Transaction processing method and apparatus, electronic device, storage medium, and program product

Abstract

Embodiments of the present application provide a transaction processing method and device, electronic equipment, storage medium and program product, relating to the field of financial technology or other related fields. The method is applied to an end-side SDK integrated on an application program of a mobile terminal device, and the method comprises: receiving transaction information sent by the application program after a user triggers a transaction; if the transaction is an automated transaction, receiving a starting instruction of the application program and responding; determining a state of a target page corresponding to the transaction, and acquiring page information in the case that the target page is in a stable state; sending the page information and the transaction information to an intelligent agent, the intelligent agent determining an operation instruction of the transaction, and receiving and executing the operation instruction fed back by the intelligent agent, so that the automation of the transaction can be realized without custom development by a transaction party. For a third-party transaction, the transaction information and the page information of the third-party transaction can also be acquired, and a corresponding operation instruction is generated to realize automation, thereby reducing the difficulty of automation of the third-party transaction.

Description

Technical Field

[0001] This application relates to the field of financial technology or other related fields, and in particular to a transaction processing method, apparatus, electronic device, storage medium and program product. Background Technology

[0002] With the accelerating pace of demand iteration and the rapid development of large-scale models in the financial industry's mobile applications, customers are increasingly demanding higher levels of intelligence from these applications. Currently, mobile applications in the financial industry offer intelligent application scenarios such as OCR text recognition and intelligent voice assistants for guided dialogue. However, these scenarios still have certain business limitations; for example, repetitive transactions still require manual completion by the user.

[0003] In existing technologies, the trading parties can perform customized development to automate transactions that require repetitive operations, but this is more difficult to implement for third-party transactions. Summary of the Invention

[0004] This application provides a transaction processing method, apparatus, electronic device, storage medium, and program product to solve the technical problem in the prior art where the transaction party needs to carry out customized development to automate transactions that require repetitive operations, but it is difficult to implement for third-party transactions.

[0005] In a first aspect, this application provides a transaction processing method, which is applied to a client-side SDK integrated into an application on a mobile device. The method includes:

[0006] After a user triggers a transaction, the system receives transaction information sent by the application.

[0007] If the transaction is automated, receive the application's start command and respond.

[0008] Determine the state of the target page corresponding to the transaction, and if the target page is in a stable state, obtain the page information of the target page;

[0009] The page information and transaction information are sent to the agent so that the agent can determine the operation instructions for the transaction and receive and execute the operation instructions fed back by the agent.

[0010] Secondly, this application provides a transaction processing method applied to a cloud server, the method comprising:

[0011] The receiving end-side SDK sends page information and transaction information. The page information is obtained by the end-side SDK after the user triggers the transaction, when the target page corresponding to the transaction is in a stable state. The transaction information is used to identify the transaction triggered by the user.

[0012] The system generates transaction operation instructions based on page information and transaction information, and sends these instructions to the client-side SDK so that the client-side SDK can execute the operation instructions.

[0013] Thirdly, this application provides a transaction processing apparatus applied to a client-side SDK, which is integrated into an application on a mobile device. The apparatus includes:

[0014] The first receiving module is used to receive transaction information sent by the application after the user triggers the transaction;

[0015] The first receiving module is also used to receive and respond to the application's start command if the transaction is an automated transaction;

[0016] The first processing module is used to determine the state of the target page corresponding to the transaction, and to obtain the page information of the target page when the target page is in a stable state.

[0017] The processing module is also used to send page information and transaction information to the intelligent agent so that the intelligent agent can determine the operation instructions for the transaction and receive and execute the operation instructions fed back by the intelligent agent.

[0018] Fourthly, this application provides a transaction processing apparatus applied to a cloud server, the apparatus comprising:

[0019] The second receiving module is used to receive page information and transaction information sent by the client-side SDK. The page information is obtained by the client-side SDK after the user triggers the transaction, when the target page corresponding to the transaction is in a stable state. The transaction information is used to identify the transaction triggered by the user.

[0020] The second processing module is used to generate transaction operation instructions based on page information and transaction information, and send the operation instructions to the client-side SDK so that the client-side SDK can execute the operation instructions.

[0021] Fifthly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0022] The memory stores the instructions that the computer executes;

[0023] The processor executes computer-executable instructions stored in memory to implement the method as described in either the first or second aspect.

[0024] In a sixth aspect, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in either the first or second aspect.

[0025] In a seventh aspect, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method of either the first aspect or the second aspect.

[0026] The transaction processing method, apparatus, electronic device, storage medium, and program product provided in this application allow the client-side SDK to receive transaction information sent by the application after a user triggers a transaction. If the transaction is automated, it receives and responds to the application's start command. It determines the state of the target page corresponding to the transaction and, if the target page is in a stable state, obtains the page information of the target page. The page information and transaction information are sent to the intelligent agent, enabling the intelligent agent to generate operation instructions for the transaction. The client-side SDK can receive and execute the operation instructions returned by the intelligent agent, achieving non-intrusive automated operation of business access without requiring customized development by the transaction party, thus improving efficiency and reducing development costs. Furthermore, for third-party transactions, since the embodiments of this application can obtain the transaction information and target page information of the third-party transaction, the intelligent agent can generate corresponding operation instructions, thereby automating third-party transactions, reducing the difficulty of implementing third-party transaction automation, and improving the intelligence of the application and user experience. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0028] Figure 1 A schematic diagram illustrating an application scenario provided in an embodiment of this application;

[0029] Figure 2 A flowchart of a transaction processing method provided in this application embodiment Figure 1 ;

[0030] Figure 3 A flowchart of a transaction processing method provided in this application embodiment Figure 2 ;

[0031] Figure 4 A flowchart illustrating a method for generating operation instructions provided in an embodiment of this application;

[0032] Figure 5 A signaling flowchart of a transaction processing method provided in an embodiment of this application;

[0033] Figure 6 A schematic diagram of the structure of a transaction processing device provided in this application embodiment. Figure 1 ;

[0034] Figure 7 This is a schematic diagram of the structure of a transaction processing device provided in an embodiment of this application;

[0035] Figure 8 This is a schematic diagram of the structure of an electronic device provided in this application.

[0036] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0037] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0038] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize or refuse.

[0039] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0040] It should be noted that the transaction processing methods, devices, electronic devices, storage media, and program products provided in this application can be used in the field of financial technology, or in any field other than financial technology. The application fields of the transaction processing methods, devices, electronic devices, storage media, and program products in this application are not limited.

[0041] As the demand for mobile applications in the financial industry iterates at an accelerated pace and large-scale models develop rapidly, customers are increasingly demanding higher levels of intelligence from their applications. It is advisable to integrate large-scale models into mobile applications and leverage their capabilities to enhance application intelligence.

[0042] Currently, mobile applications in the financial industry include intelligent application scenarios such as OCR text recognition and intelligent voice assistants to complete guided dialogues. However, these application scenarios still have certain business limitations, and there is still room for improvement in the intelligence of transaction processes and user interface interactions. For example, repetitive transactions still need to be completed manually by the user.

[0043] In existing technologies, the parties involved in the transaction can perform customized development to automate transactions that require repetitive operations. However, this approach has issues such as high development costs and difficulty in implementation for third-party transactions.

[0044] The transaction processing method, apparatus, electronic device, storage medium, and program product provided in this application are intended to solve the above-mentioned technical problems of the prior art.

[0045] Figure 1 This is a schematic diagram illustrating an application scenario provided in an embodiment of this application. (Refer to...) Figure 1 As shown, a user's mobile device has an integrated app. The user launches the app by clicking on it, and various transactions can be triggered through the app, such as topping up or claiming coupons. After the user triggers a transaction, the transaction information and the page information of the corresponding target page can be sent to the cloud server. The cloud server can then generate the transaction operation instructions and return them to the mobile device, which can then automatically execute the transaction, thus automating the transaction process.

[0046] In this application, the mobile device can be a mobile phone, tablet computer, or other such device, and the application can be a mobile banking application or other financial applications; this application does not limit the scope of the application.

[0047] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0048] Figure 2 A flowchart of a transaction processing method provided in this application embodiment Figure 1 This method is applied to a client-side SDK, which is integrated into an application on a mobile device. The method includes:

[0049] S201: After the user triggers a transaction, receive the transaction information sent by the application.

[0050] Transaction information includes, but is not limited to, session information, transaction ID, and user commands. Session information is a temporary connection credential generated after the user triggers the application launch, and includes, but is not limited to, session ID, user identity identifier, session validity period, and device information.

[0051] The transaction ID is used to identify the transaction triggered by the current user, and different transactions have different transaction IDs.

[0052] User instructions are commands that trigger a transaction process. In one implementation scenario, users can trigger a transaction through page operations, such as clicking a button or entering text. Alternatively, users can trigger a transaction by entering voice information. This application does not limit the method by which users trigger transactions.

[0053] S202: If the transaction is an automated transaction, receive the application's start instruction and respond.

[0054] In some embodiments, after a user triggers a transaction in the application, the application can determine whether the transaction is an automated transaction. In one implementation scenario, when determining whether a transaction is an automated transaction, the application can obtain a list of automated transactions, which includes at least one automated transaction; the transaction is matched against the list of automated transactions, and if a match is found, the transaction is determined to be an automated transaction.

[0055] An automated transaction list can also be called a whitelist transaction list. In one implementation scenario, an automated transaction list includes the transaction ID corresponding to at least one automated transaction.

[0056] When matching the current transaction with the automated transaction list, specifically, it checks whether the transaction ID of the current transaction is the same as the transaction IDs included in the automated transaction list. In one implementation scenario, if the transaction ID of the current transaction is the same as the transaction ID in the automated transaction list, the match is successful, and the current transaction can be determined to be an automated transaction.

[0057] In another implementation scenario, if the automated transaction list does not include the current transaction, i.e. the match fails, it indicates that the current transaction is a non-automated transaction. In this case, the user's operation can be performed.

[0058] By restricting automated transactions through an automated transaction list, business risks can be reduced. Furthermore, matching the current transaction with the automated transaction list is a quick, convenient, and efficient way to determine if a transaction is automated.

[0059] In one implementation scenario, if the transaction triggered by the user is an automated transaction, the application sends a start command to the client-side SDK to start the client-side SDK before entering the target page corresponding to the transaction.

[0060] S203: Determine the state of the target page corresponding to the transaction, and if the target page is in a stable state, obtain the page information of the target page.

[0061] In one implementation scenario, page information includes, but is not limited to, the Document Object Model (DOM) data of the target page, screenshots of the target page, and other information.

[0062] The DOM data includes information such as the type of elements on the current target page, the position of the elements on the target page, and the attributes of the elements. Elements can include interactive controls and non-interactive controls on the page. Interactive controls include, but are not limited to, buttons, images, input boxes, and text.

[0063] The screenshot of the target page is a screenshot of the visible area of ​​the target page.

[0064] When the target page is in a stable state, the position and size of the elements within the target page no longer change, resulting in higher accuracy in obtaining page information. Furthermore, compared to relying on preset page templates, obtaining page information when the target page is in a stable state allows for flexible adaptation to layout changes, improving flexibility and versatility.

[0065] S204: Send page information and transaction information to the agent so that the agent can determine the operation instructions for the transaction, and receive and execute the operation instructions fed back by the agent.

[0066] In one implementation scenario, when the page information contains a screenshot of the target page, the screenshot can be encoded, for example, using base64 encoding, and then sent to the agent. This simplifies the data transmission process and improves compatibility.

[0067] The agent can run on a cloud server. In one implementation scenario, the agent can be a GUIAgent (Graphical User Interface Agent).

[0068] Operation instructions include one or more commands. Upon receiving these instructions, the client-side SDK can simulate human touch behaviors, such as clicking, inputting, and swiping, to automatically operate the mobile device and automate transactions. For users, repetitive transactions like topping up and claiming coupons can be completed automatically without user intervention, improving the user experience.

[0069] In another implementation scenario, users can also stop the automatic execution of the transaction by clicking "Terminate".

[0070] This embodiment provides a transaction processing method. After a user triggers a transaction, the client-side SDK can receive transaction information sent by the application. If the transaction is an automated transaction, it receives and responds to the application's start command. The state of the target page corresponding to the transaction is determined, and if the target page is in a stable state, the page information of the target page is obtained. The page information and transaction information are sent to the intelligent agent so that the intelligent agent can determine the operation instructions for the transaction. The client-side SDK can receive and execute the operation instructions returned by the intelligent agent, achieving non-intrusive automated operation of business access. No custom development is required from the transaction party, improving efficiency and reducing development costs. Simultaneously, for third-party transactions, this embodiment can also obtain the page information corresponding to the target page of the third-party transaction. Therefore, the intelligent agent can determine the corresponding operation instructions, realizing the automation of third-party transactions, reducing the difficulty of implementing third-party transaction automation, and improving the intelligence of the application and user experience.

[0071] Optionally, determine the state of the target page corresponding to the transaction, including:

[0072] Obtain the target script and inject it into the target page so that the target script can monitor the state of the target page.

[0073] In one implementation scenario, the target script can be injected into the target page after the client-side SDK starts, thereby enabling the monitoring of the target page.

[0074] In one implementation scenario, the target script can monitor whether all network requests have returned during the target page loading process to determine if the target page is in a stable state. If all network requests have returned, it indicates that the target page has been fully loaded, and the position and size of elements within the target page no longer change, meaning the target page is in a stable state. At this point, the client-side bridging SDK can be called to begin retrieving page information from the target page.

[0075] In another implementation scenario, if not all network requests are returned, it indicates that the target page is still in the loading process, and the target page is in an unstable state.

[0076] In one implementation scenario, the target script can be a JS (JavaScript) script. Besides JS scripts, the target script can also be other scripts or tools capable of monitoring the state of the target page; this application does not impose any limitations on this.

[0077] In this embodiment, by injecting the target script into the target page and monitoring the state of the target page through the target script, the accuracy is high. Furthermore, when the target page is detected to be in a stable state, the client-side SDK is notified in a timely manner to obtain page information, thereby improving the efficiency of the transaction process.

[0078] Optionally, transaction processing methods may also include:

[0079] After the user launches the application, it receives and responds to the initialization instructions sent by the application.

[0080] After the user launches the application, the application can send an initialization command to the client-side SDK to initialize the SDK. During the initialization process, the client-side SDK can perform a series of basic configurations, including but not limited to establishing a connection with the cloud server, loading necessary resource files, and obtaining permissions.

[0081] After the client-side SDK completes initialization, it can run continuously in a low-power state to enable rapid startup after a user triggers a transaction.

[0082] In this embodiment, after the user starts the application, the client-side SDK can receive and respond to the initialization command sent by the application to perform initialization, so that it can start quickly after the user triggers a transaction, which is beneficial to improving transaction efficiency.

[0083] Figure 3 A flowchart of a transaction processing method provided in this application embodiment Figure 2 This method is applied to cloud servers. In one implementation scenario, the cloud server runs an intelligent agent, which can be used to execute... Figure 3 The transaction processing method shown is for reference. Figure 3 As shown, the method includes:

[0084] S301: Receive page information and transaction information sent by the client-side SDK. The page information is obtained by the client-side SDK after the user triggers the transaction, when the target page corresponding to the transaction is in a stable state. The transaction information is used to identify the transaction triggered by the user.

[0085] Transaction information includes, but is not limited to, session information, transaction ID, and user commands. Session information is a temporary connection credential generated after the user triggers the application launch, and includes, but is not limited to, session ID, user identity identifier, session validity period, and device information.

[0086] The transaction ID is used to identify the transaction triggered by the current user, and different transactions have different transaction IDs.

[0087] User instructions are commands that trigger a transaction process. In one implementation scenario, users can trigger a transaction through page operations, such as clicking a button or entering text. Alternatively, users can trigger a transaction by entering voice information. This application does not limit the method by which users trigger transactions.

[0088] Page information includes, but is not limited to, the DOM data of the target page, screenshots of the target page, and other such information.

[0089] The page information is obtained when the target page is in a stable state. In one implementation scenario, the client-side SDK can inject the target script into the target page and monitor the target page and obtain the state of the target page through the target script. The specific process can be referred to the above embodiments, and will not be described in detail here.

[0090] S302: Generate transaction operation instructions based on page information and transaction information, and send the operation instructions to the client-side SDK so that the client-side SDK can execute the operation instructions.

[0091] In one implementation scenario, a neural network model can be used to generate operation instructions.

[0092] In this embodiment, the cloud server receives page information and transaction information sent by the client-side SDK, generates transaction operation instructions based on the page information and transaction information, and sends the operation instructions to the client-side SDK so that the client-side SDK can execute the operation instructions, thereby realizing non-intrusive access and automated operation of the business. No custom development is required from the transaction party, which reduces development costs and also reduces the difficulty of realizing third-party transaction automation.

[0093] Figure 4 A flowchart illustrating a method for generating operation instructions provided in this application embodiment is shown below. Figure 4 As shown, optionally, the page information includes document object model data and a screenshot of the target page; based on the page information and transaction information, transaction operation instructions are generated, including:

[0094] S401: Parse the document object model data to obtain the position information of interactive controls on the page.

[0095] S402: Annotate the target page screenshot based on the position information of interactive controls on the page.

[0096] S403: Send the annotated target page screenshot, document object model data, and transaction information to the multimodal model so that the multimodal model can output operation instructions.

[0097] Interactive controls on a webpage include, but are not limited to, buttons, images, input fields, and text. The positional information of interactive controls can be represented by their coordinates on the mobile device screen, their width, and their height.

[0098] Since the target page screenshot is the page style presented to the user, it is impossible to identify which elements are interactive controls. Therefore, in one implementation scenario, when annotating the target page screenshot based on the location information of interactive controls, the interactive controls in the target page screenshot can be selected by drawing a box and labeling their corresponding functions, etc.

[0099] Before annotating a screenshot of a target page, the screenshot must be recognized. In one implementation scenario, OCR (Optical Character Recognition) technology can be used to recognize the text information in the screenshot, improving the accuracy of the screenshot recognition.

[0100] Multimodal models can process information in multiple modalities, including text, images, and structured data. In one implementation scenario, a multimodal model can obtain the interaction history of the current session based on session information in the transaction information. Combining the interaction history with the annotated target page screenshot and document object model data, it can determine the next step or all operations of the current transaction and generate corresponding operation instructions.

[0101] In this embodiment, the target page screenshot is annotated based on the location information of interactive controls on the page. The annotated screenshot is then input into the multimodal model to improve its recognition capability and enhance the accuracy of operation commands. Simultaneously, the multimodal model generates operation commands based on multiple dimensions of information, including the annotated target page screenshot, document object model data, and transaction information. This improves the accuracy of the operation commands without requiring manual intervention and is highly efficient.

[0102] Optionally, the page information includes document object model data; based on the page information and transaction information, transaction operation instructions are generated, including:

[0103] The document object model data and transaction information are sent to the transaction decision model so that the transaction decision model can obtain the operation rules corresponding to the transaction information, determine the corresponding operation instructions based on the operation rules, and output them.

[0104] Different transactions have different operating rules. For example, taking the transaction of recharging mobile phone credit as an example, its corresponding operating rules usually include three steps: first, enter the mobile phone number to be recharged; second, enter the recharge amount; and finally, confirm the recharge.

[0105] Taking a money transfer transaction as an example, the corresponding operation rules usually include three steps: first, enter the receiving account; second, enter the payment; and finally, confirm the transfer and verify the password.

[0106] In one implementation scenario, the transaction decision model can determine the corresponding operation rules based on the transaction ID in the transaction information and determine the interaction history within the current session based on the session information in the transaction information. At this time, based on the interaction history and operation rules, the next operation or the remaining multiple operations can be determined, and the corresponding operation instructions can be generated by combining the document object model data.

[0107] In this embodiment, by sending document object model data and transaction information to the transaction decision model, the transaction decision model can obtain the operation rules corresponding to the transaction information, locate interactive controls on the page based on the document object model data, and further generate corresponding operation instructions based on the operation rules and interactive controls on the page. This process requires no manual intervention, has a high degree of automation, and improves the efficiency of determining operation instructions.

[0108] Based on the above embodiments, the following embodiment illustrates the interaction process between a mobile device's application, a device-side SDK, and an intelligent agent. The device-side SDK is integrated into the application, and the intelligent agent resides on a cloud server.

[0109] Figure 5 A signaling flowchart of a transaction processing method provided in this application embodiment is shown below. Figure 5 As shown, the method includes:

[0110] S501: After the user opens the application on the mobile device, the application initializes the client-side SDK.

[0111] S502: After a user triggers a transaction, the application sends the transaction information to the client-side SDK.

[0112] S503: The application determines whether a transaction is an automated transaction.

[0113] S504: If the transaction is automated, the application starts the SDK on the client side.

[0114] S505: The client-side SDK injects the JS script into the target page that is about to be entered, starts the target page stability monitoring, and when all network requests are returned, it determines that the target page is in a stable state and calls the client bridge to notify the SDK to start obtaining page information.

[0115] S506: The client-side SDK sends page information and transaction information to the smart agent.

[0116] S507: The intelligent agent generates transaction operation instructions based on page information and transaction information through a multimodal model or transaction decision model.

[0117] S508: The agent returns the operation instructions to the edge SDK.

[0118] S509: The client-side SDK completes the corresponding interface interaction according to the operation instructions and automatically executes the transaction process.

[0119] In this embodiment, a complete "perception-decision-execution" transaction processing flow is formed based on the client-side SDK and the intelligent agent. Specifically, the client-side SDK can identify elements of the target page in real time, locate interactive controls on the page, and dynamically perceive changes in the state of the target page. The intelligent agent can autonomously analyze the task objective based on transaction information and page information, decide on the next operation, and generate operation instructions. This supports non-intrusive automated operation of business connections, achieving automation without requiring customized development by the transaction party, reducing development costs and addressing difficulties in third-party transaction integration. After receiving the operation instructions, the client-side SDK can simulate human touch behavior, automatically operating the mobile device without user intervention, thus automating transactions and improving the intelligence of the application and user experience.

[0120] Figure 6 A schematic diagram of the structure of a transaction processing device provided in this application embodiment. Figure 1 It is used in the device-side SDK, which is integrated into the application on the mobile device, such as... Figure 6 As shown, the transaction processing apparatus 60 provided in this embodiment includes:

[0121] The first receiving module 601 is used to receive transaction information sent by the application after the user triggers the transaction;

[0122] The first receiving module 601 is also used to receive and respond to the application's start command if the transaction is an automated transaction;

[0123] The first processing module 602 is used to determine the state of the target page corresponding to the transaction, and to obtain the page information of the target page when the target page is in a stable state.

[0124] The first processing module 602 is also used to send page information and transaction information to the intelligent agent so that the intelligent agent can determine the operation instructions for the transaction and receive and execute the operation instructions fed back by the intelligent agent.

[0125] In one possible implementation, the first processing module 602, when determining the state of the target page corresponding to the transaction, specifically performs the following:

[0126] Obtain the target script and inject it into the target page so that the target script can monitor the state of the target page.

[0127] In one possible implementation, the first receiving module 601 is further configured to:

[0128] After the user launches the application, it receives and responds to the initialization instructions sent by the application.

[0129] The transaction processing device 60 provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0130] Figure 7 This is a schematic diagram of the structure of a transaction processing device provided in an embodiment of this application, applied to a cloud server, such as... Figure 7 As shown, the transaction processing apparatus 70 provided in this embodiment includes:

[0131] The second receiving module 701 is used to receive page information and transaction information sent by the client-side SDK. The page information is obtained by the client-side SDK after the user triggers the transaction, when the target page corresponding to the transaction is in a stable state. The transaction information is used to identify the transaction triggered by the user.

[0132] The second processing module 702 is used to generate transaction operation instructions based on page information and transaction information, and send the operation instructions to the client-side SDK so that the client-side SDK can execute the operation instructions.

[0133] In one possible implementation, the page information includes document object model data and a screenshot of the target page; the second processing module 702, when generating transaction operation instructions based on the page information and transaction information, is specifically used for:

[0134] Parse the document object model data to obtain the location information of interactive controls on the page;

[0135] Annotate the target page screenshot based on the position information of interactive controls on the page;

[0136] The annotated target page screenshot, document object model data, and transaction information are sent to the multimodal model so that the multimodal model can output operation instructions.

[0137] In one possible implementation, the page information includes document object model data; the second processing module 702, when generating transaction operation instructions based on the page information and transaction information, specifically performs the following:

[0138] The document object model data and transaction information are sent to the transaction decision model so that the transaction decision model can obtain the operation rules corresponding to the transaction information, determine the corresponding operation instructions based on the operation rules, and output them.

[0139] The transaction processing device 70 provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0140] Figure 8 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 8As shown, the electronic device 80 provided in this embodiment includes at least one processor 801 and a memory 802. Optionally, the device 80 further includes a communication component 803. The processor 801, memory 802, and communication component 803 are connected via a bus 804.

[0141] In a specific implementation, at least one processor 801 executes computer execution instructions stored in memory 802, causing at least one processor 801 to perform the above-described method.

[0142] The specific implementation process of processor 801 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0143] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0144] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0145] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0146] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0147] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0148] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0149] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0150] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0151] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0152] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0153] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0154] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0155] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0156] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0157] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0158] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A transaction processing method, characterized in that, The method is applied to a client-side SDK, which is integrated into an application on a mobile device. The method includes: After a user triggers a transaction, the system receives transaction information sent by the application. If the transaction is an automated transaction, receive the application's start command and respond; Determine the state of the target page corresponding to the transaction, and if the target page is in a stable state, obtain the page information of the target page; The page information and the transaction information are sent to the intelligent agent so that the intelligent agent can determine the operation instructions for the transaction and receive and execute the operation instructions fed back by the intelligent agent.

2. The method according to claim 1, characterized in that, Determining the state of the target page corresponding to the transaction includes: Obtain the target script and inject it into the target page so that the target script can monitor the state of the target page.

3. The method according to claim 1 or 2, characterized in that, The method further includes: After the user launches the application, it receives and responds to the initialization command sent by the application.

4. A transaction processing method, characterized in that, The method is applied to a cloud server, and the method includes: The receiving end-side SDK sends page information and transaction information. The page information is obtained by the end-side SDK after the user triggers a transaction, provided that the target page corresponding to the transaction is in a stable state. The transaction information is used to identify the transaction triggered by the user. The transaction operation instructions are generated based on the page information and the transaction information, and the operation instructions are sent to the client-side SDK so that the client-side SDK executes the operation instructions.

5. The method according to claim 4, characterized in that, The page information includes document object model data and a screenshot of the target page; the step of generating transaction instructions based on the page information and the transaction information includes: The document object model data is parsed to obtain the position information of interactive controls on the page; Annotate the target page screenshot based on the location information of the interactive controls on the page. The annotated target page screenshot, the document object model data, and the transaction information are sent to the multimodal model so that the multimodal model can output operation instructions.

6. The method according to claim 4, characterized in that, The page information includes document object model data; the step of generating transaction instructions based on the page information and the transaction information includes: The document object model data and the transaction information are sent to the transaction decision model so that the transaction decision model can obtain the operation rules corresponding to the transaction information, and determine and output the corresponding operation instructions according to the operation rules.

7. A transaction processing apparatus, characterized in that, An apparatus for use with a device-side SDK, wherein the device-side SDK is integrated into an application on a mobile device, the apparatus comprising: The first receiving module is used to receive transaction information sent by the application after the user triggers the transaction; The first receiving module is further configured to receive and respond to the application's startup instruction if the transaction is an automated transaction; The first processing module is used to determine the state of the target page corresponding to the transaction, and, if the target page is in a stable state, to obtain the page information of the target page. The first processing module is further configured to send the page information and the transaction information to the intelligent agent, so that the intelligent agent can determine the operation instructions of the transaction and receive and execute the operation instructions fed back by the intelligent agent.

8. A transaction processing apparatus, characterized in that, The device, used in a cloud server, includes: The second receiving module is used to receive page information and transaction information sent by the client-side SDK. The page information is obtained by the client-side SDK after the user triggers a transaction, when the target page corresponding to the transaction is in a stable state. The transaction information is used to identify the transaction triggered by the user. The second processing module is used to generate a transaction operation instruction based on the page information and the transaction information, and send the operation instruction to the client-side SDK so that the client-side SDK executes the operation instruction.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as claimed in any one of claims 1 to 3 or 4 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 3 or 4 to 6.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 3 or 4 to 6.

Images