Information query method and device, computer program product and electronic equipment

Abstract

The invention discloses an information query method and device, a computer program product and electronic equipment. The method relates to the technical field of information, and comprises the following steps: receiving a query request sent by a target user through a user side, and identifying M target chapter units required for processing the query request; obtaining initial permission requirements for accessing each target chapter unit from the permission index table, obtaining M initial permission requirements, obtaining user information of the target user, and verifying the user information by using the M initial permission requirements; and under the condition that all the M verification results represent that the user information meets the initial permission requirement, inputting the query request into a preset large language model to obtain a query result, and feeding back the query result to the user side. By means of the information processing method and device, the problem that in the related technology, under the condition that different knowledge bases are configured for different user groups, the modification accuracy and efficiency of modifying the content of the knowledge bases are low, and then the accuracy of user information query is low is solved.

Description

Technical Field

[0001] This application relates to the field of information technology, and more specifically, to an information retrieval method, apparatus, computer program product, and electronic device. Background Technology

[0002] In enterprise operations and management, configuring a knowledge base is a key step in building efficient workflows and promoting internal knowledge sharing. A knowledge base contains internal documents, technical documentation, business manuals, customer information, and various structured and unstructured data. Employees can improve work efficiency by querying relevant data from the knowledge base during their work.

[0003] However, given the diversity and sensitivity of internal corporate information, the content in the knowledge base is not fully accessible to all employees. Different employees can only access documents relevant to them. This granular access control helps prevent the unauthorized leakage of sensitive information and protects corporate assets.

[0004] Currently, to implement refined access control, enterprises often adopt a strategy of configuring dedicated query databases for different employee groups when managing knowledge bases. The core of this approach is to ensure that each user or department has a knowledge base that matches their access permissions by physically partitioning the data. However, while this method achieves access isolation and ensures information security to a certain extent, it also brings significant management and maintenance challenges.

[0005] Whenever an enterprise's architecture is adjusted or user permissions are changed, it is necessary to synchronize the permission updates and configuration adjustments of multiple knowledge bases. This not only increases the complexity of management and reduces operational efficiency, but also makes it easy for configuration errors or omissions to occur during the operation, creating loopholes in permission management. Consequently, when users use the knowledge base to query information, they are prone to making unauthorized queries or being unable to find information within their authorized scope, affecting the accuracy of information queries.

[0006] There is currently no effective solution to the problem that when different knowledge bases are configured for different user groups, the accuracy and efficiency of modifying the knowledge base content are low, resulting in low accuracy of user information retrieval. Summary of the Invention

[0007] The main objective of this application is to provide an information retrieval method, apparatus, computer program product, and electronic device to solve the problem in related technologies where the accuracy and efficiency of modifying the content of the knowledge base are low when different knowledge bases are configured for different user groups, resulting in low accuracy of information retrieval by users.

[0008] To achieve the above objectives, according to one aspect of this application, an information query method is provided. The method includes: receiving a query request sent by a target user through a user terminal, and identifying M target chapter units required to process the query request, where M is a positive integer; obtaining the initial permission requirements for accessing each target chapter unit from a permission index table to obtain M initial permission requirements, and obtaining the target user's user information; verifying the user information using the M initial permission requirements to obtain M verification results; and, if all M verification results indicate that the user information meets the initial permission requirements, inputting the query request into a preset large language model to obtain query results, and feeding back the query results to the user terminal, wherein the preset large language model processes the query request by calling the M target chapter units to obtain the query results.

[0009] Optionally, identifying the M target chapter units required for processing the query request includes: parsing the query request to obtain the requested content and identifying the content type of the requested content; obtaining the chapter units associated with the content type from the leaf nodes of the chapter storage unit to obtain the M target chapter units, wherein the chapter storage unit includes multiple file root nodes, each file root node includes at least one intermediate node, each intermediate node includes at least one leaf node, and each intermediate node and leaf node corresponds to a chapter unit.

[0010] Optionally, the initial permission requirements include role permission requirements and department permission requirements. The permission index table is generated as follows: N files are obtained, and the file type of each file is determined, where N is a positive integer; the N files are split according to their file types to obtain N chapter unit sets, where each chapter unit set includes multiple chapter units with hierarchical relationships, and the file size of each chapter unit is greater than a preset number of bytes; the attribute information of each chapter unit is obtained, and the role permission requirements and department permission requirements of each chapter unit are determined based on the attribute information; the attribute information, role permission requirements, and department permission requirements of each chapter unit are used as the permission index information of the chapter unit, and the permission index table is constructed based on the permission index information of the chapter units under the N files.

[0011] Optionally, the user information is validated using M initial permission requirements to obtain M validation results, including: for any initial permission requirement, obtaining role permission requirements and department permission requirements from the initial permission requirements; identifying role information and department information in the user information; validating the role information using the role permission requirements to obtain a first validation result, wherein the first validation result indicates whether the role information meets the role permission requirements; validating the department information using the department permission requirements to obtain a second validation result, wherein the second validation result indicates whether the department information meets the department permission requirements; and determining the validation result of the initial permission requirements based on the first validation result and the second validation result.

[0012] Optionally, determining the role permission requirements and department permission requirements for each chapter unit based on attribute information includes: for any chapter unit, obtaining the initial role permission requirements and initial department permission requirements for the chapter unit from the permission requirement library; determining whether the information source of the initial role permission requirements and initial department permission requirements is unique; if the information source of the initial role permission requirements and / or initial department permission requirements is not unique, determining the preset role permission requirements and preset department permission requirements as the role permission requirements and department permission requirements of the chapter unit respectively; if the information source of the initial role permission requirements and initial department permission requirements is unique, determining the initial role permission requirements and initial department permission requirements as the role permission requirements and department permission requirements of the chapter unit respectively.

[0013] Optionally, if all M verification results indicate that the initial permission requirements match the user information, the method further includes: determining the update time of the permission index table update operation, and calculating the time difference between the update time and the target time, where the target time is the time when the query request is received; if the time difference is less than a time difference threshold, performing the step of inputting the query request into a preset large language model; if the time difference is greater than or equal to the time difference threshold, obtaining the target permission requirements of each target chapter unit at the target time, resulting in M ​​target permission requirements; using the M target permission requirements to verify the user information, obtaining M target verification results, and if all M target verification results indicate that the target permission requirements match the user information, performing the step of inputting the query request into the preset large language model; if any target verification result indicates that the target permission requirements do not match the user information, determining that the query request is abnormal.

[0014] Optionally, after obtaining the query results, the method further includes: determining whether there is sensitive information in the query results based on a preset set of sensitive words; if there is sensitive information in the query results, determining whether the sensitive information matches the user information; if the sensitive information matches the user information, sending the query results back to the user; if the sensitive information does not match the user information, deleting the sensitive information, obtaining updated query results, and sending the updated query results back to the user; if there is no sensitive information in the query results, sending the query results back to the user.

[0015] To achieve the above objectives, according to another aspect of this application, an information query device is provided. The device includes: a receiving module, configured to receive a query request sent by a target user through a user terminal, and identify M target chapter units required to process the query request, where M is a positive integer; a first acquisition module, configured to acquire the initial permission requirements for accessing each target chapter unit from a permission index table, obtaining M initial permission requirements, and acquiring the target user's user information, verifying the user information using the M initial permission requirements, and obtaining M verification results; and a query module, configured to, if all M verification results indicate that the user information meets the initial permission requirements, input the query request into a preset large language model, obtain query results, and feed the query results back to the user terminal, wherein the preset large language model processes the query request by calling the M target chapter units to obtain the query results.

[0016] To achieve the above objectives, according to another aspect of this application, an electronic device is provided, the electronic device including a memory storing an executable program; and a processor for running the program, wherein the program executes the above-described information query method during runtime.

[0017] To achieve the above objectives, according to another aspect of this application, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the information query method described above.

[0018] In this embodiment, the process involves receiving a query request sent by a target user through a client, identifying M target chapter units required to process the query request (where M is a positive integer), obtaining the initial permission requirements for accessing each target chapter unit from the permission index table to obtain M initial permission requirements, acquiring the target user's user information, verifying the user information using the M initial permission requirements to obtain M verification results, and inputting the query request into a preset large language model to obtain query results, which are then fed back to the client. The preset large language model obtains query results by calling the M target chapter units to process the query request, thus determining the target chapters required to generate the query result based on the query request. The system identifies and determines whether a user has reading permissions for all target chapters. If permissions are granted, query results can be generated based on the target chapters, allowing authorized users to complete the query. Users without permissions, however, cannot generate query results based on the target chapters. This allows enterprises to obtain different query results based on different user permissions, even with only one knowledge base containing all complete files. By reducing the complexity of modifying the database content, the accuracy and security of information queries are improved. This solves the technical problem in related technologies where modifying knowledge base content for different user groups results in low accuracy and efficiency, leading to low accuracy in user information queries. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 A hardware structure block diagram of a computer terminal for implementing an information retrieval method is shown.

[0021] Figure 2 This is a flowchart of the information query method provided in Embodiment 1 of this application;

[0022] Figure 3 This is a schematic diagram of an information query device according to Embodiment 2 of this application;

[0023] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0024] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] It should be noted that the information retrieval methods, devices, computer program products, and electronic devices defined in this disclosure can be used in the field of information technology, or in any field other than information technology. The application fields of the information retrieval methods, devices, computer program products, and electronic devices defined in this disclosure are not limited.

[0028] It should be noted that all information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) used in this application are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse use. If the user chooses to refuse, the process will proceed to the expert decision-making process. For example, this system has an interface with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface. After receiving consent from the aforementioned user or organization, the relevant information is obtained. Users can view the purpose of data use in real time through the authorization interface and have the right to withdraw authorization or delete data at any time. After the authorization is withdrawn, the system will terminate the relevant data processing within 24 hours.

[0029] The embodiments or examples disclosed herein are not exhaustive, but merely illustrative of some embodiments or examples, and are not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment or example can be arbitrarily interchanged. Furthermore, optional methods or examples in a particular embodiment or example can be arbitrarily combined; moreover, embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a particular embodiment or example can be arbitrarily combined with optional methods or examples of other embodiments or examples.

[0030] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0031] MD5: Message-Digest Algorithm 5.

[0032] Example 1

[0033] According to an embodiment of this application, an embodiment of an information query method is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware structure block diagram of a computer terminal for implementing an information retrieval method is shown. For example... Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, processing devices such as microprocessors or programmable logic devices), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface, a universal serial bus port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0035] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0036] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the information query method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned information query method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0037] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0038] The display may be, for example, a touchscreen LCD display that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0039] Under the aforementioned operating environment, this application provides the following: Figure 2 The information retrieval method is shown. Figure 2 This is a flowchart of the information query method provided in Embodiment 1 of this application, such as... Figure 2 As shown, the method includes:

[0040] Step S201: Receive the query request sent by the target user through the user terminal, and identify the M target chapter units required to process the query request, where M is a positive integer.

[0041] It should be noted that the execution entity in this embodiment can be an information query system. This system can output corresponding query results based on the query request sent by the user, and prohibit the output of query results when the user does not have query permissions, thereby improving the security of the data in the knowledge base and the accuracy of the output results.

[0042] It should be noted that the target user can be an employee of the company, and the information query can be an information query operation performed by the target user using the information query system configured by the company. The information query system can be connected to the company's knowledge base, so that the information query system can obtain the query results of the query request from the knowledge base.

[0043] Optionally, upon receiving a query request from a target user, the information query system first performs natural language understanding and parsing on the request text to determine the query intent. Then, using chapter-level metadata and vector indexes, it quickly locates the chapter unit that matches the query request, obtains the target chapter unit, and generates the query results based on the information content recorded in the target chapter unit.

[0044] It should be noted that in related technologies, user query permissions are typically set at the file level. That is, file 1 is allowed for a user to read, while file 2 is not. However, since only a small portion of the sensitive information in the files that are not allowed to be read may be restricted, while most of the information is accessible, using file-level permission settings can lead to a situation where "protecting 10% of sensitive content locks in 90% of usable knowledge." Therefore, this technical solution does not use file-level permission settings, but rather the lowest level of chapters within the files. When determining the information needed to process a query request, the target chapter unit is obtained from the chapter level. The target chapter unit can come from one or more files. By managing information in the knowledge base from the chapter level, the efficiency and scope of information use in the knowledge base can be improved.

[0045] Step S202: Obtain the initial permission requirements for accessing each target chapter unit from the permission index table to obtain M initial permission requirements, and obtain the user information of the target user. Use the M initial permission requirements to verify the user information to obtain M verification results.

[0046] It should be noted that the permission index table can be a dedicated data structure for maintaining the permission mapping relationship between chapters and roles. It stores key information such as the sensitivity level of each chapter and the allowed role identifiers. The permission index table can be stored locally on the system, thus eliminating the need to retrieve the permission requirements for each chapter from the knowledge base every time it is accessed. The initial permission requirements can be the most basic permission configuration for each target chapter unit, including but not limited to reading permissions and editing permissions.

[0047] Optionally, after the target chapter unit is determined, the query results corresponding to the query request are usually generated directly based on the content in the target chapter unit. However, in order to improve the security of the content of the target chapter unit, it is necessary to obtain the initial permission requirements for accessing each target chapter unit and determine whether the target user has the query permission to query the content of each target chapter unit based on the user information. This ensures that only users who meet the permission requirements can use the content of the target chapter unit to continue to perform subsequent information retrieval operations, thereby enhancing the security of information within the knowledge base.

[0048] Step S203: If all M verification results indicate that the user information meets the initial permission requirements, the query request is input into the preset large language model to obtain the query results, and the query results are fed back to the user. The preset large language model processes the query request by calling M target chapter units to obtain the query results.

[0049] It should be noted that the pre-trained large language model refers to a neural network model that is pre-trained to generate text or answer queries, possessing advanced natural language processing and knowledge retrieval capabilities. The query results are generated by the pre-trained large language model based on target chapter units that the target user has access to.

[0050] Optionally, when all verification results obtained in step S202 are satisfactory, the system will enter the information retrieval and generation stage. At this time, the query request will be sent to the preset large language model. The model will call the target chapter units that the target user has the right to access, and generate the final query results based on these chapter information. By determining the target chapter units and generating query results by calling the target chapter units through the model, the content contained in the model output results can be read and used by the target user. This avoids outputting information that the target user does not have the right to read and use, improves the security and accuracy of the output results, and enhances the security of information in the knowledge base.

[0051] The information query method provided in this application embodiment involves receiving a query request sent by a target user through a user terminal, identifying M target chapter units required to process the query request (where M is a positive integer), obtaining the initial permission requirements for accessing each target chapter unit from a permission index table to obtain M initial permission requirements, obtaining the target user's user information, verifying the user information using the M initial permission requirements to obtain M verification results, and inputting the query request into a preset large language model to obtain query results, which are then fed back to the user terminal. The preset large language model obtains query results by calling the M target chapter units to process the query request, and determines the required parameters for generating the query request results based on the query request. The system identifies target chapter units and determines whether users have reading permissions for all target chapter units. If a user has permission, query results can be generated based on the target chapter unit, allowing authorized users to complete the query. Users without permission will not be able to generate query results based on the target chapter unit. This allows enterprises to obtain different query results based on different user information even with only one knowledge base containing all complete files. By reducing the complexity of adjusting database content, the accuracy and security of information queries are improved. This solves the technical problem in related technologies where the accuracy and efficiency of modifying knowledge base content are low when different knowledge bases are configured for different user groups, resulting in low accuracy of user information queries.

[0052] To accurately obtain target chapter units, optionally, in the information query method provided in this application embodiment, identifying the M target chapter units required to process the query request includes: parsing the query request to obtain the request content and identifying the content type of the request content; obtaining chapter units associated with the content type from the leaf nodes of the chapter storage unit to obtain M target chapter units, wherein the chapter storage unit includes multiple file root nodes, each file root node includes at least one intermediate node, each intermediate node includes at least one leaf node, and each intermediate node and leaf node corresponds to a chapter unit.

[0053] It should be noted that when building the knowledge base, each file needs to be split into chapters. The splitting rules can be as follows: define the chapter splitting logic according to the file type. For document types, split by "heading level" (H1 is the first-level chapter, H2 is the second-level chapter, and so on). For table types, split by "sheet page + data topic" (e.g., "Sales Data - 2024Q1" is an independent chapter). For drawing types, split by "module / part" (e.g., "Engine Drawings - Cylinder Block" is a chapter).

[0054] After splitting, structured storage can be performed to obtain chapter storage units, which is a knowledge base built according to the chapter dimension. When performing structured storage, the split chapters can be stored as independent "knowledge units" while recording the complete hierarchical relationship (such as the parent-child relationship of "file ID-first-level chapter ID-second-level chapter ID"). Then, the file to which any chapter belongs and its hierarchical relationship can be located through any chapter.

[0055] It's important to note that after the initial construction of the knowledge base is complete, metadata and permission requirements need to be configured for each chapter unit. This metadata, used for permission assessment and retrieval filtering, can include: chapter ID, sensitivity level, business domain, parent chapter ID, effective date, and expiration date. To improve efficiency when setting permission requirements, sub-chapters can inherit parent chapter permissions by default. For example, if a file-level permission is set to "Visible to Finance Department," all its sub-chapters inherit this permission by default. Only special chapters (such as the "Core Financial Data" chapter) need to be configured separately. Furthermore, sub-chapters can have their own permissions set (with higher priority than inheritance). For instance, if the parent chapter's permission is "Internal Public," the sub-chapter "Core Customer Quotations" can be set to "Visible to Manager."

[0056] It should be noted that when setting the permission requirements for each chapter unit, the permission requirements for the chapter unit can be pre-annotated using a general model of prompt words and an internally trained risk detection model, thereby assisting users in quickly completing the permission requirement setting process.

[0057] It should be noted that after the knowledge base is built, new chapter units may be added. In this case, the MD5 hash of the new chapter unit needs to be compared with the backend data to avoid duplicate uploads, storage, and processing. Specifically, after selecting a new chapter unit, the page program will calculate the MD5 hash of the new chapter unit and send it along with the file attributes to the backend for deduplication. If it is determined to be a duplicate file, the upload process will be stopped.

[0058] Optionally, after constructing the knowledge base, the system can identify and retrieve the M target chapter units required to process the query request. First, the received query request is parsed using natural language processing, employing semantic understanding, entity recognition, and other technologies to transform the ambiguous request text into a clear query intent and key elements. Subsequently, the system identifies the content type of the parsed request content to determine the information category to which the query content belongs. For example, if the query request frequently mentions terms such as "cost analysis" and "budget report," the system will identify its content type as "financial data."

[0059] Furthermore, after obtaining the content type, the system searches for chapter units under that content type in the chapter storage unit. The chapter storage unit is designed as a tree structure, where the root node represents the complete file, intermediate nodes represent first-level chapters, and leaf nodes represent the finest-grained chapter units. Starting from the root node, the system searches for chapter information matching the query request, following the content type and moving along the intermediate nodes to the leaf nodes. By traversing the intermediate and leaf nodes, and filtering using attributes such as business domain and sensitivity level from the chapter metadata, the system ultimately determines the leaf node associated with the content type, thus obtaining the target chapter unit.

[0060] This embodiment searches for chapter units in a tree-structured knowledge base (i.e., chapter storage units) based on the content type of the requested content, so that the obtained target chapter unit is related to the query request, thereby improving the accuracy of the subsequent query results generated based on the target chapter unit.

[0061] To improve the accuracy of the permission index table, optionally, in the information query method provided in this application embodiment, the initial permission requirements include role permission requirements and department permission requirements. The permission index table is generated as follows: obtain N files and obtain the file type of each file, where N is a positive integer; split the N files according to the file type to obtain N chapter unit sets, where each chapter unit set includes multiple chapter units, and there is a hierarchical relationship between the multiple chapter units, and the file size of each chapter unit is greater than a preset number of bytes; obtain the attribute information of each chapter unit, and determine the role permission requirements and department permission requirements of each chapter unit according to the attribute information; determine the attribute information, role permission requirements, and department permission requirements of each chapter unit as the permission index information of the chapter unit, and construct the permission index table according to the permission index information of the chapter units under the N files.

[0062] It should be noted that, since the permission index table needs to include the attribute information and permission requirements of each chapter unit, when generating the permission index table, it is first necessary to obtain the file type of each file, and then split the file according to the file type to obtain the chapter units in each file. Then, the role permission requirements and department permission requirements are determined according to the attribute information of the chapter units. Then, the initial permission requirements of each chapter unit are determined according to the role permission requirements and department permission requirements. Finally, the specific permission index content under each chapter unit in the permission index table is constructed according to the initial permission requirements and attribute information, and the permission index table is constructed according to the attribute information and initial permission requirements of each chapter unit.

[0063] It should be noted that the granularity of chapter splitting needs to be controlled, with the file size of each chapter unit being larger than the preset number of bytes, in order to avoid overly fine-grained chapter splitting.

[0064] It should be noted that the permission index table can be stored locally on the system. It only needs to store the attribute information or metadata of the chapter unit and the initial permission requirements. This allows the initial permission requirements to be retrieved directly from the local system each time, without having to frequently interact with the knowledge base, thereby improving the processing efficiency of query requests.

[0065] It should be noted that when determining the role and department permission requirements for each chapter unit based on attribute information, a chapter-role mapping relationship and a chapter-department mapping relationship can be established first. Based on the above mapping relationship, the role and department permission requirements that can be read for each chapter unit can be determined. Attribute information can be represented by vector fragments, for example: Vector fragment metadata attribute information = {content: "xxx", chapter ID: "CHAP-F1-C1", allowed roles: ["R&D Engineer", "Product Manager"], sensitivity: "internal level"}.

[0066] It should be noted that other permission requirements can be added to the initial permission requirements according to the security needs of the knowledge base, but this embodiment does not limit this.

[0067] It should be noted that when determining the permission requirements for chapter units, the model can be used to assist in the determination, and permission requirements can be generated through preset permission requirement templates, thereby improving the accuracy and completeness of the permission requirements.

[0068] This embodiment generates a permission index table by obtaining the attribute information and initial permission requirements of each chapter unit, thereby improving the accuracy and comprehensiveness of the content in the permission index table.

[0069] To improve the accuracy of the verification results, optionally, in the information query method provided in this application embodiment, verifying user information using M initial permission requirements to obtain M verification results includes: for any initial permission requirement, obtaining role permission requirements and department permission requirements from the initial permission requirements; identifying role information and department information in the user information; verifying role information using role permission requirements to obtain a first verification result, wherein the first verification result indicates whether the role information meets the role permission requirements; verifying department information using department permission requirements to obtain a second verification result, wherein the second verification result indicates whether the department information meets the department permission requirements; and determining the verification result of the initial permission requirements based on the first verification result and the second verification result.

[0070] Optionally, when verifying user information, for each initial permission requirement that needs to be verified, the system first deconstructs it to extract role permission requirements and department permission requirements. For example, the fields of permission requirements can be parsed to accurately identify key information in the permission configuration.

[0071] Furthermore, the system needs to parse the user information, identify the role and department information, and verify the user's role information using role-based access requirements to obtain a first verification result. This first verification result can be determined by comparing the user's role with the roles listed in the access requirements. For example, if the access requirement for a chapter / unit is the "R&D Engineer" role, and the user information shows that the target user belongs to the "R&D Engineer" role, then the user will pass the access verification at this role level, and the system will return a "satisfied" first verification result.

[0072] Similarly, departmental access requirements are needed to verify the user's department information, resulting in a second verification result. Departmental-level verification ensures that only users from specific departments can access the corresponding chapters. For example, if the target chapter's departmental access requirement is "Marketing Department," and the target user belongs to the "Marketing Department," then the second verification result will be "satisfied."

[0073] Finally, the system will combine the first and second verification results to determine the final verification status of each initial permission requirement. Only when both verification results are satisfied will the system consider the user to fully meet the access permissions for that chapter unit, thus allowing them to perform subsequent query processing; otherwise, it will be considered that the permissions are not satisfied, and the relevant chapter information will be blocked from the user, thereby improving the accuracy of verification results and the accurate processing of chapter information.

[0074] This embodiment determines the verification result of the initial permission requirement by combining the first verification result and the second verification result, thereby improving the accuracy of the verification result of the initial permission requirement.

[0075] To improve the accuracy of permission requirements, optionally, in the information query method provided in this application embodiment, determining the role permission requirements and department permission requirements of each chapter unit based on attribute information includes: for any chapter unit, obtaining the initial role permission requirements and initial department permission requirements of the attribute information under the chapter unit from the permission requirement library; determining whether the information source of the initial role permission requirements and initial department permission requirements is unique; if the information source of the initial role permission requirements and / or initial department permission requirements is not unique, determining the preset role permission requirements and preset department permission requirements as the role permission requirements and department permission requirements of the chapter unit respectively; if the information source of the initial role permission requirements and initial department permission requirements is unique, determining the initial role permission requirements and initial department permission requirements as the role permission requirements and department permission requirements of the chapter unit respectively.

[0076] It should be noted that the permission requirement library can be a database storing various permission requirements defined by the enterprise, including role permissions and department permissions, used to guide the allocation of chapter-level permissions. Attribute information can be a set of data describing the characteristics of chapter units, such as sensitivity level, business domain, and effective time, which serves as the basis for determining permission requirements.

[0077] Optionally, for any chapter unit, the system will first read attribute information from its metadata, including but not limited to sensitivity, business domain, and department. Subsequently, the system will query the permission requirement database based on this attribute information to obtain the initial role permission requirements and initial department permission requirements for that chapter unit. The query process involves multi-table joins, thereby enabling the accurate and complete extraction of permission requirements that match the chapter unit's attributes from the permission requirement database.

[0078] Furthermore, it is necessary to check whether the initial role permission requirements and initial department permission requirements originate from a single data source. If there are multiple conflicting permission configurations within the same chapter unit (for example, if the role permission requirements for chapter unit A are configured as scheme 1 by user A and as scheme 2 by user B, a conflict will occur), this will lead to uncertainty in permission judgment, thereby causing vulnerabilities in permission control. Therefore, it is necessary to confirm the source of permission requirements to ensure that the source of permission requirements for chapter units is clear and unique, avoiding security risks caused by permission configuration conflicts and promoting the stability and reliability of permission management.

[0079] When the sources of information for initial role permission requirements and / or initial department permission requirements are not unique, in order to improve the accuracy of the permission requirements used, it is necessary to adopt preset role permission requirements and preset department permission requirements as the final permission requirements for chapter units. Among them, the preset requirements are more accurate preset permission requirements.

[0080] If the information source for the initial role permission requirements and the initial department permission requirements is unique, then the initial role permission requirements and the initial department permission requirements can be directly determined as the role permission requirements and department permission requirements of the chapter unit, respectively, without any additional adjustments.

[0081] This embodiment improves the accuracy of permission requests by determining whether the source of the permission request is unique and thus determining the content of the permission request.

[0082] To improve the accuracy of user information verification, optionally, in the information query method provided in this application embodiment, when all M verification results indicate that the initial permission requirements match the user information, the method further includes: determining the update time of the permission index table update operation, and calculating the time difference between the update time and the target time, wherein the target time is the time when the query request is received; when the time difference is less than a time difference threshold, performing the step of inputting the query request into a preset large language model; when the time difference is greater than or equal to the time difference threshold, obtaining the target permission requirements of each target chapter unit at the target time, resulting in M ​​target permission requirements; using the M target permission requirements to verify the user information, obtaining M target verification results, and when all M target verification results indicate that the target permission requirements match the user information, performing the step of inputting the query request into a preset large language model; when any target verification result indicates that the target permission requirements do not match the user information, determining that the query request is abnormal.

[0083] Optionally, since the permission index table is stored locally on the system, changes in permission information for a chapter unit in the knowledge base may not be promptly synchronized with the permission index table, leading to errors in its content. Therefore, to improve the accuracy of user information verification, the system first identifies the update time of the permission index table and stores it in the table's metadata to track the latest permission configuration status. Subsequently, the system calculates the time difference between the update time and the target time to determine if the timeliness of the permission index table meets the needs of the current query processing. For example, if the update time of the permission index table is 14:00, and the query request is received at 14:30, the system calculates a time difference of 30 minutes. By calculating this time difference, the system can determine whether the update status of the permission index table is synchronized with the latest requirements of the user's query request, thereby deciding whether to re-verify user permissions and enhancing the real-time performance and accuracy of permission control.

[0084] Optionally, if the time difference is less than the time difference threshold, it indicates that the update status of the permission index table matches the query request requirements at the target time, and no additional permission verification or update is required. In this case, the system can directly skip the secondary permission verification step, input the query request into the preset large language model for processing, and generate query results. This process simplifies the permission verification process and improves query response speed.

[0085] Optionally, if the time difference is greater than or equal to the time difference threshold, the system will consider that the permission index table has not been updated in time. In order to maintain the accuracy and security of user access permissions, the system will re-obtain the target permission requirements of each target chapter unit at the target time from the knowledge base, and use the target permission requirements to verify the user information, thereby improving the accuracy of the verification results.

[0086] This embodiment improves the accuracy of verification results by dynamically evaluating the relationship between the update status of the permission index table and the query request reception time, and intelligently adjusting the permission verification strategy.

[0087] To improve the security of query results, optionally, in the information query method provided in this application embodiment, after obtaining the query results, the method further includes: determining whether there is sensitive information in the query results based on a preset set of sensitive words; if there is sensitive information in the query results, determining whether the sensitive information matches user information; if the sensitive information matches user information, feeding the query results back to the user; if the sensitive information does not match user information, deleting the sensitive information, obtaining updated query results, and feeding the updated query results back to the user; if there is no sensitive information in the query results, feeding the query results back to the user.

[0088] Optionally, after generating the query results, the system also needs to scan the results generated by the preset large language model and perform matching detection using words from the preset sensitive word set. This can be done by using regular expression matching, keyword recognition algorithms in natural language processing, or other methods to identify the content of the query results. During matching, the system will check each sentence or paragraph in the query results one by one to determine whether it contains any words from the preset sensitive word set. For example, if the preset sensitive word set contains words such as "financial statements" or "core technology," the system will check whether these words exist in the query results.

[0089] Optionally, if sensitive information is detected in the query results, the system will invoke the permission verification module to compare the chapter / unit of the sensitive information with the role and department attributes in the user information. This comparison process can be based on the role and department permission requirements of the chapter / unit to ensure that the user information matches the access permissions of the sensitive information. For example, if the sensitive information belongs to the "Core Technology" chapter, and the access permission for that chapter is "R&D Engineer," the system will check whether the user information contains the role of "R&D Engineer" to determine whether the user has the right to access the sensitive information.

[0090] Optionally, if the sensitive information matches the user information, indicating that the user has the right to access this sensitive content, the system will directly return the complete query results to the user. Conversely, if the match fails, the system will delete or mask the sensitive information in the query results and generate updated query results, ensuring that the user can only see information within their authorized scope, thus preventing sensitive information from being leaked to unauthorized users. If the query results do not contain sensitive information, the system will directly return the original results to the user.

[0091] It should be noted that if the query results contain sensitive information and the user has the right to read it, the query results can be encrypted to maintain information security during the information transmission process.

[0092] This embodiment intelligently controls the output of sensitive information and identifies and deletes sensitive information, thereby protecting sensitive information while enabling users to obtain valid information within their authorized scope, maintaining the accuracy and validity of query results.

[0093] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0094] Example 2

[0095] This application also provides an information query device. It should be noted that the information query device of this application can be used to execute the information query method provided in the above embodiments. The information query device provided in this application is described below.

[0096] According to an embodiment of this application, an apparatus for implementing the above-described information query method is also provided. Figure 3 This is a schematic diagram of an information query device according to Embodiment 2 of this application, such as... Figure 3 As shown, the device includes:

[0097] The receiving module 31 is used to receive the query request sent by the target user through the user terminal, and identify the M target chapter units required to process the query request, where M is a positive integer.

[0098] The first acquisition module 32 is used to obtain the initial permission requirements for accessing each target chapter unit from the permission index table, obtain M initial permission requirements, obtain the user information of the target user, verify the user information using the M initial permission requirements, and obtain M verification results.

[0099] The query module 33 is used to input the query request into the preset large language model, obtain the query results, and feed the query results back to the user terminal when all M verification results indicate that the user information meets the initial permission requirements. The preset large language model processes the query request by calling M target chapter units to obtain the query results.

[0100] The information query device provided in this application embodiment receives a query request sent by a target user through a user terminal via a receiving module 31, and identifies M target chapter units required to process the query request, where M is a positive integer; a first acquisition module 32 obtains the initial permission requirements for accessing each target chapter unit from the permission index table, obtaining M initial permission requirements, and obtains the user information of the target user, verifies the user information using the M initial permission requirements, and obtains M verification results; if all M verification results indicate that the user information meets the initial permission requirements, the query module 33 inputs the query request into a preset large language model, obtains the query results, and feeds the query results back to the user terminal, wherein the preset large language model processes the query request by calling the M target chapter units to obtain the query results, and determines the generation of the query based on the query request. The system requests the target chapter units required for the desired results and determines whether the user has reading permissions for all target chapter units. If the user has permission, query results can be generated based on the target chapter units, allowing authorized users to complete the query. Users without permission will not be able to generate query results based on the target chapter units. This allows enterprises to obtain different information query results based on different user information even with only one knowledge base containing all complete files. By reducing the complexity of adjusting database content, the accuracy and security of information queries are improved. This solves the technical problem in related technologies where the accuracy and efficiency of modifying knowledge base content are low when different knowledge bases are configured for different user groups, resulting in low accuracy of user information queries.

[0101] Optionally, in the information query device provided in this application embodiment, the receiving module 31 includes: a parsing submodule, used to parse the query request, obtain the requested content, and identify the content type of the requested content; and a first obtaining submodule, used to obtain the chapter unit associated with the content type from the leaf node of the chapter storage unit, to obtain M target chapter units, wherein the chapter storage unit includes multiple file root nodes, each file root node includes at least one intermediate node, each intermediate node includes at least one leaf node, and each intermediate node and leaf node corresponds to a chapter unit.

[0102] Optionally, in the information query device provided in this application embodiment, the initial permission requirements include role permission requirements and department permission requirements. The permission index table is generated by the following devices: a second acquisition module, used to acquire N files and acquire the file type of each file, where N is a positive integer; a splitting module, used to split the N files according to the file type to obtain N chapter unit sets, where each chapter unit set includes multiple chapter units, there is a hierarchical relationship between the multiple chapter units, and the file size of each chapter unit is greater than a preset number of bytes; a third acquisition module, used to acquire the attribute information of each chapter unit and determine the role permission requirements and department permission requirements of each chapter unit according to the attribute information; and a first determination module, used to determine the attribute information, role permission requirements, and department permission requirements of each chapter unit as the permission index information of the chapter unit, and construct a permission index table according to the permission index information of the chapter units under the N files.

[0103] Optionally, in the information query device provided in this application embodiment, the first acquisition module 32 includes: a second acquisition submodule, used to acquire role permission requirements and department permission requirements from any initial permission requirements; an identification submodule, used to identify role information and department information in user information; a first verification submodule, used to verify role information using role permission requirements to obtain a first verification result, wherein the first verification result indicates whether the role information meets the role permission requirements; a second verification submodule, used to verify department information using department permission requirements to obtain a second verification result, wherein the second verification result indicates whether the department information meets the department permission requirements; and a first determination submodule, used to determine the verification result of the initial permission requirements based on the first verification result and the second verification result.

[0104] Optionally, in the information query device provided in this application embodiment, the third acquisition module includes: a third acquisition submodule, used to acquire, for any chapter unit, the initial role permission requirements and initial department permission requirements of the attribute information under the chapter unit from the permission requirement library; a second determination submodule, used to determine whether the information source of the initial role permission requirements and initial department permission requirements is unique; a third determination submodule, used to determine the preset role permission requirements and preset department permission requirements as the role permission requirements and department permission requirements of the chapter unit respectively when the information source of the initial role permission requirements and / or initial department permission requirements is not unique; and a fourth determination submodule, used to determine the initial role permission requirements and initial department permission requirements as the role permission requirements and department permission requirements of the chapter unit respectively when the information source of the initial role permission requirements and initial department permission requirements is unique.

[0105] Optionally, in the information query device provided in this application embodiment, when all M verification results indicate that the initial permission requirements match the user information, the device further includes: a second determining module, used to determine the update time of the permission index table update operation and calculate the time difference between the update time and the target time, wherein the target time is the time when the query request is received; an execution module, used to execute the step of inputting the query request into a preset large language model when the time difference is less than a time difference threshold; a fourth obtaining module, used to obtain the target permission requirements of each target chapter unit at the target time when the time difference is greater than or equal to the time difference threshold, thereby obtaining M target permission requirements; a verification module, used to verify the user information using the M target permission requirements, obtain M target verification results, and execute the step of inputting the query request into a preset large language model when all M target verification results indicate that the target permission requirements match the user information; and a third determining module, used to determine that the query request is abnormal when any one of the target verification results indicates that the target permission requirements do not match the user information.

[0106] Optionally, in the information query device provided in this application embodiment, after obtaining the query result, the device further includes: a fourth determining module, used to determine whether there is sensitive information in the query result according to a preset sensitive word set; a judging module, used to judge whether the sensitive information matches the user information if there is sensitive information in the query result; a first feedback module, used to feed back the query result to the user terminal if the sensitive information matches the user information; a deletion module, used to delete the sensitive information, obtain an updated query result, and feed back the updated query result to the user terminal if the sensitive information does not match the user information; and a second feedback module, used to feed back the query result to the user terminal if there is no sensitive information in the query result.

[0107] It should be noted that the receiving module 31, the first acquiring module 32, and the querying module 33 correspond to steps S201 to S203 in Embodiment 1. The instances and application scenarios implemented by each module and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the modules or units mentioned above can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The modules mentioned above can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0108] Example 3

[0109] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (Only one is shown) processor 1002, memory 1004, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0110] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0111] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0112] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0113] Example 4

[0114] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the information query method provided in Embodiment 1.

[0115] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0116] Embodiments of this application also provide a computer program product, which, when executed on a data processing device, is adapted to perform the steps of an information retrieval method.

[0117] Embodiments of this application also provide a computer-readable storage medium, which includes a stored executable program, wherein the executable program controls the device where the computer-readable storage medium is located to execute the above-described information query method when it runs.

[0118] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0119] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0120] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0123] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0124] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An information search method characterized by comprising: The method comprises: receiving a query request sent by a target user through a user terminal, and identifying M target chapter units required for processing the query request, wherein M is a positive integer; obtaining initial permission requirements for accessing each target chapter unit from a permission index table to obtain M initial permission requirements, and obtaining user information of the target user, verifying the user information using the M initial permission requirements to obtain M verification results; in the case where the M verification results all represent that the user information meets the initial permission requirements, inputting the query request into a preset large language model to obtain a query result, and feeding back the query result to the user terminal, wherein the preset large language model processes the query request by calling the M target chapter units to obtain the query result.

2. The method of claim 1, wherein, Identifying M target chapter units required for processing the query request comprises: parsing the query request to obtain request content, and identifying the content type of the request content; obtaining chapter units associated with the content type from leaf nodes of a chapter storage unit to obtain the M target chapter units, wherein the chapter storage unit includes multiple file root nodes, each file root node includes at least one intermediate node, and each intermediate node includes at least one leaf node, and the intermediate nodes and the leaf nodes each correspond to a chapter unit.

3. The method of claim 1, wherein, The initial permission requirements include role permission requirements and department permission requirements, and the permission index table is generated in the following manner: obtaining N files and obtaining the file type of each file, wherein N is a positive integer; splitting N files according to the file type to obtain N chapter unit sets, wherein each chapter unit set includes multiple chapter units, and there is a hierarchical relationship between the multiple chapter units, and the file size of each chapter unit is greater than a preset byte; obtaining attribute information of each chapter unit, and determining the role permission requirements and the department permission requirements of each chapter unit according to the attribute information; determining the attribute information, the role permission requirements and the department permission requirements of each chapter unit as the permission index information of the chapter unit, and constructing the permission index table according to the permission index information of the chapter units under the N files.

4. The method of claim 1, wherein, Verifying the user information using the M initial permission requirements to obtain M verification results comprises: for any one initial permission requirement, obtaining role permission requirements and department permission requirements from the initial permission requirement; identifying role information and department information in the user information; verifying the role information using the role permission requirements to obtain a first verification result, wherein the first verification result represents whether the role information meets the role permission requirements; verifying the department information using the department permission requirements to obtain a second verification result, wherein the second verification result represents whether the department information meets the department permission requirements; determining the verification result of the initial permission requirement according to the first verification result and the second verification result.

5. The method of claim 3, wherein, The determining the role permission requirement and the department permission requirement of each chapter unit according to the attribute information comprises: For any chapter unit, obtaining initial role permission requirements and initial department permission requirements of the attribute information under the chapter unit from a permission requirement library; Determining whether the information sources of the initial role permission requirements and the initial department permission requirements are unique; In the case that the information sources of the initial role permission requirements and / or the initial department permission requirements are not unique, determining preset role permission requirements and preset department permission requirements as the role permission requirement and the department permission requirement of the chapter unit, respectively; In the case that the information sources of the initial role permission requirements and the initial department permission requirements are unique, determining the initial role permission requirements and the initial department permission requirements as the role permission requirement and the department permission requirement of the chapter unit, respectively.

6. The method of claim 1, wherein, In the case that the M verification results all represent that the initial permission requirements match the user information, the method further comprises: Determining an update time at which the permission index table performs an update operation, and calculating a time difference between the update time and a target time, wherein the target time is a time at which the query request is received; In the case that the time difference is less than a time difference threshold, performing the step of inputting the query request into the preset large language model; In the case that the time difference is greater than or equal to the time difference threshold, obtaining target permission requirements of each target chapter unit at the target time, obtaining M target permission requirements; Using the M target permission requirements to verify the user information, obtaining M target verification results, and in the case that the M target verification results all represent that the target permission requirements match the user information, performing the step of inputting the query request into the preset large language model; In the case that any target verification result represents that the target permission requirements do not match the user information, determining that the query request is abnormal.

7. The method of claim 1, wherein, After obtaining the query result, the method further comprises: Determining whether there is sensitive information in the query result according to a preset sensitive word set; In the case that there is the sensitive information in the query result, determining whether the sensitive information matches the user information; In the case that the sensitive information matches the user information, feeding back the query result to the user terminal; In the case that the sensitive information does not match the user information, deleting the sensitive information, obtaining an updated query result, and feeding back the updated query result to the user terminal; In the case that there is no sensitive information in the query result, feeding back the query result to the user terminal.

8. An information inquiry apparatus characterized by comprising: Comprises: A receiving module is configured to receive a query request sent by a target user through a user terminal, and identify M target chapter units required for processing the query request, wherein M is a positive integer; The first obtaining module is configured to obtain M initial permission requirements for accessing the M target chapter units from the permission index table, and obtain user information of the target user, verify the user information by using the M initial permission requirements, and obtain M verification results. The query module is configured to input the query request into a preset large language model to obtain a query result and feed back the query result to the user terminal in a case where the M verification results all represent that the user information meets the initial permission requirements, wherein the preset large language model processes the query request by calling the M target chapter units to obtain the query result.

9. A computer program product comprising computer instructions, characterized in that, The computer instructions, when executed by the processor, implement the steps of the information query method in any one of claims 1 to 7.

10. An electronic device, comprising: The computer instructions, when executed by the processor, implement the steps of the information query method in any one of claims 1 to 7. The computer instructions, when executed by the processor, implement the steps of the information query method in any one of claims 1 to 7. The computer instructions, when executed by the processor, implement the steps of the information query method in any one of claims 1 to 7.

Images