that the user meets a specific threshold when a generated component is offset on client device 104 in a specified direction and distance from a component position known or predicted by system 100 to meet a specific threshold.

[0029] One or more boot profiles included may be associated with a combination of one or more client devices 104 and one or more tokens included in the profile. As an example, the boot profile may visually correspond to Figure 2 boot profile 200. Boot profile 200 may correspond in shape to the display of the associated client device 104. For example, boot profile 200 may be at a height (D H ) and width (D W)a rectangle corresponding to the height and width of the display of the client device 104. The guidance profile 200 may include specific threshold results, such as, for example, signal strength, which the system 100 knows or predicts as the necessary signal strength for enabling information exchange between the client device 104 and the token (at certain locations of the client device 104). These locations may correspond to the regions 202 of the guidance profile 200. As shown, the guidance profile 200 includes twenty-four regions 202. However, the guidance profile may include more or fewer regions 202.

[0030] Specifically, the specific threshold results may be included in each region 202. In some embodiments, the specific threshold may include signal strength, which the system 100 identifies as sufficient over time to facilitate information exchange between the client device 104 and the token. Additionally or alternatively, the regions 202 may include interaction information for the associated client device 104 and token. The interaction information between the client device 104 and the token may include historical interaction information, such as, for example, historical interaction signal strength, average interaction signal strength, interaction signal strength known to the system 100, or similar historical interaction information.

[0031] The interaction information may further include interaction prediction information. The interaction prediction information may include probability predictions, a set of possible regions 202, or similar prediction information based on historical interaction information. The probability prediction information may include the likelihood that a display generation component will produce a signal strength that meets a specific threshold at a location of the client device 104 corresponding to the region 202. As an example, the probability prediction information may be visualized similar to Figure 2 a shaded gradient or “heat map” overlay, where the darker the region 202, the higher the probability that the region 202 will produce a signal strength that meets a specific threshold.

[0032] The set of possible regions 202 may include a set of regions 202 that are identified as likely to produce a signal strength that meets a specific threshold and that produce a confidence score associated with achieving the specific threshold for each region 202 of the set. As an example, the set of possible regions 202 may be similarly visualized as Figure 2 a shaded gradient overlay, where any shared regions 202 are included in the set of possible regions 202, and the darker the region 202 is shaded, the higher the confidence score associated with that region 202.

[0033] In some embodiments, in response to a user request to use the token and the client device 104 together, the component generation subsystem 114 may use the profile obtained by the data analyzer subsystem 112 to generate a component for display on the client device 104. Figure 3A and Figure 3B(collectively referred to as "Figure 3") are two examples of components 304, 314 generated on client devices 300, 310 using a profile in response to a user request. As shown, client devices 300, 310 are cellular phones. Client devices 300, 310 may both have a first device type, or client device 300 may have a first device type and client device 310 may have a second device type. Client devices 300, 310 have displays 302, 312. Display 302 has a first device height (D H1 ) and width (D W1 ), and display 312 has a second device height (D H2 ) and width (D W2 ). The first device height or width may be the same as or different from the second device height or width, respectively. For ease of description, client devices 300, 310 are shown as cellular phones. However, one of ordinary skill in the art will understand that client devices 300, 310 are illustrative of any client device 104 disclosed.

[0034] Components 304, 314 may be display icons that include token outlines 306, 316 or token targets 308, 318. Token outlines 306, 316 may include dashed or solid lines, shading gradients or shadows, images, or any other similar illustration representing, for example, the outline or orientation of a token associated with a token presented on displays 302, 312. Token outlines 306, 316 may be based on the token type of the token associated with the user request. For example, token outlines 306, 316 may be based on information known to system 100 about token type identifiers, token materials, token dimensions, transmit antenna properties, or other similar token information.

[0035] The token targets 308, 318 can include an image or text within the token outlines 306, 316 that instructs a user to click on the token near or on the displays 302, 312, or to place the token near or on the displays 302, 312 for use with the client devices 300, 310. For example, the token targets 308, 318 can include the words "click here" within a circle in the upper left middle of the token outline 306, 316, as shown in FIG. 3. As another example, the token targets 308, 318 can include an image of a target (e.g., a bullseye), or the token targets 308, 318 can individually include the words "click card here" within the token outline 306, 316. Additionally or alternatively, the token targets 308, 318 can be based on the token type of the token associated with the user request. As an example, the token targets 308, 318 can be based on information known to the system 100 about the token number, user account identifier, or other similar token identification information. The component generation subsystem 114 can use this token identification information to include, for example, the token number or user account information as the token targets 308, 318 such that the components 304, 314 replicate the appearance of the token.

[0036] In some embodiments, the components 304, 314 can correspond to the shape or dimensions of the displays 302, 312. For example, the token outlines 306, 316 can include a dashed or solid line, a shading gradient or shadow, an image, or any other similar illustration that highlights or identifies a region of the displays 302, 312 (e.g., a dashed line below the center of the display, a box around the upper right quadrant of the display, etc.), regardless of the token. Additionally, when the token outline 306, 316 is a dashed line vertically displayed from the top to the bottom of the display 302, 312 or similarly a dashed line displayed corresponding to the dimensions of the display 302, 312, the token target 308, 318 can include the words "place the card anywhere to the right of the dashed line" or a similar instruction.

[0037] In Figure 3AIn the example, when the user requests to use the token with the client device 300, the component generation subsystem 114 can obtain a profile associated with the token type of the token and the first device type. The component generation subsystem 114 can use the boot profile of the obtained profile to identify the position of the display 302 to present the generated component 304 relative to the center of the display 302 or other device dimensions. The component generation subsystem 114 can also use the token type and the first device type to identify how to display the generated component 304 relative to the identified position. When the token and the client device 300 interact at the position where the generated component 304 is displayed, the system 100 can record the feedback between the token and the client device 300, such as signal strength, and the system 100 can prompt the data analysis subsystem 112 to update the profile based on the feedback. For example, the data analysis subsystem 112 can update the boot profile and the included interaction information.

[0038] Figure 3B is an example of the same process when the user requests to use the token with the client device 310 (including the second device type). Figure 3B is another example of the same process when the user requests to use a token with a different token type with the client device 310 (including the first device type). In other scenarios, the component generation subsystem 114 can obtain a profile associated with the relevant token type and the first or second device type. The component generation subsystem 114 can use the boot profile of the profile to identify the position of the display 312 relative to the center of the display 312 or other device dimensions to present the generated component 314. The component generation subsystem 114 can also use the relevant token type and the first or second device type to identify how to generate the component 314 relative to the identified position. When the token and the client device 310 interact at the position where the generated component 314 is displayed, the system 100 can record the signal strength or other information between the token and the client device 310, and the system 100 can prompt the data analysis subsystem 112 to update the profile based on the recorded signal strength. As Figure 3B shown, different token and device types cause the component generation subsystem 114 to display the generated component 314 at different positions on the display 312 than on the display 302. The component 314 is generated at a different position relative to the display 302 because based on the combination of the token type and the device type, the component generation subsystem 114 identifies that different positions have a higher likelihood of achieving the signal strength between the token and the client device 310 at different positions.

[0039] To identify the locations of displays 302, 312 for presenting the generated components 304, 314, the component generation subsystem 114 can use interaction information from a boot profile associated with the device type and token type. In this scenario, the height and width of the obtained boot profile (e.g., Figure 2 's D H and D W ) can correspond to the height (D H1 , D H2 ) and width (D W1 , D W2 ) of displays 302, 312. Each region 202 of the boot profile and the information associated with each region 202 can correspond to a location on displays 302, 312. The component generation subsystem 114 can use historical interaction information or interaction prediction information corresponding to region 202 to identify the locations on displays 302, 312 that are most likely to produce a signal strength meeting a specific threshold. Additionally, if the profile includes user accuracy information, the component generation subsystem 114 can adjust the locations of components 304, 314.

[0040] When using historical interaction information, the component generation subsystem 114 can identify the locations of displays 302, 312 associated with region 202 based on the historical interaction information, where region 202 has the highest average signal strength, the highest signal strength known to system 100, or any other metric indicating that region 202 may meet a specific threshold. When using interaction prediction information, the component generation subsystem 114 can identify the locations of displays 302, 312 associated with region 202 that has (i) the highest probability or (ii) the highest confidence of achieving a specific threshold.

[0041] When the profile includes user accuracy information (such as motion assistance or offset assistance), the component generation subsystem 114 can adjust the identified locations of displays 302, 312 based on the motion assistance or offset assistance. For example, once a location is identified, the component generation subsystem 114 can generate shifted locations around the identified location, or if the user accuracy is low, generate shifted locations between multiple identified locations based on the motion assistance information. As another example, once a location is identified, the component generation subsystem 114 can adjust the identified location by a specific offset distance based on the offset assistance information.

[0042] Once the component generation subsystem 114 has identified the locations of the displays 302, 312 and the movement around or between those locations or the offsets from those locations, the component generation subsystem 114 can identify how to display the components 304, 314 relative to the identified locations. The component generation subsystem 114 can use the token type and the device type to identify how to display the components 304, 314 relative to the identified locations. For example, the component generation subsystem 114 can use device dimensions, token reader information, or other similar device information from the device type in combination with token material, token dimensions, transmit antenna properties, contactless EMV properties, or other similar token information from the token type. The component generation subsystem 114 can use this information to generate the components 304, 314 on the display such that when the user places the token on the client devices 300, 310, the token is closest to the token reader of the client devices 300, 310, and the interaction between the token and the client devices 300, 310 achieves the highest signal strength, or there is the highest likelihood that the interaction between the token and the client devices 300, 310 will achieve a signal strength that meets a specific threshold.

[0043] When the user uses the token with the client devices 300, 310 at the components 304, 314 on the displays 302, 312, the system 100 can record the signal strength between the token and the client devices 300, 310. The system 100 can prompt the data analysis subsystem 112 to update the profile based on the recorded signal strength. The data analysis subsystem 112 can store the recorded signal strength and update the guidance profile and the historical interaction information and interaction prediction information included therein. In addition, the data analysis subsystem 112 can update the user accuracy or auxiliary information.

[0044] In some embodiments, the model subsystem 116 can train or configure one or more prediction models to facilitate one or more embodiments described herein. In some embodiments, such models can be used to perform data format detection and conversion, speech recognition, word space mapping, or language translation. As an example, such models can be trained or configured to perform the foregoing functions by non-linearly mapping input data and output data to each other based on learning (e.g., deep learning).

[0045] In some embodiments, the prediction model may include one or more neural networks or other machine learning models. As an example, a neural network may be based on a large collection of neural units (or artificial neurons). A neural network may loosely mimic the way a biological brain works (e.g., via a large cluster of biological neurons connected by axons). Each neural unit of the neural network may be connected to many other neural units of the neural network. Such connections may enforce or inhibit their influence on the activation state of the connected neural units. In some embodiments, each individual neural unit may have a summation function that combines the values of all its inputs. In some embodiments, each connection (or the neural unit itself) may have a threshold function such that a signal must exceed the threshold before it propagates to other neural units. These neural network systems can be self-learning and self-training rather than explicitly programmed and can perform significantly better in solving problems in specific domains compared to traditional computer programs. In some embodiments, a neural network may include multiple layers (e.g., where the signal path traverses from a previous layer to a subsequent layer). In some embodiments, a neural network may utilize backpropagation techniques, where forward stimuli are used to reset the weights on the "previous" neural units. In some embodiments, the stimulation and inhibition in a neural network may flow more freely, where the connections interact in a more chaotic and complex manner.

[0046] As an example, with respect to Figure 4 , the machine learning model 402 may receive an input 404, such as, for example, ground truth, and provide an output 406. In one use case, the output 406 may be fed back into the machine learning model 402 as an input to train the machine learning model 402 (e.g., alone or in combination with an indication of the accuracy of the output 406 by a user, a label associated with the input, or other reference feedback information). In another use case, the machine learning model 402 may update its configuration (e.g., weights, biases, or other parameters) based on its evaluation of its prediction (e.g., output 406) and reference feedback information (e.g., an indication of accuracy by a user, a reference label, or other information). In another use case, where the machine learning model 402 is a neural network, the connection weights may be adjusted to reconcile the differences between the prediction of the neural network and the reference feedback. In another use case, one or more neurons (or nodes) of the neural network may require their respective errors to be sent backward through the neural network to facilitate the update process (e.g., backpropagation of errors). The update of the connection weights may, for example, reflect the magnitude of the error backpropagated after a forward pass has been completed. In this way, for example, the machine learning model 402 can be trained to generate better predictions.

[0047] As an example, in the case where the prediction model includes a neural network, the neural network can include one or more input layers, hidden layers, and output layers. The input layer and the output layer can each include one or more nodes, and each hidden layer can include multiple nodes. When the entire neural network includes multiple parts trained for different objects, there may or may not be an input layer or an output layer between different parts. The neural network can also include different input layers to receive various input data. In addition, in different examples, data can be input into the input layer in various forms and into the corresponding nodes of the input layer of the neural network in various dimensional forms. In a neural network, for example, the nodes of the layers other than the output layer are connected to the nodes of the subsequent layer by links for sending output signals or information from the current layer to the subsequent layer. The number of links can correspond to the number of nodes included in the subsequent layer. For example, in adjacent fully connected layers, each node of the current layer can have a corresponding link to each node of the subsequent layer. Note that in some examples, such full connections can be pruned or minimized later during training or optimization. In a cyclic structure, the nodes of a layer can be input again into the same node or layer at a subsequent time, while in a bidirectional structure, forward and backward connections can be provided. The links are also referred to as connections or connection weights, such as referring to the hardware-implemented connections or the corresponding "connection weights" provided by those connections of the neural network. During training and implementation, such connections and connection weights can be selectively implemented, removed, and changed to generate or obtain the resulting neural network that is thus trained and can be correspondingly implemented for the trained object (such as identifying an object for any of the above examples).

[0048] Example flowchart

[0049] Figure 5 It is an example flowchart of the processing operations of method 500 that implements various features and functions of the system described in detail above. The processing operations of the method presented below are intended to be illustrative rather than restrictive. In some embodiments, for example, the method can be completed using one or more additional operations not described, or can be completed without one or more of the operations discussed. Additionally, the order of the processing operations of the method shown (and described below) is not intended to be restrictive.

[0050] In some embodiments, the method may be implemented in one or more processing devices (e.g., a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information). The processing device may include one or more devices that perform some or all of the operations of the method in response to instructions electronically stored on an electronic storage medium. The processing device may include one or more devices configured by hardware, firmware, and / or software that are specifically designed to perform one or more operations of the method.

[0051] In operation 502, first feedback related to one or more first token interactions of a token may be obtained. For example, one or more token interactions may occur in relation to the presentation of one or more first components at one or more first locations of a user interface of a user device and the interaction of the token with the user device at the one or more first locations. The first feedback may indicate that one or more results related to one or more first signal strengths correspond to the one or more first token interactions. According to one or more embodiments, operation 502 may be performed by a subsystem that is the same as or similar to subsystem 112.

[0052] In operation 504, one or more second locations of the user interface may be obtained based on the first feedback. For example, based on the correspondence between one or more results related to one or more first signal strengths and the one or more first token interactions, one or more second locations may be obtained, and when one or more second token interactions of the token occur at the one or more second locations, the one or more second locations have a predicted or known likelihood of producing one or more results related to one or more second signal strengths. According to one or more embodiments, operation 504 may be performed by a subsystem that is the same as or similar to the data analyzer subsystem 112 and includes information from the subsystem.

[0053] In operation 506, one or more second components may be presented at the one or more second locations. For example, a first one of the one or more second components may be presented at a first one of the one or more second locations, and a second one of the one or more second components may be presented at a second one of the one or more second locations. Additionally or alternatively, the first one of the one or more second components may be presented at the second one of the one or more second locations simultaneously or subsequently. According to one or more embodiments, operation 506 may be performed by a subsystem that is the same as or similar to the component generation subsystem 114.

[0054] In operation 508, second feedback related to one or more second interactions with the token can be obtained. For example, one or more second token interactions can occur in relation to the presentation of one or more second components at one or more second locations of the user interface of the user device and the interaction of the token with the user device at the one or more second locations. The second feedback can indicate results related to one or more second signal strengths corresponding to the one or more first token interactions. According to one or more embodiments, operation 508 can be performed by a subsystem that is the same as or similar to subsystem 112.

[0055] In operation 510, the profile can be updated based on the first feedback and the second feedback. For example, the profile can be associated with one or more users of the user device and include information about one or more tokens and one or more user devices. Specifically, the profile can include the location of the user interface at which future components for future token interactions are presented. This location can be associated with one or more specific tokens and one or more specific user devices. When updating the profile, the first feedback and the second feedback can be added to the profile or replace the information within the profile. Additionally, the first feedback and the second feedback can be used to modify the existing information within the profile. For example, the first feedback and the second feedback can be added to or replace the interaction information included in the guidance profile, including adding to or replacing the historical interaction information. Additionally or alternatively, the first feedback and the second feedback can be used to update the interaction prediction information. According to one or more embodiments, operation 510 can be performed by a subsystem that is the same as or similar to subsystem 112.

[0056] In some embodiments, Figure 1 the various computers and subsystems shown can include one or more computing devices programmed to perform the functions described herein. The computing device can include one or more electronic storage devices (e.g., the transformation database 132, which can include the training data database 134, the model database 136, etc., or other electronic storage devices), one or more physical processors programmed with one or more computer program instructions, and / or other components. The computing device can include communication lines or ports to enable the exchange of information within a network (e.g., network 150) or other computing platforms via wired or wireless technologies (e.g., Ethernet, fiber optic, coaxial cable, WiFi, Bluetooth, near field communication, or other technologies). The computing device can include multiple hardware, software, and / or firmware components that operate together. For example, the computing device can be implemented by a cloud that is a computing platform operating together as the computing device.

[0057] An electronic storage device may include a non-transitory storage medium that stores information electronically. The storage medium of the electronic storage device may include one or both of the following: (i) a system storage device provided integrally (e.g., substantially non-removable) with a server or a client device, or (ii) a removable storage device removably connectable to a server or a client device via, for example, a port (e.g., a USB port, a FireWire port, etc.) or a drive (e.g., a disk drive, etc.). The electronic storage device may include one or more of an optically readable storage medium (e.g., an optical disc, etc.), a magnetically readable storage medium (e.g., a magnetic tape, a magnetic hard disk drive, a floppy disk drive, etc.), a charge-based storage medium (e.g., an EEPROM, a RAM, etc.), a solid-state storage medium (e.g., a flash drive, etc.), and / or other electronically readable storage media. The electronic storage device may include one or more virtual storage resources (e.g., cloud storage, a virtual private network, and / or other virtual storage resources). The electronic memory may store software algorithms, information determined by a processor, information obtained from a server, information obtained from a client device, or other information for implementing the functions described herein.

[0058] The processor may be programmed to provide information processing capabilities in a computing device. Thus, the processor may include one or more of a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information. In some embodiments, the processor may include multiple processing units. These processing units may be physically located within the same device, or the processor may represent the processing functions of multiple devices operating in coordination. The processor may be programmed to run computer program instructions to perform the functions described herein for subsystems 112-116 or other subsystems. The processor may be programmed to run computer program instructions by software; hardware; firmware; some combination of software, hardware, or firmware; and / or other mechanisms for configuring the processing capabilities on the processor.

[0059] It should be understood that the descriptions of the functions provided by the different subsystems 112-116 described herein are for illustrative purposes and are not intended to be restrictive, as any of the subsystems 112-116 may provide more or fewer functions than described. For example, one or more of the subsystems 112-116 may be eliminated, and some or all of their functions may be provided by other subsystems among 112-116. As another example, additional subsystems may be programmed to perform some or all of the functions attributed herein to one of the subsystems 112-116.

[0060] Although, for purposes of illustration, the systems and methods have been described in detail herein based on currently considered to be the most practical and preferred embodiments, it should be understood that such details are for that purpose only and the systems and methods are not limited to the disclosed embodiments, but rather are intended to cover modifications and equivalent arrangements within the scope of the appended claims. For example, it should be understood that the systems and methods described herein contemplate, to the extent possible, that one or more features of any embodiment may be combined with one or more features of any other embodiment.

[0061] The present technology will be better understood with reference to the following enumerated embodiments:

[0062] A1. A method comprising: obtaining first feedback related to one or more first token interactions of a token, the one or more first token interactions of the token occurring in relation to the presentation of one or more first components at one or more first locations of a user interface of a user device, the first feedback indicating one or more first results corresponding to the one or more first token interactions; obtaining, based on the first feedback, one or more second locations of the user interface; causing the presentation of one or more second components at the one or more second locations of the user interface; obtaining second feedback related to one or more second token interactions of the token, the one or more second token interactions of the token occurring in relation to the presentation of the one or more second components, the second feedback indicating one or more second results corresponding to the one or more second token interactions; and updating a profile associated with a user based on the first feedback and the second feedback, the profile indicating the locations of the user interface at which components for token interaction are presented.

[0063] A2. The method according to the foregoing embodiment, wherein the one or more first results include one or more first signal strength values corresponding to the one or more first token interactions.

[0064] A3. The method according to any one of the foregoing embodiments of A1 - A2, wherein the one or more second locations are locations of the user interface at which the presentation of a component is predicted to evoke a token interaction that satisfies a signal strength threshold.

[0065] A4. The method according to any one of the foregoing embodiments of A1 - A3, wherein the one or more first token interactions include a wireless connection between the token and the user device.

[0066] A5. The method according to any one of the foregoing embodiments of A1 - A4, wherein the token includes a transmitting antenna.

[0067] A6. The method according to any one of the foregoing embodiments of A1 to A5, wherein the token comprises a transaction card.

[0068] A7. The method according to any one of the foregoing embodiments of A1 to A6, wherein the user interface of the user device comprises a display.

[0069] A8. The method according to the foregoing embodiment, wherein the rendering of the one or more first components comprises showing the one or more first components on the display.

[0070] A9. The method according to any one of the foregoing embodiments of A1 to A8, wherein the user device comprises a user handheld device.

[0071] A10. The method according to any one of the foregoing embodiments of A1 to A8, wherein the user device comprises a fixed user device.

[0072] A11. The method according to any one of the foregoing embodiments of A1 to A8, wherein the user device comprises a desktop computer, a laptop computer, a tablet computer, a point-of-sale device, a smart phone or a wearable device.

[0073] A12. The method according to any one of the foregoing embodiments of A1 to A11, wherein the one or more first components or the one or more second components comprise one or more icons.

[0074] A13. The method according to any one of the foregoing embodiments of A1 to A12, wherein the one or more first components or the one or more second components comprise a token outline.

[0075] A14. The method according to the foregoing embodiment, wherein the token outline comprises an illustration representing the token outline.

[0076] A15. The method according to embodiment A13, wherein the token outline comprises an illustration representing the orientation of the token relative to the user device.

[0077] A16. The method according to any one of the foregoing embodiments of A1 to A15, wherein the one or more first components or the one or more second components comprise a token target.

[0078] A17. The method according to the foregoing embodiment, wherein the token target comprises instructions for the user to interact with the token at the token target with the user device.

[0079] A18. The method according to embodiment A16, wherein the token target includes written instructions for the user to interact with the token at the token target using the user device.

[0080] A19. The method according to embodiment A16, wherein the token target includes visual instructions for the user to interact with the token at the token target using the user device.

[0081] A20. The method according to any one of the foregoing embodiments of A1 - A19, wherein the profile includes one or more user attributes or one or more guidance profiles.

[0082] A21. The method according to embodiment 20, wherein each of the one or more user devices includes a device type.

[0083] A22. The method according to embodiment 20, wherein each of the one or more tokens includes a token type.

[0084] A23. The method according to embodiment 20, wherein the one or more user attributes include user accuracy.

[0085] A24. The method according to embodiment 20, wherein each of the one or more guidance profiles is associated with one or more device types and one or more token types.

[0086] A25. The method according to embodiment 20, wherein each of the one or more guidance profiles indicates the position for presenting the component based on the user device type and the token type.

[0087] A26. The method according to any one of the foregoing embodiments of A1 - A25, wherein the presentation of the one or more first components at the one or more first positions is based on the position indicated by the profile.

[0088] A27. The method according to any one of the foregoing embodiments of A1 - A26, wherein the presentation of the one or more second components at the one or more second positions is based on the position indicated by the profile and the first feedback.

[0089] A28. The method according to any one of the foregoing embodiments of A1 - A27, wherein obtaining the one or more second positions of the user interface includes identifying the probability of reaching a signal strength threshold during the token interaction at each interface position included in the token interaction dataset.

[0090] A29. The method according to any one of the foregoing embodiments A1 - A27, wherein determining one or more second positions includes identifying a set of positions where the token interaction may reach a signal strength threshold and associating a confidence score with each position in the set of positions.

[0091] A30. The method according to any one of the foregoing embodiments A1 - A27, wherein determining one or more second positions includes inputting the first feedback into a neural network to cause the neural network to provide the one or more second positions.

[0092] A31. The method according to any one of the foregoing embodiments A1 - A30, further comprising: determining, based on the first feedback, a set of offsets for a first position among the one or more first positions via a prediction model; and wherein obtaining the set of positions includes determining the set of positions by offsetting the first position with the set of offsets.

[0093] A32. The method according to any one of the foregoing embodiments A1 - A31, wherein obtaining the first feedback related to the one or more first token interactions of the token includes accessing a second profile associated with a second user.

[0094] A33. The method according to the foregoing embodiment, wherein the second profile associated with the second user indicates the position of a second user interface at which a component for second user token interaction is presented, the second user interface being different from the user interface.

[0095] A34. The method according to embodiment A32, wherein the second user interface is associated with a second user device, and wherein the second user device has physical dimensions different from those of the user device.

[0096] A35. The method according to the foregoing embodiment, wherein the second profile associated with the second user indicates the position of a second user interface at which a component for second user token interaction for a second token is presented, the second token being different from the token.

[0097] A36. The method according to the foregoing embodiment, wherein each of the token and the second token has a transmitting antenna, and wherein the transmitting antenna of the token is in a different orientation from the transmitting antenna of the second token.

[0098] A37. The method according to any one of the foregoing embodiments A1 - A36, wherein the one or more first results further include historical interaction information, the historical interaction information including historical signal strength - related results corresponding to historical token interactions.

[0099] B1. A method, comprising: obtaining a token interaction data set, the token interaction data set including (i) interface location data indicating an interface location at which a given interface component is presented to a set of users, and (ii) result data, the result data being signal strength related results corresponding to token interactions performed by the set of users related to the presentation of the given interface component; and determining, based on the token interaction data set, via one or more prediction models, one or more locations at which the presentation of an interface component on a user device of a given device type is predicted to evoke a token interaction that meets a signal strength threshold.

[0100] B2. The method according to the foregoing embodiment, wherein the token interaction data set is associated with one or more token types.

[0101] B3. The method according to any one of the foregoing embodiments B1 - B2, wherein the token interaction includes wireless communication between the user device and one or more tokens.

[0102] B4. The method according to any one of the foregoing embodiments B1 - B3, further comprising presenting the interface component at the one or more locations and obtaining feedback from the token interaction between the user device and the one or more tokens at the presented interface component.

[0103] B5. The method according to any one of the foregoing embodiments B1 - B4, further comprising updating the token interaction data set based on the feedback.

[0104] B6. The method according to any one of the foregoing embodiments B1 - B5, wherein determining the one or more locations includes identifying the probability that the signal strength threshold will be reached during the token interaction at each of the interface locations included in the token interaction data set.

[0105] B7. The method according to any one of the foregoing embodiments B1 - B5, wherein determining the one or more locations includes identifying a set of locations at which the token interaction may reach the signal strength threshold and associating a confidence score with each location in the set of locations.

[0106] B8. The method according to any one of the foregoing embodiments B1 - B5, wherein determining the one or more locations includes inputting the token interaction data set into a neural network to cause the neural network to provide the one or more locations.

[0107] B9. The method according to any one of the foregoing embodiments B1 - B8, wherein the token interaction data set further includes interface positions where interface components have not been presented.

[0108] B10. The method according to any one of the foregoing embodiments B1 - B9, wherein obtaining the token interaction data set further includes: a first data subset that indicates (i) an interface position where a given interface component is presented on a first user device of a first device type, and (ii) signal strength - related results corresponding to token interactions of the first user device related to the presentation of the given interface component on the first user device; and a second data subset that indicates (i) an interface position where a given interface component is presented on a second user device of a second device type, and (ii) signal strength - related results corresponding to token interactions of the second user device related to the presentation of the given interface component on the second user device.

[0109] B11. The method according to the foregoing embodiment, wherein the first device type has a different physical dimension from the second device type.

[0110] B12. The method according to embodiment B10 or B11, wherein the first device type has a wireless token reader at a first location relative to the center of the first device type, and the second device type has a wireless token reader at a second location relative to the center of the second device type, and the second relative location is different from the first relative location.

[0111] B13. The method according to embodiment B10 or B11, wherein the token interaction with the first user device or the second user device includes corresponding token interactions with different token types of the first user device or the second user device, and each of the different token types has a transmitting antenna located at a different position from the transmitting antennas of one or more other token types among the different token types.

[0112] B14. The method according to any one of the foregoing embodiments B1 - B13, wherein the one or more prediction models are selected from a plurality of prediction models corresponding to different device types, and the prediction models are used to obtain the one or more positions.

[0113] B15. The method according to any one of the foregoing embodiments B1 - B14, wherein based on the token type of the token, the one or more prediction models are selected from a plurality of prediction models corresponding to different token types, and the prediction models are used to obtain the one or more positions.

[0114] C1. A tangible non-transitory machine-readable medium storing instructions which, when executed by a data processing apparatus, cause the data processing apparatus to perform operations including the operations of any of the foregoing method embodiments.

[0115] C2. A system comprising: one or more processors; and a memory storing instructions which, when executed by the processors, cause the processors to implement operations including the operations of any of the foregoing method embodiments.

Claims

1. A system for improving the signal strength of wireless token interactions across multiple device types and short-range radio frequency (RF) token antenna designs, the system comprising: One or more processors programmed with computer program instructions that, when executed, cause operations including: Selecting a neural network from a plurality of neural networks corresponding to different device types and different token types with different RF token antenna designs, based on the device type of a user device and the token type of the token; Initializing ground truth inputs for the neural network during a test rendering including a plurality of test rounds, the ground truth inputs including initial signal strength feedback for an initial token interaction of the token with an initial guidance icon presented at an initial interaction area of a user interface of the user device; Performing the following operations during each of the plurality of test rounds: During the round of the test rendering, providing the ground truth inputs to the neural network such that the neural network generates (i) a set of interaction areas of the user interface predicted to meet a signal strength threshold, and (ii) a set of confidence scores associated with the set of interaction areas; Selecting, based on the set of confidence scores, an interaction area from the set of interaction areas to be tested during the round, the interaction area being selected as superior to other interaction areas of the set of interaction areas based on the confidence score associated with the interaction area being greater than the confidence scores associated with the other interaction areas; And During the round, presenting a guidance icon at the selected interaction area and not presenting the guidance icon at the other interaction areas, and updating the ground truth inputs to include (i) the initial signal strength feedback and (ii) signal strength feedback for a token interaction of the token with the guidance icon presented at the selected interaction area; And Generating an interaction guidance profile associated with a user of the user device based on the initial signal strength feedback and the signal strength feedback from the plurality of test rounds, the interaction guidance profile indicating interaction areas of the user interface at which guidance icons for token interactions of the token are presented.

2. The system of claim 1, wherein the operations further include: Obtaining a token interaction data set including (i) interface area data indicating interface areas at which icons are presented to a set of users, and (ii) signal strength data indicating signal strength values corresponding to token interactions by the set of users related to the presentation of the icons; Providing the interface area data as an input to the neural network to cause the neural network to predict signal strength values corresponding to the token interactions; And Provide the signal strength data as a reference feedback to the neural network, and the neural network updates one or more weights of the neural network based on the signal strength data. Wherein, after updating the one or more weights of the neural network, initialize the ground truth input for the neural network.

3. A method, the method comprising: Obtain first feedback related to one or more first token interactions of a token, the one or more first token interactions of the token occur in relation to the presentation of one or more first interface components at one or more first positions of a user interface of a user device, and the first feedback indicates one or more first signal strength values corresponding to the one or more first token interactions. Based on the first feedback, obtain, via a prediction model, (i) a set of positions of the user interface at which the presentation of an interface component is predicted to evoke a token interaction that satisfies a signal strength threshold, and (ii) a set of confidence scores associated with the set of positions. Select, based on the set of confidence scores, one or more positions in the set of positions to be tested during a test presentation, and based on the set of confidence scores, the one or more positions are selected as being superior to one or more other positions in the set of positions. Cause the presentation of one or more second interface components at the selected positions of the user interface, and obtain second feedback related to one or more second token interactions of the token, the one or more second token interactions of the token occur in relation to the presentation of the one or more second interface components, and the second feedback indicates one or more second signal strength values corresponding to the one or more second token interactions. And Update a profile associated with a user of the user device based on the first feedback and the second feedback, the profile indicating positions of the user interface at which interface components for token interactions are presented.

4. The method according to claim 3, further comprising: Obtain a token interaction data set, the token interaction data set including (i) interface position data indicating interface positions at which a given interface component is presented to a set of users, and (ii) result data indicating signal strength related results corresponding to token interactions by the set of users in relation to the presentation of the given interface component. And Perform configuration of the prediction model based on the token interaction data set. Wherein, the set of positions and the set of confidence scores are obtained after the configuration of the prediction model.

5. The method according to claim 3, further comprising: Determine, based on the first feedback, a set of offsets for a first position among the one or more first positions via the prediction model. And Wherein, obtaining the set of positions includes determining the set of positions by offsetting the first position with the set of offsets.

6. The method according to claim 3, further comprising: Obtain a token interaction data set, the token interaction data set including: A first data subset that indicates (i) an interface location at which a given interface component is presented on a first user device of a first device type, and (ii) a signal strength related result corresponding to a token interaction with the first user device that is related to the presentation of the given interface component on the first user device; and A second data subset that indicates (i) an interface location at which a given interface component is presented on a second user device of a second device type, and (ii) a signal strength related result corresponding to a token interaction with the second user device that is related to the presentation of the given interface component on the second user device, wherein the first device type has a different physical dimension than the second device type; based on the token interaction data set, one or more common locations are determined via one or more prediction models, at which the presentation of the interface components on the first user device and the second user device is predicted to evoke a token interaction that meets the signal strength threshold; and Based on the one or more common locations, causing the presentation of the one or more first interface components at one or more first locations of the user interface, wherein the one or more common locations include the one or more first locations of the user interface.

7. The method according to claim 6, wherein The first device type has a wireless token reader at a first location relative to the center of the first device type, and the second device type has a wireless token reader at a second location relative to the center of the second device type, and the second relative location is different from the first relative location.

8. The method according to claim 6, wherein, The token interaction with the first user device or the second user device includes a corresponding token interaction with different token types of the first user device or the second user device, and wherein each token type of the different token types has a transmitting antenna, and the transmitting antenna is in a different location from the transmitting antennas of one or more other token types of the different token types.

9. The method according to claim 3, further comprising: Based on the device type of the user device, selecting the prediction model for obtaining the set of locations from a plurality of prediction models corresponding to different device types, wherein each device type of the different device types has a different physical dimension from one or more other device types of the different device types.

10. The method according to claim 3, further comprising: Based on the token type of the token, selecting the prediction model for obtaining the set of locations from a plurality of prediction models corresponding to different token types, wherein each token type of the different token types has a transmitting antenna, and the transmitting antenna is in a different location from the transmitting antennas of one or more other token types of the different token types.

11. One or more non-transitory computer-readable media comprising instructions that, when run by one or more processors, cause operations that include: Obtain first feedback related to one or more first token interactions of a token, the one or more first token interactions of the token occurring in relation to the presentation of one or more first interface components at one or more first positions of a user interface of a user device, the first feedback indicating one or more first signal strength related results corresponding to the one or more first token interactions; Based on the first feedback, obtain one or more second positions of the user interface; Cause the presentation of one or more second components at the one or more second positions of the user interface and obtain second feedback related to one or more second token interactions of the token, the one or more second token interactions of the token occurring in relation to the presentation of the one or more second interface components, the second feedback indicating one or more second signal strength related results corresponding to the one or more second token interactions; and Update a profile associated with a user of the user device based on the first feedback and the second feedback, the profile indicating positions of the user interface at which components for token interaction are presented.

12. The one or more non-transitory computer-readable media according to claim 11, wherein, The instructions also cause an operation including the following: Analyze the first feedback for comparative feedback, the comparative feedback including one or more comparative token interactions of a comparative token, the one or more comparative token interactions of the comparative token occurring in relation to the presentation of one or more comparative components at the one or more first positions of the user interface of a comparative user device; Identify one or more first feedback results that are less than a threshold result generated by the comparative feedback; Generate an offset based on the one or more first feedback results and the threshold result; and Obtaining the one or more second positions of the user interface further includes applying the offset to the first feedback.

13. The one or more non-transitory computer-readable media according to claim 11, wherein, Obtaining the first feedback related to the one or more first token interactions includes accessing a second profile associated with a second user.

14. The one or more non-transitory computer-readable media of claim 13, wherein, The second profile associated with the second user indicates positions of a second user interface at which components for second user token interaction are presented, the second user interface being different from the user interface.

15. The one or more non-transitory computer-readable media according to claim 14, wherein, The second user interface is associated with a second user device, and wherein the second user device has physical dimensions different from those of the user device.

16. The one or more non-transitory computer-readable media according to claim 13, wherein, The second profile associated with the second user indicates positions of the second user interface at which components for second user token interaction of a second token are presented, the second token being different from the token.

17. The one or more non-transitory computer-readable media according to claim 16, wherein, The token and the second token each have a transmitting antenna, and wherein the transmitting antenna of the token is in a different orientation from the transmitting antenna of the second token.

18. The one or more non-transitory computer-readable media according to claim 11, wherein, Obtaining the one or more second positions of the user interface further includes: Based on the first feedback, generate a second signal strength related result prediction via a prediction model, the second signal strength related result prediction including a result probability associated with each of the one or more second positions of the user interface; and Identify the one or more second locations that identify the associated result probabilities having a result probability greater than a threshold.

19. The one or more non-transitory computer-readable media according to claim 11, wherein, The one or more first feedback results further include historical interaction information, the historical interaction information including historical signal strength related results corresponding to historical token interactions.

20. The one or more non-transitory computer-readable media according to claim 11, wherein Obtaining the first feedback associated with the one or more first token interactions includes accessing the profile.

Images