Business data processing method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a business data processing method and device, equipment, a storage medium and a program product. The method comprises the following steps: reading service data from a front end; wherein the business data is obtained based on a target triggering operation input by a user; based on an input mapping mechanism, analyzing and mapping the business data to obtain input information; wherein the input information comprises an artificial intelligence (AI) instruction and additional information; the additional information comprises structured data which can be identified by the AI automation component; based on the AI automation component, generating a return result according to the input information; mapping the return result into at least one output field based on an output mapping mechanism; and displaying at least one output field. According to the method, a user can flexibly complete input and output mapping and logic configuration of the AI capability without coding, so that the scene requirements of quickly responding to business changes and depending on business data processing are met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a business data processing method and device, equipment, a storage medium and a program product. BACKGROUND

[0002] In recent years, a low-code platform has become a key technology for enterprises to quickly build business systems due to its visual development capabilities. It allows users to quickly build forms, processes, reports and other applications through drag-and-drop controls and configuration logic rather than writing code. At the same time, generative artificial intelligence (AI) technology represented by large language models (LLM) has rapidly developed and shown strong capabilities in content generation, intelligent question answering, and multi-modal data processing (text, speech, images).

[0003] In the prior art, a form type is matched through a predefined component library to automatically generate a form structure, and after a user fills in form data, the form is submitted.

[0004] However, in the above manner, AI is embedded in a fixed application programming interface (API) manner, and users cannot dynamically adjust input and output logic, resulting in AI capabilities that cannot adapt to flexible configuration requirements of different business scenarios. SUMMARY

[0005] The embodiments of the present application provide a business data processing method, device, equipment, storage medium and program product, so that users can flexibly complete input and output mapping and logic configuration of AI capabilities without coding to meet the needs of scenarios that require rapid response to business changes and rely on business data processing.

[0006] In a first aspect, the embodiments of the present application provide a business data processing method, comprising:

[0007] reading business data from a front end; wherein the business data is obtained based on a target trigger operation input by a user;

[0008] analyzing and mapping the business data based on an input mapping mechanism to obtain input information; wherein the input information includes an artificial intelligence (AI) instruction and additional information; and the additional information includes structured data that can be recognized by an AI automation component;

[0009] generating a return result based on the AI automation component and the input information;

[0010] Map the return result to at least one output field based on an output mapping mechanism; and display the at least one output field.

[0011] In a possible implementation, the input mapping mechanism is used to parse and map the business data to obtain input information, including:

[0012] The field value of each form field in the business data and the fixed text are combined to obtain an AI instruction in the input information.

[0013] According to the field type of each attachment field in the business data, each attachment field in the business data is parsed and processed to obtain additional information in the input information.

[0014] In a possible implementation, the parsing and processing of each attachment field in the business data according to the field type of each attachment field in the business data includes:

[0015] A backend parsing tool is called to perform text extraction mapping on a document corresponding to the attachment field.

[0016] And / or, a speech transcription tool interface is called to perform text parsing mapping on audio corresponding to the attachment field.

[0017] And / or, an optical character recognition interface is called to perform text parsing mapping on a picture corresponding to the attachment field.

[0018] In a possible implementation, the display of the at least one output field includes:

[0019] According to the field value of the at least one output field, a processing result is generated and displayed.

[0020] In a possible implementation, the display of the processing result includes:

[0021] Based on a form UI component, the output state of each output field in the processing result is determined.

[0022] If it is determined that the output state of the output field is a display state, the execution time of the processing result, the output field, and a refresh button are displayed; the refresh button is used to indicate generation of a new processing result.

[0023] If it is determined that the output state of the output field is a hidden state, the output field is hidden.

[0024] In a possible implementation, the target trigger operation is a button trigger operation or a script trigger operation; the button trigger operation is an operation on a button in a front-end interface; the button is a form custom button, a process custom button, or a view custom button.

[0025] In a possible implementation, the business data includes one or more of the following: form data, process data, and view data; the view data includes a plurality of sub-business data to be batch processed.

[0026] In a possible implementation, after the operation of mapping the return result to at least one output field, the method further includes:

[0027] According to the field state of the output field, the output field is backfilled.

[0028] In a possible implementation, the operation of backfilling the output field according to the field state of the output field includes:

[0029] If it is determined that the field state of the output field is the edit-only read state, the backfilled value of the output field is checked to obtain a check result of the output field.

[0030] If it is determined that the check result of the output field indicates that the backfilled value of the output field passes the check, the output field is backfilled.

[0031] In a possible implementation, the method further includes:

[0032] A preset callback event script is executed to read context parameters; the context parameters include the return result and associated identification information.

[0033] The context parameters are saved as at least one specified field.

[0034] According to the field value of the specified field, the specified field is displayed.

[0035] In a second aspect, an embodiment of the present application provides a business data processing apparatus, including:

[0036] A reading module is configured to read business data from a front end; the business data is obtained based on a target trigger operation input by a user.

[0037] An input module is configured to analyze and map the business data based on an input mapping mechanism to obtain input information; the input information includes an artificial intelligence (AI) instruction and additional information; the additional information includes structured data recognizable by an AI automatic component.

[0038] generating a return result based on the AI automation component and according to the input information;

[0039] outputting and displaying the at least one output field.

[0040] In a possible implementation, the input module is specifically configured to: combine and map a field value of each form field in the business data and a fixed text to obtain an AI instruction in the input information; and parse and process each attachment field in the business data according to a field type of each attachment field in the business data to obtain additional information in the input information.

[0041] In a possible implementation, the input module is specifically configured to: call a backend analysis tool to perform text extraction mapping on a document corresponding to the attachment field; and / or call a speech transcription tool interface to perform text analysis mapping on an audio corresponding to the attachment field; and / or call an optical character recognition interface to perform text analysis mapping on a picture corresponding to the attachment field.

[0042] In a possible implementation, the output module is specifically configured to: generate and display a processing result according to a field value of the at least one output field.

[0043] In a possible implementation, the output module is specifically configured to: determine an output state of each output field in the processing result based on a form UI component; if it is determined that the output state of the output field is a display state, display an execution time of the processing result, the output field, and a refresh button; wherein the refresh button is used to indicate generation of a new processing result; and if it is determined that the output state of the output field is a hidden state, hide the output field.

[0044] In a possible implementation, the target trigger operation is a button trigger operation or a script trigger operation; wherein the button trigger operation is an operation acting on a button in a front-end interface; and the button is a form custom button, or a process custom button, or a view custom button.

[0045] In a possible implementation, the business data includes one or more of the following: form data, process data, and view data; wherein the view data includes a plurality of sub-business data to be batch processed.

[0046] In a possible implementation, after mapping the return result into at least one output field, the output module is further configured to: perform backfill processing on the output field according to a field state of the output field.

[0047] In a possible implementation, the output module is further configured to: if it is determined that the field state of the output field is an edit-only read state, perform check processing on the backfilled value of the output field to obtain a check result of the output field; and if it is determined that the check result of the output field indicates that the backfilled value of the output field passes the check, perform backfill processing on the output field.

[0048] In a possible implementation, the device is further configured to: execute a preset callback event script to read context parameters; the context parameters include the return result and associated identification information; save the context parameters as at least one designated field; and display the designated field according to a field value of the designated field.

[0049] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0050] The memory stores computer execution instructions.

[0051] The processor executes the computer execution instructions stored in the memory, so that the processor executes the first aspect and / or various possible implementation manners of the first aspect.

[0052] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the first aspect and / or various possible implementation manners of the first aspect.

[0053] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and the computer program is executed by a processor to implement the first aspect and / or various possible implementation manners of the first aspect.

[0054] The business data processing method, device, equipment, storage medium and program product provided by the embodiment of the application, after the user inputs a target trigger operation to the front end, the input information is obtained by analyzing and mapping the business data read from the front end based on the configured input mapping mechanism, the artificial intelligence AI instruction and additional information in the input information are processed by the configured AI automatic component, the return result is obtained, the return result obtained is mapped into multiple output fields by the configured output mapping mechanism, and visual display processing is performed; further, by encapsulating the front-end trigger logic, the input and output field mapping mechanism and the AI configuration capability, the user can flexibly complete the input and output mapping and logic configuration of the AI capability without coding, so as to meet the scene requirements of needing to quickly respond to business changes and relying on business data processing. BRIEF DESCRIPTION OF DRAWINGS

[0055] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0056] Figure 1 An application scenario diagram provided by the present application;

[0057] Figure 2 A flowchart of a business data processing method provided by the embodiment of the present application;

[0058] Figure 3 A flowchart of another business data processing method provided by the embodiment of the present application;

[0059] Figure 4 A diagram of a business data example provided by the embodiment of the present application;

[0060] Figure 5 A diagram of a form self-defined button trigger scene interface provided by the embodiment of the present application;

[0061] Figure 6 A diagram of another form self-defined button trigger scene interface provided by the embodiment of the present application;

[0062] Figure 7 A diagram of a view self-defined button trigger scene interface provided by the embodiment of the present application;

[0063] Figure 8 A working principle diagram of an automatic form interaction system based on artificial intelligence capability integration provided by the embodiment of the present application;

[0064] Figure 9 A diagram of a callback event mechanism execution result interface provided by the embodiment of the present application;

[0065] Figure 10 A schematic diagram of a form backfill function configuration interface provided by an embodiment of the present application is shown in FIG. 1.

[0066] Figure 11 A structural schematic diagram of a service data processing device provided by an embodiment of the present application is shown in FIG. 4.

[0067] Figure 12 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 5.

[0068] The specific embodiments of the present application have been shown in the above-described drawings, and will be described in more detail hereinafter. These drawings and the written description are not intended to restrict the scope of the present application concept in any way, but to illustrate the present application concept to those skilled in the art by reference to a specific embodiment. DETAILED DESCRIPTION

[0069] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, the same numbers are used to indicate the same or similar components. The embodiments described in the following exemplary embodiments are not meant to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0070] 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 for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user selection authorization or refusal.

[0071] And the present application involves big data analysis of user information (including but not limited to personal biological characteristics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and uses artificial intelligence technology for automatic decision-making, and makes technical solutions based on automatic decision-making results that have a significant impact on personal rights and interests, provides corresponding operation portal for users to choose to agree or refuse automatic decision-making results; if the user chooses to refuse, the expert decision-making process is entered.

[0072] It should be noted that the present application can be used in the field of artificial intelligence technology, and can also be used in any field other than artificial intelligence technology, and the application field of the present application is not limited.

[0073] Figure 1 An application scenario provided by the present application is shown in FIG. 6, such asFigure 1 As shown, the specific application scenario of the present application is: matching the form type through the pre-defined component library in the device 101, automatically generating the form structure, and the user 102 fills in the form data and submits the form.

[0074] In combination with the above scenario, it can be known that in the prior art, AI is embedded in a fixed API manner, and the user cannot dynamically adjust the input and output logic, resulting in that the AI capability cannot adapt to the flexible configuration requirements of different business scenarios.

[0075] The form data processing method provided in the present application solves the technical problem that the AI capability cannot adapt to the flexible configuration requirements of different business scenarios by encapsulating the front-end trigger logic, the input and output field mapping mechanism and the AI configuration capability.

[0076] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0077] Figure 2 A flowchart of a business data processing method provided in an embodiment of the present application is shown in FIG. 1. Figure 2 As shown, the method comprises:

[0078] 201, reading business data from the front end; wherein the business data is obtained based on a target trigger operation input by a user.

[0079] Exemplarily, the execution subject of the present embodiment can be an electronic device. The user inputs a target operation mode, for example, a drag mode, through a form in a front-end display interface of the device to trigger AI capability. The device reads business data in the current business scenario from the front end for processing.

[0080] The target trigger operation is a button trigger operation or a script trigger operation; the button trigger operation is an operation on a button in the front-end interface; the button is a form custom button, or a flow custom button, or a view custom button. For example, a button in a form is configured to execute AI automatic action, and a function is triggered after a component is selected, such as clicking “compliance check” to check the content of a sub-form record in batches.

[0081] Alternatively, a JavaScript method is called in a specific form or user interface (User Interface, referred to as UI) event to forcibly execute AI automatic function; for example, uploading a contract triggers parsing, or filling in a customer problem returns a solution.

[0082] By supporting multiple trigger paths, the pluggability and controllability of AI capabilities in business are improved, such as encapsulating the JS execution method of the UI. When the front end is called asynchronously, the field / subtable or area specified as the output at this time is selected by the AIEditing box, and the return result is waited. During this period, other operations of the form can be performed normally.

[0083] 202. Based on the input mapping mechanism, the business data is parsed and mapped to obtain input information; wherein the input information includes artificial intelligence AI instructions and additional information; the additional information includes structured data that can be recognized by an AI automation component.

[0084] For example, the device pre-packages an input mapping mechanism for configuring input mapping rules. Based on the input mapping mechanism, the business data is parsed and mapped according to the preset input mapping rules to obtain input information, which includes artificial intelligence AI instructions and additional information, and the additional information includes structured data that can be recognized by an AI automation component.

[0085] For example, the instruction content (set question content) generated based on the target trigger operation in the business data is structured and processed to generate a prompt (Prompt) instruction. The background data, fields, and subtable fields added in the business data are combined into an AI understandable JSON structure by supporting the functions of checking the records or all (maximum row limit, see form assistant).

[0086] Among them, the input parameters of the artificial intelligence agent component (AI Agent) / artificial intelligence workflow (AI Workflow) can also be set as part of the input information, which is used to select fields according to formula rules, such as the current storage ID.

[0087] 203. Based on the AI automation component, a return result is generated according to the input information.

[0088] For example, based on the AI automation component, the additional information in the input information is processed according to the AI instructions in the input information to generate a return result.

[0089] For example, the AI instruction is used to instruct data checking, and the AI automation component checks and arranges the return result in the input information to generate a return result containing data checking results. The data checking results can include the checking results of each field in the business data to be used for data anomaly prompt.

[0090] Among them, the AI automation component is a pre-configured callable AI capability resource (which can be set as an AI resource accessible to form designers), including AI Workflow encapsulated for business scenarios and AI Agent with memory, context understanding and task decomposition capabilities.

[0091] 204. mapping the return result into at least one output field based on the output mapping mechanism; and displaying the at least one output field.

[0092] Exemplarily, the device pre-packages the output mapping mechanism for configuring the output mapping rule. The return result is mapped into at least one output field based on the output mapping mechanism, and the output field can be a specified field of a target data source or a specified data source. For example, the main table and the subtable field (which needs to be an ajax editable subtable to be mapped) can be mapped. All or part of the output fields are displayed on the front end through the visual component of the front end, so as to facilitate the user to view the business data processing result on the front end.

[0093] Wherein, the output mapping of the non-value virtual field and the attachment type field is not supported at present (the project can customize the processing through the callback event), and a prompt information is displayed on the form after the output mapping is successful.

[0094] In the embodiment, a business data processing method is provided, which enables the user to flexibly complete the input and output mapping and logic configuration of the AI capability without coding, realizes the configurable and extensible AI workflow embedding mechanism, and is used for processing the business data in different business scenarios to adapt to the flexible configuration requirements of different business scenarios.

[0095] Figure 3 Another flowchart of a form data processing method provided by the embodiment of the present application is shown in FIG. 6, and the method comprises the following steps. Figure 3

[0096] 301. reading the business data from the front end; wherein the business data is obtained based on the target trigger operation input by the user.

[0097] Exemplarily, this step can refer to step 201, which will not be described here.

[0098] Wherein, the business data comprises form data, process data and view data. The form data is a data set submitted to the device by the user after inputting or selecting on the form on the webpage, application (App) or software interface, for example, the text input by the user in the input box (input) or text box (textarea). The process data can include process definition data (for example, the blueprint or template of the process defining the steps, rules and paths) and process instance data (for example, a specific instance created according to the process definition, which is running or has been completed). The view data can include the state data or model data saved in the view layer in advance, which can include multiple pieces of sub-business data to be batch processed (for example, multiple pieces of contract data to be batch processed for approval), and the processing result of the multiple pieces of sub-business data after batch processing can be obtained through subsequent AI automatic processing. ​

[0099] For example, Figure 4 A schematic diagram illustrating a business data example provided in an embodiment of this application, such as... Figure 4 As shown, the data in the left area is view data, including one sub-business data entry pending approval. This sub-business data entry specifically includes the form data in the right area. In one example, Figure 5 This is a schematic diagram of a form custom button trigger scenario interface provided in an embodiment of this application, such as... Figure 5 As shown, for a custom button action in a form: Activating the "Initiate AI Assistant" button sends a command to the AI ​​assistant configured in the current form or a further specified skill. The relevant parameter mapping is handled by a pre-built assistant mechanism. The user then waits for the assistant's response on the right, initiating a dialogue. This method encapsulates fixed commands into a button for quick user operation. For example, in a project, a custom-developed form intelligent assistant skill A allows users to issue commands and initiate dialogue via a button.

[0100] In one example, Figure 6 This is a schematic diagram of another form custom button triggering scenario interface provided in an embodiment of this application, such as... Figure 6 As shown, for the custom button-action in the form: The "AI Automation" button will execute, and the result will be processed via a pop-up window or callback event script. The execution process is asynchronous or a masked prompt indicates waiting. For example, a trust project checks the form for sensitive words, displaying the check results in a pop-up window with one click. If the returned result matches a specific JSON value, the project can mark the abnormal status value via a callback script, and then intercept the form according to form rules as the process moves forward.

[0101] In one example, a custom button-action is defined for the workflow: The "AI Automation" button is activated, and the result is processed via a pop-up window or callback event script. The execution process is asynchronous or accompanied by a waiting message. For instance, a trust project checks a form for sensitive words, displaying the check results in a pop-up window with a single click. If the returned result matches a specific JSON value, the project can mark the abnormal status value via a callback script, allowing for form rule-based interception as the workflow progresses.

[0102] In one example, a custom button-action is defined for the workflow: Activating the "Summon AI Assistant" button sends a command to the AI ​​assistant configured in the current workflow / form or a further specified skill. The relevant parameter mapping is handled by a pre-built assistant mechanism. The user then waits on the right for the assistant's response and initiates a dialogue. This method encapsulates fixed commands into the toolbar for quick user interaction.

[0103] In one example, Figure 7 This is a schematic diagram of a view-customizable button-triggered scene interface provided in an embodiment of this application, such as... Figure 7As shown, for the view's custom button-action: The "AI Automation" button will execute, and the results will be processed via a pop-up window or callback event script. The execution process is asynchronous or accompanied by a waiting mask. For example, a trust project can batch check views for sensitive words, displaying the check results in a pop-up window with a single click. If the returned result matches a specific JSON value, the project can mark the abnormal status value via a callback script, and then implement form rule interception as the process moves downwards.

[0104] In one example, a custom button-action is defined for the view: Activating the "Summon AI Assistant" button sends a command to the AI ​​assistant configured in the current view or a further specified skill. The relevant parameter mapping is handled by a pre-built assistant mechanism. The user then waits for the assistant's response and initiates a dialogue. This approach encapsulates fixed commands within the toolbar for quick user interaction.

[0105] 302. Combine and map the field values ​​and fixed text of each form field in the form data to obtain the AI ​​instructions in the input information.

[0106] For example, based on the AI ​​task indicated by the user's input target trigger operation, corresponding instruction content is generated. This instruction content is then mapped to a preset instruction template. The field values ​​of each form field in the form data are combined with fixed text and the instruction content to obtain dynamic instructions, i.e., AI instructions. Field selection via @ formula is supported.

[0107] Specifically, the @ field marker in the preset template is parsed, and the field value of the corresponding form field in the form data is obtained according to the position of the @ field marker. These field values ​​are then concatenated to generate the final AI instruction.

[0108] 303. Based on the field type of each attachment field in the form data, parse and process each attachment field in the form data to obtain the additional information in the input information.

[0109] For example, when the form data includes an attachment field, each attachment field in the form data is extracted and identified to determine the field type of each attachment field. Based on the field type of the attachment field, including special fields such as document fields, table fields, and graphic element fields, the parsing mapping method corresponding to the field type is called to parse and process each attachment field to obtain the additional information in the input information.

[0110] Through the input mapping mechanism, the AI ​​capabilities required in different business scenarios can be flexibly adapted, thereby facilitating AI automation, improving business processing efficiency, and further meeting the form data processing needs in different business scenarios.

[0111] In a possible implementation, step 303 comprises: calling a backend analysis tool to perform text extraction mapping on the document corresponding to the attachment field. And / or, calling a speech transcription tool interface to perform text analysis mapping on the audio corresponding to the attachment field. And / or, calling an optical character recognition interface to perform text analysis mapping on the picture corresponding to the attachment field.

[0112] Specifically, Figure 8 A working principle diagram of an automatic form interaction system based on artificial intelligence capability integration provided by an embodiment of the present application is shown in Figure 8 As shown, after the user triggers AI capability through input target triggering operation, form data and instruction content are obtained. According to the requirements of the instruction content, the corresponding mapping rule in the input mapping mechanism is called to map the form data. When some special fields in the form data are involved, if the field is an attachment type, text analysis of common documents is supported, that is, the interface of a related tool is called by the backend to perform text extraction mapping on the document corresponding to the attachment field. And / or, audio-to-text analysis is supported, that is, a speech transcription tool interface is encapsulated, and the speech transcription tool interface is called during input mapping to perform text analysis mapping on the audio corresponding to the attachment field, and the audio is converted into text. This scenario can be in a non-agent mode, and the interface is called in the background. And / or, picture-to-text analysis is supported, that is, an optical character recognition interface is called by the backend to perform text analysis mapping on the picture corresponding to the attachment field, and the picture is converted into text to obtain additional information.

[0113] Among them, the AI easy-to-understand segmentation method can be used for isolation and splicing, including file name and file content. For fields without values, input mapping is not supported.

[0114] 304. Based on the AI automation component, a return result is generated according to the input information.

[0115] Exemplarily, in combination with Figure 8 , a corresponding AI automation component is selected through a button, a UI event, and a script (for example, a JavaScript script, referred to as a JS script) in the triggering mechanism to trigger a corresponding AI capability, including an AI Workflow and an AI Agent. The input information obtained is processed through the AI capability of the AI automation component to generate a return result. For specific processes, reference is made to the foregoing step 203, which will not be described here again.

[0116] In a possible implementation, after step 304, the following steps are included:

[0117] Step one, a preset callback event script is executed to read context parameters; wherein the context parameters include a return result and associated identification information.

[0118] Step two, save the context parameters to at least one designated field.

[0119] Step three, display the designated field according to the field value of the designated field.

[0120] Specifically, based on the callback event mechanism, after obtaining the return result of the AI, the preset callback event script can be triggered and executed to read the context parameters, including the return result of the AI and the associated identification information, including the session identity (Identity document, referred to as ID), message ID, intelligent assistant ID, and intelligent chain ID. Among them, the return result can be composed of structured data (such as JSON structured data). Save the context parameters to at least one hidden designated field, such as a designated field in a pre-set target data source. On the front end, based on the field value of each designated field, perform display processing, such as red or yellow display.

[0121] For example, Figure 9 A schematic diagram of a callback event mechanism execution result interface provided by an embodiment of the present application is shown in Figure 9 According to the contract information in the form data under the current business scenario, the AI automatically performs contract risk intelligent control, gives the field value of each field to represent the risk prompt of each field, and constructs a personalized interaction on the front end based on each field value. For example, according to the clue information in the form data under the current business scenario, the AI automatically gives the clue score, BANT insight, record summary, product intention, and solution recommendation. These information are composed of JSON returned by the AI and saved to a hidden designated field. A personalized interaction is constructed on the front end based on the field value.

[0122] By dynamically reading the form data (main table field, sub-table field, and attachment), a JSON input structure that is easy for the AI to understand is constructed, so that the AI is natively integrated with the form, supports multi-modal data processing, and the user experience is smoother.

[0123] 305, based on the output mapping mechanism, map the return result to at least one output field.

[0124] By way of example, this step can refer to step 204, which will not be described here.

[0125] In one possible implementation, after step 305, it includes: according to the field state of the output field, performing backfill processing on the output field.

[0126] Specifically, Figure 10 A schematic diagram of a form backfill function configuration interface provided by an embodiment of the present application is shown in Figure 10As shown, including configuration instruction content, binding smart chain / smart assistant, configuring input parameters, field backfill rules, and selecting AI automation components to adapt to form backfill tasks in different business scenarios. Based on the field rules configured in the output mapping mechanism, the field state of the output field is determined, such as read-only state, edit-read-only state, copyable state, and non-copyable state. For each output field, when the output field is read-only, it will not be backfilled, and when the output field is edit-read-only, it can be backfilled, that is, the output field can be backfilled into the form, combined with Figure 3 The output field can be backfilled into the form or a sub-form in the form. In this embodiment, the batch backfill processing process of multiple sub-business data in view data can also be applied, which will not be described here.

[0127] For example, the AI automation action is triggered after selecting the component and backfilling after clicking the "AI generation" button in the form to fill in the content field.

[0128] In a possible implementation, after step 305, specifically comprising: if it is determined that the field state of the output field is the edit-read-only state, the backfill value of the output field is verified to obtain a verification result of the output field; and if it is determined that the verification result of the output field indicates that the backfill value of the output field passes the verification, the output field is backfilled.

[0129] Specifically, based on the field rules configured in the output mapping mechanism, the field state of the output field is determined, and for each output field, if it is determined that the field state of the output field is the edit-read-only state, the output field can be backfilled. At this time, based on the exception handling mechanism, the backfill value of each output field needs to be read, and the backfill value of the output field is verified through a preset verification rule, for example, whether the backfill value of the output field meets a preset condition, to obtain a verification result of the output field, so as to determine whether the backfill value of the output field passes the verification. If it is determined that the verification result of the output field indicates that the backfill value of the output field passes the verification, the output field is backfilled to ensure data consistency and validity.

[0130] Among them, based on the exception handling mechanism, all exceptions are prompted with user-understandable business scripts; the background provides log query capability.

[0131] The structured data returned by the AI can be automatically filled into the specified field or display area, realizing intelligent output backfill, and through the provision of a unified backfill value verification mechanism, ensuring data security and reliability.

[0132] 306、According to the field value of at least one output field, a processing result is generated and displayed.

[0133] Exemplarily, combined with Figure 8After obtaining the output fields, all the output fields can be obtained through the front-end controller as the final processing result, and the field value of each output field is determined to determine whether each output field is displayed, how to display (high volume, bold, converted to a graphical element display), and to call a visualization component to display and process each output field in the processing result according to the field value of the output field.

[0134] Further, based on the principle of "AI trigger controllable front-end, execution echo front-end", the user directly calls the AI capability through the drag control or button, and the front-end displays the processing result in real time, which does not depend on the background processing (unless the executed AI workflow contains API calling), and ensures the transparency of interaction.

[0135] In a possible implementation, step 306 includes:

[0136] Step one, determine the output state of each output field in the processing result based on the form UI component.

[0137] Step two, if it is determined that the output state of the output field is a display state, display the execution time, the output field, and the refresh button corresponding to the processing result; wherein the refresh button is used to indicate the generation of a new processing result.

[0138] Step three, if it is determined that the output state of the output field is a hidden state, hide the output field.

[0139] Specifically, by calling the pre-configured form UI component, the output state of each output field in the processing result is determined, including a display state or a hidden state, if it is determined that the output state of the output field is a display state, the execution time of the AI task corresponding to the processing result, the output field, and the refresh button are displayed. In combination with Figure 8 The content of the display UI includes text, index card, time axis, word cloud diagram, etc. For the current processing form, the field storage is performed after the display, and the next time the form is opened, the stored field value can be used for display.

[0140] The refresh button is used to indicate the generation of a new processing result, that is, the user can execute the AI task corresponding to the processing result again through the operation of the refresh button to generate a new processing result. If it is determined that the output state of the output field is a hidden state, the output field is hidden and no display processing is performed.

[0141] In combination with Figure 8 For example, through the trigger of the foreground or the front-end, mapping fields, skeleton screens of display UIs, AI frame selection, and sub-table AI frame selection events are performed, and the results of the display UIs are returned, including display UI data, display UI scanning animation end, and field data.

[0142] In this embodiment, on the basis of the above embodiment, an AI automatic execution mechanism initiated by the front end and having input-output mapping capability is set to realize intelligent decision assistance, content generation, field backfilling and other business operations, and has high availability, high flexibility and strong expansibility.

[0143] Figure 11 A structural schematic diagram of a business data processing apparatus provided in an embodiment of the present application is shown in FIG. 1. The apparatus includes: Figure 11

[0144] The reading module 401 is configured to read business data from the front end, wherein the business data is obtained based on a target trigger operation input by a user.

[0145] The input module 402 is configured to parse and map the business data based on an input mapping mechanism to obtain input information, wherein the input information includes an artificial intelligence (AI) instruction and additional information, and the additional information includes structured data recognizable by an AI automatic component.

[0146] The generation module 403 is configured to generate a return result based on the AI automatic component and according to the input information.

[0147] The output module 404 is configured to map the return result to at least one output field based on an output mapping mechanism, and display the at least one output field.

[0148] In a possible implementation, the input module 402 is specifically configured to: combine and map a field value of each form field and fixed text in the business data to obtain the AI instruction in the input information; and parse and process each attachment field in the business data according to a field type of each attachment field in the business data to obtain the additional information in the input information.

[0149] In a possible implementation, the input module 402 is specifically configured to: call a back-end analysis tool to perform text extraction mapping on a document corresponding to the attachment field; and / or call a speech transcription tool interface to perform text analysis mapping on an audio corresponding to the attachment field; and / or call an optical character recognition interface to perform text analysis mapping on a picture corresponding to the attachment field.

[0150] In a possible implementation, the output module 404 is specifically configured to generate and display a processing result according to a field value of the at least one output field.

[0151] ​In a possible implementation, the output module 404 is specifically configured to: determine the output state of each output field in the processing result based on the form UI component; if it is determined that the output state of the output field is a display state, display the execution time corresponding to the processing result, the output field, and a refresh button; the refresh button is used to indicate generation of a new processing result; if it is determined that the output state of the output field is a hidden state, hide the output field.

[0152] In a possible implementation, the target trigger operation is a button trigger operation or a script trigger operation; the button trigger operation is an operation on a button in a front-end interface; the button is a form custom button, or a process custom button, or a view custom button.

[0153] In a possible implementation, the business data includes one or more of the following: form data, process data, and view data; the view data includes a plurality of sub-business data to be batch processed.

[0154] In a possible implementation, after the output module 404 is configured to map the return result to at least one output field, the output module is further configured to: perform backfill processing on the output field according to the field state of the output field.

[0155] In a possible implementation, the output module 404 is further configured to: if it is determined that the field state of the output field is an edit read-only state, perform check processing on the backfill value of the output field to obtain a check result of the output field; if it is determined that the check result of the output field indicates that the backfill value of the output field passes the check, perform backfill processing on the output field.

[0156] In a possible implementation, the device is further configured to: execute a preset callback event script to read context parameters; the context parameters include the return result and the associated identification information; save the context parameters as at least one specified field; and display the specified field according to the field value of the specified field.

[0157] The device of the embodiment can execute the technical solutions in the above method, and the specific implementation process and technical principles are the same, which will not be repeated here.

[0158] Figure 12 A structural schematic diagram of an electronic device provided by the embodiment of the present application is shown in FIG. 1. Figure 12 As shown in FIG. 1, the electronic device includes a memory 501 and a processor 502; the memory 501 is used to store the memory of the executable instructions of the processor 502.

[0159] The processor 502 is configured to execute the method provided by the above embodiment.

[0160] The electronic device further includes a receiver 503 and a transmitter 504. The receiver 503 is configured to receive instructions and data transmitted by other devices, and the transmitter 504 is configured to transmit instructions and data to external devices.

[0161] The specific implementation process of the processor can refer to the method embodiments described above, which have similar implementation principles and technical effects, and will not be described here.

[0162] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the disclosed method can be directly embodied as hardware processor execution or combined with hardware and software modules in the processor for execution.

[0163] The embodiment of the present application further provides a computer readable storage medium, which stores computer execution instructions, and when the computer execution instructions run on a computer, the computer executes the technical solutions of the above embodiments.

[0164] The readable storage medium described above can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0165] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. The readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in a special integrated circuit. The processor and the readable storage medium can also exist as discrete components in the device.

[0166] The embodiment of the present application further provides a computer program product, which includes a computer program stored in a computer readable storage medium, and at least one processor can read the computer program from the computer readable storage medium, and the at least one processor executes the computer program to implement the technical solutions in the above embodiments.

[0167] Those skilled in the art can understand that all or part of the steps of the foregoing method embodiments can be completed by relevant hardware of program instructions. The foregoing program can be stored in a computer readable storage medium. When the program is executed, the steps of the foregoing method embodiments are executed; and the foregoing storage medium includes various media capable of storing program codes, such as magnetic disks or optical disks.

[0168] Finally, it should be noted that other embodiments of the present application will readily occur to those skilled in the art upon consideration of the specification and practice of the present application disclosed herein. The present application is intended to include all such variations and modifications in keeping with the principles of the present application and including commonly accepted notions or practices within the art of the present application not specifically recited herein. The present application is not limited to the precise structures described and illustrated herein and can be variously modified and changed without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A business data processing method, characterized in that, include: Read business data from the front end; wherein, the business data is obtained based on the target triggered operation based on user input; Based on the input mapping mechanism, the business data is parsed and mapped to obtain input information; wherein, the input information includes artificial intelligence (AI) instructions and additional information; the additional information includes structured data that can be recognized by AI automation components; Based on the AI ​​automation component, a return result is generated according to the input information; Based on the output mapping mechanism, the returned result is mapped to at least one output field; and the at least one output field is displayed.

2. The method according to claim 1, characterized in that, The input mapping mechanism is used to parse and map the business data to obtain input information, including: The field values ​​and fixed text of each form field in the business data are combined and mapped to obtain the AI ​​instructions in the input information; Based on the field type of each attachment field in the business data, each attachment field in the business data is parsed to obtain the additional information in the input information.

3. The method according to claim 2, characterized in that, The step of parsing each attachment field in the business data according to the field type of each attachment field in the business data includes: The backend parsing tool is invoked to extract and map the main text of the documents corresponding to the attachment fields. And / or, call the speech-to-text tool interface to perform text parsing and mapping on the audio corresponding to the attachment field; And / or, call the optical character recognition interface to perform text parsing and mapping on the image corresponding to the attachment field.

4. The method according to claim 1, characterized in that, The display of the at least one output field includes: Based on the field values ​​of at least one output field, generate and display the processing result; And / or, based on the form UI components, determine the output status of each output field in the processing result; If the output state of the output field is determined to be in the display state, then the execution time corresponding to the processing result, the output field, and the refresh button are displayed; wherein, the refresh button is used to indicate the generation of a new processing result; If the output field is determined to be in a hidden state, then the output field is hidden.

5. The method according to claim 1, characterized in that, The target triggering operation is a button triggering operation or a script triggering operation; wherein, the button triggering operation is an operation performed on a button in the front-end interface; the button is a form custom button, a process custom button, or a view custom button; And / or, the business data includes one or more of the following: form data, process data, and view data; wherein the view data includes multiple sub-business data to be processed in batches.

6. The method according to claim 1, characterized in that, After mapping the returned result to at least one output field, the method further includes: Based on the field status of the output field, the output field is backfilled. And / or, if it is determined that the field status of the output field is edit-only, the backfill value of the output field is validated to obtain the validation result of the output field; If the verification result of the output field indicates that the backfill value of the output field has passed the verification, the output field is backfilled.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: Execute a preset callback event script to read context parameters; wherein, the context parameters include the return result and associated identification information; The context parameter is saved as at least one specified field; Display the specified field based on its value.

8. A business data processing device, characterized in that, include: The reading module is used to read business data from the front end; wherein, the business data is obtained based on the target triggered operation based on user input; The input module is used to parse and map the business data based on an input mapping mechanism to obtain input information; wherein, the input information includes artificial intelligence (AI) instructions and additional information; the additional information includes structured data that can be recognized by AI automation components; The generation module is used to generate a return result based on the input information, using the AI ​​automation component. An output module is used to map the returned result to at least one output field based on an output mapping mechanism, and to display the at least one output field.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium / computer program product, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when executed by a processor, are used to implement the method as described in any one of claims 1-7; and / or, the computer program product includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1-7.

Images