Interface calling method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the field of data processing, and relates to an interface calling method and device, computer equipment and a storage medium, and the method comprises the following steps: carrying out natural language processing on user request text information to obtain request semantic representation and key entity information; performing semantic matching on the request semantic representation and the key entity information according to the interface knowledge graph to obtain a target program interface document; performing structured analysis and information extraction on the target program interface document to obtain document key information; performing code generation based on a code generation model according to the document key information and the request semantic representation to obtain a target calling code; testing the target calling code to obtain a code test result; and adjusting the code generation model according to a code test result, and generating an adjusted target code to be applied to the target program interface for interface calling. According to the method and the device, accurate and effective application program interface calling can be realized according to the request text input by the user.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, specifically to the field of digital medicine, and in particular to an interface calling method, device, computer equipment and storage medium. Background Art

[0002] In the field of financial technology and digital healthcare, with the rapid development of artificial intelligence and big data technology, the need to generate API call information based on natural language requests is becoming increasingly urgent. This is not limited to the automated operation of financial transaction systems, such as smart investment advisors and risk management, but also involves digital healthcare scenarios such as medical diagnosis assistance and medical record management. However, in the process of achieving this, there are significant technical challenges.

[0003] Users may make complex and varied requests in natural language, such as "Query the total amount of credit card spending this month" or "Get Zhang San's latest physical examination report." Accurately matching these requests to the corresponding API documents becomes the primary challenge, because API documents are often numerous and in different formats, ranging from RESTful to SOAP. In addition, even if the match is successful, how to accurately generate API call information is also a big challenge. Problems such as missing parameters, wrong call order, and data type mismatch frequently occur, resulting in API call results that are very different from expectations. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an interface calling method, apparatus, computer equipment and storage medium to solve the problem that it is impossible to perform accurate and effective application program interface calls based on input request text.

[0005] In order to solve the above technical problems, the embodiment of the present application provides an interface calling method, which adopts the following technical solution:

[0006] Acquire user request text information, perform natural language processing on the user request text information, and obtain request semantic representation and key entity information;

[0007] Perform semantic matching on the request semantic representation and the key entity information according to a pre-built interface knowledge graph to obtain a target program interface document;

[0008] Performing structured analysis and information extraction on the target program interface document to obtain key information of the document;

[0009] Generate code based on the document key information and the request semantic representation based on a pre-trained code generation model to obtain a target call code;

[0010] Performing static analysis and dynamic testing on the target calling code to obtain code testing results;

[0011] The code generation model is adjusted according to the code test result to obtain a valid code generation model, and an adjusted target code is generated according to the valid code generation model, and the adjusted target code is applied to a target program interface for interface calling.

[0012] Furthermore, the step of performing natural language processing on the user request text information to obtain the request semantic representation and key entity information specifically includes:

[0013] Performing word segmentation processing on the user request text information based on a preset word segmentation algorithm to obtain request keywords;

[0014] Performing part-of-speech tagging on the request keyword based on a pre-built part-of-speech tagging model to obtain a tagged keyword;

[0015] Performing dependency analysis on the annotated keywords to obtain keyword dependency relationships;

[0016] Constructing a semantic representation graph according to the request keywords and the keyword dependencies, and using the semantic representation graph as the request semantic representation;

[0017] Key entity recognition is performed on the semantic representation graph to obtain the key entity information.

[0018] Furthermore, the step of performing semantic matching on the request semantic representation and the key entity information according to the pre-built interface knowledge graph to obtain the target program interface document specifically includes:

[0019] Extracting a semantic vector representation of a corresponding node from the interface knowledge graph according to the key entity information;

[0020] Calculating the similarity between the semantic vector representation and the request semantic representation to obtain a similarity score;

[0021] Sort the nodes in the interface knowledge graph according to the similarity scores to obtain the most relevant target nodes;

[0022] The target program interface document is extracted from a preset document database according to the most relevant target node.

[0023] Furthermore, the step of performing structured parsing and information extraction on the target program interface document to obtain key information of the document specifically includes:

[0024] Preprocessing the target program interface document to obtain a valid program interface document;

[0025] Performing semantic analysis on the valid program interface document to obtain key sentences and key paragraphs of the document;

[0026] The key sentences and the key paragraphs of the document are structurally represented to obtain the key information of the document.

[0027] Furthermore, the step of performing code generation based on the pre-trained code generation model according to the document key information and the request semantic representation to obtain the target call code specifically includes:

[0028] According to the request semantic representation, matching is performed in a predefined rule base to obtain parameter type matching rules, mandatory parameter checking rules, and return value processing rules;

[0029] Extracting a parameter list from the key information of the document, and performing type checking and conversion processing on the parameter list according to the parameter type matching rule to obtain a valid parameter list;

[0030] Check the valid parameter list according to the mandatory parameter checking rule to obtain valid parameter information;

[0031] Identify the target code type corresponding to the request semantic representation, and input the target code type and the valid parameter information into the code generation model to obtain an initial call code;

[0032] Add return value processing logic to the initial calling code according to the return value processing rule to obtain the target calling code.

[0033] Furthermore, the step of performing static analysis and dynamic testing on the target calling code to obtain code test results specifically includes:

[0034] Determining whether the syntax of the target calling code is correct according to a static analysis method;

[0035] If the syntax of the target calling code is correct, a preset test case set is obtained, and the test case set is executed to dynamically run the target calling code to obtain the code test result.

[0036] Furthermore, the step of adjusting the code generation model according to the code test result to obtain a valid code generation model specifically includes:

[0037] Obtaining a preset standard test result, and determining whether the code test result meets the standard test result;

[0038] If the code test result meets the standard test result, the code generation model corresponding to the code test result is used as the effective code generation model;

[0039] If the code test result does not conform to the standard test result, the difference item between the code test result and the standard test result is obtained, and correction information is extracted from a preset difference correction table according to the difference item, the code generation model is adjusted based on the correction information, and the adjusted code test result is re-obtained, and the steps of obtaining the difference item to adjusting the code generation model are continuously repeated until the adjusted code test result conforms to the standard test result, thereby obtaining the valid code generation model.

[0040] In order to solve the above technical problems, the embodiment of the present application further provides an interface calling device, which adopts the following technical solution:

[0041] An information processing module is used to obtain user request text information, perform natural language processing on the user request text information, and obtain request semantic representation and key entity information;

[0042] A semantic matching module, used to perform semantic matching on the request semantic representation and the key entity information according to a pre-built interface knowledge graph to obtain a target program interface document;

[0043] An information extraction module, used for performing structured analysis and information extraction on the target program interface document to obtain key information of the document;

[0044] A code generation module, used to generate code according to the document key information and the request semantic representation based on a pre-trained code generation model to obtain a target call code;

[0045] A code testing module is used to perform static analysis and dynamic testing on the target calling code to obtain code testing results;

[0046] A code adjustment module is used to adjust the code generation model according to the code test result to obtain a valid code generation model, generate an adjustment target code according to the valid code generation model, and apply the adjustment target code to the target program interface for interface calling.

[0047] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0048] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the interface calling method as described in any one of the above when executing the computer-readable instructions.

[0049] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0050] A computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the interface calling method described in any one of the above items are implemented.

[0051] Compared with the prior art, the embodiment of the present application has the following beneficial effects: the embodiment obtains user request text information, performs natural language processing on the user request text information, obtains request semantic representation and key entity information; performs semantic matching on the request semantic representation and the key entity information according to the pre-built interface knowledge graph, obtains the target program interface document; performs structured parsing and information extraction on the target program interface document, obtains document key information; performs code generation based on the document key information and the request semantic representation based on the pre-trained code generation model, obtains the target call code; performs static analysis and dynamic testing on the target call code, obtains the code test result; adjusts the code generation model according to the code test result, obtains the effective code generation model, generates the adjusted target code according to the effective code generation model, and applies the adjusted target code to the target program interface for interface calling. Thus, accurate and effective application program interface calling is effectively realized according to the request text input by the user, so as to improve the accuracy and effectiveness of the interface calling. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0054] Figure 2 A flowchart of an embodiment of an interface calling method according to the present application;

[0055] Figure 3 yes Figure 2 A flowchart of a specific implementation of step S10;

[0056] Figure 4 yes Figure 2 A flowchart of a specific implementation of step S20;

[0057] Figure 5 yes Figure 2 A flowchart of a specific implementation of step S30;

[0058] Figure 6yes Figure 2 A flowchart of a specific implementation of step S40;

[0059] Figure 7 yes Figure 2 A flowchart of a specific implementation of step S50;

[0060] Figure 8 yes Figure 2 A flowchart of a specific implementation of step S60;

[0061] Fig. 9 is a structural diagram of an embodiment of an interface calling device according to the present application;

[0062] Fig.10 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0064] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor does it refer to non-related or alternative embodiments that are mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0065] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0066] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0067] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0068] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0069] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0070] It should be noted that the interface calling method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the interface calling device is generally set in the server / terminal device.

[0071] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0072] Continue to refer Figure 2 , shows a flow chart of an embodiment of the method for interface calling according to the present application. The interface calling method comprises the following steps:

[0073] Step S10, obtaining user request text information, performing natural language processing on the user request text information, and obtaining request semantic representation and key entity information;

[0074] In this embodiment, the user request text information is the request text submitted by the user in the form of natural language, for example, the query text paragraph entered by the user in the search engine. The natural language processing of the user request text information includes word segmentation, part-of-speech tagging, dependency analysis, and semantic representation graph construction. After the user request text information is subjected to the above-mentioned natural language processing, a request semantic representation showing the semantic information and structure of the user request and key entity information reflecting the corresponding important entities in the user request text information are obtained.

[0075] Step S20, semantically matching the request semantic representation and the key entity information according to the pre-built interface knowledge graph to obtain a target program interface document;

[0076] In this embodiment, the interface knowledge graph includes structured information such as the name, function description, parameter description, return value type, etc. of the application program interface (API). Its nodes represent entities such as API, parameters, return value type, and edges represent the relationship between these entities (such as which parameters the API contains, what are the types of parameters, etc.). Semantic matching is achieved by identifying the similarity between the semantic vector representation corresponding to the node in the interface knowledge graph and the request semantic representation. The most relevant target node obtained after semantic matching of the target program interface document is extracted in a preset document database for matching query.

[0077] Step S30, performing structured analysis and information extraction on the target program interface document to obtain key information of the document;

[0078] In this embodiment, information extraction refers to semantic analysis of the target program structure (API) document, and structured analysis refers to structured representation of the information obtained after semantic analysis. Among them, information extraction includes: text sentence segmentation, keyword extraction, semantic role labeling, key sentence and paragraph recognition, etc., and structured representation includes key information extraction, data cleaning, structured storage, etc. By performing structured analysis and information extraction including the above steps, the key information of the document can be effectively obtained.

[0079] Step S40, performing code generation based on the pre-trained code generation model according to the document key information and the request semantic representation to obtain a target call code;

[0080] In this embodiment, the pre-trained code generation model can adopt a sequence-to-sequence (Seq2Seq) model, such as the GPT model of Transformer. By taking the extracted document key information and request semantic representation as input and passing them to the pre-trained code generation model, the model first encodes the input information and then gradually decodes and generates the code to realize the sequence-to-sequence process and obtain the target call code.

[0081] Step S50, static analysis and dynamic testing are performed on the target calling code to obtain code testing results;

[0082] In this embodiment, static analysis is a method of discovering potential problems by checking the syntax, structure, data flow, control flow and other information of the code without executing the code, wherein static analysis can be implemented by static analysis tools. Dynamic testing is a method of verifying the function, performance and stability of the code by executing the code, which executes the target calling code through pre-designed test cases, thereby realizing the collection of code test results.

[0083] Step S60, adjusting the code generation model according to the code test result to obtain a valid code generation model, generating an adjusted target code according to the valid code generation model, and applying the adjusted target code to a target program interface for interface calling.

[0084] In this embodiment, the code generation model is adjusted according to the differences between the code test results and the standard test results. When the adjustment is completed, the document key information and the request semantic representation are input into the adjusted valid code generation model to obtain the adjusted target code, and then the adjusted target code is applied to the target program interface of the system to realize the interface call function.

[0085] In this embodiment, the above method can be applied to a medical service system, in which a target program interface in the system is called by inputting a request text. Specifically, in this embodiment, the medical service system can be one or more of a medical insurance system and a disease insurance system, the interface knowledge graph is a graph information containing an application program (API) interface of the medical system, the interface knowledge graph and the code generation model are stored in the medical insurance system and the disease insurance system and obtained from the database of the above system, the adjustment target code is generated by the above system through the method of this embodiment, and is applied to the target program interface of the above system for calling.

[0086] This embodiment obtains user request text information, performs natural language processing on the user request text information, obtains request semantic representation and key entity information; performs semantic matching on the request semantic representation and the key entity information according to the pre-built interface knowledge graph to obtain the target program interface document; performs structured parsing and information extraction on the target program interface document to obtain document key information; performs code generation based on the pre-trained code generation model according to the document key information and the request semantic representation to obtain the target call code; performs static analysis and dynamic testing on the target call code to obtain the code test result; adjusts the code generation model according to the code test result to obtain a valid code generation model, generates an adjusted target code according to the valid code generation model, and applies the adjusted target code to the target program interface for interface calling. This effectively realizes accurate and effective application program interface calling according to the request text input by the user, so as to improve the accuracy and effectiveness of interface calling.

[0087] refer to Figure 3 In some optional implementations of this embodiment, step S10 includes the following steps:

[0088] Step S101, performing word segmentation processing on the user request text information based on a preset word segmentation algorithm to obtain request keywords;

[0089] In this embodiment, the preset word segmentation algorithm can adopt a word segmentation algorithm based on a dictionary, such as a maximum matching method, by pre-building a dictionary containing common words, and then scanning the text of the user's request text information from left to right, each time trying to match the longest word starting from the current position and not exceeding the preset maximum length. If the match is successful, the word is used as part of the word segmentation result, and the matching continues from the next character; if the match fails, the matching length is gradually reduced until a matching word is found or the minimum matching length (usually 1 character) is reached. When the above matching steps are completed, the request keyword is obtained.

[0090] Step S102, performing part-of-speech tagging on the request keyword based on a pre-built part-of-speech tagging model to obtain a tagged keyword;

[0091] In this embodiment, the pre-built part-of-speech tagging model can adopt a hidden Markov model (HMM), and use a labeled corpus (i.e., text with known vocabulary and its corresponding part-of-speech) to train the HMM model. The step of part-of-speech tagging based on the HMM model includes defining a state set: in the HMM model, each state corresponds to a part-of-speech. Therefore, it is necessary to define a state set containing all possible parts of speech. Define an observation set: The observation set contains all possible vocabulary. Initialize model parameters: Use the trained HMM model parameters. Calculate the optimal path: For a given request keyword sequence, use a dynamic programming method such as the Viterbi algorithm to calculate the most likely part-of-speech tagging sequence (i.e., the optimal path). In this process, it is necessary to calculate the probability of each state (part-of-speech) at each position, and select the path with the highest probability as the final part-of-speech tagging result. Generate annotation keywords: Combine the calculated part-of-speech tagging sequence with the request keyword sequence to generate an annotation keyword list, each annotation keyword contains the original vocabulary and the corresponding part-of-speech tagging.

[0092] Step S103, performing dependency analysis on the annotated keywords to obtain keyword dependency relationships;

[0093] In the present embodiment, dependency analysis is the task of identifying the dependency relationship between words in a sentence. Dependency analysis can adopt a rule-based analysis method. The steps of dependency analysis of the annotated keywords specifically include traversing the annotated keyword list and trying to match each word with the rules in the rule set. When a word successfully matches a rule, a dependency relationship between the word and its dependent words is constructed according to the definition of the rule. The dependency relationship includes determining the type of dependency relationship (such as subject-predicate relationship, verb-object relationship, etc.) and the dependency direction (such as which word depends on which word). The dependency analysis steps are used to perform dependency analysis on the annotated keywords to obtain keyword dependencies.

[0094] Step S104, constructing a semantic representation graph according to the request keywords and the keyword dependencies, and using the semantic representation graph as the request semantic representation;

[0095] In this embodiment, request keywords are used as nodes of the semantic representation graph, and keyword dependencies are used as edges of the semantic representation graph to construct a graph structure representation representing the semantic structure of user requests, which is a semantic representation graph.

[0096] Step S105, performing key entity recognition on the semantic representation graph to obtain the key entity information.

[0097] In this embodiment, the key entity recognition algorithm is used to identify the nodes (i.e., request keywords) in the semantic representation graph to obtain words or phrases with specific meanings and importance, which are key entity information. The key entity recognition algorithm can adopt a rule-based method to match each node in the semantic representation graph by building a rule library with lexical rules, syntactic rules, context rules, etc. to identify key entity information.

[0098] This embodiment performs word segmentation processing on the user request text information based on a preset word segmentation algorithm to obtain request keywords; performs part-of-speech tagging on the request keywords based on a pre-built part-of-speech tagging model to obtain tag keywords; performs dependency analysis on the tag keywords to obtain keyword dependencies; constructs a semantic representation graph based on the request keywords and the keyword dependencies, and uses the semantic representation graph as the request semantic representation; performs key entity recognition on the semantic representation graph to obtain the key entity information. This effectively realizes the extraction of the request semantic representation and key entity information based on the keyword part-of-speech and dependency relationships of the user request text information, so as to facilitate the subsequent semantic matching processing.

[0099] refer to Figure 4 In some optional implementations of this embodiment, step S20 includes the following steps:

[0100] Step S201, extracting a semantic vector representation of a corresponding node from the interface knowledge graph according to the key entity information;

[0101] In this embodiment, the extraction of semantic vector representation includes knowledge graph node positioning and semantic vector extraction, wherein knowledge graph node positioning includes node search: in the interface knowledge graph, use key entity information as query conditions to search for nodes that match it, which can be achieved by matching the labels, attributes or relationships of the nodes in the graph. Node confirmation: from the search results, confirm the node that best matches the key entity information based on contextual information or additional verification steps. Semantic vector extraction includes vector representation selection: on the confirmed node, select or calculate its semantic vector representation, and the semantic vector representation of the node can be obtained by using a pre-trained word vector model (such as Word2Vec, BERT, etc.) or graph embedding technology (such as TransE, DeepWalk, etc.).

[0102] Step S202, calculating the similarity between the semantic vector representation and the request semantic representation to obtain a similarity score;

[0103] In this embodiment, the cosine similarity is calculated for the semantic vector representation and the request semantic representation to obtain the corresponding similarity score. Cosine similarity is a commonly used measurement method that evaluates the similarity of two vectors by calculating the cosine value of the angle between them in a multidimensional space. Before calculating the cosine similarity, the vectors usually need to be normalized to ensure that they have the same scale when calculating. The normalization formula is: V ^ =V / ||V||, where||V|| is the modulus (length) of the vector. The formula for calculating cosine similarity is: cos(θ)=V ^ sem·V ^ req / ∥V ^ sem∥∥V ^ req∥. However, since the vector has been normalized, the modulus is 1, and the formula can be simplified to: cos(θ)=V ^ sem·V ^ req. Here, the dot product (·) represents the sum of the products of the corresponding elements of the two vectors. The value range of the cosine similarity obtained after the above calculation is [-1,1], where the closer the value is to 1, the more similar the two vectors are in terms of semantics; the closer the value is to -1, the more opposite the two vectors are in terms of semantics; and the closer the value is to 0, the more independent or irrelevant the two vectors are in terms of semantics.

[0104] Step S203, sorting the nodes in the interface knowledge graph according to the similarity scores to obtain the most relevant target node;

[0105] In this embodiment, the calculated similarity scores corresponding to the nodes are sorted from high to low to obtain a similarity score sorting table, and then the first similarity score with the highest score is selected from the similarity score sorting table, and the node corresponding to the first similarity score is determined as the most relevant target node.

[0106] Step S204: extracting the target program interface document from a preset document database according to the most relevant target node.

[0107] In this embodiment, the preset document database is a preset database storing detailed documents of various program interfaces. According to the information of the most relevant target node, a traversal query is performed in the preset document database as a query condition to extract the corresponding target program interface document.

[0108] In this embodiment, the semantic vector representation of the corresponding node is extracted from the interface knowledge graph according to the key entity information; the similarity between the semantic vector representation and the request semantic representation is calculated to obtain a similarity score; the nodes in the interface knowledge graph are sorted according to the similarity score to obtain the most relevant target node; and the target program interface document is extracted from the preset document database according to the most relevant target node. Thus, the effective acquisition of the target program structure document is realized, which facilitates the subsequent steps of structured parsing and information extraction.

[0109] Reference Figure 5 , in some optional implementation manners of this embodiment, step S30 includes the following steps:

[0110] Step S301, preprocess the target program interface document to obtain an effective program interface document;

[0111] In this embodiment, the preprocessing of the target program interface document includes denoising: removing irrelevant content in the document. Formatting: unifying the layout and format of the document to ensure the clarity and consistency of information. Removing stop words: removing common words that contribute less to the key information of the document, such as "of", "is", etc.

[0112] Step S302, perform semantic analysis on the effective program interface document to obtain the key sentences and key paragraphs of the document;

[0113] In this embodiment, the semantic analysis includes: text sentence segmentation, keyword extraction, semantic role labeling, key sentence and paragraph recognition, etc. Among them, sentence segmentation is: splitting the document into independent sentences for subsequent analysis. Keyword extraction is: using natural language processing technology to extract keywords in the document, which are usually closely related to the functions, parameters, return values, etc. of the interface. Semantic role labeling is: analyzing the semantic relationships in the sentence to identify key components such as the subject, predicate, object, etc., and their logical relationships. Key sentence and paragraph recognition is: based on the results of keyword and semantic role labeling, identifying the sentences and paragraphs containing key information. Through the above semantic analysis steps, the key sentences and key paragraphs of the document can be effectively obtained.

[0114] Step S303, perform a structured representation on the key sentences and key paragraphs of the document to obtain the key information of the document.

[0115] In this embodiment, structured representation includes key information extraction, data cleaning, structured storage, etc. Information extraction is: extracting key information such as interface name, function description, parameter list, return value type, etc. from key sentences and paragraphs. Data cleaning is: verifying and cleaning the extracted information to ensure the accuracy and consistency of the data. Structured storage is: storing the cleaned information in a structured manner, such as JSON, XML and other formats, for subsequent use. By performing structured representation processing including the above steps on the key sentences and key paragraphs of the document, the key information of the document can be effectively obtained.

[0116] This embodiment obtains a valid program interface document by preprocessing the target program interface document; performs semantic analysis on the valid program interface document to obtain document key sentences and document key paragraphs; and performs structured representation on the document key sentences and document key paragraphs, thereby effectively obtaining document key information that structurally represents the key sentences and key paragraphs included in the target program structure document, so as to facilitate subsequent code generation processing.

[0117] Continue to refer Figure 6 In some optional implementations of this embodiment, step S40 includes the following steps:

[0118] Step S401, matching is performed in a predefined rule base according to the request semantic representation to obtain parameter type matching rules, mandatory parameter checking rules, and return value processing rules;

[0119] In this embodiment, the request semantic representation is used as a query condition to traverse and match in a predefined rule library to query and obtain parameter type matching rules, mandatory parameter checking rules, and return value processing rules. Parameter type matching rules: used to determine the data type that each parameter in the request should conform to. Required parameter checking rules: list the parameters that must be included in the request. Return value processing rules: describe how to process the return value of the called function or API.

[0120] Step S402, extracting a parameter list from the key information of the document, and performing type checking and conversion processing on the parameter list according to the parameter type matching rule to obtain a valid parameter list;

[0121] In this embodiment, the key information of the document is read, and the information related to the parameter (including parameter name, type, description, default value, etc.) is identified from the read information through regular expressions, and then the identified parameter information is organized into a parameter list. The parameter list is a data structure (such as an array, a dictionary, or an object), in which each element represents a parameter. The parameter type matching rule is specifically a parameter type matching mapping table, and the parameter type matching mapping table is used to perform a type check on each parameter in the parameter list, which can be achieved by verifying whether the actual data type of the parameter matches the expected data type. The parameter type matching mapping table is used to convert the type of parameters that do not match the type, and the type conversion includes converting a string into an integer, a floating point number, a date, etc.

[0122] Step S403, checking the valid parameter list according to the mandatory parameter checking rule to obtain valid parameter information;

[0123] In this embodiment, the step of checking the valid parameter list includes traversing the parameter list: traversing each parameter in the valid parameter list to check whether it is a required parameter. Matching required parameters: For each required parameter, check whether it exists in the valid parameter list. If the parameter exists, further check whether its value meets the restrictions defined in the rule (such as data type, value range, etc.). Record missing or non-compliant parameters: If it is found that a required parameter does not exist in the valid parameter list, or its value does not meet the rule requirements, record this error. Filter valid parameters: Based on the results of the required parameter check, filter out missing or non-compliant parameters from the valid parameter list, and use the remaining parameters as valid parameter information.

[0124] Step S404, identifying the target code type corresponding to the request semantic representation, and inputting the target code type and the valid parameter information into the code generation model to obtain an initial call code;

[0125] In this embodiment, semantic analysis is performed on the request semantic representation to understand the intent of the request, and then a matching target code type is searched in a predefined code type mapping table or rule base according to the understood intent, wherein the target code type includes a programming language (such as Python, Java, JavaScript, etc.), a framework (such as Django, Spring, etc.) or a specific API calling method. By constructing an input data structure containing target code type and valid parameter information, and inputting the input data structure into a code generation model to obtain the initial calling code output by the model, the code generation model can use a pre-trained sequence to sequence (Seq2Seq) model, which is a model commonly used in natural language processing tasks, which can convert a sequence (such as text) into another sequence (such as code), wherein the sequence to sequence model can be specifically trained using a Transformer-based model (such as GPT).

[0126] Step S405: adding return value processing logic to the initial calling code according to the return value processing rule to obtain the target calling code.

[0127] In this embodiment, according to the return value processing rules, the initial call code is expanded to add appropriate return value processing logic, wherein the return value processing logic includes error handling, result parsing, data conversion, etc. After the above return value processing logic is added to the initial call code, the final target call code is obtained.

[0128] This embodiment obtains parameter type matching rules, mandatory parameter checking rules, and return value processing rules by matching in a predefined rule library according to the request semantic representation; extracts a parameter list from the document key information, and performs type checking and conversion processing on the parameter list according to the parameter type matching rules to obtain a valid parameter list; checks the valid parameter list according to the mandatory parameter checking rules to obtain valid parameter information; identifies the target code type corresponding to the request semantic representation, and inputs the target code type and the valid parameter information into the code generation model to obtain an initial call code; adds return value processing logic to the initial call code according to the return value processing rules, thereby effectively obtaining the target call code generated based on the document key information and the request semantic representation, so as to improve the accuracy and effectiveness of the target call code and facilitate subsequent static analysis and dynamic test processing.

[0129] Continue to refer Figure 7 In some optional implementations of this embodiment, step S50 includes the following steps:

[0130] Step S501, judging whether the syntax of the target calling code is correct according to a static analysis method;

[0131] In the present embodiment, static analysis is a method for discovering potential errors by checking the source code of the code without executing the code. The static analysis step can be performed by a static analysis tool, and the static analysis performed by the static analysis tool includes word segmentation: dividing the code string into a series of tokens, which are usually keywords, identifiers, literals, operators and separators in the code. Construct a syntax tree: According to the results of lexical analysis, use grammar rules (usually defined in grammar files, such as BNF, EBNF, etc.) to construct a syntax tree (AST, abstract syntax tree) of the code. Verify the syntax tree: Check whether the syntax tree conforms to the grammar rules of the target programming language. The syntax tree can be traversed to verify whether the type of each node, the number and type of subnodes, etc. are as expected. Verify the mark: Check whether each mark is legal, that is, whether they are valid components of the target programming language. Thereby effectively realizing the judgment of whether the target call code is correct.

[0132] Step S502, if the syntax of the target calling code is correct, a preset test case set is obtained, and the test case set is executed to dynamically run the target calling code to obtain the code test result;

[0133] In this embodiment, the test case set is a set of preset test cases, which should cover the main functions and boundary conditions of the code. By configuring the necessary test environment, including dependency libraries, database connections, file systems, etc., each test case in the test case set is executed using a test framework or tool. Each test case should contain input data and expected output. When executing each test case, the actual output and any exception or error information are recorded. The actual output is compared with the expected output to determine whether the test case passes. Based on the execution results of all test cases, the code test results are obtained. After obtaining the code test results, a code test result report can be generated based on the code test results. The test result report can include information such as the pass status of the test case, the failure reason (if any), and the code coverage.

[0134] Step S503, if the syntax of the target calling code is incorrect, the target calling code is input into a pre-trained syntax correction model for correction processing to obtain a corrected target substitute code, and whether the syntax of the corrected target calling code is correct is re-determined until the syntax of the corrected target calling code is correct.

[0135] In this embodiment, the grammar correction model can adopt a conditional random field (CRF) to annotate the grammatical errors of the collected sample codes (mark the location and type of the grammatical errors), and then train and optimize the CRF model based on the annotated sample codes to obtain a pre-trained grammar correction model.

[0136] This embodiment determines whether the syntax of the target call code is correct according to a static analysis method; if the syntax of the target call code is correct, a preset test case set is obtained, and the test case set is executed to dynamically run the target call code to obtain the code test result. If the syntax of the target call code is incorrect, the target call code is input into a pre-trained syntax correction model for correction processing to obtain a corrected target substitute code, and re-determines whether the syntax of the corrected target call code is correct until the syntax of the corrected target call code is correct. This achieves effective analysis and testing of the target call code to obtain the corresponding code test results, which facilitates the subsequent adjustment of the code generation model.

[0137] Continue to refer Figure 8 In some optional implementations of this embodiment, step S60 includes the following steps:

[0138] S601, obtaining a preset standard test result, and determining whether the code test result meets the standard test result;

[0139] In this embodiment, the standard test result is preset test result information. The various parameters in the standard test result correspond to the parameters of the code test result. The standard test result may include expected output: the output that the code should produce under specific input; performance indicators: such as execution time, memory usage, resource consumption, etc.; behavioral characteristics: such as whether the code throws specific exceptions, whether it handles all boundary conditions, etc.

[0140] S602, if the code test result meets the standard test result, taking the code generation model corresponding to the code test result as the effective code generation model;

[0141] In this embodiment, a code generation model whose code test results conform to standard test results is used as a valid code generation model to obtain a model that can effectively output qualified target calling code.

[0142] S603: If the code test result does not conform to the standard test result, the difference item between the code test result and the standard test result is obtained, and correction information is extracted from a preset difference correction table according to the difference item, and the code generation model is adjusted based on the correction information, and the adjusted code test result is re-obtained, and the steps of obtaining the difference item to adjusting the code generation model are continuously repeated until the adjusted code test result conforms to the standard test result, thereby obtaining the valid code generation model.

[0143] In this embodiment, the parameters of the code test results and the standard test results are compared one by one to identify the difference items, and then the correction information is extracted from the preset difference correction table according to the identified difference items, wherein the difference correction table can be a preset database or knowledge base containing common errors and their correction solutions. After the correction information containing the correction solution is obtained, the corresponding parameters and structure of the model are adjusted according to the correction information to obtain the adjusted code generation model. Then, continuous iteration is performed based on the adjusted code generation model so that the adjusted code generation model can eventually output the target call code that meets the standard test results.

[0144] This embodiment obtains a preset standard test result to determine whether the code test result meets the standard test result; if the code test result meets the standard test result, the code generation model corresponding to the code test result is used as the effective code generation model; if the code test result does not meet the standard test result, the difference item between the code test result and the standard test result is obtained, and correction information is extracted from a preset difference correction table according to the difference item, the code generation model is adjusted based on the correction information, and the adjusted code test result is obtained again, and the steps of obtaining the difference item to adjusting the code generation model are continuously repeated until the adjusted code test result meets the standard test result, and the effective code generation model is obtained. In this way, the code generation model is accurately adjusted according to the difference item between the code test result and the standard test result, so as to improve the adjustment efficiency of the code generation model, and obtain an effective code generation model that can output the target call code that meets the standard test result.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0146] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0147] Further references Fig. 9 , as a response to the above Figure 1 The present application provides an embodiment of an interface calling device, and the device embodiment is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0148] like Fig. 9 As shown, the interface calling device 700 described in this embodiment includes: an information processing module 701, a semantic matching module 702, an information extraction module 703, a code generation module 704, a code testing module 705, and a code adjustment module 706. Among them:

[0149] The information processing module 701 is used to obtain user request text information, perform natural language processing on the user request text information, and obtain request semantic representation and key entity information;

[0150] A semantic matching module 702 is used to perform semantic matching on the request semantic representation and the key entity information according to a pre-built interface knowledge graph to obtain a target program interface document;

[0151] The information extraction module 703 is used to perform structured analysis and information extraction on the target program interface document to obtain key information of the document;

[0152] A code generation module 704 is used to generate code according to the document key information and the request semantic representation based on a pre-trained code generation model to obtain a target call code;

[0153] The code testing module 705 is used to perform static analysis and dynamic testing on the target calling code to obtain code testing results;

[0154] The code adjustment module 706 is used to adjust the code generation model according to the code test result to obtain a valid code generation model, generate an adjustment target code according to the valid code generation model, and apply the adjustment target code to the target program interface for interface calling.

[0155] By adopting the above-mentioned interface calling device, this embodiment can obtain user request text information, perform natural language processing on the user request text information, obtain request semantic representation and key entity information; perform semantic matching on the request semantic representation and the key entity information according to the pre-built interface knowledge graph to obtain the target program interface document; perform structured parsing and information extraction on the target program interface document to obtain document key information; perform code generation based on the pre-trained code generation model according to the document key information and the request semantic representation to obtain the target call code; perform static analysis and dynamic testing on the target call code to obtain the code test result; adjust the code generation model according to the code test result to obtain a valid code generation model, and generate an adjusted target code according to the valid code generation model, and apply the adjusted target code to the target program interface for interface calling. Thus, accurate and effective application program interface calling is effectively realized according to the request text input by the user, so as to improve the accuracy and effectiveness of interface calling.

[0156] To solve the above technical problems, the present application also provides a computer device. Fig.10 , Fig.10 This is a basic structural block diagram of the computer device in this embodiment.

[0157] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 8 with components 81-83, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0158] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0159] The memory 81 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 8. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions of the interface calling method, etc. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0160] The processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run computer-readable instructions stored in the memory 81 or process data, such as computer-readable instructions for running the interface calling method.

[0161] The network interface 83 may include a wireless network interface or a wired network interface. The network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0162] By adopting the above-mentioned computer device, this embodiment can obtain user request text information, perform natural language processing on the user request text information, obtain request semantic representation and key entity information; perform semantic matching on the request semantic representation and the key entity information according to the pre-built interface knowledge graph to obtain the target program interface document; perform structured parsing and information extraction on the target program interface document to obtain document key information; perform code generation based on the pre-trained code generation model according to the document key information and the request semantic representation to obtain the target call code; perform static analysis and dynamic testing on the target call code to obtain the code test result; adjust the code generation model according to the code test result to obtain a valid code generation model, and generate an adjusted target code according to the valid code generation model, and apply the adjusted target code to the target program interface for interface calling. Thus, accurate and effective application program interface calling is effectively realized according to the request text input by the user, so as to improve the accuracy and effectiveness of interface calling.

[0163] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the interface calling method as described above.

[0164] By adopting the above-mentioned computer-readable storage medium, this embodiment can obtain user request text information, perform natural language processing on the user request text information, obtain request semantic representation and key entity information; perform semantic matching on the request semantic representation and the key entity information according to the pre-built interface knowledge graph to obtain the target program interface document; perform structured parsing and information extraction on the target program interface document to obtain document key information; perform code generation based on the pre-trained code generation model according to the document key information and the request semantic representation to obtain the target call code; perform static analysis and dynamic testing on the target call code to obtain the code test result; adjust the code generation model according to the code test result to obtain a valid code generation model, and generate an adjusted target code according to the valid code generation model, and apply the adjusted target code to the target program interface for interface calling. Thus, accurate and effective application program interface calls can be effectively implemented according to the request text input by the user to improve the accuracy and effectiveness of interface calls.

[0165] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0166] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

[0167] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

Claims

1. An interface calling method, characterized in that: The steps include: Acquire user request text information, perform natural language processing on the user request text information, and obtain request semantic representation and key entity information; Perform semantic matching on the request semantic representation and the key entity information according to a pre-built interface knowledge graph to obtain a target program interface document; Performing structured analysis and information extraction on the target program interface document to obtain key information of the document; Generate code based on the document key information and the request semantic representation based on a pre-trained code generation model to obtain a target call code; Performing static analysis and dynamic testing on the target calling code to obtain code testing results; The code generation model is adjusted according to the code test result to obtain a valid code generation model, and an adjusted target code is generated according to the valid code generation model, and the adjusted target code is applied to a target program interface for interface calling.

2. The interface calling method according to claim 1, characterized in that: The step of performing natural language processing on the user request text information to obtain the request semantic representation and key entity information specifically includes: Performing word segmentation processing on the user request text information based on a preset word segmentation algorithm to obtain request keywords; Performing part-of-speech tagging on the request keyword based on a pre-built part-of-speech tagging model to obtain a tagged keyword; Performing dependency analysis on the annotated keywords to obtain keyword dependency relationships; Constructing a semantic representation graph according to the request keywords and the keyword dependencies, and using the semantic representation graph as the request semantic representation; Key entity recognition is performed on the semantic representation graph to obtain the key entity information.

3. The interface calling method according to claim 1, characterized in that: The step of performing semantic matching on the request semantic representation and the key entity information according to the pre-built interface knowledge graph to obtain the target program interface document specifically includes: Extracting a semantic vector representation of a corresponding node from the interface knowledge graph according to the key entity information; Calculating the similarity between the semantic vector representation and the request semantic representation to obtain a similarity score; Sort the nodes in the interface knowledge graph according to the similarity scores to obtain the most relevant target nodes; The target program interface document is extracted from a preset document database according to the most relevant target node.

4. The interface calling method according to claim 1, characterized in that: The step of performing structural analysis and information extraction on the target program interface document to obtain key information of the document specifically includes: Preprocessing the target program interface document to obtain a valid program interface document; Performing semantic analysis on the valid program interface document to obtain key sentences and key paragraphs of the document; The key sentences and the key paragraphs of the document are structurally represented to obtain the key information of the document.

5. The interface calling method according to claim 1, characterized in that: The step of performing code generation based on the pre-trained code generation model according to the document key information and the request semantic representation to obtain the target call code specifically includes: According to the request semantic representation, matching is performed in a predefined rule base to obtain parameter type matching rules, mandatory parameter checking rules, and return value processing rules; Extracting a parameter list from the key information of the document, and performing type checking and conversion processing on the parameter list according to the parameter type matching rule to obtain a valid parameter list; Check the valid parameter list according to the mandatory parameter checking rule to obtain valid parameter information; Identify the target code type corresponding to the request semantic representation, and input the target code type and the valid parameter information into the code generation model to obtain an initial call code; Add return value processing logic to the initial calling code according to the return value processing rule to obtain the target calling code.

6. The interface calling method according to claim 1, characterized in that: The step of performing static analysis and dynamic testing on the target calling code to obtain code test results specifically includes: Determining whether the syntax of the target calling code is correct according to a static analysis method; If the syntax of the target calling code is correct, a preset test case set is obtained, and the test case set is executed to dynamically run the target calling code to obtain the code test result.

7. The interface calling method according to claim 1, characterized in that: The step of adjusting the code generation model according to the code test result to obtain a valid code generation model specifically includes: Obtaining a preset standard test result, and determining whether the code test result meets the standard test result; If the code test result meets the standard test result, the code generation model corresponding to the code test result is used as the effective code generation model; If the code test result does not conform to the standard test result, the difference item between the code test result and the standard test result is obtained, and correction information is extracted from a preset difference correction table according to the difference item, the code generation model is adjusted based on the correction information, and the adjusted code test result is re-obtained, and the steps of obtaining the difference item to adjusting the code generation model are continuously repeated until the adjusted code test result conforms to the standard test result, thereby obtaining the valid code generation model.

8. An interface calling device, characterized in that: include: An information processing module is used to obtain user request text information, perform natural language processing on the user request text information, and obtain request semantic representation and key entity information; A semantic matching module, used to perform semantic matching on the request semantic representation and the key entity information according to a pre-built interface knowledge graph to obtain a target program interface document; An information extraction module, used for performing structured analysis and information extraction on the target program interface document to obtain key information of the document; A code generation module, used to generate code according to the document key information and the request semantic representation based on a pre-trained code generation model to obtain a target call code; A code testing module is used to perform static analysis and dynamic testing on the target calling code to obtain code testing results; A code adjustment module is used to adjust the code generation model according to the code test result to obtain a valid code generation model, generate an adjustment target code according to the valid code generation model, and apply the adjustment target code to the target program interface for interface calling.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the interface calling method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the interface calling method according to any one of claims 1 to 7 are implemented.

Images