Conversation processing method, computing device and storage medium

Abstract

The invention discloses a dialogue processing method, which comprises the steps of identifying user input information based on a vectorization model and a first large model to determine a service card of a target service, filling the service card of the target service based on the user input information to determine a service execution card corresponding to the target service, and executing the target service based on the service execution card. According to the dialogue processing method, the computing device and the storage medium provided by the invention, the service card corresponding to the target service can be accurately identified according to the user input information, and the service card is automatically filled based on the user input information to generate the execution service card, so that the execution of the target service is completed based on the execution service card; therefore, the accuracy and execution efficiency of business processing in the natural language interaction scene are improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and more specifically, to a dialogue processing method, a computing device, and a storage medium. Background Technology

[0002] As enterprises continuously improve their IT-enabled office practices, high-frequency HR processes such as leave requests, attendance tracking, and card replacements are gradually migrating from offline workflows and traditional PC systems to intelligent dialogue terminals. Therefore, accurately identifying and efficiently processing user business needs in natural language interaction scenarios has become a crucial development direction for enterprise HR systems. Summary of the Invention

[0003] To address the aforementioned issues, this invention proposes a dialogue processing method, computing device, and storage medium. This method can accurately identify the business card corresponding to the target business based on user input information, automatically fill in the business card based on the user input information to generate an execution business card, and then complete the execution of the target business based on the execution business card, thereby improving the accuracy and execution efficiency of business processing in natural language interaction scenarios.

[0004] This invention provides a dialogue processing method. In one embodiment, the method includes: identifying user input information based on a vectorization model and a first large model to determine a service card for a target service; filling in the service card for the target service based on the user input information to determine an execution service card corresponding to the target service; and executing the target service based on the execution service card.

[0005] In one embodiment, the user input information includes user input information for the current round and context information corresponding to the user input information for the current round; the step of identifying the user input information based on the vectorization model and the first large model to determine the business card of the target business includes: performing vector filtering on the user input information based on the vectorization model to obtain candidate business cards; and inputting the user input information and the candidate business cards into the first large model to determine the business card of the target business.

[0006] In one embodiment, the service card of the target service includes an output card and an input card; the step of filling in the service card of the target service based on the user input information to determine the execution service card corresponding to the target service includes: when the service card of the target service is the output card, filling in the service card of the target service based on the user input information and the second major model to determine the execution service card corresponding to the target service; when the service card of the target service is the input card, filling in the service card of the target service based on the user input information, the second major model, and user editing information to determine the execution service card corresponding to the target service.

[0007] In one embodiment, when the business card of the target service is the output card, the business card of the target service is filled in based on the user input information and the second major model to determine the execution business card corresponding to the target service. This includes: inputting the description of the items to be filled in the business card of the target service and the user input information into the second major model to obtain the filling parameters corresponding to each item to be filled in; and after converting the format and validating the rules of the filling parameters, filling them into the corresponding items to be filled in to obtain the execution business card corresponding to the target service.

[0008] In one embodiment, when the business card of the target service is the input type card, the business card of the target service is filled in based on the user input information, the second large model, and the user editing information to determine the execution business card corresponding to the target service. This includes: inputting the description of the items to be filled in the business card of the target service and the user input information into the second large model to obtain the filling parameters corresponding to each item to be filled in; after converting the format and validating the rules of the filling parameters, filling them into the corresponding items to be filled in to obtain the first filling state business card of the target service; after sending the first filling state business card of the target service to the interactive interface, obtaining the user editing information of the interactive interface for the first filling state business card of the target service; and filling in the first filling state business card of the target service based on the user editing information to obtain the execution business card of the target service.

[0009] In one embodiment, after converting the format of the input parameter and performing rule validation, the parameter is then filled into the corresponding field to be filled. This includes: converting the format of the input parameter into a format compatible with the corresponding field to be filled; performing rule validation on the input parameter according to the validation rules corresponding to the field to be filled; when the input parameter passes the rule validation, the input parameter is filled into the corresponding field to be filled; when the input parameter fails the rule validation, the corresponding field to be filled is set to a pending state, or the field to be filled is filled according to the default value of the field to be filled.

[0010] In one embodiment, the step of executing the target service based on the execution service card includes: obtaining the target interface corresponding to the target service based on the service card of the target service; determining the interface call parameters of the target interface based on the execution service card; and sending the interface call parameters to the target interface so that the target interface executes the target service based on the interface call parameters.

[0011] In one embodiment, the step of executing the target service based on the execution service card includes: obtaining the target interface and execution feedback information for the target service; when the execution feedback information includes query feedback results and guidance information, filling in the result feedback card corresponding to the target service based on the query feedback results and the guidance information to generate a filled result feedback card; and sending the filled result feedback card to the interactive interface.

[0012] The present invention also provides a computing device, including a processor and a memory storing a computer program, wherein when the processor runs the computer program, it implements the steps of the dialogue processing method described above.

[0013] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the dialogue processing method described above.

[0014] The dialogue processing method, computing device, and storage medium provided by this invention identify user input information based on a vectorization model and a first-order model to determine the business card for the target service. Based on the user input information, the business card for the target service is filled in to determine the corresponding execution business card. The target service is then executed based on the execution business card. This invention can accurately identify the business card corresponding to the target service based on user input information, automatically fill in the business card to generate the execution business card, and then complete the execution of the target service based on the execution business card, thereby improving the accuracy and efficiency of business processing in natural language interaction scenarios. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a dialogue processing method according to an embodiment of the present invention.

[0016] Figure 2 for Figure 1 A flowchart illustrating step S12.

[0017] Figure 3 This is a schematic diagram of the structure of a dialogue processing system according to an embodiment of the present invention.

[0018] Figure 4This is a schematic diagram of the structure of a computing device according to an embodiment of the present invention.

[0019] Reference numerals: Dialogue processing system-30; Agent core module-301, parameter processing module-302, card hitting module-303, interface binding module-304; Processor-410; Memory-411; Network interface-412; Bus system-413. Detailed Implementation

[0020] The foregoing and other technical contents, features, and effects of the present invention will be clearly presented in the following detailed description of preferred embodiments with reference to the accompanying drawings. Through the description of the specific embodiments, a more in-depth and specific understanding can be gained of the technical means and effects adopted by the present invention to achieve the intended purpose. However, the accompanying drawings are only provided for reference and illustration and are not intended to limit the present invention.

[0021] To further illustrate the technical means and effects adopted by the present invention in order to achieve the intended purpose, the present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments.

[0022] Figure 1 This is a flowchart illustrating a dialogue processing method according to an embodiment of the present invention.

[0023] like Figure 1 As shown, the dialogue processing method provided in this embodiment includes the following steps: Step S11: Identify user input information based on the vectorization model and the first major model to determine the business card of the target business.

[0024] Specifically, user input information includes user input information from the current round (i.e., information most recently entered by the user) and contextual information corresponding to the current round's user input information. In one implementation, user input information only includes user input information from the current round. The bge-m3 (BAAI General Embedding-M3) vectorization model generates semantic vectors based on user input information. The semantic vectors are then compared with the description vectors of pre-configured business cards to calculate similarity. Several business cards with a similarity ≥ 0.8 are selected as candidate business cards. The candidate business cards and user input information are input into a first-level model. This first-level model obtains the card descriptions of the candidate business cards and matches them with the user input information, outputting a uniquely matched candidate business card. This uniquely matched candidate business card is then set as the target business card. This two-level recognition mechanism—first performing preliminary screening of candidate business cards based on the vectorization model, and then using the first-level model for semantic matching and fine-grained judgment of the candidate business cards and user input information—improves the accuracy of hitting the target business card and reduces business misjudgment.

[0025] Step S12: Fill in the business card of the target business based on the user input information to determine the execution business card corresponding to the target business.

[0026] like Figure 2 As shown, step S12 includes: Step S121: Determine whether the business card of the target business is an output card.

[0027] Specifically, the business cards for the target business are divided into output cards and input cards. Output cards are cards that do not require further user input; the system can immediately call the interface to complete the query or processing and directly return the result. All fields for output cards are automatically filled by the system using user input or default values ​​before being displayed. Input cards, on the other hand, require user confirmation or completion of parameters. When displayed to the user, fields remain to be filled, and the user must edit or confirm them in the interactive interface before proceeding to the next step. Output cards include attendance exception query cards, holiday balance query cards, and approval progress query cards, while input cards include leave application cards and vacation application cards. By dividing the business cards for the target business into output and input cards and adopting differentiated interactive processes for different types of business cards, query-type businesses that do not require additional parameters can be executed automatically and results returned directly. For application-type businesses that require additional parameters, only the necessary fields are displayed for interaction, thereby reducing the number of steps the user takes in the business processing, significantly improving parameter confirmation efficiency, and enhancing the interactive experience of human resources services.

[0028] Specifically, when the business card of the target service is an output card, proceed to step S123: fill in the business card of the target service based on the user input information and the second major model to determine the execution business card corresponding to the target service; when the business card of the target service is not an output card, proceed to step S122: fill in the business card of the target service based on the user input information, the second major model and user editing information to determine the execution business card corresponding to the target service.

[0029] Specifically, step S122 includes inputting the descriptions of the fields to be filled in the business card of the target business (e.g., the first field to be filled in is the start time of leave, the second field to be filled in is the end time of leave, and the third field to be filled in is the type of leave) and user input information (e.g., "I want to take personal leave from next Monday to next Wednesday") into the second large model. The second large model outputs the filling parameters corresponding to each field to be filled in the business card of the target business (e.g., outputting the filling parameters corresponding to the first field to be filled in as next Monday, the second field to be filled in as next Wednesday, and the third field to be filled in as personal leave). After converting the format of the filling parameters to a format compatible with the corresponding field to be filled in (e.g., converting the format of the filling parameter corresponding to the first field to be filled in from next Monday to 2026-1-5), the corresponding filling parameters are validated according to the validation rules corresponding to the field to be filled in (e.g., when the validation rule is that the time of a single personal leave shall not exceed 7 days, then the filling parameter of the start time of leave is validated to be consistent with the leave). The time difference between the end time parameters is checked against the rule. If the difference is greater than 7 days, the rule fails; otherwise, it passes. When a parameter passes the rule check, it is entered into the corresponding field to be filled. When a parameter fails the rule check, the corresponding field to be filled is set to a pending state to obtain the first filling state business card for the target business. After sending the first filling state business card to the corresponding interactive interface, the user's editing information (including the information to be filled and / or the modification information) and / or confirmation information (e.g., confirming to submit the card or confirming to execute the card) on the interactive interface are obtained to generate user editing information. Based on the user editing information, the first filling state business card of the target business is filled (including filling the empty fields to be filled in the first filling state business card and / or modifying the fields to be filled in the first filling state business card) to obtain the execution business card for the target business.

[0030] Specifically, in one embodiment, based on the filling status of each item to be filled in the first filling status business card, the display status of the item to be filled in the interactive interface is set. The filling status of the item to be filled includes filled status, unfilled status, and pending status.

[0031] Specifically, step S123 includes inputting the description of the pending items of the business card of the target business (e.g., the first pending item is the reason for card replacement) and user input information (e.g., my phone broke and I didn't clock in last Wednesday, please replace my card) into the second large model. The second large model outputs the filling parameters corresponding to each pending item in the business card of the target business (phone broke). After converting the format of the filling parameters into a format compatible with the corresponding pending item, the corresponding filling parameters are validated according to the validation rules corresponding to the pending item (e.g., the reason for card replacement cannot exceed 15 characters). When the filling parameters pass the rule validation, the filling parameters are filled into the corresponding pending item. When the filling parameters fail the rule validation, the pending item is filled according to the default value of the pending item (e.g., I forgot to clock in) to obtain the execution business card corresponding to the target business.

[0032] This application addresses common input scenarios in human resources operations, such as fuzzy time expressions and natural language descriptions. It utilizes a second major model to perform semantic parsing of dates, time periods, and business types, and combines this with pre-configured validation rules for human resources operations to validate the entered parameters. This makes the generated execution business cards more compliant with human resources business standards, thereby effectively reducing interface call failures caused by non-standard parameter formats or non-compliance with business rules, and significantly improving the success rate and accuracy of human resources business processing.

[0033] Step S13: Execute the target service based on the execution service card.

[0034] Specifically, based on the business card of the target business (e.g., leave application card), the target interface corresponding to the target business (e.g., leave application interface) is obtained. Each field to be filled in the business card has parameters corresponding to the target interface. Therefore, based on the content filled in each field to be filled in the business card, the interface call parameters of the target interface can be determined (e.g., when the first field to be filled in the business card is 2025-11-17, the second field to be filled in is 2025-11-19, and the third field to be filled in is personal leave, and the parameter corresponding to the target interface of the first field to be filled in is leave_start_date, the parameter corresponding to the target interface of the second field to be filled in is leave_end_date, and the parameter corresponding to the target interface of the third field to be filled in is leave_type, then the interface call parameters of the target interface are leave_start_date=2025-11-17, leave_end_date=2025-11-19, and leave_type = personal leave). The interface call parameters are then sent to the target interface so that the target interface executes the target business based on the interface call parameters.

[0035] In one embodiment, after step S13, the process includes obtaining the execution feedback information of the target interface for the target business. When the execution feedback information includes query feedback results and guidance information, the process involves filling in the result feedback card corresponding to the target business based on the query feedback results and guidance information to generate a filled result feedback card, and then sending the filled result feedback card to the interactive interface. For example, if the execution business card corresponding to the target business is an attendance exception query card, and the target business has been executed based on the execution business card, the execution feedback information of the target interface for the target business is obtained. The execution feedback information includes the query feedback result abnormal_reason = not clocked in, and the guidance information solution = can submit a replacement clock-in application. Based on abnormal_reason = not clocked in and solution = can submit a replacement clock-in application, the result feedback card corresponding to the target business is automatically filled in to generate a filled result feedback card. In the result feedback card, the field to be filled in for displaying the reason for the exception is filled in as "not clocked in", and the field to be filled in for displaying the guidance information is filled in as "can submit a replacement clock-in application".

[0036] In one embodiment, after sending the interface call parameters to the target interface, if no execution receipt is received from the target interface after a preset timeout period, it is determined that a timeout exception has occurred at the target interface. When a timeout exception occurs, an interface timeout prompt message is sent to the interactive interface, and the fields to be filled in the execution business card are kept intact so that the user does not need to fill in the fields again when retrying.

[0037] In one implementation, after sending the interface call parameters to the target interface, if the target interface returns an error code, the error code is parsed based on a preset error code mapping relationship to determine the corresponding exception reason message, and then the exception reason message is sent to the interactive interface for display. For example, when the returned error code is code=400, the corresponding exception reason message is "Parameter error, leave days exceeded limit", and when the returned error code is code=403, the corresponding exception reason message is "No permission to apply for this type of leave".

[0038] In one implementation, when the error code returned by the target interface is a preset temporary error code (e.g., error code = 503), the interface retry mechanism is automatically triggered, and the interface call parameters are sent to the target interface again within a preset number of retries. Preferably, the number of retries is 2, and the time interval between two adjacent retries is 1 second.

[0039] In summary, the dialogue processing method provided by this invention identifies user input information based on a vectorization model and a first-level model to determine the business card for the target service. Based on the user input information, the method fills in the business card for the target service to determine the corresponding execution business card. Finally, the method executes the target service based on the execution business card. This invention can accurately identify the business card corresponding to the target service based on user input information, automatically fill in the business card to generate the execution business card, and then complete the execution of the target service based on the execution business card, thereby improving the accuracy and efficiency of business processing in natural language interaction scenarios.

[0040] Based on the same inventive concept as the foregoing embodiments, this invention provides a dialogue processing system, such as... Figure 3 As shown, the dialogue processing system 30 includes: an intelligent agent core module 301, a parameter processing module 302, a card-hitting module 303, and an interface binding module 304.

[0041] The intelligent agent core module 301 is used to receive user input information, send the user input information to the card-hitting module 303 so that the card-hitting module 303 determines the service card of the target service, send the service card of the target service and the user input information to the parameter processing module 302 so that the parameter processing module 302 determines the execution service card corresponding to the target service, and send the execution service card corresponding to the target service to the interface binding module 304 so that the interface binding module 304 executes the target service based on the execution service card.

[0042] The card-hitting module 303 is used to identify user input information based on a vectorized model and a first-order model in order to determine the business card of the target business.

[0043] The parameter processing module 302 is used to fill in the business card of the target business based on the user input information, so as to determine the execution business card corresponding to the target business.

[0044] The interface binding module 304 is used to execute target business based on the execution business card.

[0045] In one embodiment, the dialogue processing system 30 further includes a card management module (not shown in the figure), which is used to edit cards and store card information.

[0046] The dialogue processing system in this embodiment is used to implement the dialogue processing method described above. The functions implemented by each module of the dialogue processing system can be found in [reference needed]. Figure 1 , Figure 2 The descriptions in the embodiments are not repeated here.

[0047] Based on the same inventive concept as the foregoing embodiments, this embodiment of the invention provides a computing device, such as... Figure 4As shown, the computing device includes: a processor 410 and a memory 411 storing computer programs; wherein, Figure 4 The processor 410 shown in the diagram does not indicate that there is only one processor 410, but only indicates the positional relationship of the processor 410 relative to other devices. In practical applications, there can be one or more processors 410; similarly, Figure 4 The memory 411 shown in the diagram has the same meaning, that is, it is only used to indicate the positional relationship of memory 411 relative to other devices. In practical applications, there can be one or more memories 411. When the processor 410 runs the computer program, the above-mentioned dialogue processing method is implemented.

[0048] The computing device may also include at least one network interface 412. Various components of the computer device are coupled together via a bus system 413. It is understood that the bus system 413 is used to implement communication between these components. In addition to a data bus, the bus system 413 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 4 The general designated all buses as Bus System 413.

[0049] The memory 411 can be volatile or non-volatile, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 411 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0050] The memory 411 in this embodiment of the invention is used to store various types of data to support the operation of the computing device. Examples of this data include any computer programs used to operate on the computing device, such as operating systems and applications. The operating system includes various system programs, such as framework layers, core library layers, and driver layers, used to implement various basic business functions and handle hardware-based tasks. Applications can include various applications, such as media players and browsers, used to implement various application functions. Here, the program implementing the method of this embodiment of the invention can be included in the application.

[0051] Based on the same inventive concept as the foregoing embodiments, this embodiment also provides a storage medium storing a computer program. The storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it can also be various devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc. When the computer program stored in the storage medium is run by a processor, it implements the above-described dialogue processing method. For the specific steps implemented when the computer program is executed by the processor, please refer to [link to relevant documentation]. Figure 1 , Figure 2 The description of the illustrated embodiments will not be repeated here.

[0052] The dialogue processing method, computing device, and storage medium provided by this invention identify user input information based on a vectorization model and a first-order model to determine the business card for the target service. Based on the user input information, the business card for the target service is filled in to determine the corresponding execution business card. The target service is then executed based on the execution business card. This invention can accurately identify the business card corresponding to the target service based on user input information, automatically fill in the business card to generate the execution business card, and then complete the execution of the target service based on the execution business card, thereby improving the accuracy and efficiency of business processing in natural language interaction scenarios.

[0053] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the accompanying drawings may include multiple sub-steps or multiple stages, which are not necessarily completed at the same time, but may be executed at different times, and their execution order is not necessarily sequential, but may be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0054] Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments of the present invention can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions of the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the embodiments of the present invention.

[0055] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A dialog processing method characterized by, The method includes: Based on the vector model and the first major model, user input information is identified to determine the business card of the target business; Based on the user input information, fill in the business card of the target business to determine the execution business card corresponding to the target business; The target service is executed based on the execution service card.

2. The dialog processing method of claim 1, wherein, The user input information includes the user input information for the current round and the context information corresponding to the user input information for the current round; The step of identifying user input information based on a vectorized model and the first major model to determine the business card of the target business includes: Based on the vectorization model, the user input information is filtered by vector to obtain candidate service cards; The user input information and the candidate business cards are input into the first large model to determine the business card of the target business.

3. The dialog processing method of claim 1, wherein, The target business's business cards include output cards and input cards; The step of filling in the service card for the target service based on the user input information to determine the execution service card corresponding to the target service includes: When the business card of the target business is the output type card, the business card of the target business is filled in based on the user input information and the second major model to determine the execution business card corresponding to the target business; When the business card of the target business is the input type card, the business card of the target business is filled in based on the user input information, the second major model and the user editing information, so as to determine the execution business card corresponding to the target business.

4. The dialog processing method of claim 3, wherein, When the business card for the target service is the output type card, based on the user input information and the second major model, the business card for the target service is filled in to determine the execution business card corresponding to the target service, including: The description of the items to be filled in the business card of the target business and the user input information are input into the second large model to obtain the filling parameters corresponding to each item to be filled in. After converting the format and validating the rules of the input parameters, fill in the corresponding fields to obtain the execution business card corresponding to the target business.

5. The dialog processing method of claim 3, wherein, When the business card for the target service is the input-type card, the business card for the target service is filled in based on the user input information, the second major model, and the user editing information to determine the execution business card corresponding to the target service, including: The description of the items to be filled in the business card of the target business and the user input information are input into the second large model to obtain the filling parameters corresponding to each item to be filled in. After converting the format and validating the rules of the filling parameters, fill in the corresponding fields to be filled in to obtain the first filling status business card of the target business; After sending the first filled-in status service card of the target service to the interactive interface, the user editing information of the first filled-in status service card of the target service is obtained from the interactive interface. Based on the user's edit information, fill in the first fill-in status service card of the target service to obtain the execution service card of the target service.

6. The dialogue processing method according to any one of claims 4 or 5, characterized by, After format conversion and rule validation of the input parameters, they are filled into the corresponding fields to be filled, including: After converting the format of the input parameters into a format compatible with the corresponding field to be filled, the input parameters are validated according to the validation rules corresponding to the field to be filled. When the input parameters pass the rule verification, the input parameters are entered into the corresponding fields to be filled. When the input parameter fails the rule validation, the corresponding field to be filled is set to a pending state, or the field to be filled is filled according to the default value of the field to be filled.

7. The dialogue processing method of claim 1, wherein, The steps of executing the target service based on the execution service card include: Based on the business card of the target business, obtain the target interface corresponding to the target business; Based on the execution business card, determine the interface call parameters of the target interface; The interface call parameters are sent to the target interface so that the target interface executes the target service based on the interface call parameters.

8. The dialog processing method of claim 7, wherein, The step of executing the target service based on the execution service card is followed by: Obtain the execution feedback information of the target interface for the target service; When the execution feedback information includes query feedback results and guidance information, the result feedback card corresponding to the target service is filled in based on the query feedback results and guidance information to generate a filled result feedback card; Send the completed result feedback card to the interactive interface.

9. A computing device, comprising: It includes a processor and a memory storing a computer program, wherein when the processor runs the computer program, it implements the steps of the dialogue processing method according to any one of claims 1 to 8.

10. A storage medium storing a computer program, characterized by When the computer program is executed by a processor, it implements the steps of the dialogue processing method as described in any one of claims 1 to 8.

Images