Information query method and device, equipment and medium
By retrieving information from the knowledge base and generating reply information using preset models, the problem of low query efficiency and poor accuracy in the existing information acquisition methods is solved, and more efficient and accurate information query results are achieved.
Patent Information
- Application Number
- CN202411877125.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-18
- Publication Date
- 2025-03-28
AI Technical Summary
The existing information acquisition methods have problems such as low query efficiency, poor accuracy, and incomplete results, which are difficult to effectively improve the efficiency of information query and the accuracy and comprehensiveness of results.
After obtaining the query request, the relevant information is retrieved from the knowledge base, and the query request and the retrieved information are input into the preset model to generate reply information, and finally output reply information. This method includes steps such as information classification retrieval, matching degree filtering, reply information evaluation and optimization model training.
It improves the efficiency of information query, enhances the accuracy and comprehensiveness of query results, and continuously improves the user experience through optimized model training.
Smart Images
Figure CN119719304A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of information query technology, and in particular to an information query method, device, equipment and medium. Background Art
[0002] In the information age, it is very important to master information in certain specific aspects (such as economy, law, regulations, education, science and technology, etc.) for work and life. The current ways to obtain relevant information mainly include manual consultation and query from the content published on relevant platforms. However, the current information acquisition methods have problems such as low query efficiency, poor accuracy, and incomplete results. Therefore, how to improve the query efficiency of information and the accuracy and comprehensiveness of query results is a technical problem that needs to be solved. Summary of the invention
[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an information query method, device, equipment and medium.
[0004] In a first aspect, an embodiment of the present disclosure provides an information query method, the method comprising:
[0005] Get the query request;
[0006] Based on the query request, retrieve information related to the request content of the query request from a knowledge base;
[0007] Inputting the query request and the information into a preset model, and generating reply information of the query request based on the preset model;
[0008] The reply information is output.
[0009] In some implementations, retrieving information related to the request content of the query request from a knowledge base based on the query request includes:
[0010] Based on the information classification corresponding to the request content, information related to the request content is retrieved from the information classification.
[0011] In some implementations, after retrieving information related to the request content from the information classification based on the information classification corresponding to the request content, the method further includes:
[0012] Inputting the information and the query request into a preset matching model, and determining the matching degree between the information and the request content based on the matching model;
[0013] The information whose matching degree is lower than a first preset threshold is filtered out from the information.
[0014] In some implementations, after inputting the query request and the information into a preset model and generating the reply information of the query request based on the preset model, the method further includes:
[0015] Inputting the reply information into a preset evaluation model, and evaluating the accuracy and / or completeness of the reply information based on the evaluation model;
[0016] In response to the accuracy and / or completeness being greater than or equal to a second preset threshold, performing the operation of outputting the reply information;
[0017] In response to the accuracy and / or the completeness being lower than a second preset threshold, the reply information is regenerated based on the preset model.
[0018] In some embodiments, the method provided in the first aspect may further include:
[0019] receiving user feedback on the reply information;
[0020] The preset model is optimized and trained based on the feedback to obtain an optimized preset model.
[0021] In some embodiments, the method provided in the first aspect may further include:
[0022] obtaining updated information of information contained in the knowledge base;
[0023] Based on the update information, the information contained in the knowledge base is updated.
[0024] In a second aspect, an embodiment of the present disclosure provides an information query device, including:
[0025] A first acquisition module, used to acquire a query request;
[0026] A retrieval module, configured to retrieve information related to the query content of the query request from a knowledge base based on the query request;
[0027] A reply generation module, used for inputting the query request and the information into a preset model, and generating reply information of the query request based on the preset model;
[0028] An output module is used to output the reply information.
[0029] In some embodiments, the retrieval module is used to:
[0030] Based on the information classification corresponding to the request content, information related to the request content is retrieved from the information classification.
[0031] In some implementations, the information query device may further include:
[0032] a matching module, configured to input the information and the query request into a preset matching model, and determine a matching degree between the information and the request content based on the matching model; and
[0033] The information whose matching degree is lower than a first preset threshold is filtered out from the information.
[0034] In some implementations, the information query device may further include:
[0035] An evaluation module, used to: input the response information into a preset evaluation model, and evaluate the accuracy and / or completeness of the response information based on the evaluation model;
[0036] The output module is configured to execute the operation of outputting the reply information in response to the accuracy and / or completeness being greater than or equal to a second preset threshold;
[0037] The reply generation module is configured to regenerate reply information based on the preset model in response to the accuracy and / or the completeness being lower than a second preset threshold.
[0038] In some implementations, the information query device may further include:
[0039] A receiving module, used for receiving user feedback on the reply information;
[0040] The optimization training module is used to optimize the preset model based on the feedback to obtain an optimized preset model.
[0041] In some implementations, the information query device may further include:
[0042] A first acquisition module, used to acquire update information of the information contained in the knowledge base;
[0043] An updating module is used to update the information contained in the knowledge base based on the update information.
[0044] In a third aspect, an embodiment of the present disclosure provides a computer device, including:
[0045] Memory;
[0046] Processor; and
[0047] Computer programs;
[0048] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in the first aspect.
[0049] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method described in the first aspect.
[0050] The information query method, apparatus, device and medium provided by the embodiments of the present disclosure can improve the efficiency of information query and the accuracy and comprehensiveness of query results by, after obtaining a query request, retrieving information related to the request content of the query request from a knowledge base based on the query request, inputting the query request and the retrieved information into a preset model, generating reply information of the query request through the preset model, and outputting the reply information. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0053] Figure 1 is a flow chart of an information query method provided by an embodiment of the present disclosure;
[0054] Figure 2 is a flow chart of a method for evaluating reply information provided by an embodiment of the present disclosure;
[0055] Figure 3 is a structural diagram of an information query system provided by an embodiment of the present disclosure;
[0056] Figure 4 is a structural diagram of an information query device provided by an embodiment of the present disclosure;
[0057] Figure 5 A schematic diagram of the structure of a computer device embodiment provided in the present disclosure. DETAILED DESCRIPTION
[0058] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0060] Figure 1 is a flowchart of an information query method provided by an embodiment of the present disclosure, which can be executed by a computer device or an information query system. The computer device or information query system can be understood as any device or system with information receiving and sending, information query, and information processing capabilities. Figure 1 As shown, in some implementations, the information query method provided by the embodiment of the present disclosure may include steps 101 to 104.
[0061] Step 101: Get a query request.
[0062] The query information referred to in the embodiments of the present disclosure may exemplarily include one or more query statements or one or more query keywords, wherein the query statement may be, for example, a question about certain content (e.g., law, regulations, economy, finance, technology, education, etc.) or a description of a query demand (e.g., query conditions, but not limited to query conditions).
[0063] In some embodiments, one or more query statements or one or more query keywords input by the user may be collected by a preset audio collection device, and the query statements or query keywords input by the user voice may be converted into corresponding text by a preset voice conversion device. Alternatively, in other embodiments, the query statements or query keywords input in text form may be obtained from a preset human-computer interaction interface.
[0064] It should be noted that the above-mentioned query request acquisition method is only an example description, and is not the only limitation of the embodiment of the present disclosure. In fact, in other embodiments, the query request acquisition method can be set as needed, without being limited to one or several specific acquisition methods.
[0065] Step 102: Based on the query request, information related to the request content of the query request is retrieved from the knowledge base.
[0066] Among them, the knowledge base referred to in the embodiments of the present disclosure may include knowledge and / or cases in one or more fields (such as economy, law, technology, education, policies and regulations, etc., but not limited to the fields listed here).
[0067] The request content of the query request can be understood as the query statement or query keyword contained in the query request.
[0068] The information related to the request content of the query request may include knowledge and / or cases retrieved based on the query statement or query keywords. For example, when the user inputs a question about certain regulations, the information related to the request content of the query request may be knowledge and / or cases related to the regulations retrieved based on the question. Of course, this is only an example, not a limitation.
[0069] In the embodiments of the present disclosure, there may be multiple methods for retrieving information related to the request content based on the query request. For example, in one embodiment, information related to the request content may be retrieved from the information classification according to the information classification corresponding to the request content. For example, when the user inputs a question about some legal issue, the content related to the question may be retrieved from the content corresponding to the legal classification (such as legal clauses, judicial interpretations, and cases). By querying information related to the request content from the corresponding information classification through the information classification corresponding to the request content, the efficiency of information can be improved.
[0070] It should be noted that the above retrieval method is only an example and not a sole limitation. In other implementations of the embodiments of the present disclosure, any retrieval engine and retrieval method provided by the relevant technology can be used to retrieve information.
[0071] For example, in some embodiments, after retrieving information related to the request content, a step of screening the information may also be included. For example, in one example, the retrieved information and the query request may be input into a preset matching model, and the preset matching model is used to determine the degree of match between the information and the request content of the query request, and the information with a matching degree lower than a first preset threshold is screened out. Among them, the preset matching model can be any type of model (such as a machine learning model, a neural network model, etc., but not limited to the models listed here). The matching model in the embodiment of the present disclosure is trained to determine the degree of match between the information and the request content. The model can be trained using the model training method provided by the relevant technology. The specific training method can be referred to the relevant technology, and the embodiment of the present disclosure will not be repeated.
[0072] Step 103: Input the query request and the retrieved information into a preset model, and generate reply information of the query request based on the preset model.
[0073] The preset model referred to in the embodiments of the present disclosure may be a model of any network structure, such as a large language model, but is not limited to a large language model. The model is trained to generate response information (e.g., answers and / or suggestions) based on query requests and retrieved information. For example, when a user inputs a question about a certain regulation, the response output by the preset model may be the specific content and / or application case of the regulation. The preset model referred to in the embodiments of the present disclosure may be trained using the training method provided by the relevant technology, and the training method is not limited in the embodiments of the present disclosure.
[0074] Step 104: Output reply information.
[0075] The reply information may be output in the form of voice or text, but is not limited to voice and text. For example, in other implementations, the reply information may be output in the form of graphics or a combination of voice and text.
[0076] The disclosed embodiment, after obtaining a query request, retrieves information related to the request content of the query request from a knowledge base based on the query request, inputs the query request and the retrieved information into a preset model, generates reply information of the query request through the preset model, and outputs the reply information, thereby improving the efficiency of information query and the accuracy and comprehensiveness of the query results.
[0077] For example, in some embodiments, after the reply information of the query request is output to the user, the user's feedback on the reply information can also be obtained through a preset human-computer interaction interface, and the feedback can be voice information or text information. Further, the user's feedback, the query request, and the information retrieved based on the query request can be input into a preset model, and the preset model is optimized and trained to obtain an optimized model. Among them, the specific method of optimizing the preset model based on the user's feedback can be referred to the relevant technology, which will not be repeated here.
[0078] Optimizing and training the model through user feedback can improve the accuracy of the model.
[0079] For example, in some implementations, for the information in the knowledge base referred to in the embodiments of the present disclosure, the embodiments of the present disclosure can also subscribe to update information of the information in the knowledge base from a preset database or platform. When update information of the information in the knowledge base is obtained, the information in the knowledge base is updated according to the update information to ensure the accuracy and real-time nature of the knowledge in the knowledge base.
[0080] For example, Figure 2 FIG. 1 is a flow chart of a method for evaluating a reply message provided by an embodiment of the present disclosure. Figure 2As shown, in some implementations, the method for evaluating reply information may include steps 201 to 203.
[0081] Step 201: input the reply information into a preset evaluation model, and evaluate the accuracy and / or completeness of the reply information based on the evaluation model.
[0082] The evaluation model of the embodiment of the present disclosure inputs the reply information of the query request, and outputs the evaluation result of the accuracy and / or completeness of the reply information. The evaluation result may include the evaluation score of the accuracy and / or completeness, as well as the content with low accuracy and / or missing content in the reply information.
[0083] In the embodiment of the present disclosure, the evaluation model can be a model of any network structure, such as a machine learning model, a neural network model, etc. The evaluation model in the embodiment of the present disclosure can be trained using a model training method of the prior art, and the training process is not limited in the embodiment of the present disclosure.
[0084] Step 202: In response to the accuracy and / or completeness being greater than or equal to a second preset threshold, an operation of outputting reply information is executed.
[0085] Step 203: In response to the accuracy and / or completeness being lower than a second preset threshold, regenerate the reply information based on the preset model.
[0086] In one implementation, information related to the request content may be retrieved based on the query request and the query request and the retrieved information may be input into a preset model, and response information to the query request may be retrieved through the preset model.
[0087] In another embodiment, the evaluation result of the evaluation model, the query request and the retrieved information may be re-input into the preset model, and the response information of the query request may be obtained again through the preset model.
[0088] The embodiments of the present disclosure evaluate the accuracy and / or completeness of the reply information, output the reply information when the accuracy and / or completeness is greater than or equal to a second preset threshold, and regenerate the reply information when the accuracy and / or completeness is lower than the second preset threshold, thereby ensuring the accuracy and / or completeness of the reply information and improving the user experience.
[0089] Figure 3 Schematic diagram of the structure of an information query system provided by an embodiment of the present disclosure. Figure 3 As shown, in some implementations, the information query system provided by the embodiments of the present disclosure may exemplarily include: a user interface 31, a human-computer interaction module 32, a large model generation module 33, a knowledge base 34, a retrieval module 35 and an evaluation and feedback module 36.
[0090] The user interface 31 provides a human-computer interaction interface, which may include a text input area, through which a user may input a query request. Alternatively, the human-computer interaction interface may also include a voice collection button, through which a user may operate (such as click, long press, etc.) the voice collection button to output a query request in voice form.
[0091] In some implementations, the user interface 31 may further include guidance information for guiding the user to input a query request according to a preset rule.
[0092] The human-computer interaction module 32 is used to obtain a query request from the user interface 31, and input the query request into the retrieval module 35. The retrieval module 35 is used to retrieve information related to the request content from the knowledge base 34 according to the query request, and send the retrieved information and the query request to the human-computer interaction module 32. The retrieved information and the query request are input into the large model generation module 33 through the human-computer interaction module 32, and the reply information of the query request is generated through the preset model pre-trained in the large model generation module 33. The accuracy and / or completeness of the reply information are evaluated through the evaluation and feedback module 36. If the accuracy and / or completeness is greater than or equal to the second preset threshold, the reply message is output through the user interface 31. If the accuracy and / or completeness of the reply information is lower than the second preset threshold, the reply information is regenerated through the preset model in the large model generation module 33, and when the accuracy and / or completeness of the regenerated reply information is greater than or equal to the second preset threshold, the reply information is output through the user interface 31. If the accuracy and / or completeness of the regenerated reply information is lower than the second preset threshold, an error message may be output through the user interface 31, or the reply information may be regenerated again through the preset model until the accuracy and / or completeness of the regenerated reply information is greater than or equal to the second preset threshold.
[0093] For example, in some embodiments, the user can also input feedback on the reply information through the user interface 31, such as "The answer is quite detailed, but can you provide some specific operation steps?" The evaluation and feedback module 36 obtains the user's feedback from the user interface 31, and sends the feedback result to the large model generation module 33, so that the large model generation module 33 optimizes and trains the preset model based on the user's feedback, thereby ensuring the accuracy of the preset model.
[0094] It should be noted that Figure 3 The execution mode and beneficial effects of the system shown are similar to those described above. Figure 1 or Figure 2 The embodiments are similar and will not be described again here.
[0095] Figure 4Schematic diagram of the structure of an information query device provided by an embodiment of the present disclosure. Figure 4 As shown, in some implementations, the information query device 40 provided by the embodiment of the present disclosure includes:
[0096] A first acquisition module 41, used to acquire a query request;
[0097] A retrieval module 42, configured to retrieve information related to the query content of the query request from a knowledge base based on the query request;
[0098] A reply generation module 43, used for inputting the query request and the information into a preset model, and generating reply information of the query request based on the preset model;
[0099] The output module 44 is used to output the reply information.
[0100] In some implementations, the retrieval module 42 is used to:
[0101] Based on the information classification corresponding to the request content, information related to the request content is retrieved from the information classification.
[0102] In some implementations, the information query device 40 may further include:
[0103] a matching module, configured to input the information and the query request into a preset matching model, and determine a matching degree between the information and the request content based on the matching model; and
[0104] The information whose matching degree is lower than a first preset threshold is filtered out from the information.
[0105] In some implementations, the information query device 40 may further include:
[0106] An evaluation module, used to: input the response information into a preset evaluation model, and evaluate the accuracy and / or completeness of the response information based on the evaluation model;
[0107] The output module is configured to execute the operation of outputting the reply information in response to the accuracy and / or completeness being greater than or equal to a second preset threshold;
[0108] The reply generation module is configured to regenerate reply information based on the preset model in response to the accuracy and / or the completeness being lower than a second preset threshold.
[0109] In some implementations, the information query device 40 may further include:
[0110] A receiving module, used for receiving user feedback on the reply information;
[0111] The optimization training module is used to optimize the preset model based on the feedback to obtain an optimized preset model.
[0112] In some implementations, the information query device 40 may further include:
[0113] A first acquisition module, used to acquire update information of the information contained in the knowledge base;
[0114] An updating module is used to update the information contained in the knowledge base based on the update information.
[0115] The device provided in the embodiments of the present disclosure can execute the method of any of the above method embodiments, and its execution method and beneficial effects are similar, which will not be repeated here.
[0116] Figure 5 The schematic diagram of the structure of the computer device embodiment provided by the present disclosure embodiment. Figure 5 As shown, the computer device includes a memory 121 and a processor 122 .
[0117] The memory 121 is used to store programs. In addition to the above programs, the memory 121 can also be configured to store various other data to support operations on the computer device. Examples of these data include instructions, pictures, videos, etc. for any application or method operating on the computer device.
[0118] The memory 121 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0119] The processor 122 is coupled to the memory 121 and executes the program stored in the memory 121 to:
[0120] Get the query request;
[0121] Based on the query request, retrieve information related to the request content of the query request from a knowledge base;
[0122] Inputting the query request and the information into a preset model, and generating reply information of the query request based on the preset model;
[0123] The reply information is output.
[0124] In some implementations, retrieving information related to the request content of the query request from a knowledge base based on the query request includes:
[0125] Based on the information classification corresponding to the request content, information related to the request content is retrieved from the information classification.
[0126] In some implementations, after retrieving information related to the request content from the information classification based on the information classification corresponding to the request content, the method further includes:
[0127] Inputting the information and the query request into a preset matching model, and determining the matching degree between the information and the request content based on the matching model;
[0128] The information whose matching degree is lower than a first preset threshold is filtered out from the information.
[0129] In some implementations, after inputting the query request and the information into a preset model and generating the reply information of the query request based on the preset model, the method further includes:
[0130] Inputting the reply information into a preset evaluation model, and evaluating the accuracy and / or completeness of the reply information based on the evaluation model;
[0131] In response to the accuracy and / or completeness being greater than or equal to a second preset threshold, performing the operation of outputting the reply information;
[0132] In response to the accuracy and / or the completeness being lower than a second preset threshold, the reply information is regenerated based on the preset model.
[0133] In some embodiments, the method provided in the first aspect may further include:
[0134] receiving user feedback on the reply information;
[0135] The preset model is optimized and trained based on the feedback to obtain an optimized preset model.
[0136] In some embodiments, the method provided in the first aspect may further include:
[0137] obtaining updated information of information contained in the knowledge base;
[0138] Based on the update information, the information contained in the knowledge base is updated.
[0139] Further, such as Figure 5As shown, the computer device may also include: a communication component 123, a power component 124, an audio component 125, a display 126 and other components. Figure 5 Only some components are shown schematically, which does not mean that the computer equipment only includes Figure 5 Components shown.
[0140] The communication component 123 is configured to facilitate wired or wireless communication between the computer device and other devices. The computer device can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 123 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 123 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
[0141] The power supply component 124 provides power to various components of the computer device. The power supply component 124 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the computer device.
[0142] The audio component 125 is configured to output and / or input audio signals. For example, the audio component 125 includes a microphone (MIC), and when the computer device is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 121 or sent via the communication component 123. In some embodiments, the audio component 125 also includes a speaker for outputting audio signals.
[0143] The display 126 includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.
[0144] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the method described in any of the above method embodiments.
[0145] The exemplary embodiments of the present disclosure further provide a computer program product, comprising a computer program, wherein when the computer program is executed by a processor of a computer, it is used to enable the computer to execute to implement the method described in any of the above method embodiments.
[0146] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0147] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An information query method, characterized in that: The method comprises: Get the query request; Based on the query request, retrieve information related to the request content of the query request from a knowledge base; Inputting the query request and the information into a preset model, and generating reply information of the query request based on the preset model; The reply information is output.
2. The method according to claim 1, characterized in that The retrieving information related to the request content of the query request from a knowledge base based on the query request includes: Based on the information classification corresponding to the request content, information related to the request content is retrieved from the information classification.
3. The method according to claim 2, characterized in that After retrieving information related to the request content from the information classification based on the information classification corresponding to the request content, the method further includes: Inputting the information and the query request into a preset matching model, and determining the matching degree between the information and the request content based on the matching model; The information whose matching degree is lower than a first preset threshold is filtered out from the information.
4. The method according to claim 1, characterized in that After inputting the query request and the information into a preset model and generating reply information of the query request based on the preset model, the method further includes: Inputting the reply information into a preset evaluation model, and evaluating the accuracy and / or completeness of the reply information based on the evaluation model; In response to the accuracy and / or completeness being greater than or equal to a second preset threshold, performing the operation of outputting the reply information; In response to the accuracy and / or the completeness being lower than a second preset threshold, the reply information is regenerated based on the preset model.
5. The method according to claim 1, characterized in that The method further comprises: receiving user feedback on the reply information; The preset model is optimized and trained based on the feedback to obtain an optimized preset model.
6. The method according to claim 1, characterized in that The method further comprises: obtaining updated information of information contained in the knowledge base; Based on the update information, the information contained in the knowledge base is updated.
7. An information query device, characterized in that: include: A first acquisition module, used to acquire a query request; A retrieval module, configured to retrieve information related to the query content of the query request from a knowledge base based on the query request; A reply generation module, used for inputting the query request and the information into a preset model, and generating reply information of the query request based on the preset model; An output module is used to output the reply information.
8. The device according to claim 7, characterized in that The retrieval module is used to: Based on the information classification corresponding to the request content, information related to the request content is retrieved from the information classification.
9. A computer device, wherein: include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 6.
10. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.