Data query method, data interaction method and electronic equipment

Abstract

The invention provides a data query method, a data interaction method and electronic equipment, and relates to the field of artificial intelligence technology and intelligent customer service. The method comprises the following steps: under the condition that an initial query request is received, rewriting the initial query request based on historical query data to obtain a first query request, and performing data query based on the first query request to obtain a first query result; rewriting the first query request based on the first query result and the historical query data to obtain a second query request, and performing data query based on the second query request to obtain a second query result; obtaining a target query result based on the first query result and the second query result; wherein the historical query data is used for representing data which is generated when data query is carried out in a historical time period and has an association relationship with the initial query request. According to the method and the device, the technical problem that a query result obtained through data query does not accord with a query demand of a user in related technologies is solved.

Description

Technical Field

[0001] This application relates to artificial intelligence technology and intelligent customer service, specifically to a data query method, a data interaction method, and an electronic device. Background Technology

[0002] Currently, when querying data based on user input, query systems typically filter and retrieve content from the database based on literal keywords or simple semantic matching. While this method can quickly return a large number of initial results directly related to the keywords, it often struggles to adapt to complex query contexts and fails to accurately identify the user's query needs, resulting in query results that may not match the user's actual query requirements.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a data query method, a data interaction method, and an electronic device to at least solve the technical problem in related technologies where the query results obtained through data query do not match the user's query needs.

[0005] According to one aspect of the embodiments of this application, a data query method is provided, comprising: upon receiving an initial query request, rewriting the initial query request based on historical query data to obtain a first query request, and performing a data query based on the first query request to obtain a first query result; rewriting the first query request based on the first query result and historical query data to obtain a second query request, and performing a data query based on the second query request to obtain a second query result; and obtaining a target query result based on the first query result and the second query result; wherein, the historical query data is used to characterize data generated during data queries within a historical time period that is associated with the initial query request.

[0006] According to another aspect of the embodiments of this application, a data interaction method is also provided, comprising: upon receiving query information, generating an initial query request based on the query information; rewriting the initial query request based on the initial query request and historical interaction information to obtain a first query request, and performing a data query based on the first query request to obtain a first query result; rewriting the first query request based on the first query result and historical interaction information to obtain a second query request, and performing a data query based on the second query request to obtain a second query result; and generating response information based on the first query result, the second query result, and historical interaction information; wherein, the historical interaction information includes: historical query information and historical response information generated during data interaction within a historical time period.

[0007] According to another aspect of the embodiments of this application, a data query method is also provided, comprising: displaying an initial query request on the operation interface when an input instruction acting on the operation interface is detected; and displaying a target query result on the operation interface when a processing instruction acting on the operation interface is detected, wherein the target query result is constructed from a first query result and a second query result, the second query result is obtained by performing a data query on a second query request, the second query request is obtained by rewriting the first query request using the first query result and historical query data, the first query result is used to characterize the data obtained by performing a data query based on the first query request, the historical query data is used to characterize the data generated during a data query within a historical time period that is related to the initial query request, and the first query request is obtained by rewriting the initial query request using the historical query data.

[0008] According to another aspect of the embodiments of this application, a data query apparatus is also provided, comprising: a first rewriting module, configured to, upon receiving an initial query request, rewrite the initial query request based on historical query data to obtain a first query request, and perform a data query based on the first query request to obtain a first query result; a second rewriting module, configured to, based on the first query result and historical query data, rewrite the first query request to obtain a second query request, and perform a data query based on the second query request to obtain a second query result; and a data query module, configured to, based on the first query result and the second query result, obtain a target query result; wherein, historical query data is used to characterize data generated during data queries within a historical time period that is associated with the initial query request.

[0009] According to another aspect of the embodiments of this application, a data interaction device is also provided, comprising: a request generation module, configured to generate an initial query request based on the query information received; a third rewriting module, configured to rewrite the initial query request based on the initial query request and historical interaction information to obtain a first query request, and perform a data query based on the first query request to obtain a first query result; a fourth rewriting module, configured to rewrite the first query request based on the first query result and historical interaction information to obtain a second query request, and perform a data query based on the second query request to obtain a second query result; and an information generation module, configured to generate response information based on the first query result, the second query result, and historical interaction information; wherein the historical interaction information includes: historical query information and historical response information generated during data interaction within a historical time period.

[0010] According to another aspect of the embodiments of this application, a data query device is also provided, comprising: a first display module, configured to display an initial query request on the operation interface when an input instruction acting on the operation interface is detected; and a second display module, configured to display a target query result on the operation interface when a processing instruction acting on the operation interface is detected, wherein the target query result is constructed from a first query result and a second query result, the second query result is obtained by performing a data query on a second query request, the second query request is obtained by rewriting the first query request using the first query result and historical query data, the first query result is used to characterize the data obtained by performing a data query based on the first query request, the historical query data is used to characterize data generated during data queries within a historical time period that is related to the initial query request, and the first query request is obtained by rewriting the initial query request using the historical query data.

[0011] According to another aspect of the embodiments of this application, a computing device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0012] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory storing an executable program; and a processor connected to the memory via a bus for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0013] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0014] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0015] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the methods in various embodiments of this application.

[0016] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0017] In this embodiment, upon receiving an initial query request, the system rewrites the initial query request based on historical query data to obtain a first query request, and performs a data query based on the first query request to obtain a first query result. Then, based on the first query result and historical query data, the system rewrites the first query request to obtain a second query request, and performs a data query based on the second query request to obtain a second query result. Finally, based on the first and second query results, the system obtains the target query result. By rewriting the initial query request using historical query data and then further rewriting the first query request based on the first query result corresponding to the rewritten first query request and combining it with historical query data, the rewritten second query request can fully meet the user's query needs. This improves the matching degree between the target query result constructed using the first and second query results and the user's query needs, thereby solving the technical problem in related technologies where the query results obtained through data query do not match the user's query needs.

[0018] The above general description and the following detailed description are for illustrative and explanatory purposes only and do not constitute a limitation thereof. Attached Figure Description

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

[0020] Figure 1 This is a flowchart illustrating a data query method according to an embodiment of this application;

[0021] Figure 2 This is a flowchart illustrating a data query method according to an embodiment of this application;

[0022] Figure 3 This is a flowchart illustrating a data interaction method according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram illustrating a data interaction process according to an embodiment of this application;

[0024] Figure 5 This is a flowchart illustrating another data query method according to an embodiment of this application;

[0025] Figure 6 This is a structural block diagram of a data query device according to an embodiment of this application;

[0026] Figure 7 This is a structural block diagram of a data interaction device according to an embodiment of this application;

[0027] Figure 8 This is a structural block diagram of a data query device according to an embodiment of this application;

[0028] Figure 9 This is a structural block diagram of a computing device according to an embodiment of this application;

[0029] Figure 10 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0030] 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 embodiments described below are only some, not all, of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative effort should fall within the scope of protection of the present application.

[0031] The terms "first," "second," etc., used 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 other orders. Wherein, "other orders" refers to orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such as a process, method, system, product, or apparatus that comprises a series of steps or units, not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed, or inherent to such processes, methods, products, or apparatus.

[0032] The 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, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0033] The technical solution provided in this application is mainly implemented using a deep learning model. Deep learning models can be widely applied in fields such as Natural Language Processing (NLP), computer vision, and speech processing. Specifically, they can be applied to computer vision tasks such as Visual Question Answering (VQA), Image Captioning (IC), and image generation, as well as to natural language processing tasks such as text-based sentiment classification, text summarization, and machine translation. Therefore, the main application scenarios of this application include, but are not limited to, digital assistants, intelligent robots, search, online education, office software, e-commerce, and intelligent design. In this application's embodiments, data processing using a data query model in a data query scenario is used as an example for explanation and illustration.

[0034] According to an embodiment of this application, a data query method is provided. 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 performed in a different order than that shown here.

[0035] The technical solutions provided in this application can employ deep learning models with relatively large parameter scales, such as large models containing billions or even more model parameters. Here, "large model" is just one example; this application does not limit the number of model parameters supported by the deep learning model used, aiming to meet actual needs. The deep learning models involved in this application can be artificial intelligence-based language models (LM) or multimodal models (MM).

[0036] Considering the limited computing resources of mobile terminals, the methods described above in this application embodiment can be applied to, for example... Figure 1 The application scenarios shown. Figure 1 This is a flowchart illustrating a data query method according to an embodiment of this application. Figure 1 In the application scenario shown, the deep learning model is deployed on server 10. Server 10 can connect to one or more client devices 20 via a local area network (LAN), wide area network (WAN), internet connection, or other types of data network. Client devices 20 may include, but are not limited to, smartphones, tablets, laptops, PDAs, personal computers, smart home devices, and in-vehicle devices. Client devices 20 can interact with users through a graphical user interface to invoke the deep learning model, thereby implementing the method provided in this embodiment.

[0037] In this embodiment, the system consisting of a client device and a server can perform the following steps: the client device executes an initial query request; and outputs the target query result. The server rewrites the initial query request based on historical query data to obtain a first query request, and performs a data query based on the first query request to obtain a first query result; it rewrites the first query request based on the first query result and historical query data to obtain a second query request, and performs a data query based on the second query request to obtain a second query result; and based on the first query result and the second query result, it obtains the target query result.

[0038] With the rapid development of high-performance computing units, the methods provided in this application embodiment can also be applied to model-in-the-loop machines in other application scenarios. In one optional embodiment, the model-in-the-loop machine has multiple built-in models. Users can select a model to adjust as needed to obtain their own model. The high-performance computing unit built into the model-in-the-loop machine can then directly call the adjusted model to execute the methods provided in this application embodiment. In another optional embodiment, the deep learning model-in-the-loop machine has a pre-trained model built-in. The high-performance computing unit built into the model-in-the-loop machine can then directly call this model to execute the methods provided in this application embodiment.

[0039] Furthermore, when users need to train their own models, they can upload their own datasets via the client. This dataset is sent from the client to the server. The server can then use this dataset to fine-tune the pre-trained model, resulting in the user's customized model, which can then be deployed to the production environment. To facilitate user adjustments, the server provides complete adjustment tools, development frameworks, and processes, supporting various adjustment strategies. This allows the adjusted model to better adapt to different application domains and achieve a high degree of customization.

[0040] Under the aforementioned operating environment, this application provides the following: Figure 2 The data query method shown. Figure 2 This is a flowchart illustrating a data query method according to an embodiment of this application. For example... Figure 2 As shown, the method may include the following steps:

[0041] Step S202: Upon receiving the initial query request, the initial query request is rewritten based on historical query data to obtain the first query request, and data is queried based on the first query request to obtain the first query result.

[0042] Historical query data is used to represent data generated during data queries within a historical time period that is related to the initial query request.

[0043] The initial query request mentioned above can refer to the instruction generated by the query system based on the content entered by the user on the operation interface, used to perform data queries. The aforementioned correlation can refer to the relevance of historical query data and the initial query request in terms of topic, or the continuity in the problem-solving path.

[0044] In one optional solution of this embodiment, considering that during the data query process, the content entered by the user on the operation interface may not intuitively and clearly reflect their true intentions, i.e., their query needs for different data, the initial query request generated by the query system based on the user's input may have a deviation in understanding or capturing the user's needs. This leads to the query system obtaining results that do not match the user's true intentions. For example, assuming the user's true intention is to obtain tutorials on advanced photo editing techniques, the content entered by the user on the operation interface might be "how to edit photos." While this statement summarizes the basic intent of the query, it fails to fully express the user's specific needs for advanced techniques and tutorial formats. The corresponding data query instruction generated by the query system based on the user's input might then become a search for only basic photo editing guides. The results obtained from this data query instruction might be basic introductions to photo editing software and explanations of common editing functions, which do not match the advanced technique tutorials the user expects, thus affecting the user's problem-solving efficiency and satisfaction.

[0045] Therefore, upon receiving an initial query request, the query system can rewrite the initial query request to obtain a first query request, thereby improving the matching degree between the first query request and the user's true thoughts, and thus improving the accuracy of the query results and user satisfaction.

[0046] Furthermore, considering that when users find that the results obtained by the query system based on their input do not match their true thoughts, they will usually adjust their input to better express their true ideas, thereby improving the query system's ability to understand the user's true thoughts. Moreover, given that the content continuously entered by users in a short period of time usually revolves around the same topic, which is often related to the user's true thoughts, the query data generated in this process is also usually related to the user's true thoughts.

[0047] Therefore, to improve the accuracy of rewriting the initial query request and ensure a good match between the rewritten first query request and the user's true intentions, the query system can first obtain data generated during historical data queries that are related to the initial query request—the aforementioned historical query data. The query system can then rewrite the initial query request based on this historical query data to obtain the aforementioned first query request, thereby improving the relevance of the query results and user satisfaction.

[0048] Correspondingly, after receiving the first query request, the query system can use the first query request to perform data query and obtain the first query result mentioned above, thereby improving the accuracy and efficiency of data query and better meeting the user's query needs.

[0049] In one optional embodiment, in order to improve the accuracy of rewriting the initial query request, some acquisition conditions can be set for the above-mentioned historical query data, which may include, but are not limited to: setting a time window, a topic relevance threshold, and user behavior frequency.

[0050] Setting a time window means that the query system can select to analyze historical query data within a recent period, such as query records from the past hour, to ensure that the query system rewrites the initial query request based on the user's latest query behavior and interests, and avoids using outdated or irrelevant data.

[0051] The topic relevance threshold refers to the fact that the query system can use natural language processing to calculate the topic relevance between historical query times and the current initial query request. Only data with relevance exceeding the set threshold will be used in the rewriting process to prevent irrelevant historical data from interfering with the rewriting and to ensure the focus and accuracy of the rewriting request.

[0052] User behavior frequency refers to how often a query system analyzes a user's queries on a specific topic. Topics that users query repeatedly can be given higher weight to satisfy users' long-term interests.

[0053] Step S204: Based on the first query result and historical query data, the first query request is rewritten to obtain the second query request, and data is queried based on the second query request to obtain the second query result.

[0054] In one optional embodiment, considering that the first query result obtained from the data query based on the first query request, even if it deviates from the user's query needs, can still reflect the user's true thoughts from the perspective of user preferences and behavioral patterns. For example, if the user's initial query is "How to improve my Wi-Fi (Wireless Fidelity) signal strength?" and the first query result mainly focuses on suggestions for Wi-Fi hardware upgrades, but by analyzing the user's historical query data, it is found that the user also frequently queries content about network settings and software adjustments, then the first query result indirectly indicates that the user may have a need for a comprehensive Wi-Fi adjustment strategy, rather than just a hardware adjustment need.

[0055] Therefore, after obtaining the first query result using the first query request, the query system can further rewrite the first query request based on the first query result and in combination with historical query data to obtain the aforementioned second query request. This enhances the comprehensiveness and accuracy of the query process, thereby improving user satisfaction with the query results and the efficiency of the query system in data retrieval.

[0056] Correspondingly, after rewriting the first query request to obtain the second query request, the query system can perform data queries based on the second query request to obtain the second query results, so as to more comprehensively cover user needs and thus provide more accurate and satisfactory query results.

[0057] Step S206: Based on the first query result and the second query result, obtain the target query result.

[0058] In one optional solution of this embodiment, it is considered that both the first query result and the second query result can more or less meet the user's query needs. However, relying solely on the first query result or the second query result may not be sufficient to fully reflect the multifaceted and in-depth nature of the user's needs and provide complete and targeted response content.

[0059] Therefore, after obtaining the second query result by using the second query request to query data, the query system can further construct the above-mentioned target query result based on the first and second query results, thereby integrating all relevant knowledge, providing a comprehensive solution covering all user needs, and enhancing user satisfaction and query efficiency.

[0060] For example, when constructing a target query result using the first and second query results, the query system can employ knowledge fusion technology to integrate key information from the two query results, forming a unified knowledge framework to ensure the coherence and completeness of the solution. For instance, when a user asks how to improve their home Wi-Fi network speed, the first query result might focus on hardware upgrade suggestions, while the second query result might provide information on network security settings and software adjustments. Through knowledge fusion, the target query result can simultaneously include hardware, software, and security solutions, forming a comprehensive adjustment guide.

[0061] Alternatively, the query system can utilize deep learning models to analyze the historical context of the user's query and the relationship between the first and second query results, automatically filtering out the most relevant and valuable information to form the target query results. This approach can intelligently identify the user's query intent and automatically sort the information according to its importance, ensuring that the target query results are not only comprehensive in content but also clearly structured, easy for users to understand and operate, thereby more effectively meeting user needs and improving the query experience.

[0062] In this embodiment, upon receiving an initial query request, the system rewrites the initial query request based on historical query data to obtain a first query request, and performs a data query based on the first query request to obtain a first query result. Then, based on the first query result and historical query data, the system rewrites the first query request to obtain a second query request, and performs a data query based on the second query request to obtain a second query result. Finally, based on the first and second query results, the system obtains the target query result. By rewriting the initial query request using historical query data and then further rewriting the first query request based on the first query result corresponding to the rewritten first query request and combining it with historical query data, the rewritten second query request can fully meet the user's query needs. This improves the matching degree between the target query result constructed using the first and second query results and the user's query needs, thereby solving the technical problem in related technologies where the query results obtained through data query do not match the user's query needs.

[0063] In this embodiment of the application, the first query request is rewritten based on the first query result and historical query data to obtain the second query request, including: parsing the initial query request to obtain the initial query requirement corresponding to the initial query request, wherein the initial query requirement is used to characterize the execution purpose of the initial query request; adjusting the initial query requirement based on the first query result and historical query data to obtain the target query requirement; and rewriting the first query request based on the target query requirement to obtain the second query request.

[0064] In one optional embodiment, to accurately rewrite the first query request and more precisely capture the user's true thoughts, the query system can first parse the initial query request to obtain the initial cleansing requirements corresponding to it. This determines the meaning of the content currently entered by the user in the interface and thus the execution purpose of the initial query request. After obtaining the initial query requirements, the query system can further utilize the first query results and historical query data to adjust the initial query requirements to obtain the target query requirements. This allows for analysis and reasoning about the user's true thoughts, uncovering potential, unstated needs and information gaps. Finally, the query system can use the adjusted target query requirements to rewrite the first query request, resulting in the aforementioned second query request. This enhances the breadth and depth of knowledge retrieval, ensuring that the corresponding query results fully satisfy the user's query needs.

[0065] For example, if the initial query is: "How to make potted plants grow faster?", the query system can determine the initial query requirement by parsing it. This means the first query is about methods to accelerate plant growth. If the initial query result is the basic principles of plant care, and historical query data includes information such as "the impact of insufficient indoor lighting on plants" and "types of organic fertilizers," the query system can infer that the user may also be concerned about lighting conditions and fertilizer use. Based on this inference, the system can then adjust the parsed initial query requirement to obtain the user's target query requirement. This target query could be about what lighting conditions and fertilizer use can improve plant growth speed.

[0066] Based on this, the query system can adjust the first query request based on the inferred results, rewriting the first query request into a second query request, for example, rewriting it as "In an indoor environment, how can we promote plant growth by improving lighting conditions, fertilization, and daily care?" This allows the rewritten second query request to more comprehensively cover multiple aspects that the user may be concerned about, thereby ensuring that the query results can provide the user with a satisfactory answer.

[0067] In this embodiment of the application, the initial query requirement is adjusted based on the first query result and historical query data to obtain the target query requirement, including: determining the query topic corresponding to the first query request based on the first query result, wherein the query topic is used to characterize the query direction of the first query request; determining the behavior pattern corresponding to the first query request based on historical query data, wherein the behavior pattern is used to characterize the changing trend of data query behavior within a historical time period; and adjusting the initial query requirement based on the query topic and behavior pattern to obtain the target query requirement.

[0068] The aforementioned query topic can refer to the central topic or core content that users focus on when entering the content they want to query on the user interface. The aforementioned behavioral pattern can refer to the general behavioral patterns that users exhibit during the data query process, such as query frequency, preferences, and other patterns.

[0069] In one optional embodiment, to improve the accuracy of the adjusted target query requirements, the query system can first determine the query topic corresponding to the first query request based on the first query result, reflecting the query direction of the first query request. Simultaneously, the query system can analyze historical query data to determine the behavioral pattern corresponding to the first query request, i.e., to determine the changing trend of data query behavior within a historical time period. This allows the system to understand the user's potential needs through behavioral patterns, thereby comprehensively considering the explicit and implicit characteristics of the user's query behavior to more accurately predict the knowledge points the user may be interested in. For example, if a user queries "how to set up a home Wi-Fi network," and the query system finds that the user has previously inquired about router models and software versions, it can infer that the user may have questions about the hardware compatibility and software configuration of the Wi-Fi network.

[0070] Finally, after obtaining the corresponding query topics and behavioral patterns, the query system can adjust the initial query requirements based on the query topics and behavioral patterns to obtain the corresponding target query requirements, thereby improving the targeting of knowledge retrieval and ensuring that the query results can comprehensively cover the user's current and potential needs, providing more personalized and in-depth services.

[0071] In this embodiment of the application, rewriting the first query request based on the target query requirement to obtain the second query request includes: decomposing the first query request to obtain at least one keyword; expanding any one keyword based on the target query requirement to obtain a keyword set corresponding to the keyword; and updating the first query request based on the keyword set corresponding to at least one keyword to obtain the second query request.

[0072] In one optional embodiment, during the process of rewriting the first query request using the target query requirements, the query system can first decompose the first query request to obtain at least one keyword in the first query request that is related to the user's query requirements. Then, it can expand any keyword according to the target query requirements to obtain the keyword set corresponding to that keyword. Finally, it can update the first query request according to the keyword sets corresponding to different keywords to obtain the second query request. This allows the second query request to meet the user's true thoughts as much as possible and provide the user with more comprehensive knowledge services.

[0073] For example, suppose the first query request is "methods to improve home Wi-Fi network speed". The query system can first extract relevant keywords from the first query request, such as "Wi-Fi network", "speed" and "method". Then, guided by the target query requirements, it can expand the keywords by identifying information points that need to be supplemented, such as "hardware upgrade", "software adjustment" and "network settings", to obtain the corresponding keyword set. Finally, it can update the first query request using the keyword set corresponding to different keywords, thereby obtaining a more complete and accurate second query request.

[0074] In this embodiment of the application, data querying based on a second query request to obtain a second query result includes: obtaining the request execution process corresponding to the first query request and the request execution tool corresponding to the second query request; and executing the second query request using the request execution tool based on the request execution process to obtain the second query result.

[0075] In one optional embodiment, when performing a data query based on the second query request, in order to improve the efficiency and accuracy of the data query, the query system can first obtain the request execution flow corresponding to the first query request, and then execute the second query request according to the request execution flow, thereby achieving continuous follow-up on user needs, avoiding information loss or duplicate queries, and improving the relevance and usability of the query results.

[0076] However, considering the complexity and diversity of user query needs, simply executing the second query request according to the request execution process corresponding to the first query request may lead to one-sided and generalized query results due to a lack of in-depth understanding of domain expertise and sensitivity to users' personalized needs, failing to accurately capture and respond to users' true needs.

[0077] Therefore, during the execution of the second query request, additional request execution tools are introduced, such as knowledge graph query engines, semantic understanding modules, and professional database interfaces. Then, according to the request execution process, the corresponding request execution tools are used to execute the second query request and obtain the corresponding second query results. This ensures the depth and breadth of the query, meets the user's need for detailed information in a specific field, and provides a higher-value solution.

[0078] In this embodiment of the application, obtaining the request execution tool corresponding to the second query request includes: determining the tool usage conditions corresponding to the second query request based on historical query data; detecting the second query request to obtain the request type of the second query request; and selecting a request execution tool from the tool library based on the request type and the tool usage conditions.

[0079] In one optional embodiment, to determine the appropriate execution tool that matches the second query request and improve its efficiency and accuracy, the query system can first determine the tool usage conditions corresponding to the second query request based on historical query data, such as user preference history, domain specificity of the query, and real-time data requirements. Simultaneously, the query system can parse the second query request to obtain its request type, such as information query, guidance operation, or question answering. Finally, the query system can select a suitable execution tool from the tool library based on the request type and tool usage conditions, thereby ensuring that the second query request efficiently and accurately meets user needs and provides personalized query services.

[0080] In this embodiment of the application, obtaining the target query result based on the first query result and the second query result includes: evaluating any query data contained in the first query result based on the target query requirement corresponding to the second query request to obtain a data evaluation index, wherein the data evaluation index is used to characterize the degree of matching between the query data and the target query requirement; filtering the query data contained in the first query result based on the data evaluation index to obtain a third query result; and summarizing the third query result and the second query result to obtain the target query result.

[0081] In one optional embodiment, to ensure that the target query results displayed to the user fully meet the user's query needs, during the process of constructing the target query results using the first and second query results, the query system can first evaluate any query data included in the first query results according to the target query needs corresponding to the second query request, obtaining data evaluation indicators. These indicators are then used to determine the degree of matching between the query data and the target query needs. Correspondingly, if the degree of matching is high, it indicates that the query data is closely related and can directly or indirectly solve the user's problem or meet their information needs; conversely, if the degree of matching is low, it indicates that the query data may deviate from the user's core concerns and cannot effectively answer the user's questions or provide useful information.

[0082] Based on this, the query system can filter the query data contained in the first query result according to the evaluation indicators obtained from the assessment, thereby obtaining the third query result. This removes irrelevant or low-quality information and retains high-matching data that effectively meets the user's target query needs. Finally, the query system can summarize the third query result and the second query result to obtain the aforementioned target query result. This integrates information from different query levels to form a comprehensive, in-depth, and highly customized query result set, ensuring that users can fully understand the corresponding query data from multiple perspectives and depths.

[0083] For the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions. This is because, according to this application, certain steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0084] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms, or by hardware. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0085] According to an embodiment of this application, a data interaction method is also provided. Figure 3 This is a flowchart illustrating a data interaction method according to an embodiment of this application, such as... Figure 3 As shown, the method may include the following steps.

[0086] Step S302: Upon receiving the query information, generate an initial query request based on the query information.

[0087] Step S304: Based on the initial query request and historical interaction information, the initial query request is rewritten to obtain the first query request, and data is queried based on the first query request to obtain the first query result.

[0088] Step S306: Based on the first query result and historical interaction information, the first query request is rewritten to obtain the second query request, and data is queried based on the second query request to obtain the second query result.

[0089] Step S308: Generate response information based on the first query result, the second query result, and historical interaction information.

[0090] Historical interaction information includes: historical query information and historical reply information generated during data interaction within a historical time period.

[0091] In one optional embodiment, to accurately respond to user-input queries, the query system can generate an initial query request based on the user's input on the interface upon receiving the query. After generating the initial query request, the query system can rewrite the initial query request based on the initial query request and historical interaction information—that is, historical query and response information generated by data interactions within a historical time period—to obtain a first query request. Data is then queried based on the first query request to obtain a first query result. To further improve the match between the obtained query result and the user's actual thoughts, the query system can reuse the first query result to rewrite the first query request a second time based on historical interaction information, resulting in a second query request. Data is then queried based on the second query request to obtain a second query result. Finally, the query system can generate corresponding response information based on the first and second query results, combined with historical interaction information.

[0092] In this embodiment of the application, generating response information based on the first query result, the second query result, and historical interaction information includes: determining the content generation tool corresponding to the initial query request based on the first query result and historical interaction information; inputting the first query result, the second query result, and historical interaction information into the content generation tool; and using the content generation tool to fuse the first query result, the second query result, and historical interaction information to generate response information.

[0093] In one optional embodiment, considering the importance of users' query habits, preferences, and historical interaction information, when generating response information, the query system can first determine the content generation tool corresponding to the initial query request based on the first query result and historical interaction information, and then input the first query result, the second query result, and historical interaction information into the content generation tool. The content generation tool is then used to fuse the first query result, the second query result, and historical interaction information to generate response information.

[0094] For example, if historical interaction information shows that users prefer illustrated guides, the query system can select an image and text content generation tool with rich illustrations and detailed step-by-step instructions, input relevant information into the selected tool, and use the tool to integrate and process multiple types of information to generate a multi-layered and complete response to meet the user's multi-layered needs.

[0095] To facilitate understanding of the above data interaction process, Figure 4 This is a schematic diagram illustrating a data interaction process according to an embodiment of this application, such as... Figure 4 As shown, during the data interaction process, the query system can obtain an initial query request and historical query data. Then, using a pre-trained rewriting model, it performs a shallow rewriting of the initial query request using the historical query data to obtain the corresponding first query request. By executing the first query request, data is retrieved, and the corresponding query data is obtained. Simultaneously, knowledge retrieval and sorting are performed on the query data based on the first query request to construct the corresponding first query result. After obtaining the first query result, the query system can further refine the user's target query needs in the planning module using the first query result and historical query data to perform a deep rewriting of the first query request, obtaining the corresponding second query request. Then, the data query, knowledge retrieval, and sorting process is repeated based on the second query request to obtain the corresponding second query result. Finally, the query system can use a content generation tool to merge the first and second query results to generate the corresponding response information.

[0096] According to an embodiment of this application, another data query method is also provided. Figure 5 This is a flowchart illustrating another data query method according to an embodiment of this application, such as... Figure 5 As shown, the method may include the following steps:

[0097] Step S502: If an input command is detected on the operation interface, the initial query request is displayed on the operation interface.

[0098] Step S504: If a processing instruction is detected on the operation interface, the target query result is displayed on the operation interface.

[0099] The target query result is constructed from the first query result and the second query result. The second query result is obtained by querying data using the second query request. The second query request is obtained by rewriting the first query request using the first query result and historical query data. The first query result is used to represent the data obtained by querying data based on the first query request. The historical query data is used to represent the data generated during data queries in historical time periods that are related to the initial query request. The first query request is obtained by rewriting the initial query request using historical query data.

[0100] In one optional embodiment, upon detecting an input command applied to the user interface, the query system may first display an initial query request on the user interface. Upon detecting a processing command applied to the user interface, the query system may then display the target query results corresponding to the initial query request on the user interface for easy viewing.

[0101] In determining the target query result, the query system can first use historical query data—data generated during data queries within a historical time period that is related to the initial query request—to rewrite the initial query request, obtaining a first query request. This first query request is then used to perform a data query to obtain the corresponding first query result. Next, the query system can use the first query result and historical query data to rewrite the first query request, obtaining a second query request. This second query request is then used to perform a data query to obtain the corresponding second query result. Finally, by summarizing the first and second query requests, the target query request described above can be constructed.

[0102] According to an embodiment of this application, a data query apparatus for implementing the above-described data query method is also provided. Figure 6 This is a structural block diagram of a data query device according to an embodiment of this application, such as... Figure 6 As shown, the device includes: a first rewriting module 602, a second rewriting module 604, and a data query module 606.

[0103] The first rewriting module 602, upon receiving an initial query request, rewrites the initial query request based on historical query data to obtain a first query request, and performs a data query based on the first query request to obtain a first query result. The second rewriting module 604, based on the first query result and historical query data, rewrites the first query request to obtain a second query request, and performs a data query based on the second query request to obtain a second query result. The data query module 606, based on the first query result and the second query result, obtains a target query result. The historical query data represents data generated during data queries within a historical time period that is related to the initial query request.

[0104] The first rewriting module 602, the second rewriting module 604, and the data query module 606 described above correspond to steps S202 to S206 in the above embodiments. The three modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. The modules or units described above may be hardware or software components stored in memory and processed by one or more processors. The modules may also be part of a device and may run in the server 10 provided in the above embodiments.

[0105] In this embodiment of the application, the second rewriting module is further configured to: parse the initial query request to obtain the initial query requirement corresponding to the initial query request, wherein the initial query requirement is used to characterize the execution purpose of the initial query request; adjust the initial query requirement based on the first query result and historical query data to obtain the target query requirement; and rewrite the first query request based on the target query requirement to obtain the second query request.

[0106] In this embodiment of the application, the second rewriting module is further configured to: determine the query topic corresponding to the first query request based on the first query result, wherein the query topic is used to characterize the query direction of the first query request; determine the behavior pattern corresponding to the first query request based on historical query data, wherein the behavior pattern is used to characterize the changing trend of data query behavior within a historical time period; and adjust the initial query requirements based on the query topic and behavior pattern to obtain the target query requirements.

[0107] In this embodiment of the application, the second rewriting module is further configured to: decompose the first query request to obtain at least one keyword; expand any keyword based on the target query requirements to obtain a keyword set corresponding to the keyword; and update the first query request based on the keyword set corresponding to at least one keyword to obtain a second query request.

[0108] In this embodiment of the application, the second rewriting module is further configured to: obtain the request execution flow corresponding to the first query request and the request execution tool corresponding to the second query request; and execute the second query request using the request execution tool based on the request execution flow to obtain the second query result.

[0109] In this embodiment of the application, the second rewriting module is further configured to: determine the tool usage conditions corresponding to the second query request based on historical query data; detect the second query request to obtain the request type of the second query request; and select a request execution tool from the tool library based on the request type and the tool usage conditions.

[0110] In this embodiment of the application, the data query module is further configured to: evaluate any one of the query data contained in the first query result based on the target query requirement corresponding to the second query request, and obtain a data evaluation index, wherein the data evaluation index is used to characterize the degree of matching between the query data and the target query requirement; filter the query data contained in the first query result based on the data evaluation index to obtain a third query result; and summarize the third query result and the second query result to obtain the target query result.

[0111] According to an embodiment of this application, a data interaction apparatus for implementing the above-described data interaction method is also provided. Figure 7 This is a structural block diagram of a data interaction device according to an embodiment of this application, such as... Figure 7 As shown, the device includes: a request generation module 702, a third rewriting module 704, a fourth rewriting module 706, and an information generation module 708.

[0112] The request generation module 702 generates an initial query request based on the received query information. The third rewriting module 704 rewrites the initial query request based on the initial query request and historical interaction information to obtain a first query request, and performs a data query based on the first query request to obtain a first query result. The fourth rewriting module 706 rewrites the first query request based on the first query result and historical interaction information to obtain a second query request, and performs a data query based on the second query request to obtain a second query result. The information generation module 708 generates response information based on the first query result, the second query result, and historical interaction information. The historical interaction information includes historical query information and historical response information generated during data interactions within a historical time period.

[0113] The request generation module 702, the third rewriting module 704, the fourth rewriting module 706, and the information generation module 708 described above correspond to steps S302 to S208 in the above embodiments. The four modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. The modules or units described above may be hardware or software components stored in memory and processed by one or more processors. These modules may also be part of a device and may run in the server 10 provided in the above embodiments.

[0114] In this embodiment of the application, the information generation module is further configured to: determine the content generation tool corresponding to the initial query request based on the first query result and historical interaction information; input the first query result, the second query result and historical interaction information into the content generation tool; and use the content generation tool to fuse the first query result, the second query result and historical interaction information to generate response information.

[0115] According to an embodiment of this application, another data query apparatus for implementing the above-described data query method is also provided. Figure 8 This is a structural block diagram of a data query device according to an embodiment of this application, such as... Figure 8 As shown, the device includes: a first display module 802 and a second display module 804.

[0116] The first display module 802 is used to display an initial query request on the operation interface when an input command is detected on the operation interface; the second display module 804 is used to display a target query result on the operation interface when a processing command is detected on the operation interface. The target query result is constructed from the first query result and the second query result. The second query result is obtained by querying data using the second query request. The second query request is obtained by rewriting the first query request using the first query result and historical query data. The first query result is used to represent the data obtained by querying data based on the first query request. The historical query data is used to represent the data generated during data queries within a historical time period that is related to the initial query request. The first query request is obtained by rewriting the initial query request using the historical query data.

[0117] The first display module 802 and the second display module 804 described above correspond to steps S502 to S504 in the above embodiments. The two modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. The modules or units described above may be hardware or software components stored in memory and processed by one or more processors. The modules may also be part of a device and may run in the server 10 provided in the above embodiments.

[0118] The preferred embodiments involved in the above embodiments of this application are the same as the solutions, application scenarios and implementation processes provided in the above embodiments, and will not be repeated here.

[0119] Embodiments of this application may provide a computing device. Figure 9 This is a structural block diagram of a computing device according to an embodiment of this application. Figure 9 As shown, the computing device 900 may include: one or more (one shown in the figure) processors 902, memory 904, memory controller, and peripheral interfaces.

[0120] The aforementioned computing device can be understood as an integrated intelligent terminal, including but not limited to servers, desktop computers, PCs (Personal Computers), and all-in-one model machines. Furthermore, the computing device may have the model described in the above embodiments of this application pre-installed.

[0121] Specifically, this computing device can pre-install various types of models, including but not limited to models in fields such as natural language processing, visual processing, speech processing, code processing, and multimodal task processing, thus providing diverse model choices. In different product forms, this computing device can support one or more model usage methods, including but not limited to model training, model invocation, model fine-tuning, model deployment, model inference, and application. In some product forms, this computing device also supports model management, including but not limited to multi-type model management (supporting the management of discriminative, generative, and other model types), model version control (supporting the control of different model versions), and model evaluation (evaluating model performance and effectiveness based on model evaluation tools). In other product forms, this computing device can also create applications based on models, providing API calling capabilities. Models can be called into created applications through API interfaces, and application management tools are provided to control and manage applications.

[0122] Furthermore, this computing device can also include data management (supporting the creation and management of model tuning datasets), a training center (providing abundant training resources to help users learn and master AI technologies), and basic control capabilities (providing enterprise-level basic control capabilities to ensure system security and efficient operation). Through these functions, it provides a comprehensive, integrated device for AI development, training, deployment, and application.

[0123] 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 methods in the above embodiments. The memory may include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks (LANs), mobile communication networks, and combinations thereof.

[0124] The processor can invoke an executable program stored in memory via a transmission device to execute any of the methods described in the above embodiments.

[0125] Embodiments of this application may provide an electronic device. Figure 10 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 10 As shown, the electronic device may include: an input / output device 1002; a memory 1004; and a processor 1006, wherein the processor 1006 is connected to the input / output device 1002 and the memory 1004 via a bus 1008.

[0126] 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 methods in the above embodiments. The memory may include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks (LANs), mobile communication networks, and combinations thereof.

[0127] The processor can invoke an executable program stored in memory via a transmission device to execute any of the methods described in the above embodiments.

[0128] Those skilled in the art will understand that, Figure 10The structure shown is illustrative. Electronic devices can also be smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, mobile internet devices (MIDs), PADs, and other terminal devices. This diagram does not limit the structure of the aforementioned electronic devices. For example, electronic devices may include more or fewer components (such as network interfaces, display devices, etc.) than shown in the diagram, or have a different configuration than shown in the diagram.

[0129] 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: a flash drive, read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0130] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the aforementioned computer-readable storage medium can be used to store program code executed by the method provided in the above embodiments.

[0131] Optionally, in this embodiment, the storage medium may be located in a computing device or an electronic device.

[0132] Optionally, in this embodiment, the computer-readable storage medium is configured to store an executable program. When the executable program runs, it controls the device where the computer-readable storage medium is located to perform any of the methods described in the above embodiments.

[0133] Embodiments of this application also provide a computer program product. Optionally, in this embodiment, the computer program product may include a computer program. When executed by a processor, the computer program implements the methods provided in the above embodiments.

[0134] Embodiments of this application also provide a computer program product. Optionally, the computer program product may include a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium can be used to store a computer program. When the computer program is executed by a processor, it implements the method provided in the above embodiments.

[0135] Embodiments of this application also provide a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it implements the method provided in the above embodiments.

[0136] 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.

[0137] 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 illustrative; for example, the division of units is a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined, integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling, direct coupling, or communication connection shown or discussed may be through some interfaces, indirect coupling of units or modules, or communication connection, and may be electrical or other forms.

[0138] 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 according to actual needs to achieve the purpose of this embodiment.

[0139] 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.

[0140] 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 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.

[0141] The above are preferred embodiments of this application. For those skilled in the art, various improvements and modifications can be made without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A data query method, characterized in that, include: Upon receiving an initial query request, the initial query request is rewritten based on historical query data to obtain a first query request, and a data query is performed based on the first query request to obtain a first query result; The first query request is rewritten based on the first query result and the historical query data to obtain a second query request, and data is queried based on the second query request to obtain a second query result; Based on the first query result and the second query result, the target query result is obtained; The historical query data is used to represent data generated during data queries within a historical time period that is related to the initial query request.

2. The method according to claim 1, characterized in that, Based on the first query result and the historical query data, the first query request is rewritten to obtain a second query request, including: The initial query request is parsed to obtain the initial query requirement corresponding to the initial query request, wherein the initial query requirement is used to characterize the execution purpose of the initial query request; Based on the first query result and the historical query data, the initial query requirement is adjusted to obtain the target query requirement; The first query request is rewritten based on the target query requirements to obtain the second query request.

3. The method according to claim 2, characterized in that, The step of adjusting the initial query requirement based on the first query result and the historical query data to obtain the target query requirement includes: Based on the first query result, the query topic corresponding to the first query request is determined, wherein the query topic is used to characterize the query direction of the first query request; Based on the historical query data, the behavior pattern corresponding to the first query request is determined, wherein the behavior pattern is used to characterize the changing trend of data query behavior within a historical time period; The initial query requirement is adjusted based on the query topic and the behavioral pattern to obtain the target query requirement.

4. The method according to claim 2, characterized in that, The step of rewriting the first query request based on the target query requirement to obtain the second query request includes: The first query request is broken down to obtain at least one keyword; Based on the target query requirements, any keyword is expanded to obtain the keyword set corresponding to the keyword; The first query request is updated based on the keyword set corresponding to the at least one keyword to obtain the second query request.

5. The method according to any one of claims 1-4, characterized in that, The process of performing a data query based on the second query request to obtain a second query result includes: Obtain the request execution flow corresponding to the first query request, and the request execution tool corresponding to the second query request; Based on the aforementioned request execution process, the second query request is executed using the aforementioned request execution tool to obtain the second query result.

6. The method according to claim 5, characterized in that, The step of obtaining the request execution tool corresponding to the second query request includes: Based on the historical query data, determine the tool usage conditions corresponding to the second query request; The second query request is detected to obtain the request type of the second query request; Based on the request type and the tool usage conditions, the request execution tool is selected from the tool library.

7. The method according to any one of claims 1-4, characterized in that, The step of obtaining the target query result based on the first query result and the second query result includes: Based on the target query requirement corresponding to the second query request, any query data contained in the first query result is evaluated to obtain a data evaluation index, wherein the data evaluation index is used to characterize the degree of matching between the query data and the target query requirement; Based on the data evaluation metrics, the query data contained in the first query result is filtered to obtain the third query result; The third query result and the second query result are summarized to obtain the target query result.

8. A data interaction method, characterized in that, include: Upon receiving an inquiry, an initial query request is generated based on the inquiry. Based on the initial query request and historical interaction information, the initial query request is rewritten to obtain a first query request, and data is queried based on the first query request to obtain a first query result; The first query request is rewritten based on the first query result and the historical interaction information to obtain a second query request, and data is queried based on the second query request to obtain a second query result; Based on the first query result, the second query result, and the historical interaction information, a response message is generated; The historical interaction information includes: historical query information and historical reply information generated during data interaction within a historical time period.

9. The method according to claim 8, characterized in that, The step of generating response information based on the first query result, the second query result, and the historical interaction information includes: Based on the first query result and the historical interaction information, determine the content generation tool corresponding to the initial query request; The first query result, the second query result, and the historical interaction information are input into the content generation tool, and the content generation tool is used to merge the first query result, the second query result, and the historical interaction information to generate the response information.

10. A data query method, characterized in that, include: Upon detecting an input command applied to the user interface, an initial query request is displayed on the user interface. Upon detecting a processing instruction applied to the operation interface, the target query result is displayed on the operation interface. The target query result is constructed from a first query result and a second query result. The second query result is obtained by querying data using a second query request. The second query request is obtained by rewriting the first query request using the first query result and historical query data. The first query result is used to represent data obtained by querying data based on the first query request. The historical query data is used to represent data generated during data queries within a historical time period that is related to the initial query request. The first query request is obtained by rewriting the initial query request using the historical query data.

11. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor, connected to a memory via a bus, is used to run the program, wherein the program, when running, performs the method described in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 10.

13. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 10.

Images