Processing method and apparatus

Abstract

The disclosure provides a processing method and device, which are applied to the technical field of terminals. The processing method is applied to a first electronic device, and the method comprises the following steps: obtaining target information of a target user, wherein the target information comprises at least one of environmental information in which the target user is currently located and current physiological information of the target user; inputting the target information into a large language model to obtain decision information of at least one commodity for the target user, wherein the decision information represents that a transaction of the at least one commodity currently meets an expectation of the target user; and in response to the target user confirming the decision information, generating target payment information, wherein the target payment information is used for completing payment of the at least one commodity.

Description

Technical Field

[0001] This disclosure relates to the field of terminal technology, and in particular to a processing method and apparatus. Background Technology

[0002] Currently, users' shopping decisions often rely on subjective judgment, and the shopping process still requires users to make their own choices, resulting in low shopping efficiency. Summary of the Invention

[0003] In view of this, the present disclosure provides a processing method and apparatus.

[0004] According to a first aspect of this disclosure, a processing method is provided, applied to a first electronic device, the method comprising: obtaining target information of a target user, the target information including at least one of the target user's current environmental information and current physiological information; inputting the target information into a large language model to obtain decision information for at least one item for the target user, the decision information representing that the transaction of at least one item currently meets the target user's expectations; and generating target payment information in response to the target user confirming the decision information, the target payment information being used to complete the payment for at least one item.

[0005] According to embodiments of this disclosure, if the first electronic device has an authentication function, in response to the target user confirming decision information, generating target payment information includes: in response to obtaining decision information, generating a first authentication request from the first electronic device regarding the target user, authenticating the target user, and generating target payment information if the authentication is successful.

[0006] According to embodiments of this disclosure, if the first electronic device does not have an authentication function, in response to the target user confirming the decision information, target payment information is generated, including: in response to obtaining the decision information, generating instruction information, the instruction information being used to instruct the target user to be authenticated through the second electronic device; in response to receiving confirmation information, generating target payment information, the confirmation information indicating that the second electronic device has successfully authenticated the target user.

[0007] According to embodiments of this disclosure, the method further includes: sending target payment information to a second electronic device to display the target payment information in a display area of ​​the second electronic device.

[0008] According to embodiments of this disclosure, the large language model is obtained through the following operations: obtaining multiple sample data, the sample data including the target user's historical information, the historical information including historical environmental information, historical physiological information corresponding to the historical environmental information, and historical transaction information, the historical transaction information including historical purchase information and historical payment information; inputting the historical environmental information and historical physiological information into the large language model to obtain predicted transaction information corresponding to each sample data, the predicted transaction information including predicted purchase information and predicted payment information; updating the large language model according to the difference between the predicted transaction information and the historical transaction information, until the large language model converges, thus obtaining the trained large language model.

[0009] A second aspect of this disclosure provides a processing method applied to a second electronic device, the method comprising: displaying the target payment information in a display area of ​​the second electronic device in response to receiving target payment information.

[0010] According to embodiments of this disclosure, the method further includes: in response to a read operation on target payment information, generating a second authentication request for a target user, authenticating the target user, and, if the authentication is successful, confirming that a second electronic device has completed payment for at least one item.

[0011] According to embodiments of this disclosure, if the first electronic device does not have an authentication function, the method further includes: in response to receiving an instruction message, generating a third authentication request for the target user regarding decision information, authenticating the target user, and if the authentication is successful, generating confirmation information and sending it to the first electronic device, wherein the confirmation information is used by the first electronic device to generate target payment information.

[0012] A third aspect of this disclosure provides a processing apparatus applied to a first electronic device, comprising: an acquisition module for acquiring target information of a target user, the target information including at least one of the target user's current environmental information and current physiological information; an input module for inputting the target information into a large language model to obtain decision information for at least one item for the target user, the decision information indicating that the transaction of at least one item currently meets the target user's expectations; and a generation module for generating target payment information in response to the target user confirming the decision information, the target payment information being used to complete the payment for at least one item.

[0013] A fourth aspect of this disclosure provides a processing apparatus for a second electronic device, comprising: a display module for displaying target payment information in a display area of ​​the second electronic device in response to receiving target payment information.

[0014] A fifth aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the processing method described above.

[0015] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0016] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0017] Figure 1 A flowchart illustrating a processing method according to an embodiment of the present disclosure is shown, wherein the method is applied to a first electronic device;

[0018] Figure 2 A schematic diagram illustrating a processing method according to an embodiment of the present disclosure is shown.

[0019] Figure 3 A schematic block diagram of a processing apparatus according to an embodiment of the present disclosure is shown, wherein the method is applied to a first electronic device;

[0020] Figure 4 The schematic diagram illustrates a structural block diagram of a processing apparatus according to an embodiment of the present disclosure, wherein the method is applied to a second electronic device;

[0021] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a processing method according to an embodiment of the present disclosure. Detailed Implementation

[0022] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0023] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0024] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0025] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0026] This disclosure provides a processing method and apparatus. Before introducing the technical solutions provided by this disclosure, the relevant technologies involved in this disclosure will be described first.

[0027] Currently, users' shopping decisions often rely on subjective judgment, and the shopping process still requires users to make their own choices, resulting in low shopping efficiency.

[0028] For example, shopping malls offer a wide variety of goods at varying prices. During the shopping process, users often want to calculate or categorize the final cost of their selected items. If they see discounts or other offers, they can only calculate them from memory. With many items to choose from, the calculation of prices and discounts becomes difficult to grasp, hindering effective purchasing decisions. Furthermore, during payment, users may not be aware of the discounts and account information for multiple payment methods, leading to less than ideal payment results.

[0029] The following will be through Figures 1-2 The processing method of the embodiments of this disclosure will be described in detail.

[0030] The processing method of this disclosure embodiment is applied to a first electronic device.

[0031] For example, the first electronic device may be a terminal device with data processing and communication capabilities. The first electronic device may be a different device from the second electronic device. For instance, the first electronic device may be a wearable device, such as smart glasses, a smartwatch, etc.

[0032] The second electronic device can be a device with a display screen and payment functionality. The second electronic device can also be a device capable of pairing with the first electronic device. For example, the second electronic device can be a handheld mobile device, such as a mobile phone or tablet.

[0033] Figure 1A flowchart illustrating a processing method according to an embodiment of the present disclosure is shown, wherein the method is applied to a first electronic device. Figure 2 A schematic diagram of a processing method according to an embodiment of the present disclosure is shown.

[0034] like Figure 1 As shown, the processing method of this embodiment includes operations S110 to S130.

[0035] In operation S110, target information of the target user is obtained, including at least one of the target user's current environmental information and current physiological information.

[0036] In operation S120, the target information is input into the large language model to obtain decision information for at least one product for the target user. The decision information indicates that the transaction of at least one product currently meets the expectations of the target user.

[0037] In operation S130, in response to the target user's confirmation decision information, target payment information is generated, which is used to complete the payment for at least one item.

[0038] The decision information is generated by reasoning from a large language model, representing that the transaction of at least one item currently meets the target user's expectations. The first electronic device provides the large language model with collected current environmental and / or physiological information of the target user, which then performs reasoning.

[0039] For example, environmental information can be descriptive data about the target user's current external environment, reflecting the objective scenario in which the user is located. For instance, environmental information includes, but is not limited to: geographic location information (such as GPS coordinates, city name, specific location), current time information (such as date, time, holiday markers), weather information (such as temperature, humidity, weather conditions), and scene semantic information (such as the user's current location being a gym, supermarket, airport, etc.). For example, the smart glasses worn by the target user obtain information about the target user's current location at an outdoor sports venue in a certain city, and simultaneously obtain information about the current temperature being 35 degrees Celsius and the weather being sunny and hot by calling a weather interface. This data together constitutes the target user's environmental information.

[0040] Physiological information can be biometric data reflecting the current physical state of a target user. For example, physiological information includes, but is not limited to: heart rate, blood oxygen saturation, skin conductivity (reflecting the degree of sweating), body temperature, steps taken, exercise intensity, and sleep status. This physiological information can be collected in real time by sensors integrated into a first electronic device. For instance, if the smart glasses worn by the target user detect that their current heart rate is 148 beats per minute and their skin conductivity shows excessive sweating, it can be determined that the user is currently in a state of high-intensity exercise; this data constitutes the target user's physiological information.

[0041] It should be noted that the target information may include only environmental information, only physiological information, or both, thus taking into account the needs of devices with different hardware configurations and different application scenarios.

[0042] A Large Language Model (LLM) is an artificial intelligence model trained on massive amounts of text data, possessing the ability to understand and generate natural language. The LLM undertakes the core functions of semantic understanding and reasoning decision-making regarding target information. The LLM can be deployed locally on a primary electronic device or on a cloud server connected to the primary electronic device. The primary electronic device calls the inference service of the cloud-based LLM through a network interface.

[0043] In some embodiments, the data provided to the large language model undergoes sensitive field filtering and / or de-identification processing. For example, this sensitive field filtering and / or de-identification processing includes: downgrading the precision of location data (e.g., downgrading from GPS coordinates to city / business district labels), dividing physiological data into intervals (e.g., converting heart rate from a specific value to an interval label), anonymizing or tokenizing user identifiers, and providing only the minimum necessary fields relevant to the current decision to the large language model. In some embodiments, the first electronic device may also locally convert the raw sensor data into scene semantic tags (scene_tag) before providing it to the large language model to reduce the amount of raw sensitive data.

[0044] Decision information is the product purchase decision output by the large language model based on target information, meaning whether the current timing is suitable for the target user to purchase the product. For example, decision information may include the recommended product name, product price, reason for recommendation, and recommended quantity.

[0045] The large language model operates as an information processing module. Its input is structured target information data automatically collected and formed by the first electronic device, and its output is structured decision data for subsequent processing by the first electronic device. The decision data includes at least status identifier information indicating whether the transaction triggering conditions are met, enabling the first electronic device to perform corresponding control operations based on the status identifier.

[0046] The transaction timing is appropriate, based on the comprehensive judgment of the large language model, which indicates that purchasing the product can meet the user's potential needs under the current environmental and / or physiological conditions.

[0047] "Target user confirmation of decision information" refers to the target user's active acceptance of the product purchase suggestion output by the large language model, thereby triggering the payment process. For example, the confirmation action could be clicking the "Confirm Purchase" button on a touchscreen, using the voice command "Confirm," or a gesture operation.

[0048] The target payment information is not directly generated by the large language model, but rather by the first electronic device after detecting that the transaction triggering conditions indicated by the decision information are met and receiving confirmation from the target user, following a preset payment processing flow. Therefore, the transaction processing is executed by the device-side control logic, ensuring the controllability and security of the payment process.

[0049] The target payment information is a data set generated by the first electronic device after user confirmation, used to drive the payment process. In some embodiments, the target payment information may include a product order identifier, payment amount, payment account information, delivery address (for products requiring delivery), and payment channel identifier (such as mobile payment or bank card payment). For example, after user confirmation, the first electronic device automatically retrieves the user's pre-linked mobile payment account, generates target payment information containing the product SKU, amount of 3.5 yuan, and payment channel of a certain mobile payment platform, and submits this information to the payment server to complete the deduction. The entire process does not require the user to manually fill in any payment elements.

[0050] In one example, refer to Figure 2 User A's smart glasses acquire information about the target user's current location at an outdoor sports venue in a certain city. Simultaneously, by accessing a weather interface, the glasses obtain the current temperature as 35 degrees Celsius and the weather as sunny and hot (environmental information). The smart glasses also detect the target user's current heart rate as 148 beats per minute and skin conductivity indicating profuse sweating, thus determining that User A is currently in a state of high-intensity exercise (physiological information). The environmental and physiological information are input into a large language model, which infers that User A is in a post-exercise hydration need scenario and outputs the decision information: "It is recommended to purchase one bottle of sports drink (500ml). This transaction meets the user's expectation of replenishing electrolytes." User A views the decision information displayed on the smart glasses screen ("It is recommended to purchase a sports drink. Confirm purchase?") and nods to confirm the decision information. After User A confirms, the smart glasses automatically retrieve the user's pre-linked mobile payment account and generate a payment QR code for a mobile payment platform. The purchase of the goods can be completed by scanning the payment QR code.

[0051] The above technical solutions can reduce the number of manual interaction steps on the terminal side, shorten the triggering path of the payment process, thereby reducing the operational complexity of the terminal device in the transaction processing process and improving the transaction processing efficiency and the stability of the device-side control.

[0052] Understandably, by introducing a large language model to perform semantic understanding and reasoning on the target user's real-time environmental and physiological information, it is possible to proactively trigger commodity transactions at the appropriate time and based on the user's real needs, significantly reducing the user's decision-making costs and operational paths, and realizing a proactive intelligent business interaction experience.

[0053] In some embodiments, the target information may also include the target user's first historical behavior information.

[0054] For example, the first historical behavioral information refers to the behavioral data records generated by the target user before the current interaction time. For instance, the first historical behavioral information includes, but is not limited to, historical purchase information and historical activity information.

[0055] For example, large language models can match the target user's preferred brand, specifications, and price range based on the target user's environmental information, physiological information, and first historical behavior information, thereby accurately targeting the specific product that best meets the user's expectations.

[0056] As described above, if the first electronic device has an authentication function, in operation S130, in response to the target user confirming the decision information, target payment information is generated. In one possible implementation, the operation may further include: in response to obtaining the decision information, generating a first authentication request from the first electronic device regarding the target user, authenticating the target user, and generating target payment information if the authentication is successful.

[0057] For example, the identity verification function refers to a functional module integrated within the first electronic device for real-time verification of the legitimacy of the target user's identity. For instance, the identity verification function includes, but is not limited to, biometric verification methods such as iris recognition, facial recognition, and voiceprint recognition.

[0058] The first identity verification request refers to the identity verification instruction initiated by the first electronic device to the target user after obtaining decision information. This is used to confirm account operation permissions before the generation of target payment information. For example, the first identity verification request can notify the target user that identity verification is required through on-screen visual prompts, voice announcements, or device vibration feedback. The target user responds to the first identity verification request, cooperates with the first electronic device to complete the collection of corresponding biometric data, and the first electronic device executes feature comparison and verification logic, determining whether identity verification is successful based on the comparison results.

[0059] It should be noted that if the target user's identity verification fails, the first electronic device will terminate the payment process and provide the target user with verification failure information through appropriate prompts. The target payment information will not be generated.

[0060] In one example, continuing the application scenario of User A at an outdoor sports venue, User A's smart glasses have iris recognition capabilities. After obtaining decision-making information, the smart glasses initiate an initial identity verification request to User A, prompting on the screen, "Please look at the lens camera to complete identity verification." User A follows the prompt and looks at the built-in camera module of the smart glasses. The smart glasses collect User A's iris feature data and compare it with locally stored iris baseline data to confirm successful identity verification. After successful identity verification, the smart glasses automatically retrieve User A's pre-linked mobile payment account, generate target payment information including product information and payment amount, and present it as a payment QR code. User A completes the purchase of the sports drink by scanning the payment QR code.

[0061] Understandably, by introducing a first identity verification request on the first electronic device side, the identity of the user initiating the payment operation can be effectively verified before the target payment information is generated. While retaining the convenience of intelligent decision-making by the big language model, this further strengthens the security of payment identity on the device side.

[0062] As described above, if the first electronic device does not have authentication functionality, in operation S130, in response to the target user confirming the decision information, target payment information is generated. In one possible implementation, this operation may further include: in response to obtaining the decision information, generating instruction information to instruct the target user to be authenticated via the second electronic device; and in response to receiving confirmation information, generating target payment information, the confirmation information indicating that the second electronic device has successfully authenticated the target user.

[0063] For example, the second electronic device refers to a terminal device that establishes a communication connection with the first electronic device, and is used to perform identity verification for the target user when the first electronic device lacks authentication capabilities. For instance, the second electronic device includes, but is not limited to, portable terminal devices with authentication modules such as smartphones, tablets, and smartwatches. The communication connection methods between the first and second electronic devices include, but are not limited to, short-range wireless communication methods such as Bluetooth, Wi-Fi, and near-field communication.

[0064] The instruction information refers to the identity verification delegation instruction sent by the first electronic device to the second electronic device after obtaining the decision information, which is used to notify the second electronic device that an identity verification operation needs to be performed on the target user.

[0065] The confirmation message refers to the result notification sent back to the first electronic device after the second electronic device completes the authentication of the target user, which indicates that the authentication of the target user on the second electronic device side has been successful.

[0066] It should be noted that if the second electronic device fails to verify the identity of the target user, the second electronic device will not send a confirmation message to the first electronic device, or will send a verification failure notification to the first electronic device. The first electronic device will then terminate the payment process and provide feedback on the verification failure to the target user through appropriate prompts. The target payment information will not be generated.

[0067] In one example, continuing the application scenario of User A at an outdoor sports venue, User A's smart glasses do not have any identity verification function. After obtaining decision information through the smart glasses, User A sends an instruction via Bluetooth to User A's smartphone (a second electronic device). This instruction notifies the smartphone that "the user has confirmed the purchase of a sports drink; please complete identity verification on this device to continue the payment process." Upon receiving the instruction, User A's smartphone automatically displays an identity verification interface, prompting User A to complete identity verification through fingerprint recognition. User A presses the fingerprint recognition area on the smartphone, which compares the collected fingerprint features with pre-stored baseline data to confirm User A's identity verification and sends a confirmation message back to User A's smart glasses. Upon receiving the confirmation message, User A's smart glasses automatically retrieve User A's pre-linked mobile payment account, generate target payment information containing product information and payment amount, and present it in the form of a payment QR code. User A completes the purchase of the sports drink by scanning the payment QR code.

[0068] Understandably, by generating instruction information to delegate the identity verification of the target user to a second electronic device when the first electronic device lacks identity verification capabilities, and generating the target payment information only after receiving confirmation information, it is possible to achieve secure identity verification before payment without relying on the local hardware capabilities of the first electronic device. This extends payment security capabilities to devices without verification hardware, taking into account payment security needs under different hardware configurations, and significantly improving the applicability and security reliability of the solution.

[0069] As described above, the processing method of this embodiment may further include the operation of sending the target payment information to a second electronic device to display the target payment information in the display area of ​​the second electronic device.

[0070] It should be noted that sending the target payment information to the second electronic device for display is to take into account that the display area of ​​the first electronic device may be limited by its device form factor, resulting in a small size and insufficient display brightness. This would make it difficult for external scanning and recognition devices (such as merchant POS terminals) to accurately read the target payment information if it is directly displayed on the first electronic device. The second electronic device usually has a larger and brighter display area, which can more effectively ensure that the target payment information is accurately identified and processed by external devices.

[0071] In one example, continuing the application scenario of User A at an outdoor sports venue, considering the limited display area of ​​the smart glasses lenses and the small size of the displayed payment QR code, which is not conducive to accurate recognition by the scanner at the sports venue's beverage vending machine, the smart glasses, after generating the target payment information, send it via Bluetooth to User A's smartphone (a second electronic device). Upon receiving the target payment information, User A's smartphone automatically displays the payment QR code in full screen. User A points their smartphone screen at the scanner at the beverage vending machine, and the machine recognizes the payment QR code and deducts the payment, thus completing User A's purchase of the sports drink.

[0072] As described above, the large language model in this embodiment is obtained through the following operations: obtaining multiple sample data, including the target user's historical information, which includes historical environmental information, historical physiological information corresponding to the historical environmental information, and historical transaction information, which includes historical purchase information and historical payment information; inputting the historical environmental information and historical physiological information into the large language model to obtain predicted transaction information corresponding to each sample data, which includes predicted purchase information and predicted payment information; updating the large language model based on the difference between the predicted transaction information and the historical transaction information until the large language model converges, thus obtaining the trained large language model.

[0073] For example, historical transaction information includes two parts: historical purchase information and historical payment information. Historical purchase information reflects the product categories, names, and quantities actually purchased by the target user in the corresponding historical scenario; historical payment information reflects the payment channel, amount, and account used by the target user in that transaction. Historical environmental information and historical physiological information serve as input features, while historical transaction information serves as the corresponding real-world label; together, they constitute the input-output pair required for supervised training.

[0074] Predicted transaction information refers to the inference results output by the large language model during training, based on the input historical environmental and physiological information. This includes predicted purchase information and predicted payment information. The difference between the predicted transaction information and historical transaction information reflects the deviation between the large language model's current inference ability and the target user's actual behavior. This difference serves as an update signal, driving iterative adjustments to the large language model's parameters. When the difference decreases to within a preset range after multiple iterations, the large language model's parameters stabilize, indicating convergence and training completion.

[0075] In one example, several sample data points were extracted from user A's historical records. The historical environmental information and historical physiological information of the above sample data were input into the large language model, and the model output the predicted transaction information corresponding to each sample data point. The predicted transaction information of each sample data point was compared with its historical transaction information, and the model parameters were continuously adjusted according to the difference between the two. After multiple rounds of iteration, the large language model converged and the training was completed.

[0076] In some embodiments, the sample data during the training of the large language model may also include the user's second historical behavior, so that during the training process, the second historical behavior, historical environmental information and historical physiological information are input into the large language model, so that the large language model is trained based on the three types of user information and the prediction results are input.

[0077] The processing method of the embodiments of this disclosure will be described in detail below.

[0078] The processing method of this disclosure embodiment is applied to a second electronic device.

[0079] For example, the second electronic device may be a terminal device that is independent of the first electronic device, communicatively connected to the first electronic device, and has receiving and display functions. For instance, the second electronic device includes, but is not limited to, handheld or wearable terminal devices such as smartphones, tablets, and smartwatches that can receive data and display information on a screen.

[0080] The processing method of this embodiment includes operation S210.

[0081] In operation S210, in response to receiving the target payment information, the target payment information is displayed in the display area of ​​the second electronic device.

[0082] For example, the display area refers to the screen area on the second electronic device used to present the target payment information to the target user. For instance, the display area includes, but is not limited to, the touchscreen display of a smartphone, the LCD screen of a tablet computer, or the watch face display area of ​​a smartwatch.

[0083] In one example, consider the scenario where User A confirms their intention to purchase a sports drink at an outdoor sports venue. After User A nods to "confirm," triggering the generation of target payment information, User A's smart glasses (the first electronic device) immediately transmit this information via Bluetooth to User A's smartphone (the second electronic device). Upon receiving the payment information, the smartphone immediately displays a QR code for a mobile payment platform indicating a payment amount of 3.5 yuan. User A then points their smartphone screen towards the merchant's scanner at the checkout counter. After the merchant scans the QR code and confirms receipt, the purchase of the sports drink is successfully completed.

[0084] As described above, the processing method of this embodiment may further include the following operations: in response to a read operation for target payment information, generating a second authentication request for the target user, authenticating the target user, and, if the authentication is successful, confirming that the second electronic device has completed the payment for at least one item.

[0085] For example, the reading operation can be a scanning and recognition operation performed by the payee's terminal on the target payment information displayed in the display area of ​​the second electronic device, indicating that the payee has initiated a request to the second electronic device to obtain the target payment information. For instance, the reading operation includes, but is not limited to: scanning the payment QR code in the target payment information by the payee's terminal camera, or sensing and reading the payment information by a Near Field Communication (NFC) terminal.

[0086] A second authentication request is an identity verification instruction initiated by the second electronic device to the target user after detecting a read operation. It is used to perform a secondary verification of the target user's identity at the payment confirmation node. For example, the verification methods corresponding to the second authentication request include, but are not limited to, fingerprint recognition, facial recognition, iris recognition, and numeric password input. These verification methods can collect the target user's verification information through biometric sensors or input components integrated into the second electronic device and compare it with an identity template pre-stored in the second electronic device.

[0087] It should be noted that the second authentication request is triggered when the target payment information is read, which is different from the authentication operation performed during the generation stage of the target payment information. It belongs to the secondary verification mechanism of the payment confirmation node in the payment process.

[0088] In one example, continuing the scenario of User A mentioned earlier, after User A confirms the purchase of a sports drink, the smart glasses relay the generated payment QR code to User A's mobile phone (a second electronic device), which is then displayed on the phone screen. At the checkout, User A holds the phone screen towards the payment terminal. The cashier scans the payment QR code on the phone screen using the terminal's camera, triggering a read operation for the target payment information. Upon detecting this read operation, the phone immediately displays a second identity verification request, prompting User A to verify their identity with their fingerprint. User A presses their finger onto the phone's fingerprint recognition area. The phone compares the collected fingerprint information with a pre-stored fingerprint template. If the comparison is successful, the phone sends a payment confirmation instruction to the payment server, confirming the payment for the sports drink (3.5 yuan). The phone screen then displays a payment success message.

[0089] Understandably, by triggering a second identity verification request on the second electronic device when the target payment information is read, and introducing secondary identity verification for the target user at the payment confirmation node, the risk of unauthorized payment caused by the loss of the second electronic device or the interception of the target payment information can be effectively prevented, thereby further strengthening the overall security of the payment chain while ensuring the convenience of payment operations.

[0090] As described above, if the first electronic device does not have an authentication function, the processing method of this embodiment may further include the following operations: in response to receiving the instruction information, generating a third authentication request for the target user regarding the decision information, authenticating the target user, and if the authentication is successful, generating confirmation information and sending it to the first electronic device, wherein the confirmation information is used by the first electronic device to generate target payment information.

[0091] For example, the instruction information may be an authentication delegation instruction issued by the first electronic device to the second electronic device after the target user confirms the decision information, when the first electronic device does not have its own authentication function. For example, the instruction information includes, but is not limited to: a verification delegation instruction carrying a summary of the decision information, a verification trigger data packet containing a product order identifier and payment amount, etc., used to notify the second electronic device to perform the authentication operation for the target user on its behalf.

[0092] A third identity verification request is an identity verification instruction initiated by the second electronic device to the target user after receiving the instruction information. It is used to verify the target user's operational intent and the legitimacy of their identity before the generation of target payment information. For example, the verification methods corresponding to a third identity verification request include, but are not limited to, fingerprint recognition, facial recognition, and numeric password input. These verification methods can collect the target user's verification information through biometric sensors or input components integrated into the second electronic device and compare it with an identity template pre-stored in the second electronic device.

[0093] The confirmation information is an authorization credential generated by the second electronic device and sent to the first electronic device after the target user's identity has been verified. It informs the first electronic device that the target user's identity has been confirmed, allowing the first electronic device to generate target payment information. For example, the confirmation information includes, but is not limited to: identity verification pass identifier, verification timestamp, session token, etc.

[0094] It should be noted that the third authentication request described in operation S230 occurs before the target payment information is generated. It belongs to the identity verification mechanism during the payment information generation authorization phase, and is different from the second authentication request triggered when the target payment information is read in operation S220. In scenarios where the first electronic device does not have authentication functionality, the second electronic device, as the entity performing authentication, achieves the purpose of cross-device collaborative payment authorization by feeding back the verification result to the first electronic device in the form of confirmation information.

[0095] In one example, continuing the scenario of User A mentioned earlier, the difference is that User A is currently wearing basic smart glasses (the first electronic device) without biometric recognition capabilities. After the large language model outputs the decision information "It is recommended to purchase one bottle of sports drink (500ml), and the current transaction meets the user's expectation of replenishing electrolytes," User A nods in confirmation. The smart glasses detect User A's confirmation operation. Since it does not have an identity verification function, it cannot verify User A's identity locally. It then sends an instruction message to User A's mobile phone (the second electronic device). This instruction message carries a summary of the decision information to be verified and the payment amount (3.5 yuan). After receiving the above instruction message, the mobile phone immediately initiates a third identity verification request to User A. The mobile phone screen displays the prompt "Please verify your identity to confirm the purchase of sports drink (3.5 yuan)" and activates the facial recognition function. User A faces the mobile phone towards himself. The mobile phone captures User A's facial feature information through the front-facing camera and compares it with the facial recognition template pre-stored in the mobile phone. After the comparison is successful, the mobile phone generates a confirmation message containing a verification success identifier and a session token, and sends the confirmation message back to the smart glasses. After receiving the confirmation message, the smart glasses generate a payment QR code for 3.5 yuan and relay it to the mobile phone screen for the recipient to scan and read, thus completing the payment for the sports drink.

[0096] Based on the above processing method, this disclosure also provides a processing apparatus. The following will be combined with... Figure 3 and Figure 4 The device is described in detail.

[0097] Figure 3 A schematic block diagram of a processing apparatus according to an embodiment of the present disclosure is shown, wherein the method is applied to a first electronic device.

[0098] like Figure 3 As shown, the processing device 300 of this embodiment includes an acquisition module 310, an input module 320, and a generation module 330.

[0099] The acquisition module 310 is used to acquire target information of the target user, including at least one of the target user's current environmental information and current physiological information. In one embodiment, the acquisition module 310 can be used to perform the operation S110 described above, which will not be repeated here.

[0100] The input module 320 is used to input target information into the large language model to obtain decision information for at least one product for the target user. The decision information indicates that the transaction of at least one product currently meets the target user's expectations. In one embodiment, the input module 320 can be used to perform the operation S120 described above, which will not be repeated here.

[0101] The generation module 330 is used to generate target payment information in response to the target user's confirmation decision information. The target payment information is used to complete the payment for at least one item. In one embodiment, the generation module 330 can be used to perform the operation S130 described above, which will not be repeated here.

[0102] Figure 4 A schematic block diagram of a processing apparatus according to an embodiment of the present disclosure is shown, wherein the method is applied to a second electronic device.

[0103] like Figure 4 As shown, the processing device 400 in this embodiment includes a display module 410.

[0104] The display module 410 is used to display the target payment information in the display area of ​​the second electronic device in response to receiving the target payment information. In one embodiment, the display module 410 can be used to perform the operation S210 described above, which will not be repeated here.

[0105] According to embodiments of this disclosure, any plurality of modules among the obtaining module 310, input module 320, and generating module 330 (display module 410) can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the obtaining module 310, input module 320, and generating module 330 (display module 410) can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any one of the three implementation methods or a suitable combination of any of them. Alternatively, at least one of the acquisition module 310, input module 320, and generation module 330 (display module 410) may be implemented at least partially as a computer program module that can perform corresponding functions when the computer program module is run.

[0106] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a processing method according to an embodiment of the present disclosure.

[0107] like Figure 5As shown, an electronic device 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0108] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 502 and / or RAM 503. It should be noted that programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in one or more memories.

[0109] According to embodiments of this disclosure, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0110] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0111] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 502 and / or RAM 503 and / or one or more memories other than ROM 502 and RAM 503 described above.

[0112] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the processing methods provided in the embodiments of this disclosure.

[0113] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0114] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0115] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0116] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0118] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0119] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A processing method applied to a first electronic device, the method comprising: Obtain target information of the target user, wherein the target information includes at least one of the target user's current environmental information and current physiological information; The target information is input into a large language model to obtain decision information for at least one product for the target user. The decision information indicates that the transaction of the at least one product currently meets the expectations of the target user. In response to the target user confirming the decision information, target payment information is generated, which is used to complete the payment for the at least one item.

2. The method according to claim 1, wherein if the first electronic device has an authentication function, in response to the target user confirming the decision information, target payment information is generated, including: In response to obtaining the decision information, the first electronic device generates a first authentication request for the target user, authenticates the target user, and generates target payment information if the authentication is successful.

3. The method according to claim 1, wherein if the first electronic device does not have an authentication function, in response to the target user confirming the decision information, target payment information is generated, including: In response to obtaining the decision information, an instruction information is generated, which instructs the target user to be authenticated through a second electronic device; In response to receiving confirmation information, target payment information is generated, wherein the confirmation information indicates that the second electronic device has successfully authenticated the target user.

4. The method according to claim 1, further comprising: The target payment information is sent to a second electronic device to be displayed in the display area of ​​the second electronic device.

5. The method according to claim 1, wherein the large language model is obtained through the following operations: Multiple sample data are obtained, including the target user's historical information, which includes historical environmental information, historical physiological information corresponding to the historical environmental information, and historical transaction information, including historical purchase information and historical payment information. The historical environmental information and the historical physiological information are input into the large language model to obtain the predicted transaction information corresponding to each of the sample data. The predicted transaction information includes predicted purchase information and predicted payment information. Based on the difference between the predicted transaction information and the historical transaction information, the large language model is updated until the large language model converges, thus obtaining the trained large language model.

6. A processing method applied to a second electronic device, the method comprising: In response to receiving the target payment information, the target payment information is displayed in the display area of ​​the second electronic device.

7. The method according to claim 6, further comprising: In response to the read operation of the target payment information, a second authentication request for the target user is generated, the target user is authenticated, and if the authentication is successful, the second electronic device is confirmed to have completed the payment for the at least one item.

8. The method according to claim 6, wherein if the first electronic device does not have authentication functionality, the method further comprises: In response to receiving the instruction information, a third authentication request for the target user regarding the decision information is generated, the target user is authenticated, and if the authentication is successful, confirmation information is generated and sent to the first electronic device. The confirmation information is used by the first electronic device to generate target payment information.

9. A processing apparatus applied to a first electronic device, comprising: The acquisition module is used to acquire target information of the target user, the target information including at least one of the target user's current environmental information and current physiological information; An input module is used to input the target information into a large language model to obtain decision information for at least one product for the target user, wherein the decision information indicates that the transaction of the at least one product currently meets the expectations of the target user; A generation module is used to generate target payment information in response to the target user confirming the decision information, the target payment information being used to complete the payment for the at least one item.

10. A processing apparatus applied to a second electronic device, comprising: The display module is used to display the target payment information in the display area of ​​the second electronic device in response to receiving the target payment information.

Images