Employee information query method and device based on AI assistant platform and storage medium

Abstract

This application discloses a method, apparatus, and storage medium for querying employee information based on an AI assistant platform. The method includes: extracting key fields from an employee information query question and generating a target query statement based on the key fields; if a first terminal device reports that the target query statement is correct, querying the application system for a first query result corresponding to the target query statement and displaying the first query result or displaying a link to the application system; if the target query statement is incorrect, displaying alternative query statements on the screen; if the first terminal device selects an alternative query statement, querying the application system for a second query result corresponding to the alternative query statement and displaying the second query result on the screen; if the first terminal device does not select an alternative query statement, prompting the first terminal device to continue inputting information and returning to the above steps until the target query statement is correct or an alternative query statement is selected. This application can reduce the time spent querying employee information and improve query efficiency.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, electronic device, and computer-readable storage medium for querying employee information based on an AI assistant platform. Background Technology

[0002] Employee information is often scattered across different application systems. Retrieving employee information can require significant time and effort to collect and integrate this information, leading to low query efficiency. For example, users may need to navigate through multiple pages to find relevant information when processing onboarding or offboarding procedures, checking social security information, housing provident fund payment information, or salary payment information, or when service teams check employee processing progress. Furthermore, users may not accurately express their questions when querying employee information, or their stated questions may deviate from their actual inquiries, resulting in unexpected query results and a poor user experience. Summary of the Invention

[0003] In view of the above, embodiments of this application provide an employee information query method, apparatus, electronic device, and computer-readable storage medium based on an AI assistant platform to solve at least one of the above-mentioned technical problems.

[0004] This application provides an employee information query method based on an AI assistant platform. The method includes: responding to an employee information query question input by a first terminal device on the operation page of the AI ​​assistant platform; extracting key fields from the employee information query question; generating a target query statement based on the extracted key fields; and displaying the target query statement on the screen of the first terminal device. If the first terminal device reports that the target query statement is correct, then, based on the target query statement, querying a first query result corresponding to the target query statement in the application system associated with the target query statement, and displaying the first query result on the screen of the first terminal device, or displaying the link address of the application system on the screen of the first terminal device. If the first terminal device reports that the target query statement is incorrect, then... The terminal device displays at least one alternative query statement associated with the target query statement on its screen. If the first terminal device selects an alternative query statement, it queries the application system associated with the selected alternative query statement for a second query result corresponding to the alternative query statement and displays the second query result on the screen of the first terminal device, or displays the link address of the application system on the screen of the first terminal device. If the first terminal device does not select any alternative query statement, it prompts the first terminal device to continue entering employee information query questions, and returns to the steps of extracting key fields from the employee information query questions, generating the target query statement based on the extracted key fields, and displaying the target query statement on the screen of the first terminal device, until the first terminal device reports that the target query statement is correct or selects an alternative query statement.

[0005] According to some embodiments of this application, optionally, extracting key fields from employee information inquiry questions and generating target inquiry statements based on the extracted key fields includes: performing semantic analysis on employee information inquiry questions based on a trained AI large language model, extracting key fields from employee information inquiry questions, and generating target inquiry statements based on the extracted key fields; the employee information query method based on the AI ​​assistant platform further includes: performing semantic similarity calculation on key fields based on the AI ​​large language model to obtain at least one alternative field whose similarity to the key field is greater than a preset similarity threshold; and generating at least one alternative inquiry statement based on at least one alternative field.

[0006] According to some embodiments of this application, optionally, based on a target query statement, querying a first query result corresponding to the target query statement in an application system associated with the target query statement, and displaying the first query result on the screen of a first terminal device, includes: if the target query statement contains multiple employee information query items, then for any employee information query item, querying the data interface of the target application system associated with the employee information query item, accessing the target application system based on the data interface, and querying the employee information query result corresponding to the employee information query item in the target application system; calling the query result display template corresponding to the target query statement, filling the employee information query results corresponding to each of the multiple employee information query items into the query result display template, and displaying the filled query result display template as the first query result on the screen of the first terminal device.

[0007] According to some embodiments of this application, optionally, displaying the link address of the application system on the screen of the first terminal device includes: if the target query statement is associated with multiple application systems, sorting the link addresses of the multiple application systems according to a preset query order, and displaying the sorted link addresses of the multiple application systems on the screen of the first terminal device; for any link address of an application system, when the cursor is detected to move to the link address of the application system or when the link address of the application system is clicked, displaying guidance information for querying the target query statement of the application system on the screen.

[0008] According to some embodiments of this application, optionally, before extracting key fields from employee information inquiry questions and generating target inquiry statements based on the extracted key fields, the employee information query method based on the AI ​​assistant platform further includes: updating the number of inquiries of the first terminal device in response to the employee information inquiry questions entered by the first terminal device on the operation page; when the updated number of inquiries reaches a preset threshold, determining a second user associated with the first user based on the identity information of the first user, and sending an inquiry message to the second terminal device used by the second user indicating whether the first terminal device agrees to continue inquiring; if the second terminal device responds with disagreement, then no target inquiry statement is generated; extracting key fields from employee information inquiry questions and generating target inquiry statements based on the extracted key fields includes: if the second terminal device responds with agreement, then extracting key fields from employee information inquiry questions and generating target inquiry statements based on the extracted key fields.

[0009] According to some embodiments of this application, optionally, the target query statement includes a query user, a query time period, and employee information query items. The employee information query items include at least one of the following: onboarding information, offboarding information, social security information, housing provident fund information, salary information, task completion status information, and employee feedback information. If the first terminal device does not select any of the alternative query statements, the first terminal device is prompted to continue entering employee information query questions, and the process returns to extract key fields from the employee information query questions, generate the target query statement based on the extracted key fields, and display the target query statement on the screen of the first terminal device. The steps include: if the first terminal device does not select any of the alternative query statements... If the first terminal device is prompted to select the user, query time period, and employee information query item as the source of the error, the AI ​​language model will query the first terminal device for the user, query time period, and employee information query item. If the first terminal device reports an error item as an employee information query item, at least one prompt field associated with the employee information query item will be displayed on the screen. In response to the prompt field selected or entered by the first terminal device, the AI ​​language model will regenerate the target query statement based on the user, query time period, and prompt field. If the first terminal device reports an error item as a user or query time period, the AI ​​language model will regenerate the target query statement based on the re-entered user, query time period, and employee information query item after prompting the first terminal device to enter the correct user or query time period.

[0010] According to some embodiments of this application, optionally, the employee information query method based on the AI ​​assistant platform further includes: if the first terminal device does not select any of the candidate query statements, then update the number of failures; when the updated number of failures reaches a preset threshold, send the contact information of the second user to the first terminal device, and / or send a prompt message to the second terminal device to reply to the employee information query question of the first user.

[0011] This application provides an employee information query device based on an AI assistant platform. The device includes: a generation module, configured to respond to an employee information query question input by a first terminal device on the operation page of the AI ​​assistant platform, extract key fields from the employee information query question, generate a target query statement based on the extracted key fields, and display the target query statement on the screen of the first terminal device; a first processing module, configured to, if the first terminal device reports that the target query statement is correct, query a first query result corresponding to the target query statement in an application system associated with the target query statement, and display the first query result on the screen of the first terminal device, or display the link address of the application system on the screen of the first terminal device; and a second processing module, configured to, if the first terminal device reports that the target query statement is correct... If the query statement is incorrect, at least one alternative query statement associated with the target query statement will be displayed on the screen of the first terminal device. If the first terminal device selects an alternative query statement, a second query result corresponding to the alternative query statement will be queried in the application system associated with the selected alternative query statement and displayed on the screen of the first terminal device, or the link address of the application system will be displayed on the screen of the first terminal device. If the first terminal device does not select any alternative query statement, it will prompt the first terminal device to continue entering employee information query questions, and return to the steps of extracting key fields from the employee information query questions, generating the target query statement based on the extracted key fields, and displaying the target query statement on the screen of the first terminal device, until the first terminal device reports that the target query statement is correct or selects an alternative query statement.

[0012] This application provides an electronic device, which includes a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the steps of the method described above.

[0013] This application provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the steps of the method described above.

[0014] This application provides a computer program product, which includes computer program instructions that, when executed by a processor, implement the steps of the method described above.

[0015] The embodiments of this application, based on an AI assistant platform, provide an employee information query method, apparatus, electronic device, and computer-readable storage medium. On one hand, through the AI ​​assistant platform, users can input employee information queries. The AI ​​assistant platform can perform semantic analysis on the employee information queries, extract key fields from the queries, and generate a target query statement based on the extracted key fields. Based on the target query statement, a first query result corresponding to the target query statement can be queried in the corresponding application system and displayed on the screen of a first terminal device, or the link address of the application system can be displayed on the screen of the first terminal device, thereby reducing the time users spend querying employee information and improving query efficiency. On the other hand, the AI ​​assistant platform can perform semantic analysis on the employee information queries, extract key fields from the queries, and generate a more accurate target query statement based on the extracted key fields, thereby improving the accuracy of the query, the accuracy of the query results, and the user experience. On the other hand, when the target query statement is incorrect, at least one alternative query statement associated with the target query statement can be displayed. In response to the selection of an alternative query statement, a second query result corresponding to the alternative query statement is queried in the corresponding application system and displayed on the screen of the first terminal device. Alternatively, the link address of the application system can be displayed on the screen of the first terminal device. This provides multiple options for query statements, further improves the accuracy of the query questions, reduces the time users spend asking questions, and improves the user experience. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings of the embodiments of this application will be briefly described below.

[0017] Figure 1 This is a schematic diagram of a system architecture according to an embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating an employee information query method based on an AI assistant platform, according to an embodiment of this application.

[0019] Figure 3 This is a flowchart illustrating step S202 of the employee information query method based on an AI assistant platform in an embodiment of this application.

[0020] Figure 4 This is another flowchart illustrating step S202 of the employee information query method based on an AI assistant platform according to an embodiment of this application.

[0021] Figure 5 This is a schematic diagram of an employee information query device based on an AI assistant platform, according to an embodiment of this application.

[0022] Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0023] The principles and spirit of this application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided to make the principles and spirit of this application clearer and more thorough, enabling those skilled in the art to better understand and implement the principles and spirit of this application. The exemplary embodiments provided herein are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments described herein without inventive effort are within the scope of protection of this application.

[0024] The embodiments of this application relate to terminal devices and / or servers. Those skilled in the art will understand that the embodiments of this application can be implemented as a system, apparatus, device, method, computer-readable storage medium, or computer program product. Therefore, this disclosure can be specifically implemented in at least one of the following forms: entirely hardware, entirely software, or a combination of hardware and software. According to the embodiments of this application, this application claims protection for a method, apparatus, electronic device, computer-readable storage medium, and computer program product for querying employee information based on an AI assistant platform. Figure 1 This is a schematic diagram of a system architecture according to an embodiment of this application. Figure 1 As shown, the system includes a terminal device 102 and a server 104. The terminal device 102 can include at least one of the following: a smartphone, tablet, laptop, desktop computer, smart TV, various wearable devices, augmented reality (AR) devices, virtual reality (VR) devices, etc. A client can be installed on the terminal device 102. For example, the client can be a client specifically designed to perform a particular function (such as an application app), or a client with multiple embedded application applets (with different functions), or a client logged in via a browser. Users can operate on the terminal device 102. For example, a user can open the client installed on the terminal device 102 and input commands through the client, or a user can open the browser installed on the terminal device 102 and input commands through the browser. After receiving the user's input command, the terminal device 102 sends a request message containing the command to the server 104. After receiving the request message, the server 104 performs the corresponding processing and then returns the processing result information to the terminal device 102. The user command is completed through a series of data processing and information interaction.

[0025] In this document, terms such as first, second, and third are used only to distinguish one entity (or operation) from another, and are not intended to require or imply any order or relationship between these entities (or operations).

[0026] Before describing the technical solutions provided in the embodiments of this application, in order to facilitate understanding of the embodiments of this application, this application first specifically explains the problems existing in the related technologies:

[0027] Employee information is often scattered across different application systems. Retrieving employee information can require significant time and effort to collect and integrate this information, leading to low query efficiency. For example, users may need to navigate through multiple pages to find relevant information when processing onboarding or offboarding procedures, checking social security information, housing provident fund payment information, or salary payment information, or when service teams check employee processing progress. Furthermore, users may not accurately express their questions when querying employee information, or their stated questions may deviate from their actual inquiries, resulting in unexpected query results and a poor user experience.

[0028] To address the problems in the prior art, embodiments of this application provide a method, apparatus, electronic device, and computer-readable storage medium for querying employee information based on an AI assistant platform.

[0029] The following section first introduces the employee information query method based on the AI ​​assistant platform provided in the embodiments of this application.

[0030] Figure 2 This is a flowchart illustrating an employee information query method based on an AI assistant platform, as described in an embodiment of this application. Figure 2 As shown, the method includes the following steps S201 to S204.

[0031] S201: In response to the employee information inquiry question entered by the first terminal device on the operation page of the AI ​​assistant platform, extract the key fields in the employee information inquiry question, generate the target inquiry statement based on the extracted key fields, and display the target inquiry statement on the screen of the first terminal device.

[0032] The first terminal device can be, for example, Figure 1 The terminal device 102 shown is a first terminal device that can display the operation page of the AI ​​assistant platform. Users can input employee information inquiries into the AI ​​assistant platform through the first terminal device. For example, employee information inquiries may include processing onboarding procedures, processing offboarding procedures, querying social security information, querying housing provident fund payment information, querying salary payment information, querying task completion status information, or querying employee feedback information, etc., and this application does not limit this.

[0033] After receiving an employee information inquiry, the AI ​​assistant platform can extract key fields from the inquiry, generate a target query statement based on these fields, and display the target query statement on the screen of the first terminal device. For example, key fields include, but are not limited to, keywords, key phrases, and / or key sentences.

[0034] In S201, semantic analysis can be performed on employee information queries to extract key fields, and an accurate target query statement can be regenerated based on these extracted key fields. For example, if the employee information query is "How much social security did A pay in March?", the key fields could include "A", "March", and "social security", and the target query statement could be "Query A's social security contributions for March". Then, the target query statement is displayed on the screen of the first terminal device.

[0035] S202: If the first terminal device reports that the target query statement is correct, then based on the target query statement, query the first query result corresponding to the target query statement in the application system associated with the target query statement, and display the first query result on the screen of the first terminal device, or display the link address of the application system on the screen of the first terminal device.

[0036] After the target query is displayed on the screen of the first terminal device, the user can use the first terminal device to provide feedback to the AI ​​assistant platform on whether the target query is correct. If the first terminal device reports that the target query is correct, then based on the target query, the system will query for the first query result corresponding to the target query in the application system associated with the target query, and display the first query result on the screen of the first terminal device, or display the link address of the application system on the screen of the first terminal device.

[0037] The application system associated with the target query can be one application system or multiple application systems, which can be flexibly adjusted according to the actual situation, and this application does not limit it. For example, the application system may include an employee management application system, a social security application system, a housing provident fund application system, and / or a work progress management application system, etc.

[0038] In some embodiments, the AI ​​assistant platform can access the application system associated with the target query statement through a pre-configured data interface, query the first query result corresponding to the target query statement from the application system, and display the first query result on the screen of the first terminal device for the user to view.

[0039] In other embodiments, the AI ​​assistant platform may also display the link address of the application system associated with the target query statement on the screen of the first terminal device. Users can access the corresponding application system based on the link address and then query the results corresponding to the target query statement within the application system; this application does not limit this approach.

[0040] S203: If the first terminal device reports an error in the target query statement, at least one alternative query statement associated with the target query statement is displayed on the screen of the first terminal device. If the first terminal device selects an alternative query statement, a second query result corresponding to the alternative query statement is queried in the application system associated with the selected alternative query statement, and the second query result is displayed on the screen of the first terminal device. Alternatively, the link address of the application system is displayed on the screen of the first terminal device.

[0041] If the first terminal device reports an error in the target query statement, at least one alternative query statement associated with the target query statement can be displayed on the screen of the first terminal device. The alternative query statements can be similar to or highly similar to the target query statement. The number of alternative query statements can be flexibly set according to actual circumstances, and this application does not limit this.

[0042] If the first terminal device selects an alternative query statement, it queries the application system associated with the selected alternative query statement to find the second query result corresponding to the alternative query statement and displays the second query result on the screen of the first terminal device, or displays the link address of the application system on the screen of the first terminal device.

[0043] The application system associated with the selected alternative query statement can be one application system or multiple application systems, which can be flexibly adjusted according to the actual situation, and this application does not limit it. For example, the application system may include an employee management application system, a social security application system, a housing provident fund application system, and / or a work progress management application system, etc.

[0044] It should be noted that the application system associated with the selected alternative query can be the same as or different from the application system associated with the target query.

[0045] In some embodiments, the AI ​​assistant platform can access the application system associated with the selected alternative query statement through a pre-configured data interface, query the second query result corresponding to the selected alternative query statement from the application system, and display the second query result on the screen of the first terminal device for the user to view.

[0046] In other embodiments, the AI ​​assistant platform may also display the link address of the application system associated with the selected alternative query statement on the screen of the first terminal device. Users can access the corresponding application system based on the link address and then query the desired results within the application system; this application does not limit this approach.

[0047] S204: If the first terminal device does not select any of the alternative query statements, then prompt the first terminal device to continue entering employee information query questions, and return to extract the key fields from the employee information query questions, generate the target query statement based on the extracted key fields, and display the target query statement on the screen of the first terminal device, until the first terminal device reports that the target query statement is correct or selects an alternative query statement.

[0048] If the first terminal device does not select any of the alternative query statements, it will be prompted to continue entering employee information and query questions, and will return to step S201. The above steps will be repeated until the first terminal device reports that the target query statement is correctly executed (S202), or selects an alternative query statement and executes S203.

[0049] The embodiments of this application are based on an employee information query method using an AI assistant platform. On one hand, through the AI ​​assistant platform, users can input employee information query questions. The AI ​​assistant platform can perform semantic analysis on the employee information query questions, extract key fields from the employee information query questions, and generate target query statements based on the extracted key fields. Based on the target query statements, a first query result corresponding to the target query statement can be queried in the corresponding application system, and the first query result can be displayed on the screen of the first terminal device, or the link address of the application system can be displayed on the screen of the first terminal device, thereby reducing the time users spend querying employee information and improving query efficiency. On the other hand, the AI ​​assistant platform can perform semantic analysis on the employee information query questions, extract key fields from the employee information query questions, and generate more accurate target query statements based on the extracted key fields, thereby improving the accuracy of the query questions, improving the accuracy of the query results, and improving the user experience. On the other hand, when the target query statement is incorrect, at least one alternative query statement associated with the target query statement can be displayed. In response to the selection of an alternative query statement, a second query result corresponding to the alternative query statement is queried in the corresponding application system and displayed on the screen of the first terminal device. Alternatively, the link address of the application system can be displayed on the screen of the first terminal device. This provides multiple options for query statements, further improves the accuracy of the query questions, reduces the time users spend asking questions, and improves the user experience.

[0050] According to some embodiments of this application, optionally, S201: extracting key fields from employee information inquiry questions and generating target inquiry statements based on the extracted key fields may include the following steps:

[0051] Based on a trained AI large language model, semantic analysis is performed on employee information inquiry questions to extract key fields from the questions, and target inquiry statements are generated based on the extracted key fields.

[0052] Specifically, sample employee information queries with various expressions or wordings can be obtained. These sample queries are then used to train an AI Large Language Model (LLM). The LLM can extract key fields (core content) from the sample employee information queries and generate target query statements based on these extracted key fields. Furthermore, the LLM can perform semantic similarity calculations on the key fields to obtain at least one candidate field with a similarity greater than a preset similarity threshold. Based on this candidate field, at least one candidate query statement can be generated.

[0053] The AI ​​assistant platform can call a pre-trained AI language model to perform semantic analysis on employee information inquiry questions, extract key fields from the employee information inquiry questions, and generate target inquiry statements based on the extracted key fields.

[0054] Accordingly, the employee information query method based on the AI ​​assistant platform may also include the following steps one and two.

[0055] Step 1: Calculate the semantic similarity of key fields based on the AI ​​large language model to obtain at least one candidate field whose similarity to the key field is greater than the preset similarity threshold.

[0056] The AI ​​assistant platform can call a pre-trained AI large language model to calculate the semantic similarity of key fields, obtaining at least one candidate field whose similarity to the key field is greater than a preset similarity threshold. That is, it obtains at least one candidate field with a high similarity to the key field. The preset similarity threshold can be flexibly adjusted according to actual circumstances, and this application does not limit it. Taking "employment application" as an example, candidate fields may include "onboarding procedures," "onboarding process," and / or "onboarding process," etc.

[0057] Step 2: Generate at least one alternative query statement based on at least one alternative field.

[0058] AI-powered large language models can generate at least one alternative query statement based on at least one alternative field. Taking alternative fields including "onboarding procedures", "onboarding process", and "onboarding procedures" as an example, alternative query statements can include "process onboarding procedures", "process onboarding process", and / or "process onboarding procedures".

[0059] In this way, the AI ​​large language model can not only generate target query statements based on extracted key fields, but also perform semantic similarity calculations on the key fields to obtain alternative fields, and then generate at least one alternative query statement. This provides users with multiple choices of query statements, further improving the accuracy of the query and reducing the time users spend asking the same question again, thus improving the user experience.

[0060] Figure 3 This is a flowchart illustrating step S202 of the employee information query method based on an AI assistant platform according to an embodiment of this application. Figure 3 As shown, according to some embodiments of this application, optionally, S202: based on the target query statement, querying the first query result corresponding to the target query statement in the application system associated with the target query statement, and displaying the first query result on the screen of the first terminal device, may include the following steps S301 and S302.

[0061] S301: If the target query statement contains multiple employee information query items, then for any employee information query item, query the data interface of the target application system associated with the employee information query item, access the target application system based on the data interface, and query the employee information query results corresponding to the employee information query item in the target application system.

[0062] A target query statement can contain one or more employee information query items. If the target query statement contains multiple employee information query items, such as social security information, housing provident fund information, and salary information, then for any one employee information query item, the data interface of the target application system associated with that employee information query item can be queried. Based on the data interface, the target application system can be accessed, and the employee information query results corresponding to the employee information query item can be queried within the target application system. The target application system is the application system associated with the employee information query item. Different employee information query items can be associated with the same or different target application systems.

[0063] S302: Call the query result display template corresponding to the target query statement, fill in the employee information query results corresponding to each of the multiple employee information query items into the query result display template, and display the filled query result display template as the first query result on the screen of the first terminal device.

[0064] To facilitate users' viewing of query results and subsequent export, a query result display template can be pre-set. The query result display template can be used to display the employee information query results corresponding to one employee information query item, or it can be used to display the employee information query results corresponding to multiple employee information query items.

[0065] When the target query contains multiple employee information query items, a query result display template corresponding to the target query can be invoked, and the employee information query results corresponding to each of the multiple employee information query items can be filled into the query result display template. For example, the employee information query results corresponding to each of the multiple employee information query items can be filled into different columns or different rows in the query result display template. After completion, the filled query result display template can be displayed as the first query result on the screen of the first terminal device, so that users can view the employee information query results corresponding to multiple employee information query items.

[0066] In some embodiments, the employee information query method based on the AI ​​assistant platform may further include the following steps:

[0067] In response to the export operation of the first terminal device, export the template for displaying the filled-in query results.

[0068] Optionally, the exported query results display template can be watermarked with the exporter's name and / or exporter's identification to reduce the risk of employee information leakage.

[0069] Thus, when the target query statement contains multiple employee information query items, the query result display template corresponding to the target query statement is invoked, and the employee information query results corresponding to each of the multiple employee information query items are filled into the query result display template. This allows users to clearly view the employee information query results corresponding to multiple employee information query items, and / or allows users to directly export the filled query result display template without having to edit it again, making it convenient for users to use directly.

[0070] Figure 4 This is another flowchart illustrating step S202 of the employee information query method based on an AI assistant platform according to an embodiment of this application. Figure 4 As shown, according to some embodiments of this application, optionally, S202: displaying the link address of the application system on the screen of the first terminal device may include the following steps S401 and S402.

[0071] S401: If the target query statement is associated with multiple application systems, the link addresses of the multiple application systems are sorted according to the preset query order, and the sorted link addresses of the multiple application systems are displayed on the screen of the first terminal device.

[0072] The preset query order, also known as the default query order, can be flexibly set according to actual conditions, and this application does not limit it. In some embodiments, the target query statement may be associated with multiple application systems. When the target query statement is associated with multiple application systems, the link addresses of the multiple application systems can be sorted according to the preset query order, and the sorted link addresses of the multiple application systems can be displayed on the screen of the first terminal device. In this way, it is convenient for users to access multiple application systems sequentially to perform query operations based on the sorted link addresses of the multiple application systems.

[0073] S402: For any application system link address, when the cursor is detected to move to the application system link address or when the application system link address is clicked, display the guiding information of the application system query target statement on the screen.

[0074] For any application system link displayed on the screen, when the mouse cursor moves to or clicks on that application system link, guiding information for querying the target query statement within that application system can be displayed on the screen. This guiding information can be used to guide the user to search for the corresponding query results within that application system. For example, the guiding information includes, but is not limited to, text, images, or videos. While the guiding information for querying the target query statement within that application system is displayed, the guiding information for querying the target query statement in other application systems can be hidden to avoid user confusion.

[0075] In this way, when the cursor moves to the application system's link address or is clicked, guidance information for querying the target query statement in the application system is displayed on the screen. Users can learn how to query the corresponding query results in the application system without performing complicated operations, thereby improving query efficiency and accuracy.

[0076] According to some embodiments of this application, optionally, before S101: extracting key fields from employee information inquiry questions and generating target inquiry statements based on the extracted key fields, the employee information query method based on the AI ​​assistant platform may further include steps three to five.

[0077] Step 3: In response to the employee information inquiry question entered on the operation page by the first terminal device, update the inquiry count of the first terminal device.

[0078] In some embodiments, before responding to an employee information query entered by the first terminal device on the operation page of the AI ​​assistant platform, the identity information of the first user using the first terminal device can be authenticated. That is, the first user can enter their own identity information through the first terminal device. If the authentication is successful, the first terminal device can be allowed to enter an employee information query on the operation page of the AI ​​assistant platform. If the authentication fails, the first terminal device can be prevented from entering an employee information query on the operation page of the AI ​​assistant platform.

[0079] After successful identity verification, in response to the employee information inquiry questions entered by the first terminal device on the AI ​​assistant platform's operation page, the query count of the first terminal device can be updated, i.e., the number of questions asked. The query count can be the total number of queries by the first terminal device, or the number of queries by the first terminal device within a target time period. The target time period can be flexibly adjusted according to the actual situation, such as the current day, the week, or the month; this application does not limit this.

[0080] Step 4: When the number of updated inquiries reaches the preset threshold, the second user associated with the first user is identified based on the first user's identity information, and an inquiry message is sent to the second terminal device used by the second user, asking whether the first terminal device agrees to continue inquiring.

[0081] For example, the second user can be a manager or human resources personnel. The preset threshold number of queries can be flexibly adjusted according to actual circumstances, and this application does not limit it. When the updated number of queries reaches the preset threshold number, a second user associated with the first user can be identified based on the first user's identity information, such as a manager or human resources personnel of the first user's organization, and an inquiry message asking whether the second user agrees to continue querying through the first terminal device can be sent to the second terminal device used by the second user. The second terminal device can be a different terminal device from the first terminal device.

[0082] Step 5: If the second terminal device disagrees, the target query statement will not be generated.

[0083] If the second terminal device responds that it does not agree with the first terminal device continuing to query, then the target query statement will not be generated.

[0084] Accordingly, S101: Extracting key fields from employee information inquiry questions and generating target inquiry statements based on the extracted key fields may include the following steps:

[0085] If the second terminal device agrees, the key fields in the employee information inquiry questions are extracted, and the target inquiry statement is generated based on the extracted key fields.

[0086] If the second terminal device agrees to allow the first terminal device to continue the inquiry, then key fields from the employee information inquiry questions are extracted, and a target inquiry statement is generated based on the extracted key fields. This can be achieved by using an AI large language model to extract key fields from the employee information inquiry questions and generating a target inquiry statement based on those extracted fields.

[0087] Thus, by authenticating the first user using the first terminal device and / or limiting the number of queries to the first terminal device, anti-crawler design can be implemented to prevent unauthorized users from using the AI ​​assistant platform to query employee information, or to reduce the number of times unauthorized users use the AI ​​assistant platform, thereby reducing the risk of employee information leakage.

[0088] According to some embodiments of this application, optionally, the target query statement may include the querying user, the query time period, and employee information query items. Employee information query items may include at least one of the following: onboarding information, offboarding information, social security information, housing provident fund information, salary information, task completion status information, and employee feedback information. For example, if the target query statement is "Query A's social security information and housing provident fund information for March 2024," the querying user is "A," the query time period is "March 2024," and the employee information query items are "social security information" and "housing provident fund information."

[0089] Accordingly, S204: If the first terminal device does not select any of the alternative query statements, the first terminal device is prompted to continue entering employee information query questions, and the steps of extracting key fields from the employee information query questions, generating target query statements based on the extracted key fields, and displaying target query statements on the screen of the first terminal device may include the following steps six to nine.

[0090] Step Six: If the first terminal device does not select any of the alternative query statements, then query the first terminal device for errors in the query user, query time period, and employee information query items.

[0091] If the first terminal device does not select any of the alternative query statements, it can be asked which of the following is incorrect in the query user, query time period, and employee information query items. In other words, it can be asked which one or more of the following three items are incorrect: query user, query time period, and employee information query items.

[0092] Step 7: If the error reported by the first terminal device is the employee information query item, then display at least one prompt field associated with the employee information query item on the screen.

[0093] For example, a user might actually want to query "social security," but the question they entered for employee information is "salary," causing the query result to also be "salary." In this case, at least one prompt field associated with the employee information query result, such as "social security" or "housing provident fund," can be displayed on the screen.

[0094] Step 8: In response to the prompt field selected or entered by the first terminal device, the AI ​​big language model regenerates the target query statement based on the query user, query time period, and prompt field.

[0095] Users can select or enter a prompt field based on at least one prompt field displayed on the screen. In response to the prompt field selected or entered by the first terminal device, the AI ​​large language model can regenerate the target query statement based on the query user, query time period, and prompt field, thereby obtaining the target query statement that the user expects to ask.

[0096] Step 9: If the error reported by the first terminal device is the query user or query time period, after prompting the first terminal device to enter the correct query user or query time period, the AI ​​big language model will regenerate the target query statement based on the re-entered query user, query time period and employee information query item.

[0097] If the first terminal device reports an error related to the query user or query time period, it will prompt the first terminal device to enter the correct query user or query time period. After the first terminal device re-enters the query user or query time period, the AI ​​large language model will be invoked to regenerate the target query statement based on the re-entered query user, query time period, and employee information query items.

[0098] Thus, when the target query is incorrect and the first terminal device does not select any of the alternative query statements, steps six to nine above can reduce the number of times the user needs to enter employee information to ask questions, better ensuring that the user can find the query results they expect and improving the user experience.

[0099] According to some embodiments of this application, the employee information query method based on an AI assistant platform may optionally include the following steps:

[0100] If the first terminal device does not select any of the alternative query statements, the update failure count will be updated.

[0101] When the number of failures after the update reaches a preset threshold, the contact information of the second user is sent to the first terminal device, and / or a prompt message is sent to the second terminal device to reply to the employee information inquiry question of the first user.

[0102] The preset failure threshold can be flexibly adjusted according to actual circumstances, and this application does not impose any limitations on it. When the updated failure count reaches the preset threshold, manual intervention can be initiated, such as sending the contact information of the second user to the first terminal device, and / or sending a prompt message to the second terminal device to reply to the employee information inquiry question from the first user. This allows the first user to promptly query the expected query results or to be informed of the expected query results by the second user.

[0103] Based on the employee information query method based on the AI ​​assistant platform provided in the above embodiments, this application also provides a specific implementation of the employee information query device based on the AI ​​assistant platform. Please refer to the following embodiments.

[0104] Figure 5 This is a schematic diagram of a structure of an employee information query device based on an AI assistant platform, according to an embodiment of this application. Figure 5 As shown, the employee information query device 50 based on the AI ​​assistant platform may include:

[0105] The generation module 501 is used to respond to the employee information inquiry question entered by the first terminal device on the operation page of the AI ​​assistant platform, extract key fields from the employee information inquiry question, generate a target inquiry statement based on the extracted key fields, and display the target inquiry statement on the screen of the first terminal device.

[0106] The first processing module 502 is configured to, if the first terminal device reports that the target query statement is correct, query the first query result corresponding to the target query statement in the application system associated with the target query statement, and display the first query result on the screen of the first terminal device, or display the link address of the application system on the screen of the first terminal device.

[0107] The second processing module 503 is configured to, if the first terminal device reports an error in the target query statement, display at least one alternative query statement associated with the target query statement on the screen of the first terminal device. Specifically, if the first terminal device selects an alternative query statement, it queries the application system associated with the selected alternative query statement for a second query result corresponding to the alternative query statement and displays the second query result on the screen of the first terminal device; or, it displays the link address of the application system on the screen of the first terminal device. If the first terminal device does not select any alternative query statement, it prompts the first terminal device to continue entering employee information query questions, and returns to the steps of extracting key fields from the employee information query questions, generating a target query statement based on the extracted key fields, and displaying the target query statement on the screen of the first terminal device, until the first terminal device reports that the target query statement is correct or selects an alternative query statement.

[0108] The embodiments of this application are based on an employee information query device using an AI assistant platform. On one hand, through the AI ​​assistant platform, users can input employee information query questions. The AI ​​assistant platform can perform semantic analysis on the employee information query questions, extract key fields from the employee information query questions, and generate target query statements based on the extracted key fields. Based on the target query statements, users can query the first query results corresponding to the target query statements in the corresponding application system and display the first query results on the screen of the first terminal device, or display the link address of the application system on the screen of the first terminal device, thereby reducing the time users spend querying employee information and improving query efficiency. On the other hand, the AI ​​assistant platform can perform semantic analysis on the employee information query questions, extract key fields from the employee information query questions, and generate more accurate target query statements based on the extracted key fields, thereby improving the accuracy of the query questions, improving the accuracy of the query results, and improving the user experience. On the other hand, when the target query statement is incorrect, at least one alternative query statement associated with the target query statement can be displayed. In response to the selection of an alternative query statement, a second query result corresponding to the alternative query statement is queried in the corresponding application system and displayed on the screen of the first terminal device. Alternatively, the link address of the application system can be displayed on the screen of the first terminal device. This provides multiple options for query statements, further improves the accuracy of the query questions, reduces the time users spend asking questions, and improves the user experience.

[0109] According to some embodiments of this application, optionally, the generation module 501 can be used to perform semantic analysis on employee information inquiry questions based on a trained AI large language model, extract key fields from employee information inquiry questions, and generate target inquiry statements based on the extracted key fields; perform semantic similarity calculation on key fields based on the AI ​​large language model to obtain at least one alternative field whose similarity to the key field is greater than a preset similarity threshold; and generate at least one alternative inquiry statement based on at least one alternative field.

[0110] According to some embodiments of this application, optionally, the first processing module 502 can be used to: if the target query statement contains multiple employee information query items, for any one employee information query item, query the data interface of the target application system associated with the employee information query item, access the target application system based on the data interface, and query the employee information query results corresponding to the employee information query item in the target application system; call the query result display template corresponding to the target query statement, fill the employee information query results corresponding to each of the multiple employee information query items into the query result display template, and display the filled query result display template as the first query result on the screen of the first terminal device.

[0111] According to some embodiments of this application, optionally, the first processing module 502 can be used to sort the link addresses of multiple application systems according to a preset query order if the target query statement is associated with multiple application systems, and display the sorted link addresses of multiple application systems on the screen of the first terminal device; for any link address of an application system, when the cursor is detected to move to the link address of the application system or when the link address of the application system is clicked, guide information for querying the target query statement of the application system is displayed on the screen.

[0112] According to some embodiments of this application, optionally, the employee information query device 50 based on the AI ​​assistant platform may further include a counting module, used to update the query count of the first terminal device in response to the employee information query question entered by the first terminal device on the operation page; when the updated query count reaches a preset threshold, a second user associated with the first user is determined based on the identity information of the first user, and a query message indicating whether the second terminal device agrees to continue querying is sent to the second terminal device used by the second user; if the second terminal device responds with disagreement, no target query statement is generated. The generation module 501 may be used to extract key fields from the employee information query question if the second terminal device responds with agreement, and generate a target query statement based on the extracted key fields.

[0113] According to some embodiments of this application, optionally, the target query statement includes the query user, the query time period, and employee information query items. The employee information query items include at least one of the following: onboarding information, offboarding information, social security information, housing provident fund information, salary information, task completion status information, and employee feedback information.

[0114] The second processing module 503 can be used to: if the first terminal device does not select any of the alternative query statements, then query the first terminal device for errors in the query user, query time period, and employee information query items; if the first terminal device reports an error in the employee information query item, then display at least one prompt field associated with the employee information query item on the screen; in response to the prompt field selected or entered by the first terminal device, the AI ​​big language model regenerates the target query statement based on the query user, query time period, and prompt field; if the first terminal device reports an error in the query user or query time period, then after reminding the first terminal device to enter the correct query user or query time period, the AI ​​big language model regenerates the target query statement based on the re-entered query user, query time period, and employee information query item.

[0115] According to some embodiments of this application, optionally, the employee information query device 50 based on the AI ​​assistant platform may further include a sending module, used to update the failure count if the first terminal device does not select any of the alternative query statements; when the updated failure count reaches a preset threshold, send the contact information of the second user to the first terminal device, and / or send a prompt message to the second terminal device to reply to the employee information query question of the first user.

[0116] Figure 5 Each module / unit in the device shown has the function of implementing each step in the employee information query method based on the AI ​​assistant platform provided in the above method embodiment, and can achieve its corresponding technical effect. For the sake of brevity, it will not be described in detail here.

[0117] The electronic device in this application embodiment may be a user terminal device, a server, other computing devices, or a cloud server. Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. The electronic device may include a processor 601 and a memory 602 storing computer program instructions. When the processor 601 executes the computer program instructions, it implements the process or function of any of the methods described above.

[0118] Specifically, processor 601 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. Memory 602 may include mass storage for data or instructions. For example, memory 602 may be at least one of the following: hard disk drive (HDD), read-only memory (ROM), random access memory (RAM), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, universal serial bus (USB) drive, or other physical / tangible memory storage device. Alternatively, memory 602 may include removable or non-removable (or fixed) media. Furthermore, memory 602 may be internal or external to the integrated gateway disaster recovery device. Memory 602 may be non-volatile solid-state memory. In other words, typically memory 602 includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in the methods of the embodiments of this application. The processor 601 implements the process or function of any of the methods described in the above embodiments by reading and executing computer program instructions stored in the memory 602.

[0119] In one example Figure 6 The illustrated electronic device may also include a communication interface 603 and a bus 610. The processor 601, memory 602, and communication interface 603 are connected via bus 610 and communicate with each other. Communication interface 603 is primarily used to enable communication between modules, devices, units, and / or equipment in the embodiments of this application. Bus 610 may include hardware, software, or both, and can couple components of the online data traffic billing device together. For example, the bus may include at least one of the following: Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) Interconnect, Industry Standard Architecture (ISA) bus, Infinite Bandwidth Interconnect, Low Pin Count (LPC) bus, memory bus, Microchannel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus, or other suitable buses. Bus 610 may include one or more buses. Although specific buses are described or illustrated in the embodiments of this application, any suitable bus or interconnection method may be considered in the embodiments of this application.

[0120] In conjunction with the methods in the above embodiments, this application also provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the process or function of any of the methods in the above embodiments.

[0121] In addition, this application also provides a computer program product that stores computer program instructions, which, when executed by a processor, implement the process or function of any of the methods described above.

[0122] The flowcharts and / or block diagrams of methods, apparatuses, systems, and computer program products according to embodiments of this application have been exemplarily described above, and related aspects have been described. It should be understood that each block or combination thereof in the flowcharts and / or block diagrams may be implemented by computer program instructions, by dedicated hardware performing a specified function or action, or by a combination of dedicated hardware and computer instructions. For example, these computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to form a machine that enables the implementation of the function / action specified in each block or combination thereof in the flowcharts and / or block diagrams, executable via such processor. Such a processor may be a general-purpose processor, a dedicated processor, a special-purpose application processor, or a field-programmable logic circuit.

[0123] The functional blocks shown in the structural block diagrams of this application can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc.; when implemented in software, they are programs or code segments used to perform the required tasks. Programs or code segments can be stored in memory or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. Code segments can be downloaded via computer networks such as the Internet or intranets.

[0124] It should be noted that this application is not limited to the specific configurations and processes described above or shown in the figures. The above descriptions are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the described systems, devices, modules, or units can be referred to the corresponding processes in the method embodiments, and need not be repeated here. It should be understood that the scope of protection of this application is not limited thereto. Any person skilled in the art can conceive of various equivalent modifications or substitutions within the scope of the technology disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application.

Claims

1. An AI assistant platform-based employee information query method, characterized in that, include: In response to an employee information inquiry question entered by the first terminal device on the operation page of the AI ​​assistant platform, the system extracts key fields from the employee information inquiry question, generates a target inquiry statement based on the extracted key fields, and displays the target inquiry statement on the screen of the first terminal device. The employee information inquiry questions include: handling onboarding procedures, handling offboarding procedures, querying social security information, querying housing provident fund payment information, querying salary payment information, querying task completion status information, or querying employee feedback information. If the first terminal device reports that the target query statement is correct, then based on the target query statement, the system queries one or more application systems associated with the target query statement for the first query result corresponding to the target query statement, and displays the first query result on the screen of the first terminal device; or, the system displays the link address of the one or more application systems on the screen of the first terminal device; the one or more application systems include an employee management application system, a social security application system, a housing provident fund application system, and / or a work progress management application system. If the first terminal device reports an error in the target query statement, at least one alternative query statement associated with the target query statement is displayed on the screen of the first terminal device. If the first terminal device selects an alternative query statement, a second query result corresponding to the alternative query statement is queried in one or more application systems associated with the selected alternative query statement, and the second query result is displayed on the screen of the first terminal device. Alternatively, the link address of the one or more application systems is displayed on the screen of the first terminal device. If the first terminal device does not select any of the alternative query statements, it will prompt the first terminal device to continue entering employee information query questions, and return to extract the key fields from the employee information query questions, generate the target query statement based on the extracted key fields, and display the target query statement on the screen of the first terminal device, until the first terminal device reports that the target query statement is correct or selects an alternative query statement; Displaying the application system's link address on the screen of the first terminal device includes: If the target query statement is associated with multiple application systems, the link addresses of the multiple application systems are sorted according to the preset query order, and the sorted link addresses of the multiple application systems are displayed on the screen of the first terminal device. For any application system link address, when the cursor moves to the application system link address or the application system link address is clicked, guide information for the application system query target statement is displayed on the screen; Before displaying at least one alternative query statement associated with the target query statement on the screen of the first terminal device, the method further includes: Based on the trained AI large language model, semantic similarity is calculated for key fields to obtain at least one candidate field whose similarity to the key field is greater than a preset similarity threshold. Generate at least one alternative query statement based on at least one alternative field.

2. The method of claim 1, wherein, Extract key fields from employee information inquiry questions and generate target inquiry statements based on the extracted key fields, including: Based on a trained AI large language model, semantic analysis is performed on employee information inquiry questions to extract key fields from the questions, and target inquiry statements are generated based on the extracted key fields.

3. The method of claim 1, wherein, Based on the target query statement, the system queries for a first query result corresponding to the target query statement in the application system associated with the target query statement, and displays the first query result on the screen of the first terminal device, including: If the target query statement contains multiple employee information query items, then for any employee information query item, query the data interface of the target application system associated with the employee information query item, access the target application system based on the data interface, and query the employee information query results corresponding to the employee information query item in the target application system. The system calls the query result display template corresponding to the target query statement, fills the query results corresponding to the employee information query items into the query result display template, and displays the filled query result display template as the first query result on the screen of the first terminal device.

4. The method according to claim 1, characterized in that, Before extracting key fields from employee information inquiry questions and generating target inquiry statements based on the extracted key fields, the method further includes: In response to employee information queries entered on the operation page by the first terminal device, update the query count of the first terminal device; When the number of updated inquiries reaches a preset threshold, the second user associated with the first user is identified based on the first user's identity information, and an inquiry message is sent to the second terminal device used by the second user to ask whether the first terminal device agrees to continue inquiring. If the second terminal device disagrees, the target query statement will not be generated. Extract key fields from employee information inquiry questions and generate target inquiry statements based on the extracted key fields, including: If the second terminal device agrees, the key fields in the employee information inquiry questions are extracted, and the target inquiry statement is generated based on the extracted key fields.

5. The method according to claim 1, characterized in that, The target query statement includes the query user, query time period, and employee information query items. The employee information query items include at least one of the following: onboarding information, offboarding information, social security information, housing provident fund information, salary information, task completion status information, and employee feedback information. If the first terminal device does not select any of the alternative query statements, the first terminal device is prompted to continue entering employee information query questions, and the process of extracting key fields from the employee information query questions, generating the target query statement based on the extracted key fields, and displaying the target query statement on the screen of the first terminal device includes: If the first terminal device does not select any of the alternative query statements, then query the first terminal device for the error items in the query user, query time period, and employee information query items; If the error reported by the first terminal device is an employee information query item, then at least one prompt field associated with the employee information query item will be displayed on the screen. In response to the prompt fields selected or entered by the first terminal device, the AI ​​big language model regenerates the target query statement based on the query user, query time period and prompt fields; If the first terminal device reports an error related to the query user or query time period, the AI ​​big language model will regenerate the target query statement based on the re-entered query user, query time period, and employee information query item after prompting the first terminal device to enter the correct query user or query time period.

6. The method of claim 5, wherein, The method further includes: If the first terminal device does not select any of the alternative query statements, the update failure count will be updated. When the number of failures after the update reaches a preset threshold, the contact information of the second user is sent to the first terminal device, and / or a prompt message is sent to the second terminal device to reply to the employee information inquiry question of the first user.

7. An employee information query device based on an AI assistant platform, characterized by, include: The generation module is used to respond to employee information inquiry questions entered by the first terminal device on the operation page of the AI ​​assistant platform, extract key fields from the employee information inquiry questions, generate target inquiry statements based on the extracted key fields, and display the target inquiry statements on the screen of the first terminal device; the employee information inquiry questions include processing onboarding procedures, processing offboarding procedures, querying social security information, querying housing provident fund payment information, querying salary payment information, querying task completion status information, or querying employee feedback information; The first processing module is configured to, if the first terminal device reports that the target query statement is correct, query the first query result corresponding to the target query statement in one or more application systems associated with the target query statement, and display the first query result on the screen of the first terminal device, or display the link address of the one or more application systems on the screen of the first terminal device; the one or more application systems include an employee management application system, a social security application system, a housing provident fund application system, and / or a work progress management application system; The second processing module is configured to, if the first terminal device reports an error in the target query statement, display at least one alternative query statement associated with the target query statement on the screen of the first terminal device. Specifically, if the first terminal device selects an alternative query statement, it queries one or more application systems associated with the selected alternative query statement for a second query result corresponding to the alternative query statement and displays the second query result on the screen of the first terminal device; or, it displays the link addresses of the one or more application systems on the screen of the first terminal device. If the first terminal device does not select any alternative query statement, it prompts the first terminal device to continue entering employee information query questions, and returns to the steps of extracting key fields from the employee information query questions, generating a target query statement based on the extracted key fields, and displaying the target query statement on the screen of the first terminal device, until the first terminal device reports that the target query statement is correct or selects an alternative query statement. Displaying the application system's link address on the screen of the first terminal device includes: If the target query statement is associated with multiple application systems, the link addresses of the multiple application systems will be sorted according to the preset query order, and the sorted link addresses of the multiple application systems will be displayed on the screen of the first terminal device. For any application system link address, when the cursor moves to the application system link address or the application system link address is clicked, guide information for the application system query target statement is displayed on the screen; The generation module is specifically used to perform semantic similarity calculation on key fields based on the trained AI large language model, and obtain at least one candidate field whose similarity to the key field is greater than a preset similarity threshold; based on at least one candidate field, at least one candidate query statement is generated.

8. An electronic device, comprising: The electronic device includes a processor and a memory storing computer program instructions; when the electronic device executes the computer program instructions, it implements the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the method as described in any one of claims 1-6.

Images