Interface information query method and program product

Abstract

The invention discloses an interface information query method and a program product. The method comprises the steps of obtaining first query information in response to an information query request; wherein the first query information is used for describing an interface information query task for at least one service interface; determining a query content category corresponding to the first query information, and determining second query information according to the query content category; wherein the second query information is used for prompting the content needing to be queried by the information query model and / or the expected output content of the information query model; and inputting the second query information into the information query model to enable the information query model to generate target feedback information according to interface associated information stored in a pre-established interface database, and displaying the target feedback information based on output information of the information query model, and the efficiency and accuracy of interface information query are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data query, and in particular to an interface information query method and program product. Background Art

[0002] With the rapid development of Internet technology, the interconnection between various information systems is becoming increasingly frequent. Interface information, as the core carrier for realizing data interaction and function call between systems, plays a vital role in software development, system integration and service collaboration.

[0003] However, there are still many technical bottlenecks in the query and management of interface information, which seriously restrict the development efficiency and the ability of collaboration between systems. On the one hand, because interface documents are scattered and stored in different platforms, databases or local file systems, there is a lack of a unified centralized management mechanism and an efficient indexing system. This makes it difficult for developers to quickly and accurately locate the required information when faced with massive interface resources, resulting in a lot of time wasted in the information retrieval process. On the other hand, even if the target information is successfully located, due to the common problems of redundant content and irregular structure in interface documents, developers need to screen and analyze massive unstructured data line by line to extract key information. This inefficient manual retrieval method is not only time-consuming and labor-intensive, but also very easy to miss important parameter descriptions, exception handling logic and other key content, making it difficult for query results to cover all valid information, thereby affecting the accuracy and stability of interface calls. Summary of the Invention

[0004] The present invention provides an interface information query method and a program product to solve the problems of low retrieval efficiency and difficulty in information extraction in the existing interface information query process.

[0005] According to one aspect of the present invention, a method for querying interface information is provided, the method comprising:

[0006] In response to the information query request, obtaining first query information; wherein the first query information is used to describe an interface information query task for at least one service interface;

[0007] Determine a query content category corresponding to the first query information, and determine second query information based on the query content category; wherein the second query information is used to prompt the information query model for content to be queried and / or expected output content of the information query model;

[0008] The second query information is input into the information query model so that the information query model generates target feedback information according to the interface association information stored in the pre-established interface database, and the target feedback information is displayed based on the output information of the information query model.

[0009] According to another aspect of the present invention, there is provided an interface information query device, the device comprising:

[0010] A first query information acquisition module is configured to acquire first query information in response to an information query request; wherein the first query information is used to describe an interface information query task for at least one service interface;

[0011] A second query information determination module is configured to determine a query content category corresponding to the first query information and determine second query information based on the query content category; wherein the second query information is used to prompt the information query model for content to be queried and / or the expected output content of the information query model;

[0012] A target feedback information generation module is used to input the second query information into the information query model so that the information query model generates target feedback information based on the interface association information stored in the pre-established interface database, and displays the target feedback information based on the output information of the information query model.

[0013] According to another aspect of the present invention, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the interface information query method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the interface information query method according to any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, an embodiment of the present disclosure further provides a computer program product, including a computer program, which implements the interface information query method as described in any one of the embodiments of the present disclosure when executed by a processor.

[0019] The technical solution of the embodiment of the present invention first obtains first query information in response to an information query request; wherein the first query information is used to describe an interface information query task for at least one business interface, which can accurately locate the query demand and effectively improve the efficiency of information acquisition; then, by determining the query content category corresponding to the first query information, second query information is determined according to the query content category. Since the second query information is used to prompt the information query model for the content to be queried and / or the expected output content of the information query model, the query content category can be identified to first filter invalid information by the category, and then generate refined query instructions for valid categories, clearly limiting the query scope of the model, thereby reducing the randomness of the content generated by the model and improving the pertinence and efficiency of the interface information query; finally, by inputting the second query information into the information query model, the information query model generates target feedback information based on the interface association information stored in a pre-established interface database, and displays the target feedback information based on the output information of the information query model. Through the linkage between the information query model and the interface database, the target feedback information is automatically generated and intuitively displayed, greatly improving the efficiency and accuracy of interface management, and effectively solving the problems of complex interface management and high labor costs.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flowchart of an interface information query method provided according to the first embodiment of the present invention;

[0023] Figure 2 This is a flowchart of an interface information query method applicable to the second embodiment of the present invention;

[0024] Figure 3a This is a flowchart of an interface information query method that can be used in an embodiment of the present invention, provided according to the third embodiment.

[0025] Figure 3b The flowchart of the process of establishing an interface database for the interface information query method of the embodiment of the present invention is provided according to the third embodiment of the present invention.

[0026] Figure 4 This is a structural diagram of an interface information query device provided according to a fourth embodiment of the present invention;

[0027] Figure 5 The present invention is a schematic diagram of the structure of an electronic device that implements the interface information query method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0031] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0032] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the categories, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0033] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0034] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0035] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0036] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0037] Example 1

[0038] Figure 1 A flowchart of an interface information query method is provided for embodiment 1 of the present invention. This embodiment is applicable to interface information query scenarios. The method can be executed by an interface information query device, which can be implemented in the form of hardware and / or software. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, PC or server, etc.

[0039] like Figure 1 As shown, the method may specifically include:

[0040] S110. In response to the information query request, obtain first query information.

[0041] In the embodiments of the present invention, an information query request refers to a request instruction initiated to obtain information related to an interface. An interface is a connection point for information exchange and function calls between different program modules or systems. Interfaces can exist at different levels, and can be interfaces between different modules of a system or between different systems. Interfaces define the interaction rules and communication methods between different software components or systems.

[0042] The information query request is used to trigger the acquisition of the first query information. The first query information refers to the basic query content obtained after responding to the information query request. The first query information is mainly presented in the form of natural language text and can be used to describe the interface information query task for one or more interfaces. The first query information may include but is not limited to at least one of the following basic elements: query object (such as specific interface name, functional module, belonging system, etc.), query direction (such as interface function description, field meaning, parameter type and value requirements, etc.).

[0043] Optionally, when the information query request is received, the first query information inputted is obtained.

[0044] Specifically, an interface information query interface can be displayed, in which an information input box for entering query content is set. Query statements related to the interface information, such as "parameter requirements for the query interface", are entered in the input box through a keyboard or other input device; in response to the input operation, after detecting the information query request, such as clicking a search button or pressing the Enter key, the first query information is extracted and obtained as a basis for subsequent processing.

[0045] To improve input efficiency and query accuracy, the interface information query interface can also display several candidate terms, recommended terms, or historical query records related to the interface information. Candidate terms can include at least one of common interface names, functional keywords, and business modules. Appropriate terms can be selected from the candidate list by clicking, sliding, or other methods to combine into query content. In response to the selection operation, after the information query request is detected, the selected terms are combined into the first query information.

[0046] Furthermore, it can also support automatically initiating information query requests through preset target trigger events. This trigger event can be a click on the query box in the information query interface, a click on the "Search" button, a timed automatic trigger after input is completed, or a predicted potential query demand, such as the cursor focusing on the input box and no further operation for a set time. Once the trigger condition is met, the first query information in the current context is automatically obtained, such as the text content already in the input box or the associated historical query records, thus achieving efficient and intelligent information query.

[0047] Responding to an information query request and obtaining the first query information helps to quickly identify the interface to be queried, effectively improving the speed and accuracy of information retrieval; at the same time, it supports multiple input methods, such as manual input, candidate word selection or automatic triggering, etc., which improves interaction efficiency and user experience.

[0048] S120: Determine a query content category corresponding to the first query information, and determine second query information according to the query content category.

[0049] Among them, the query content category is the classification result obtained by mapping the first query information to a predefined category system based on a preset scenario or semantic logic rule. The user's actual query intention can be identified through the query content category. The second query information is a structured instruction or prompt information generated based on the query content category to which the first query information belongs. The second query information is used to clearly prompt the information query model for the content to be queried and / or the expected output content of the information query model. The information query model is used to call a pre-established interface database based on the input second query information to obtain relevant information, and return the query results in a pre-set output format. By determining the second query information through the query content category, the transformation from natural language query to structured instruction is realized, and the intelligence level and accuracy of interface information retrieval are improved.

[0050] Optionally, the query content category corresponding to the first query information may be determined based on a model or keyword matching, and then the content to be queried or the expected output content, ie, the second query information, may be determined based on the query content category.

[0051] As an optional technical solution of an embodiment of the present invention, optionally, determining the query content category corresponding to the first query information includes: determining the query content category corresponding to the first query information based on the first query information and a semantic recognition model; wherein, the semantic recognition model is obtained by training a first machine learning model based on sample query information corresponding to a sample interface and an expected content category corresponding to the sample query information.

[0052] Specifically, the semantic recognition model can analyze the first query information and automatically identify the corresponding query content category. For example, the first query information is input into the semantic recognition model, and its built-in natural language processing algorithm and feature extraction mechanism are used to analyze the semantic structure, keywords, and contextual logic of the text, thereby outputting the corresponding query content category, achieving efficient and accurate automatic classification.

[0053] Optionally, a training data set can be constructed by preprocessing and annotating the correspondence between query information and query content categories to train a machine learning model and obtain a semantic recognition model, so that it can accurately identify user query intentions and automatically classify them into corresponding query content categories, providing support for generating refined query instructions.

[0054] For example, a semantic recognition model can be trained by a machine learning model in the following manner: First, sample query information corresponding to various sample interfaces is collected, and each sample query information is labeled with the expected content category. Next, the labeled data is used as the training set to initialize the machine learning model parameters. During the training process, the model's built-in natural language processing algorithm is used to perform feature extraction and semantic analysis on each sample, identifying key information such as keywords, semantic structure, and contextual logic in the text. Then, based on the differences between the current model output and the labeled labels, a backpropagation algorithm is used to dynamically adjust the model parameters, gradually optimizing the model's learning capabilities. Through repeated training and parameter updates, the model continuously iterates, learning from the sample query information in the training set and gradually capturing the inherent connections between different query information and category labels. Multiple rounds of iterative training are continued until the model's performance on the validation set stabilizes, i.e., the loss function value reaches a minimum and the classification accuracy no longer significantly improves, indicating that the model has converged. At this point, the trained semantic recognition model can quickly and accurately classify the first query information entered by the user in real time into predefined query content categories, greatly improving query efficiency and accuracy and enhancing the user experience.

[0055] In addition, the machine learning model supports a continuous learning mechanism, which can effectively improve the adaptability and intelligence level of the semantic recognition model. For example, when new query information appears, the query content category can be dynamically defined according to the newly added business scenario. At the same time, the query information and query content category under the newly added scenario can be added to the training set, and the machine learning model can be incrementally trained or retrained according to the above training process. During the training process, cross-validation and hyperparameter tuning are used to ensure that the model can accurately capture the relationship between the new query content category and the query information. Ultimately, the trained model can not only maintain the accuracy of the original query information recognition, but also quickly adapt to new scenarios, thereby achieving accurate identification and classification of diversified interface query requirements, and continuously optimizing the user interaction experience.

[0056] By training the semantic recognition model with labeled samples, it can automatically learn the deep semantic mapping relationship between query information and query content categories, accurately respond to complex semantic scenarios, have strong adaptability to complex semantic scenarios, and significantly improve the accuracy and efficiency of query information classification.

[0057] As an optional technical solution of an embodiment of the present invention, optionally, determining the query content category corresponding to the first query information further includes: determining the query keyword in the first query information, and determining the query content category corresponding to the first query information based on the query keyword and the preset keyword corresponding to the preset content category.

[0058] Among them, the preset content category is a standardized query information classification pre-divided according to business scenarios. The preset content category is used to map the query information input by the user to a fixed business dimension. The preset keyword is a characteristic word or phrase predefined for each preset content category, used to represent the core business-representative requirements of this content category. The preset keyword can be determined by means of expert experience and / or historical data statistics, etc.

[0059] To improve the recognition accuracy, optionally, a set of strongly relevant keywords can be predefined for each preset content category, and a mapping relationship between the keywords and the query content category can be established, and then the preset keywords corresponding to the preset content category can be obtained, so as to quickly locate the content query category to which the user's needs belong based on the keywords.

[0060] Optionally, training data can be collected and keyword extraction can be performed to construct keywords corresponding to each preset content category to improve the recognition accuracy of the query content category. The training data can be collected by simulating common user questions or collecting historical interaction data, and can cover a variety of business scenarios and query types. For example, 1) Interface usage consultation, such as "I want to know the field meaning and parameter requirements of a certain interface"; 2) Function implementation requirements, such as "Which interfaces do I need to call to implement a certain function"; 3) Joint debugging test requirements, such as "Please provide a request example and test data for a certain interface"; 4) Comparative analysis requirements, such as "What is the difference between these two interfaces". For the above problems, the core keywords can be extracted to construct a keyword list for each type of query content category. For example, "interface", "field", "parameter", etc. are used to identify interface usage type queries; "function", "call" correspond to function implementation types; "example", "test data" correspond to test types; "difference" belongs to the comparative analysis type.

[0061] Optionally, before determining the query content category corresponding to the first query information, the first query information can be preprocessed. The preprocessing can include removing irrelevant content such as punctuation marks and special characters, removing stop words such as "de" and "le" without actual semantics, and performing one or more of stemming or lemmatization according to language characteristics to achieve text standardization.

[0062] Through the cleaning and optimization of the original first query information, noise can be effectively removed, fuzzy expressions can be corrected, ensuring that the input data is accurate and standardized, providing a high-quality data basis for subsequent precise matching and semantic recognition, and thus improving the overall query efficiency and the accuracy of the feedback results.

[0063] Exemplarily, a keyword extraction algorithm based on statistical features can be used for query keyword extraction, such as the TF-IDF algorithm, which calculates the product of the term frequency and inverse document frequency of each word in the text, and filters out representative high-frequency words as query keywords.

[0064] Optionally, the query keywords in the first query information are determined, and the extracted query keywords are compared with the preset keywords corresponding to each preset content category. For example, based on a string matching algorithm or a text similarity calculation method, the semantic similarity between the keywords is identified, and then the query content category corresponding to the first query information is determined.

[0065] Optionally, a matching threshold is set. When the number of keyword matches or the similarity score of a preset content category exceeds the set threshold, the category can be determined to be the query content category corresponding to the first query information.

[0066] Through the above steps, keywords are extracted based on the first query information, and corresponding query content categories are automatically identified based on the keyword matching method, providing support for subsequent generation of structured query instructions.

[0067] Furthermore, after the query content category corresponding to the first query information is determined, the second query information may be determined according to the corresponding query content category.

[0068] As an optional technical solution of an embodiment of the present invention, a preset information template may be optionally populated with keywords to obtain the second query information. Specifically, determining the second query information based on the query content category includes: determining the query keyword in the first query information, and determining a preset information template corresponding to the query content category; wherein the preset information template includes a keyword filling position; filling the query keyword into the keyword filling position corresponding to the query keyword in the preset information template, and determining the filled preset information template as the second query information.

[0069] Specifically, the first query information is analyzed to determine the query keywords. Based on the determined query content category, a corresponding preset information template is retrieved from a template library. This template contains one or more preset keyword filler positions. The extracted query keywords are sequentially filled into the keyword filler positions corresponding to the query keywords in the preset information template according to semantic matching rules. The filled template is then used as the second query information and passed to the information query model for retrieval.

[0070] By filling in the corresponding preset information template based on the keyword to generate the second query information, the keyword and template can be flexibly adjusted to adapt to diverse user queries, thereby improving the flexibility of the query.

[0071] As an optional technical solution of the embodiment of the present invention, optionally, the second query information can also be determined by directly calling preset query information. Specifically, determining the second query information according to the query content category includes: determining the preset query information corresponding to the query content category as the second query information.

[0072] Specifically, fixed preset query information is pre-set for each query content category. After the query content category of the first query information is determined, the preset query information corresponding to the category is directly used as the second query information.

[0073] By pre-building preset query information corresponding to each query content category, there is no need to analyze the keywords in the first query information. The logic is simple and the execution efficiency is high, which can reduce computing resource consumption while providing a quick response.

[0074] S130: Input the second query information into the information query model, so that the information query model generates target feedback information according to the interface association information stored in the pre-established interface database, and displays the target feedback information based on the output information of the information query model.

[0075] In an embodiment of the present invention, the information query model is at least configured to query target-related information corresponding to the second query information from interface-related information stored in a pre-established interface database, and generate target feedback information based on the retrieved target-related information. The information query model may be trained based on a machine learning model. The interface database is a pre-established database in the system that stores various types of interface-related information. Interface-related information can be understood as specific data entries stored in the interface database. Each piece of information is associated with a specific interface or business scenario and is the target of retrieval by the information query model. The interface-related information may include, but is not limited to, at least one of business description data, interface description information, interface fields, field description data, interface message examples, and interface test data. For example, the interface description information may include interface function description information and / or preset description data (e.g., special instructions). The business description data may include business usage scenarios. The field description data may include field usage instructions. The interface test data may include, among other content, valid test data. The interface-related information is stored in an unstructured form in the database to facilitate rapid retrieval by the information query model.

[0076] The target associated information is specific interface information that meets the conditions and is found by the information query model in the interface database according to the second query information. The target feedback information is content generated by the information query model according to the found target associated information and is used to feed back to the user.

[0077] After generating the second query information, the second query information is optionally input into the information query model. The information query model matches and searches the interface association information stored in the interface database, searches the interface association information most relevant to the current query content from the interface database, and generates target feedback information.

[0078] Based on the output result of the information query model, the target feedback information is displayed to the user to provide accurate and structured interface information query results.

[0079] The information query model possesses natural language processing capabilities, enabling it to perform semantic analysis and keyword extraction on input query information. It then employs a variety of matching strategies, such as keyword matching, tag matching, and semantic similarity calculation, to search the interface database for the interface-related information most relevant to the current query. For example, when a user asks, "How do I call transaction code 01?" the information query model will automatically identify "transaction code 01" and "calling method" as core keywords and search the interface database for relevant interface-related information, including interface function descriptions, parameter specifications, and sample messages.

[0080] Optionally, after the information query model queries one or more pieces of target-related information, the query results may be processed according to preset rules to generate target feedback information.

[0081] Specifically, when the query results contain multiple possible target-related information, the information query model can calculate the relevance between each target-related information and the second query information based on indicators such as keyword matching degree and semantic similarity, and rank the candidate target-related information accordingly. For example, the priority of the target-related information can be determined by calculating the degree of keyword overlap or measuring semantic similarity using a semantic vector space model.

[0082] Optionally, after ranking, the information query model can select one or more pieces of candidate target-related information that best meet the user's needs. For simple questions, a single optimal target-related information piece can be selected as the target feedback information. For complex questions, multiple target-related information pieces can be integrated to form a more comprehensive target feedback information.

[0083] Optionally, the information query model can convert the retrieved target-related information into a user-friendly expression, such as converting complex industry terms into easy-to-understand language, supplementing necessary background explanations and detailed descriptions, and ensuring that the output target feedback information is easy to understand.

[0084] Optionally, the target feedback information can be structured and organized in a logical order. For example, technical field descriptions can be translated into plain language and supplemented with intuitive examples or diagrams; interface message samples can be formatted as a table, with detailed annotations added to each field to improve information readability and search efficiency.

[0085] Based on the output of the information query model, the generated target feedback information is displayed to the user, completing the entire information query and feedback process. Through the above processing steps, the accuracy, readability, and practicality of the feedback content can be effectively improved, enhancing the overall query experience.

[0086] Furthermore, the interface database can be continuously updated and expanded, including but not limited to adding new interface information, supplementing test data, and correcting errors. The information query model can also continuously improve its understanding and retrieval accuracy through the introduction of new training data and algorithm optimization. The information query model also supports a multi-round dialogue mechanism, allowing users to continue asking questions based on initial feedback, achieving deeper information interaction.

[0087] As an optional technical solution of an embodiment of the present invention, optionally, before inputting the second query information into the information query model, it also includes: determining the interface association information corresponding to the business interface according to the interface call association log corresponding to the business interface and the interface information description document, and constructing an interface database according to the interface association information corresponding to the business interface.

[0088] Among them, the business interface refers to the standardized channel used to realize data interaction corresponding to a specific business scenario in the system docking. The interface call association log records various types of historical data generated by the business interface during the actual operation process, including but not limited to one or more key information such as request parameters, response results, call time and transaction status. The interface call association log reflects the usage and behavioral characteristics of the interface in the actual scenario. The interface information description document is a standardized document written by the development team or business department, which details the technical specifications and business rules of the interface. The interface information description document may include but is not limited to at least one of the following data: business description data, interface description information, interface fields, field description data, interface message samples, and interface test data. Business description data includes but is not limited to one or more contents such as business identification, business function description, and usage scenario.

[0089] Specifically, the interface association information corresponding to the business interface can be determined from the call association log and the interface description document corresponding to the business interface, and then a unified interface database can be constructed.

[0090] Exemplarily, the interface database can be constructed by combining structured and unstructured knowledge, wherein structured knowledge is captured from the historical transaction logs of the test environment, and after deduplication, cleaning and refinement, it is combined with the interface list and indexed with the interface number to store the interface message in a standardized manner according to dimensions such as request parameters, response format, field definition, data type, and length limit. By processing structured knowledge, an interface structured database is generated, so that the interface information is presented in a clear and orderly manner, significantly improving the efficiency of knowledge retrieval and call. Unstructured knowledge is formed by integrating text materials such as interface description documents, product descriptions, and design documents to form an unstructured database, which can cover one or more contents such as the business background, user guide, and precautions of the interface.

[0091] Optionally, to achieve efficient integration and retrieval of knowledge, structured data and unstructured documents can be associated through core identifiers such as interface numbers and interface names to generate a unified destructured organizational database.

[0092] Optionally, when building an interface database, the interface number can be used as the primary thread, and information such as interface fields, field descriptions, business functions, application scenarios, message samples, test data sets, and special rule descriptions can be structured and organized according to a standardized data model. By integrating structured and unstructured knowledge and building a unified knowledge organization structure, not only can knowledge be stored in a clear and orderly manner, but the unified search dimension can also improve the retrieval efficiency and matching accuracy of the information query model.

[0093] Furthermore, to ensure the timeliness and accuracy of the interface database, a full-lifecycle maintenance mechanism can be established. On the one hand, outdated or erroneous content can be promptly revised in response to changes such as business rule adjustments and interface version updates. On the other hand, knowledge about newly added interfaces can be dynamically supplemented as new business scenarios expand and technologies evolve. By continuously optimizing the knowledge system, the interface database can be kept in sync with business development.

[0094] Optionally, you can set access control policies to ensure access control and security of the interface database, preventing unauthorized access and data leakage. For example, users can be divided into internal and external users. Internal users include personnel in testing, development, and business operations, while external users are partners or clients. Strong authentication mechanisms such as two-factor authentication can be used to strictly verify user identities and enhance access security.

[0095] Optionally, based on the principle of least privilege, access rights can be precisely allocated according to the responsibilities of different roles to eliminate unauthorized access and data leakage risks at the source.

[0096] Optionally, a regular data backup mechanism can be established to perform full and incremental backups of the interface database to ensure that data can be quickly restored in the event of an unexpected situation, thereby fully protecting the security, integrity, and availability of system data.

[0097] The technical solution of an embodiment of the present invention first obtains first query information in response to an information query request; wherein the first query information is used to describe an interface information query task for at least one business interface; accurately locates the query requirement, avoids fuzzy search, and effectively improves information acquisition efficiency; then, determines the query content category corresponding to the first query information, and determines second query information based on the query content category; wherein the second query information is used to prompt the information query model for the content to be queried and / or the expected output content of the information query model; by identifying the query content category, first uses the category to filter invalid information, and then generates refined query instructions for valid categories, clearly limiting the query scope of the model, thereby reducing the randomness of the model-generated content and improving the pertinence and efficiency of the interface information query; finally, inputs the second query information into the information query model, so that the information query model generates target feedback information based on the interface association information stored in a pre-established interface database, and displays the target feedback information based on the output information of the information query model; through the linkage between the information query model and the interface database, the automatic generation and intuitive display of the target feedback information are realized, greatly improving the efficiency and accuracy of interface management, and effectively solving the problems of complex interface management and high labor costs.

[0098] Example 2

[0099] Figure 2 A flowchart of an interface information query method provided in the second embodiment of the present invention further describes the process of determining the query content category corresponding to the first query information based on the query keyword and the preset keyword corresponding to the preset content category. Optionally, the process of determining the query content category corresponding to the first query information based on the query keyword and the preset keyword corresponding to the preset content category includes: separately determining the keyword matching degree between the preset keyword corresponding to each preset content category and the query keyword; wherein the keyword matching degree includes the keyword matching number and / or keyword similarity; determining the query content category corresponding to the first query information from a plurality of the preset content categories based on the keyword matching degree corresponding to each of the preset content categories. For specific implementation methods, please refer to the description of this embodiment. Among them, technical features that are the same or similar to those in the aforementioned embodiments are not repeated here. Figure 2 As shown, the method may specifically include:

[0100] S210: Respond to the information query request and obtain first query information.

[0101] S220: Determine the keyword matching degree between the preset keyword corresponding to each preset content category and the query keyword.

[0102] The keyword matching degree can be understood as a quantitative indicator that measures the degree of association between the query keyword and the preset keyword. The keyword matching degree may include the number of keyword matches and / or keyword similarity.

[0103] Optionally, the preset keyword list is traversed to count the number of query keywords that completely match the preset keywords. Further, the number of matches is divided by the total number of extracted query keywords to obtain a keyword matching ratio.

[0104] Optionally, a word vector model such as Word2Vec can be used to generate word vectors corresponding to the query keyword and the preset keyword respectively, and the semantic proximity between the two can be measured by calculating the cosine similarity to obtain a keyword similarity index to facilitate keyword matching based on semantics.

[0105] These two indicators can be used independently or weighted according to actual business needs, combining them to form a comprehensive keyword matching degree. This provides a more comprehensive and accurate basis for subsequent query content classification, capturing both explicit keyword correspondences and identifying potential semantic associations, significantly improving the accuracy of mapping query information to pre-set content categories.

[0106] S230: Determine a query content category corresponding to the first query information from a plurality of preset content categories according to the keyword matching degree corresponding to each preset content category.

[0107] Optionally, based on the keyword matching degree corresponding to each preset content category, one or more query content categories that may meet the query information corresponding to the first query information may be preliminarily screened out from the multiple preset content categories.

[0108] Optionally, when the user input contains a keyword that uniquely matches a preset content category, the preset content category is directly determined as the query content category corresponding to the first query information. If there are multiple query content categories that may match the first query information, a judgment is made based on the keyword matching degree or preset rules to determine the query content category that best meets the requirements, thereby resolving query ambiguity.

[0109] When the keyword matching degree includes keyword similarity, as an optional technical solution of an embodiment of the present invention, optionally, determining the query content category corresponding to the first query information from a plurality of the preset content categories based on the keyword matching degree corresponding to each of the preset content categories includes: determining the category matching degree corresponding to the preset content category based on the keyword weight and the keyword similarity corresponding to each of the query keywords; and determining the query content category corresponding to the first query information from a plurality of the preset content categories based on the category matching degree corresponding to each of the preset content categories.

[0110] Optionally, a weight can be pre-set for each keyword in the preset keyword list. The weight value is set according to the business importance of the keyword in the corresponding preset content category. For example, in the "Interface Parameter Query" category, core keywords such as "parameter" and "field" can be given a higher weight, while auxiliary words such as "how" and "obtain" can be given a lower weight, so as to reflect the differentiated impact of different words on the judgment of the query content category.

[0111] Optionally, when a query keyword input by a user matches a preset keyword, the weight of the preset keyword may be directly transferred to the corresponding query keyword to obtain a keyword weight value corresponding to the query keyword.

[0112] Optionally, the keyword weight corresponding to each query keyword and the keyword similarity corresponding thereto may be multiplied and then added together to obtain the category matching degree corresponding to the preset content category.

[0113] Optionally, the preset content categories are sorted according to their comprehensive matching degrees, and the query content category with the highest matching degree with the first query information is automatically screened out.

[0114] By introducing keyword weights, we can more effectively distinguish users' core needs from auxiliary information, thereby improving the accuracy of query classification in complex semantic scenarios.

[0115] As an optional technical solution of an embodiment of the present invention, optionally, determining the query content category corresponding to the first query information from a plurality of the preset content categories according to the keyword matching degree corresponding to each of the preset content categories includes: determining a candidate content category corresponding to the first query information from a plurality of the preset content categories according to the keyword matching degree corresponding to each of the preset content categories; when there is only one candidate content category, determining the candidate content category as the query content category corresponding to the first query information; when there are multiple candidate content categories, determining the query content category corresponding to the first query information from a plurality of the candidate content categories according to preset priorities of the multiple candidate content categories and / or query words adjacent to the query keyword in the first query information.

[0116] Optionally, a hierarchical screening method may be used to obtain the query content category information. Preliminary screening may be performed based on the keyword matching degree corresponding to each preset content category, for example, a matching degree threshold is set and only categories with matching degrees above the threshold are retained as candidate content categories corresponding to the first query information.

[0117] Optionally, when there is only one candidate content category, it may be directly determined as the final query content category.

[0118] Optionally, when there are multiple candidate content categories, a priority can be set in advance for each preset content category. This priority can be set based on factors such as business urgency and frequency of use. During the screening process, the high-priority category can be selected as the final query content category based on the priority order. For example, if "Exception Handling" is set to high priority and "Operation Guide" is set to low priority, when the user enters "Interface Call Failure" and triggers both categories at the same time, the system will prioritize "Exception Handling."

[0119] Optionally, for queries that are semantically ambiguous but contain contextual clues, we can also analyze adjacent query terms to mine potential semantic associations and further determine the most appropriate query content category. For example, the query "How do I handle an interface error code 500?" might match both the "Interface Instructions" and "Troubleshooting" categories. However, by analyzing contextual terms like "error" and "handling," we determine that the query information is more inclined towards the "Troubleshooting" category.

[0120] Optionally, the priority of the candidate content categories and the context semantic analysis results may be combined to comprehensively evaluate the matching degree of each candidate content category through a weighted scoring mechanism, thereby determining the query content category that best meets the user's intention.

[0121] By hierarchically screening preset content categories, we can accurately identify users' core needs and ensure that the corresponding query content categories are accurately matched in various query scenarios, providing a solid foundation for subsequent information retrieval and response.

[0122] S240: Determine second query information according to the query content category.

[0123] The second query information is used to prompt the information query model of the content to be queried and / or the expected output content of the information query model.

[0124] S250: Input the second query information into the information query model, so that the information query model generates target feedback information according to the interface association information stored in the pre-established interface database, and displays the target feedback information based on the output information of the information query model.

[0125] The technical solution of the embodiment of the present invention is as follows: first, by responding to an information query request, first query information is obtained, thereby achieving timely response to the query request and information collection, and laying the foundation for subsequent precise matching; then, by respectively determining the keyword matching degree between the preset keywords corresponding to each preset content category and the query keywords, keyword matching is performed to improve the accuracy of semantic understanding and reduce the impact of ambiguity; then, by determining the query content category corresponding to the first query information from a plurality of preset content categories according to the keyword matching degree corresponding to each of the preset content categories, query classification is achieved based on the quantitative matching results, thereby improving classification efficiency and accuracy; finally, by determining the second query information according to the query content category, the second query information is input into the information query model, so that the information query model generates target feedback information according to the interface association information stored in the pre-established interface database, and combines the query content category with the interface database to achieve intelligent and structured information feedback generation.

[0126] Example 3

[0127] As an optional example of an embodiment of the present invention, the interface information query method of the embodiment of the present invention may specifically include:

[0128] (1) Query content category identification

[0129] 1. Define query content and keywords. First, use the interface requirement keywords entered to determine the query content category to be identified, i.e., the preset content category. For each preset query content category, define a set of preset keywords that are closely related to the preset content category.

[0130] 2. Prepare data. Anticipate questions users might ask, or collect common expressions and question phrases they might use. Extract keywords from these expressions and create a list of predefined keywords for each predefined query. For example, users might ask the following types of questions:

[0131] 1) Consultation on specific interface usage. For example, I want to consult the meaning of the interface fields and the value requirements.

[0132] 2) Implement a certain functional requirement: For example, I want to query which interfaces can be used for a certain function.

[0133] 3) Joint debugging and testing requirements: For example, if I am conducting a test, please provide message samples and test data.

[0134] 4) Personalization issue: the difference between the two interfaces.

[0135] The list of keywords raised from the above questions includes "interface", "field", "meaning", "value", "query", "message sample", "test data", "difference", etc.

[0136] 3. Text preprocessing. Preprocess the first query input, such as removing punctuation and stop words. This can be done by performing stemming or lemmatization to unify the word form. Train the machine learning model using the prepared training data, ensuring the dataset is properly preprocessed.

[0137] 4. Keyword matching. Analyze the input text to see if it contains pre-set keywords. This can use simple string matching or more complex text matching algorithms.

[0138] 5. Query content category identification. If a query contains a preset keyword for a preset content category, the corresponding query content category will be directly identified. If multiple preset content categories are matched, the most likely query content category can be determined by matching the number of keywords, the degree of match, or specific matching rules.

[0139] For example, a user might ask what the interface for a certain feature is and ask for test data. You can define keywords for the query categories "asking for the interface" and "providing test data," such as "interface" for "what" and "providing" for "data." Then, you can identify the user's query category by matching these keywords.

[0140] 6. Handling ambiguity. Because keywords may appear in multiple predefined content categories, strategies need to be defined to handle ambiguity. For example, priority rules assign priorities to predefined content categories, prioritizing those with higher priority. Keyword weighting: assign a full weight to keywords and categorize them based on the query with the highest weight. Contextual analysis: consider surrounding words or phrases to eliminate ambiguity.

[0141] 7. Feedback and Iteration. Collect user feedback to evaluate the accuracy of query category identification. Adjust the keyword list and matching rules based on the feedback, and continuously iterate and optimize the model.

[0142] 8. Integrate the semantic recognition model into the user interface and deploy the trained model into actual applications to recognize the first query information input in real time.

[0143] (2) Interface database construction

[0144] Taking the transaction service scenario as an example, we collect interface data and information and build an interface database. Data can be divided into structured data and unstructured data.

[0145] 1) Structured Data: Transaction messages are captured, deduplicated, and refined through the historical transaction logs of the test environment. Combined with the transaction list, filtered transaction messages are stored in a database based on transaction codes. A structured database of transaction interfaces can be formed based on dimensions such as transaction codes, request parameters, response formats, data fields, data types, and length limits.

[0146] 2) Unstructured Database: This database is created by compiling existing transaction interface documentation, business product descriptions, transaction design documents, and other textual materials. For new interfaces, existing tools can be used to generate and maintain API documentation. These tools can be integrated into the development workflow to ensure real-time documentation updates.

[0147] Structured and unstructured data can be linked using key information such as transaction codes and names. Interface information is organized in a structured database based on attributes and dimensions such as transaction codes, interface fields, field descriptions, transaction function descriptions, business usage scenarios, message examples, valid test data, and special instructions, facilitating systematic storage and retrieval. Furthermore, the interface database requires regular maintenance, including revising inaccurate information and supplementing new knowledge.

[0148] (3) Answer retrieval and generation

[0149] Through the first step of query content category identification, questions can be assigned to predefined categories and converted into a queryable database format, which is the second query information. Input into the information query model as a method of retrieving answers in the form of "keyword matching" and "labels", and retrieve interface-related information from the interface database, such as interface function descriptions, business usage scenarios, interface message samples, field usage instructions, valid test data, special instructions, etc. If multiple possible answers are retrieved, they are sorted according to relevance. Select the most suitable one or several from the candidate answers, and then convert the retrieved information into a user-friendly answer format, perform formatting adjustments to suit user needs, and output the target feedback information.

[0150] (4) Interface database access control and security

[0151] To ensure data security, you must establish access control policies to ensure access control and security of the interface database, preventing unauthorized access and data leakage. Users can be categorized by role into internal and external personnel. Internal personnel include those in testing, development, and sales roles. External personnel primarily include corporate clients. Verify user identities, such as through two-factor authentication, and assign different permission levels based on user roles and responsibilities. Follow the principle of least privilege to ensure that users only have the access necessary to complete their tasks. Additionally, regularly back up interface database data to ensure rapid recovery and prevent data loss or corruption.

[0152] (V) Interface database maintenance and optimization

[0153] Test the interface database to ensure it meets the requirements of the interface question system and optimize and improve its quality and performance based on feedback. Gather user feedback on the information query model to understand its strengths and weaknesses, and make adjustments and improvements based on user feedback. Technical staff can adjust question matching and answer retrieval strategies based on user feedback and can also use machine learning techniques to continuously optimize the accuracy of question matching and answer retrieval.

[0154] The technical solution of the embodiment of the present invention, by constructing an interface database and information query model, has a higher degree of automation. It can quickly understand user questions, automatically extract information from the interface database, and generate clear and accurate interface search results and extended information. At the same time, it can automatically generate test cases and fill in test data, which is convenient for interface joint debugging testing. Through automation and intelligent methods, while improving the efficiency and accuracy of interface queries and enhancing the user experience, it also greatly reduces reliance on manual labor, reduces manual maintenance costs, and provides strong technical support for interface management.

[0155] Example 4

[0156] Figure 4This is a schematic diagram of the structure of an interface information query device provided in the fourth embodiment of the present invention. The device is used to execute the interface information query method provided in any of the above embodiments. The device and the interface information query method of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the interface information query device, please refer to the embodiment of the above interface information query method. Figure 4 As shown, the device includes: a first query information acquisition module 410, a second query information determination module 420 and a target feedback information generation module 430.

[0157] Among them, the first query information acquisition module 410 is used to obtain the first query information in response to the information query request; wherein, the first query information is used to describe the interface information query task for at least one business interface; the second query information determination module 420 is used to determine the query content category corresponding to the first query information, and determine the second query information according to the query content category; wherein, the second query information is used to prompt the information query model for the content to be queried and / or the expected output content of the information query model; the target feedback information generation module 430 is used to input the second query information into the information query model, so that the information query model generates target feedback information according to the interface association information stored in the pre-established interface database, and displays the target feedback information based on the output information of the information query model.

[0158] The technical solution of the embodiment of the present invention is as follows: first, a first query information acquisition module 410 is used to respond to an information query request to obtain first query information; wherein, the first query information is used to describe an interface information query task for at least one business interface, which can accurately locate the query demand and improve the efficiency of information acquisition; then, a second query information determination module 420 is used to determine the query content category corresponding to the first query information, and second query information is determined according to the query content category; wherein, the second query information is used to prompt the information query model for the content to be queried and / or the expected output content of the information query model; by identifying the query content category, invalid information is first filtered out by using the category, and then the valid category is filtered out. Generate refined query instructions, clearly define the query scope of the model, thereby reducing the randomness of the model generation content, and improving the pertinence and efficiency of the interface information query; finally, input the second query information into the information query model through the target feedback information generation module 430, so that the information query model generates target feedback information according to the interface association information stored in the pre-established interface database, and displays the target feedback information based on the output information of the information query model. Through the linkage between the information query model and the interface database, the automatic generation and intuitive display of the target feedback information are realized, which greatly improves the efficiency and accuracy of interface management; effectively solves the problems of complex interface management and high labor costs.

[0159] Based on the above solution, the second query information determination module 420 optionally includes a first query content category determination submodule. The first query content category determination submodule is configured to determine a query content category corresponding to the first query information based on the first query information and a semantic recognition model, wherein the semantic recognition model is obtained by training a first machine learning model based on sample query information corresponding to a sample interface and an expected content category corresponding to the sample query information.

[0160] Based on the above solution, the second query information determination module 420 may optionally further include a query content category second confirmation submodule. The query content category second confirmation submodule is configured to determine a query keyword in the first query information and determine a query content category corresponding to the first query information based on the query keyword and a preset keyword corresponding to a preset content category.

[0161] Based on the above solution, the query content category second confirmation submodule optionally includes a keyword determination unit and a query content category determination unit. The keyword determination unit is configured to determine the keyword matching degree between the preset keywords corresponding to each preset content category and the query keyword; the keyword matching degree includes the number of keyword matches and / or keyword similarity; and the query content category determination unit is configured to determine the query content category corresponding to the first query information from the plurality of preset content categories based on the keyword matching degree corresponding to each preset content category.

[0162] Based on the above solution, optionally, the keyword matching degree includes keyword similarity.

[0163] Based on the above solution, the query content category determination unit optionally includes a category matching degree determination subunit and a query content category first determination unit. The category matching degree determination subunit is configured to determine the category matching degree corresponding to the preset content category based on the keyword weight and keyword similarity corresponding to each query keyword; and the first query content category determination unit is configured to determine the query content category corresponding to the first query information from a plurality of preset content categories based on the category matching degree corresponding to each preset content category.

[0164] Based on the above solution, optionally, the query content category determination unit further includes a candidate content category determination subunit, a second query content category determination unit, and a third query content category determination unit. The candidate content category determination subunit is configured to determine, from among the plurality of preset content categories, a candidate content category corresponding to the first query information based on the keyword matching degree corresponding to each preset content category; the second query content category determination unit is configured to, when there is only one candidate content category, determine the candidate content category as the query content category corresponding to the first query information; and the third query content category determination unit is configured to, when there are multiple candidate content categories, determine, from among the plurality of candidate content categories, a query content category corresponding to the first query information based on preset priorities of the plurality of candidate content categories and / or query terms adjacent to the query keyword in the first query information.

[0165] Based on the above solution, the second query information determination module 420 optionally includes a query keyword and preset information template determination submodule and a second query information first determination submodule. The query keyword and preset information template determination submodule is configured to determine the query keyword in the first query information and the preset information template corresponding to the query content category; the preset information template includes a keyword filling position; and the second query information first determination submodule is configured to fill the query keyword into the keyword filling position corresponding to the query keyword in the preset information template and determine the filled preset information template as the second query information.

[0166] Based on the above solution, optionally, the second query information determining module 420 further includes a second query information second determining submodule, wherein the second query information second determining submodule is configured to determine preset query information corresponding to the query content category as the second query information.

[0167] Based on the above solution, the apparatus may optionally further include an interface database construction module. The interface database construction module is configured to, before inputting the second query information into the information query model, determine interface association information corresponding to the business interface based on the interface call association log and the interface information description document corresponding to the business interface, and construct an interface database based on the interface association information corresponding to the business interface; wherein the interface association information includes at least one of business description data, interface description information, interface fields, field description data, interface message samples, and interface test data.

[0168] The interface information query device provided in the embodiment of the present invention can execute the interface information query method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0169] Example 5

[0170] Figure 5 The structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0171] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0172] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0173] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the interface information query method.

[0174] In some embodiments, the interface information query method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the interface information query method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the interface information query method in any other appropriate manner (for example, by means of firmware).

[0175] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0176] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0177] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0178] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0179] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0180] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0181] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-mentioned functions defined in the method of the embodiment of the present invention are performed.

[0182] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0183] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. An interface information query method, characterized in that: include: In response to the information query request, obtaining first query information; wherein the first query information is used to describe an interface information query task for at least one service interface; Determine a query content category corresponding to the first query information, and determine second query information based on the query content category; wherein the second query information is used to prompt the information query model for content to be queried and / or expected output content of the information query model; The second query information is input into the information query model so that the information query model generates target feedback information according to the interface association information stored in the pre-established interface database, and the target feedback information is displayed based on the output information of the information query model.

2. The interface information query method according to claim 1, characterized in that: The determining of the query content category corresponding to the first query information includes: Determine the query content category corresponding to the first query information based on the first query information and the semantic recognition model; wherein the semantic recognition model is obtained by training the first machine learning model based on the sample query information corresponding to the sample interface and the expected content category corresponding to the sample query information.

3. The interface information query method according to claim 1, characterized in that: The determining of the query content category corresponding to the first query information includes: A query keyword in the first query information is determined, and a query content category corresponding to the first query information is determined based on the query keyword and a preset keyword corresponding to a preset content category.

4. The interface information query method according to claim 3, characterized in that: The determining the query content category corresponding to the first query information according to the query keyword and the preset keyword corresponding to the preset content category includes: Determining respectively the keyword matching degree between the preset keywords corresponding to each preset content category and the query keyword; wherein the keyword matching degree includes the number of keyword matches and / or keyword similarity; A query content category corresponding to the first query information is determined from a plurality of the preset content categories according to the keyword matching degree corresponding to each of the preset content categories.

5. The interface information query method according to claim 4, characterized in that: The keyword matching degree includes keyword similarity; and determining the query content category corresponding to the first query information from a plurality of preset content categories according to the keyword matching degree corresponding to each preset content category includes: Determining the category matching degree corresponding to the preset content category according to the keyword weight corresponding to each query keyword and the keyword similarity; A query content category corresponding to the first query information is determined from a plurality of the preset content categories according to the category matching degree corresponding to each of the preset content categories.

6. The interface information query method according to claim 4, characterized in that: The determining, from a plurality of preset content categories according to the keyword matching degree corresponding to each preset content category, a query content category corresponding to the first query information includes: determining, according to the keyword matching degree corresponding to each of the preset content categories, a candidate content category corresponding to the first query information from among the plurality of preset content categories; When the number of the candidate content category is only one, determining the candidate content category as the query content category corresponding to the first query information; In the case that there are multiple candidate content categories, the query content category corresponding to the first query information among the multiple candidate content categories is determined according to the preset priorities of the multiple candidate content categories and / or the query words adjacent to the query keyword in the first query information.

7. The interface information query method according to claim 1, characterized in that: The determining of the second query information according to the query content category includes: Determine the query keyword in the first query information, and determine a preset information template corresponding to the query content category; wherein the preset information template includes a keyword filling position; The query keyword is filled into the keyword filling position corresponding to the query keyword in the preset information template, and the filled preset information template is determined as the second query information.

8. The interface information query method according to claim 1, characterized in that: The determining of the second query information according to the query content category includes: The preset query information corresponding to the query content category is determined as the second query information.

9. The interface information query method according to claim 1, characterized in that: Before inputting the second query information into the information query model, the method further includes: According to the interface call association log corresponding to the business interface and the interface information description document, the interface association information corresponding to the business interface is determined respectively, and an interface database is constructed according to the interface association information corresponding to the business interface; wherein, the interface association information includes at least one of business description data, interface description information, interface field, field description data, interface message sample and interface test data.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the interface information query method according to any one of claims 1 to 9.

Images