Transaction service processing method and device, program product and electronic equipment

Abstract

The invention discloses a transaction service processing method and device, a program product and electronic equipment, and relates to the field of financial science and technology, and the processing method comprises the steps: receiving user interaction information; processing the user interaction information to obtain a processing result, and calling a processing component under the condition that the processing result indicates that the user interaction information contains the target transaction service; collecting a page loading file and network request data of the current page by adopting a processing component, and judging whether the current page is loaded or not based on the page loading file and the network request data; capturing page state data of the current page under the condition that the loading of the current page is completed; and processing the page loading file, the page state data and the user interaction information by adopting a preset identification model to complete a target transaction service. According to the invention, the technical problem of low business transaction processing efficiency in related technologies is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of financial technology, in particular to a transaction service processing method and device, program product and electronic equipment. BACKGROUND

[0002] Currently, the detection of client page state and the processing of business transactions mainly rely on preset rules or manual intervention. For example, traditional automated testing tools detect changes in page elements through preset scripts or rules. However, this method is not flexible and efficient when faced with dynamically changing pages or complex business scenarios. In addition, although current multi-modal large models have shown strong capabilities in natural language processing, image recognition, etc., they cannot effectively analyze the diverse interaction information of customers, resulting in insufficient ability to process real-time business transactions of financial institutions.

[0003] There is currently no effective solution to the above problems. SUMMARY

[0004] The embodiments of the present application provide a transaction service processing method and device, program product and electronic equipment to at least solve the technical problem of low efficiency of business transaction processing in related technologies.

[0005] According to an aspect of an embodiment of the present application, a transaction service processing method is provided, applied to a client, the client being pre-integrated with a processing component, comprising: receiving user interaction information, wherein the user interaction information is text information or voice information; processing the user interaction information to obtain a processing result, and in the case that the processing result indicates that the user interaction information contains a target transaction service, invoking the processing component; using the processing component to collect page loading files and network request data of the current page, and determining whether the current page is loaded based on the page loading files and the network request data; in the case that the current page is loaded, capturing page state data of the current page; using a preset recognition model to process the page loading files, the page state data and the user interaction information to complete the target transaction service.

[0006] Further, the step of processing the user interaction information to obtain a processing result comprises: in the case that the user interaction information is voice information, converting the voice information into text; in the case that the user interaction information is text information, extracting the text in the text information; dividing the text to obtain a plurality of word groups; matching each word group based on a preset transaction table, wherein the preset transaction table records keywords corresponding to each transaction service; in the case that a word group matches a keyword, determining the transaction service corresponding to the keyword as the target transaction service contained in the user interaction information.

[0007] Further, after the processing component is used to collect the page loading file and the network request data of the current page, the method further includes: cleaning the page loading file to obtain a target page loading file; and parsing the target page loading file to obtain a plurality of groups of key-value pairs, wherein the primary key in the key-value pair is an element, and the primary key value in the key-value pair is an element coordinate.

[0008] Further, the step of determining whether the current page is loaded based on the page loading file and the network request data includes: determining whether the element coordinate in each group of key-value pairs in the page loading file changes within a preset time period; in a case where the element coordinate in all key-value pairs in the page loading file does not change within the preset time period, determining whether the network request for the current page is loaded based on the network request data; and in a case where the network request for the current page is loaded, determining that the current page is loaded.

[0009] Further, the step of capturing the page state data of the current page includes: taking a screenshot of the current page; identifying the page elements and the page element positions on the screenshot based on the page loading file; and determining the page state data based on the screenshot, the page elements, and the page element positions.

[0010] Further, before the preset recognition model is used to process the page loading file, the page state data, and the user interaction information, the method further includes: determining a plurality of business transactions involved by the client; establishing a corresponding prompt word for each business transaction and determining the execution information corresponding to each prompt word, wherein the execution information at least includes: at least one element, an action performed on each element, and an element order; collecting a plurality of historical texts corresponding to each business transaction; and training the initial recognition model based on the plurality of historical texts corresponding to each business transaction, the prompt word, and the execution information to obtain the preset recognition model trained.

[0011] Further, the preset recognition model is used to process the page loading file, the page state data and the user interaction information to complete the target transaction service, including: determining a target prompt word corresponding to the target transaction service included in the user interaction information, and determining target execution information based on the target prompt word; determining a first target element of the current page and a first target action performed on the first target element based on the page loading file, the page state data and the target execution information; performing the first target action on the first target element of the current page by using the processing component, jumping to a next page, and collecting a page loading file of the next page; capturing page state data of the next page in the case that the next page is loaded; determining a second target element of the next page and a second target action performed on the second target element based on the page loading file and the page state data of the next page; and performing the second target action on the second target element of the next page by using the processing component until the page jumped to is a transaction page, and the target transaction service is completed.

[0012] According to another aspect of the embodiment of the present application, a transaction service processing device is also provided, which is applied to a client, the client is integrated with a processing component in advance, and includes: a first receiving unit, configured to receive user interaction information, wherein the user interaction information is text information or voice information; a first processing unit, configured to process the user interaction information to obtain a processing result, and call the processing component in the case that the processing result indicates that the user interaction information contains a target transaction service; a first collecting unit, configured to collect a page loading file and network request data of a current page by using the processing component, and determine whether the current page is loaded based on the page loading file and the network request data; a first capturing unit, configured to capture page state data of the current page in the case that the current page is loaded; and a second processing unit, configured to process the page loading file, the page state data and the user interaction information by using a preset recognition model to complete the target transaction service.

[0013] Further, the first processing unit includes: a first conversion module, configured to convert the voice information into text in the case that the user interaction information is voice information; a first extraction module, configured to extract text in the text information in the case that the user interaction information is text information; a first division module, configured to divide the text to obtain a plurality of word groups; a first matching module, configured to match each word group based on a preset transaction table, wherein the preset transaction table records keywords corresponding to each transaction service; and a first determination module, configured to determine a transaction service corresponding to the keyword as the target transaction service contained in the user interaction information in the case that the keyword is matched to the word group.

[0014] Further, the transaction business processing apparatus comprises: a first cleaning module, configured to clean the page loading file to obtain a target page loading file after collecting the page loading file and the network request data of the current page by using the processing component; and a first analysis module, configured to analyze the target page loading file to obtain a plurality of groups of key-value pairs, wherein the primary key in the key-value pair is an element, and the primary key value in the key-value pair is an element coordinate.

[0015] Further, the first acquisition unit comprises: a first judgment module, configured to judge whether the element coordinate in each group of key-value pairs in the page loading file changes within a preset time length; a second judgment module, configured to, in a case where the element coordinates in all key-value pairs in the page loading file do not change within the preset time length, judge whether the network request for the current page is loaded based on the network request data; and a second determination module, configured to, in a case where the network request for the current page is loaded, determine that the current page is loaded.

[0016] Further, the first acquisition unit comprises: a first judgment module, configured to judge whether the element coordinate in each group of key-value pairs in the page loading file changes within a preset time length; a second judgment module, configured to, in a case where the element coordinates in all key-value pairs in the page loading file do not change within the preset time length, judge whether the network request for the current page is loaded based on the network request data; and a second determination module, configured to, in a case where the network request for the current page is loaded, determine that the current page is loaded.

[0017] Further, the transaction business processing apparatus further comprises: a fourth determination module, configured to determine a plurality of business transactions involved by the client before processing the page loading file, the page state data and the user interaction information by using the preset recognition model; a fifth determination module, configured to establish a corresponding prompt word for each business transaction and determine execution information corresponding to each prompt word, wherein the execution information at least comprises: at least one element, an action performed on each element and an element order; a first acquisition module, configured to acquire a plurality of historical texts corresponding to each business transaction; and a first training module, configured to train an initial recognition model based on the plurality of historical texts corresponding to each business transaction, the prompt word and the execution information to obtain a trained preset recognition model.

[0018] Further, the second processing unit comprises: a sixth determination module, configured to determine a target prompt word corresponding to the target transaction service contained in the user interaction information, and determine target execution information based on the target prompt word; a seventh determination module, configured to determine a first target element of the current page and a first target action performed on the first target element based on the page loading file, the page state data and the target execution information; a first execution module, configured to perform the first target action on the first target element of the current page by using the processing component, jump to a next page, and collect a page loading file of the next page; a first capturing module, configured to capture page state data of the next page in a case where the next page is loaded; an eighth determination module, configured to determine a second target element of the next page and a second target action performed on the second target element based on the page loading file and the page state data of the next page; and a second execution module, configured to perform the second target action on the second target element of the next page by using the processing component, until the jumped-to page is a transaction page, and the target transaction service is completed.

[0019] According to another aspect of the embodiments of the present application, a computer program product is also provided, comprising a nonvolatile computer readable storage medium, the nonvolatile computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the processing method of any one of the transaction services.

[0020] According to another aspect of the embodiments of the present application, an electronic device is also provided, comprising one or more processors and a memory, the memory being configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the processing method of any one of the transaction services.

[0021] In the present application, user interaction information is received, the user interaction information is processed to obtain a processing result, and in a case where the processing result indicates that the user interaction information contains a target transaction service, a processing component is called, the processing component is used to collect a page loading file and network request data of a current page, and it is determined whether the current page is loaded based on the page loading file and the network request data, in a case where the current page is loaded, page state data of the current page is captured, a preset recognition model is used to process the page loading file, the page state data and the user interaction information, and a target transaction service is completed, thereby solving the technical problem of low efficiency of transaction service processing in the related art.

[0022] In the present application, by processing the user interaction information (such as text information or voice information), and judging whether the user interaction information includes the target transaction service, in the case that the user interaction information contains the target transaction service, the processing component is called to collect the page loading file and the network request data of the current page in real time, and to judge whether the current page is loaded, in the case that the current page is loaded, the page state data of the current page is captured, and then the page loading file, the page state data and the user interaction information are input to the preset recognition model for analysis, the processing logic is dynamically generated, and the transaction process of the target transaction service is automatically executed, thereby realizing the technical effect of improving the efficiency of business transaction processing. BRIEF DESCRIPTION OF DRAWINGS

[0023] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0024] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a transaction service processing method is shown;

[0025] Figure 2 is a flowchart of a transaction service processing method according to an embodiment of the present application;

[0026] Figure 3 is a schematic diagram of an optional transaction service processing device according to an embodiment of the present application;

[0027] Figure 4 is a structure block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second" and the like in the present application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) collected and related to the present application are all authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards in relevant regions, necessary security measures are taken, public order and good customs are not violated, and appropriate operation portals are provided for users to choose authorization or refusal. For example, interfaces are provided between the system and related users or agencies, and before obtaining the relevant information, the interface needs to send a request to the aforementioned user or agency, and after receiving the consent information feedback from the aforementioned user or agency, the relevant information is obtained; if the user chooses to refuse, the expert decision-making process is entered.

[0031] In the present application, the multi-modal large model can intelligently analyze natural language or other forms of input and dynamically generate transaction processing logic without pre-writing complex rule logic, can quickly respond to diversified requests of users, automatically complete complex transactions and business processing through intelligent analysis and automatic processing, reduce manual intervention, improve the flexibility and scalability of processing business requests, and improve user experience.

[0032] The present application will be described in detail below in conjunction with various embodiments.

[0033] Embodiment 1

[0034] According to the embodiments of the present application, an embodiment of a transaction business processing method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0035] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a transaction processing method is shown. Figure 1 As shown, computer terminal 10 (or mobile device) may include one or more ( Figure 1 The processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions may also be included. In addition, it may include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera, wherein the network interface can be connected to wired and / or wireless networks. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs of application software and modules, such as program instructions / data storage means corresponding to the transaction processing method in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, i.e. implements the transaction processing method as described above. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include memories remotely arranged with respect to the processor 102, which can be connected to the computer terminal 10 through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network interface controller (NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module which is used to communicate with the Internet in a wireless manner.

[0039] The display can be, for example, a touch screen type liquid crystal display (LCD) which can enable a user to interact with the user interface of the computer terminal 10 (or mobile device).

[0040] In the above operating environment, the present application provides a transaction processing method as shown in Figure 2 Figure 2 is a flowchart of the transaction processing method according to Embodiment 1 of the present application, which includes the following steps: Figure 2

[0041] Step S201: receiving user interaction information, wherein the user interaction information is text information or voice information.

[0042] Optionally, the transaction processing method is applied to a client, and the client is pre-integrated with a processing component (a software component for monitoring and analyzing the state of a client page, which can be a plug-in, a script, an API interface (Application Programming Interface), etc.).

[0043] ​​In the embodiments of the present application, the interactive information (such as text information or voice information) sent by the user on the client (such as a webpage or a mobile application) is received, and the information includes the type of business transaction or specific needs (such as filling out a form, searching, etc.) that the user wants to perform.

[0044] In step S202, the user interactive information is processed to obtain a processing result, and in the case where the processing result indicates that the user interactive information contains a target transaction business, a processing component is called.

[0045] In the embodiments of the present application, the user interactive information is processed to obtain a processing result, which is used to indicate whether the user interactive information contains a target transaction business (a specific business transaction that the user wants to perform, such as transferring money, buying a product, submitting an application, etc.), and in the case where the processing result indicates that the user interactive information contains a target transaction business, a processing component is called for subsequent automated processing.

[0046] In step S203, the processing component is used to collect the page loading file and network request data of the current page, and to determine whether the current page is loaded based on the page loading file and network request data.

[0047] In the embodiments of the present application, the processing component can be used to collect the page loading file (such as a DOM (Document Object Model) file) and network request (a request initiated to the server during the page loading process, used to obtain dynamic content or data) data of the current page, and to determine whether the current page is loaded based on the page loading file and network request data. By monitoring the client page and network request data in real time, it can be determined whether the page is in a stable state, ensuring that the page state data is collected only after the page is completely loaded, and avoiding incomplete or incorrect data due to incomplete page loading.

[0048] In step S204, the page state data of the current page is captured in the case where the current page is loaded.

[0049] In the embodiments of the present application, in the case where the current page is loaded, the page state data (which can include the visual state (such as a screenshot) of the page, the DOM tree structure, the text content, and possibly the user operation traces (such as mouse movement traces, input box history values), etc.) of the current page is captured.

[0050] In step S205, the page loading file, the page state data, and the user interactive information are processed using a preset recognition model to complete the target transaction business.

[0051] In the embodiments of the present application, the preset recognition model (a pre-trained multi-modal large model capable of comprehensively analyzing various types of data including text, images and user behavior data to understand the context and specific needs of business transactions) is used to process the page loading file, page state data and user interaction information, which can identify the specific business needs of the user and generate a corresponding automatic business transaction processing scheme (such as automatically filling out forms, triggering transaction processes, etc.). The processing scheme can be fed back to the client page through an API interface or an automated tool to complete the automatic execution of the target transaction business.

[0052] In summary, the user interaction information of the received client is processed to obtain a processing result. In the case where the processing result indicates that the user interaction information includes a target transaction business, the processing component is called to collect and monitor the page loading file and network request data of the current page in real time, and the page loading state is determined according to the monitored page loading file and network request data. Once the page loading is completed, the processing component immediately captures the page state data (including visual elements and user operation traces, etc.). Then, the preset recognition model is used to process the page loading file, page state data and user interaction information to dynamically generate processing logic, which can realize the intelligentization and automation of business transaction processing, and improve the efficiency and accuracy of business processing.

[0053] In order to accurately obtain the target transaction business, in the transaction business processing method provided in Embodiment 1 of the present application, in the case where the user interaction information is voice information, the voice information is converted into text; in the case where the user interaction information is text information, the text in the text information is extracted; the text is divided to obtain a plurality of word groups; each word group is matched based on a preset transaction table, wherein the preset transaction table records the keywords corresponding to each transaction business; in the case where a word group matches a keyword, the transaction business corresponding to the keyword is determined as the target transaction business contained in the user interaction information.

[0054] Optionally, the user interaction information can be voice information or text information.

[0055] In the embodiment of the present application, in the case that the user interaction information is voice information, the voice information can be first converted into text by using voice recognition technology, and in the case that the user interaction information is text information, the text in the text information can be extracted by using text recognition technology, then the text can be divided to obtain a plurality of word groups, and based on a preset transaction table (a preset transaction table recording keywords corresponding to each transaction service (such as transfer, payment, account inquiry, etc.)), keyword matching is performed on each word group, in the case that a word group matches a keyword, the transaction service corresponding to the keyword is determined as the target transaction service contained in the user interaction information, whether the user interaction information is text or voice, the business transaction intention expressed thereby can be accurately recognized through keyword matching, and processing errors caused by inaccurate information interpretation are avoided.

[0056] In order to accurately obtain a plurality of groups of key-value pairs, in the transaction service processing method provided in Embodiment 1 of the present application, the page loading file is cleaned to obtain a target page loading file; the target page loading file is parsed to obtain a plurality of groups of key-value pairs, wherein the primary key in the key-value pair is an element, and the primary key value in the key-value pair is an element coordinate.

[0057] In the embodiment of the present application, the data cleaning operation (such as removing unnecessary tags, comments, and blank characters) can be first performed on the page loading file to obtain the target page loading file, and more pure and structured data is provided to ensure the efficiency and accuracy of the subsequent parsing process, then the target page loading file is parsed to extract the elements constituting the page and the position coordinates of the elements in the page (i.e. a plurality of groups of key-value pairs are obtained, the primary key in the key-value pair is an element, and the primary key value in the key-value pair is an element coordinate), and through data cleaning and accurate element positioning, the precision of automatic transaction processing is improved.

[0058] In order to accurately determine that the current page loading is completed, in the transaction service processing method provided in Embodiment 1 of the present application, it is judged whether the element coordinates in each group of key-value pairs in the page loading file change within a preset time length; in the case that the element coordinates in all key-value pairs in the page loading file do not change within the preset time length, it is judged based on the network request data whether the network request for the current page is loaded; in the case that the network request for the current page is loaded, it is determined that the current page loading is completed.

[0059] In the embodiments of the present application, the coordinates of the elements in each group of key-value pairs in the page loading file can be continuously monitored to determine whether they change within a preset time period (for example, 1s) (that is, whether the page is in a dynamic loading state or whether all elements have been loaded and stabilized in the corresponding positions), in the case that the coordinates of the elements in all key-value pairs in the page loading file do not change within the preset time period, the network request data is further analyzed to determine whether the network request for the current page is loaded, in the case that the network request for the current page is loaded, it is determined that the current page is loaded, so as to ensure that all necessary resources and data have reached the client. Through the judgment of the page loading completion, the transaction processing is avoided in the case that the page elements are not stable or the resources are not completely loaded, and the risk of processing errors is reduced.

[0060] In order to accurately determine the page state data, in the transaction business processing method provided in Embodiment 1 of the present application, the current page is captured; based on the page loading file, the page elements and the positions of the page elements on the screenshot are identified; based on the screenshot, the page elements and the positions of the page elements, the page state data is determined.

[0061] In the embodiments of the present application, after confirming that the page is loaded, the processing component can capture the current page, capture the complete visual presentation state of the page (including all texts, images, layout information, etc.), based on the loading file of the page, further analyze the content on the screenshot, identify the specific page elements and their positions, and determine the latest state data of the current page, including dynamically generated content, user input state, hidden or visible element state, etc., to ensure that the automated transaction processing can be based on the real page state, and avoid processing errors caused by changes in the page state.

[0062] In order to accurately obtain the preset recognition model, in the transaction business processing method provided in Embodiment 1 of the present application, a plurality of business transactions involving the client are determined; a corresponding prompt word is established for each business transaction, and execution information corresponding to each prompt word is determined, wherein the execution information at least includes: at least one element, an action performed on each element, and an element order; a plurality of historical texts corresponding to each business transaction are collected; based on the plurality of historical texts corresponding to each business transaction, the prompt word and the execution information, the initial recognition model is trained to obtain the trained preset recognition model.

[0063] Optionally, a plurality of business transaction types that the client may involve can be listed and determined through historical business records and expert experience, such as transfer, deposit, loan application, account information modification, etc.

[0064] In the embodiments of the present application, for each service transaction, a set of prompt words are created, which can reflect the key features of the transaction or the key words that the user may mention, support adding, deleting, modifying and querying, and meanwhile, the execution information of the transaction is formulated, including the page elements (such as buttons, input boxes, etc.) that need to be interacted, the actions (such as clicking, inputting text, etc.) that should be taken on these elements, and the element order that needs to be followed according to the business process. Then, a plurality of historical texts corresponding to each service transaction are collected, and based on the plurality of historical texts corresponding to each service transaction, the prompt words and the execution information, the initial recognition model is trained in multiple rounds of iteration to obtain the trained preset recognition model.

[0065] In order to accurately complete the target transaction business, in the transaction business processing method provided in Embodiment 1 of the present application, the target prompt word corresponding to the target transaction business contained in the user interaction information is determined, and based on the target prompt word, the target execution information is determined; based on the page loading file, the page state data and the target execution information, the first target element of the current page and the first target action performed on the first target element are determined; the first target action performed on the first target element of the current page is performed by using the processing component, the next page is jumped to, and the page loading file of the next page is collected; in the case that the next page is loaded, the page state data of the next page is captured; based on the page loading file and the page state data of the next page, the second target element of the next page and the second target action performed on the second target element are determined; the second target action performed on the second target element of the next page is performed by using the processing component, until the page jumped to is the transaction page, and the target transaction business is completed.

[0066] Optionally, according to the output results (such as element position coordinates, actions performed on each element and element order) of the preset recognition model, automatic clicking and form filling can be performed, page loading can be performed, and the above operations can be performed in a loop until the corresponding transaction page is reached.

[0067] In the embodiments of the present application, the target prompt corresponding to the target transaction business contained in the user interaction information can be found, and based on the target prompt, the target execution information (including the elements to be operated, the actions to be performed on these elements, and the operation sequence) matched with the target transaction business is determined, the first target element of the current page that needs to be operated and the corresponding first target action are determined by combining the page loading file and the page state data of the current page and the target execution information, then the first target action (such as clicking a button, inputting text, etc.) of the first target element of the current page is performed by the integrated processing component, the automatic operation on the current page is realized, and the page is prompted to jump to the next page (i.e. to promote the transaction process to the next stage), after that, the page loading file of the next page is collected, the page state data of the next page is captured under the condition that the next page is loaded, the second target element of the next page and the second target action performed on the second target element are determined based on the page loading file and the page state data of the next page, and the second target action of the second target element of the next page is performed by the processing component, the transaction process is continuously promoted, through continuous automatic operation, it is ensured that the transaction processing can be carried out along the expected execution path, until the page jumped to is a transaction page, the target transaction business is completed, and manual intervention is not required, thereby improving the efficiency of transaction processing and user experience.

[0068] Optionally, the result (success or failure) of each business transaction processing can be recorded, and the training data of the preset recognition model is updated regularly in combination with user feedback (such as manual correction operation), so as to improve the processing capability of the model in complex business scenarios.

[0069] The transaction business processing method provided by the embodiments of the present application integrates a multi-modal large model and an automatic processing component to build an efficient and intelligent real-time page state detection and business transaction processing system. First, the dynamic changes of the client page are captured, including DOM element update, user interaction behavior and network request state, to generate page state data in real time. Then, based on the matching mechanism of business transaction prompt and execution information, the transaction demand of the user is accurately identified, and the optimal transaction execution path (i.e. target execution information) is dynamically planned. After that, the automatic processing component is used to continuously perform page operations related to the transaction according to the page loading file, the page state data and the target execution information, from the first page to the transaction completion page, to realize automatic transaction flow transfer across pages, and realize full-automatic processing of business transactions, thereby improving the efficiency of the transaction process and user experience.

[0070] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown.

[0071] Embodiment 2

[0072] The embodiment of the present application further provides a transaction service processing apparatus. It should be noted that the transaction service processing apparatus of the embodiment of the present application can be used to execute the transaction service processing method provided by the embodiment of the present application. The transaction service processing apparatus provided by the embodiment of the present application is introduced as follows.

[0073] According to the embodiment of the present application, a device for implementing the transaction service processing method is further provided. Figure 3 is a schematic diagram of an optional transaction service processing apparatus according to an embodiment of the present application, as shown in the figure, the processing apparatus can include a first receiving unit 30, a first processing unit 31, a first collecting unit 32, a first capturing unit 33 and a second processing unit 34. Figure 3

[0074] The first receiving unit 30 is configured to receive user interaction information, wherein the user interaction information is text information or voice information.

[0075] The first processing unit 31 is configured to process the user interaction information to obtain a processing result, and in the case that the processing result indicates that the user interaction information contains a target transaction service, call a processing component.

[0076] The first collecting unit 32 is configured to collect, by using the processing component, a page loading file and network request data of a current page, and determine whether the current page is loaded based on the page loading file and the network request data.

[0077] The first capturing unit 33 is configured to capture, in the case that the current page is loaded, page state data of the current page.

[0078] The second processing unit 34 is configured to process, by using a preset recognition model, the page loading file, the page state data and the user interaction information, to complete the target transaction service.

[0079] ​The transaction processing device provided by the embodiments of the present application can receive user interaction information through the first receiving unit 30, process the user interaction information through the first processing unit 31 to obtain a processing result, and in the case where the processing result indicates that the user interaction information contains a target transaction service, call a processing component, collect the page loading file and the network request data of the current page by using the processing component through the first collecting unit 32, and judge whether the current page is loaded based on the page loading file and the network request data, capture the page state data of the current page in the case where the current page is loaded through the first capturing unit 33, and process the page loading file, the page state data and the user interaction information by using a preset recognition model through the second processing unit 34 to complete the target transaction service.

[0080] Optionally, the first processing unit comprises: a first conversion module, configured to convert the voice information into text in the case where the user interaction information is voice information; a first extraction module, configured to extract the text in the text information in the case where the user interaction information is text information; a first division module, configured to divide the text to obtain a plurality of word groups; a first matching module, configured to match each word group based on a preset transaction table, wherein the preset transaction table records the keywords corresponding to each transaction service; and a first determination module, configured to determine the transaction service corresponding to the keyword as the target transaction service contained in the user interaction information in the case where the word group matches the keyword.

[0081] Optionally, the transaction processing device comprises: a first cleaning module, configured to clean the page loading file to obtain a target page loading file after collecting the page loading file and the network request data of the current page by using the processing component; and a first analysis module, configured to analyze the target page loading file to obtain a plurality of groups of key-value pairs, wherein the primary key in the key-value pair is an element, and the primary key value in the key-value pair is an element coordinate.

[0082] Optionally, the first collecting unit comprises: a first judgment module, configured to judge whether the element coordinates in each group of key-value pairs in the page loading file change within a preset time length; a second judgment module, configured to judge whether the network request for the current page is loaded based on the network request data in the case where the element coordinates in all key-value pairs in the page loading file do not change within the preset time length; and a second determination module, configured to determine that the current page is loaded in the case where the network request for the current page is loaded.

[0083] Optionally, the first capturing unit includes: a first screenshot module for taking a screenshot of the current page; a first recognition module for recognizing page elements and their positions in the screenshot based on the page loading file; and a third determination module for determining page state data based on the screenshot, page elements, and their positions.

[0084] Optionally, the transaction processing device further includes: a fourth determining module, used to determine multiple business transactions involved in the client before processing the page loading file, page state data, and user interaction information using a preset recognition model; a fifth determining module, used to establish corresponding prompt words for each business transaction and determine the execution information corresponding to each prompt word, wherein the execution information includes at least: at least one element, the action performed on each element, and the order of the elements; a first acquisition module, used to acquire multiple historical texts corresponding to each business transaction; and a first training module, used to train the initial recognition model based on the multiple historical texts, prompt words, and execution information corresponding to each business transaction to obtain a trained preset recognition model.

[0085] Optionally, the second processing unit includes: a sixth determining module, used to determine the target prompt word corresponding to the target transaction business contained in the user interaction information, and to determine the target execution information based on the target prompt word; a seventh determining module, used to determine the first target element of the current page and the first target action to be performed on the first target element based on the page loading file, page state data, and target execution information; a first execution module, used to execute the first target action on the first target element of the current page using the processing component, jump to the next page, and collect the page loading file of the next page; a first capturing module, used to capture the page state data of the next page when the next page has finished loading; an eighth determining module, used to determine the second target element of the next page and the second target action to be performed on the second target element based on the page loading file and page state data of the next page; and a second execution module, used to execute the second target action on the second target element of the next page using the processing component until the page to be jumped to is a transaction page, thus completing the target transaction business.

[0086] The aforementioned processing device may further include a processor and a memory. The first receiving unit 30, the first processing unit 31, the first acquisition unit 32, the first capture unit 33, the second processing unit 34, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0087] The aforementioned processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and by adjusting kernel parameters, a preset recognition model can be used to process page loading files, page state data, and user interaction information to complete the target transaction.

[0088] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0089] It should be noted that the first receiving unit 30, the first processing unit 31, the first acquisition unit 32, the first capture unit 33, and the second processing unit 34 mentioned above correspond to steps S201 to S205 in Embodiment 1. The instances and application scenarios implemented by the above units and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0090] Example 3

[0091] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 Only one of the following is shown: processor 402, memory 404, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0092] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the transaction processing method and apparatus in this embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned transaction processing method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0093] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: receiving user interaction information, wherein the user interaction information is text information or voice information; processing the user interaction information to obtain a processing result, and calling a processing component in a case where the processing result indicates that the user interaction information contains a target transaction service; collecting a page loading file and network request data of a current page using the processing component, and determining whether the current page is loaded based on the page loading file and the network request data; capturing page state data of the current page in a case where the current page is loaded; processing the page loading file, the page state data, and the user interaction information using a preset recognition model to complete the target transaction service.

[0094] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: converting the voice information into text in a case where the user interaction information is voice information; extracting text in the text information in a case where the user interaction information is text information; dividing the text to obtain a plurality of word groups; matching each word group based on a preset transaction table, wherein the preset transaction table records keywords corresponding to each transaction service; and determining a transaction service corresponding to the keyword as the target transaction service contained in the user interaction information in a case where the word group matches the keyword.

[0095] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: cleaning the page loading file to obtain a target page loading file; and parsing the target page loading file to obtain a plurality of groups of key-value pairs, wherein a primary key in the key-value pair is an element, and a primary key value in the key-value pair is an element coordinate.

[0096] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: determining whether the element coordinate in each group of key-value pairs in the page loading file changes within a preset time length; determining whether a network request for the current page is loaded based on the network request data in a case where the element coordinates in all key-value pairs in the page loading file do not change within the preset time length; and determining that the current page is loaded in a case where the network request for the current page is loaded.

[0097] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: capturing a screenshot of the current page; identifying a page element and a page element position on the screenshot based on the page loading file; and determining the page state data based on the screenshot, the page element, and the page element position.

[0098] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: determining a plurality of business transactions involved by the client; establishing a corresponding prompt word for each business transaction and determining the execution information corresponding to each prompt word, wherein the execution information at least includes: at least one element, an action performed on each element, and an element sequence; collecting a plurality of historical texts corresponding to each business transaction; training an initial recognition model based on the plurality of historical texts corresponding to each business transaction, the prompt word, and the execution information to obtain a trained preset recognition model.

[0099] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: determining a target prompt word corresponding to a target transaction business contained in the user interaction information, and determining target execution information based on the target prompt word; determining a first target element of the current page and a first target action performed on the first target element based on the page loading file, the page state data, and the target execution information; performing the first target action on the first target element of the current page using the processing component, jumping to the next page, and collecting the page loading file of the next page; in the case that the next page is loaded, capturing the page state data of the next page; determining a second target element of the next page and a second target action performed on the second target element based on the page loading file and the page state data of the next page; and performing the second target action on the second target element of the next page using the processing component until the jumped-to page is a transaction page, and the target transaction business is completed.

[0100] By using the embodiments of the present application, a transaction business processing scheme is provided. Through the method of combining real-time page state detection and multi-modal large model intelligent analysis, the user's interaction behavior on the interface can be dynamically captured. The changes of page elements, user operations, and network request states are monitored in real time, and the multi-modal large model is used to analyze these changes to determine the transaction intent, and then the corresponding business transaction processing logic is automatically generated and executed until the transaction is completed. Through continuous analysis and optimization of the multi-modal large model, more complex business scenarios can be adapted, the speed and accuracy of transaction processing are improved, and the dependence on manual work is reduced, thereby solving the technical problem of low efficiency of business transaction processing in the related art.

[0101] Those skilled in the art can understand that Figure 4 The structure shown is only schematic, and the electronic device can also be a terminal device such as a smart phone, a tablet computer, a palm computer, and a Mobile Internet Device (MID). Figure 4 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device can further include more Figure 4more or less components than shown, such as no network interface, display, or the like, or a different configuration of components, such as a different arrangement of network interfaces, display, or the like. Figure 4

[0102] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiments can be completed by a program instructing the related hardware of the terminal device, and the program can be stored in a computer readable storage medium, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like.

[0103] Embodiment 4

[0104] The embodiments of the present application further provide a storage medium. Optionally, in the embodiments, the storage medium can be used to store the program code executed by the processing method of the transaction service provided in the embodiment 1.

[0105] Optionally, in the embodiments, the storage medium can be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

[0106] The present application further provides a computer program product, which, when executed on a data processing device, is adapted to execute the steps of the processing method of the transaction service.

[0107] The serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0108] In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0109] In the several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit division in the above-mentioned device embodiment is only a logical function division, and there can be another division manner during actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different parts can be indirect couplings or communication connections through some interfaces, units or modules, and can be electrical or other forms.

[0110] ​The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0111] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0112] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. 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 storage medium 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 described in the various embodiments of this application. The aforementioned storage medium 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.

[0113] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of processing a transaction service, characterized by, The application is applied to a client which is integrated with a processing component in advance, and the client comprises: receiving user interaction information, wherein the user interaction information is text information or voice information; processing the user interaction information to obtain a processing result, and calling the processing component in a case where the processing result indicates that the user interaction information contains a target transaction service; collecting page loading files and network request data of a current page by using the processing component, and judging whether the current page is loaded based on the page loading files and the network request data; capturing page state data of the current page in a case where the current page is loaded; processing the page loading files, the page state data and the user interaction information by using a preset recognition model to complete the target transaction service.

2. The treatment method according to claim 1, characterized in that, The step of processing the user interaction information to obtain a processing result comprises: converting the voice information into text in a case where the user interaction information is the voice information; extracting text in the text information in a case where the user interaction information is the text information; dividing the text to obtain a plurality of word groups; matching each word group based on a preset transaction table, wherein the preset transaction table records keywords corresponding to each transaction service; determining the transaction service corresponding to the keyword as the target transaction service contained in the user interaction information in a case where the word group is matched to the keyword.

3. The treatment method of claim 1, wherein After the step of collecting page loading files and network request data of a current page by using the processing component, the method further comprises: cleaning the page loading files to obtain target page loading files; parsing the target page loading files to obtain a plurality of key-value pairs, wherein a primary key in the key-value pair is an element, and a primary key value in the key-value pair is an element coordinate.

4. The treatment method according to claim 3, characterized in that, The step of judging whether the current page is loaded based on the page loading files and the network request data comprises: judging whether the element coordinates in each key-value pair in the page loading files change within a preset time length; judging whether network requests for the current page are loaded based on the network request data in a case where the element coordinates in all key-value pairs in the page loading files do not change within a preset time length; determining that the current page is loaded in a case where the network requests for the current page are loaded.

5. The treatment method of claim 1, wherein The step of capturing page state data of the current page comprises: taking a screenshot of the current page; identifying page elements and page element positions on the screenshot based on the page loading files; determining the page state data based on the screenshot, the page elements and the page element positions.

6. The treatment method of claim 1, wherein Before the step of processing the page loading files, the page state data and the user interaction information by using a preset recognition model, the method further comprises: determining a plurality of business transactions involved in the client; corresponding to each of the business transactions is established, and corresponding execution information of each of the prompt words is determined, wherein the execution information at least includes at least one element, an action performed on each of the elements, and an element sequence; a plurality of historical texts corresponding to each of the business transactions are collected; based on the plurality of historical texts corresponding to each of the business transactions, the prompt words, and the execution information, an initial recognition model is trained to obtain a trained preset recognition model.

7. The treatment method according to claim 6, characterized in that, The step of processing the page loading file, the page state data, and the user interaction information by using the preset recognition model includes: determining a target prompt word corresponding to the target transaction business included in the user interaction information, and determining target execution information based on the target prompt word; based on the page loading file, the page state data, and the target execution information, determining a first target element of the current page and a first target action performed on the first target element; performing the first target action on the first target element of the current page by using the processing component, jumping to a next page, and collecting a page loading file of the next page; in the case that the next page is loaded, capturing page state data of the next page; based on the page loading file and the page state data of the next page, determining a second target element of the next page and a second target action performed on the second target element; performing the second target action on the second target element of the next page by using the processing component until the jumped-to page is a transaction page, and completing the target transaction business.

8. A processing apparatus of a transaction service, characterized by comprising: The application is applied to a client, and the client is pre-integrated with a processing component, and includes: a first receiving unit configured to receive user interaction information, wherein the user interaction information is text information or voice information; a first processing unit configured to process the user interaction information to obtain a processing result, and in the case that the processing result indicates that the user interaction information includes a target transaction business, invoke the processing component; a first collecting unit configured to collect a page loading file and network request data of a current page by using the processing component, and determine whether the current page is loaded based on the page loading file and the network request data; a first capturing unit configured to, in the case that the current page is loaded, capture page state data of the current page; a second processing unit configured to process the page loading file, the page state data, and the user interaction information by using a preset recognition model, and complete the target transaction business.

9. A computer program product, characterised in that, The application includes a non-volatile computer readable storage medium storing a computer program, and the computer program is executed by a processor to implement the transaction business processing method in any one of claims 1 to 7.

10. An electronic device, comprising: An apparatus, including one or more processors and memory storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the transaction processing method of any one of claims 1 to 7.

Images