AI agent real-time data verification method and system based on dynamic mapping, medium, program and terminal

Abstract

According to the method, the dynamic mapping table is constructed by using the historical data, the historical input data and the historical output data are collected, and the one-to-one correspondence relation is established with the mapping identifiers. When the real-time input data is obtained, the system can judge which category set the real-time input data belongs to by matching the mapping identifier, and judge in combination with the characteristic range of the historical input data corresponding to the set, so as to determine whether the real-time input data conforms to the characteristic mode of the category or not. After real-time input data is obtained, the system can generate corresponding real-time output data and determine which category set the output belongs to through the matched mapping identifier. Then, the system compares the result range or mode of the real-time output data with the result range or mode of the historical output data in the category set to determine whether the result range or mode accords with the output expectation of the category. Therefore, the input and output accuracy, stability and business controllability of the AI agent in the operation process are improved.

Description

Technical Field

[0001] The present application relates to the field of AI agents, and in particular to a method, system, medium, program and terminal for real-time data verification of AI agents based on dynamic mapping. Background Art

[0002] With the rapid development of artificial intelligence technology, AI agents have been widely used in many fields such as natural language processing and decision support. However, the consistency and reliability of their input and output are becoming increasingly prominent. The input of AI agents usually comes from multimodal data provided by users, such as text and voice. However, their output results are easily affected by many factors, including the limitations of model training data, defects in algorithm design, and uncertainty in the external environment. The combined effect of these factors may cause the output results to be biased, inconsistent, or even confusing.

[0003] At present, the verification methods for AI agents mainly focus on the training phase, while the verification of input and output during runtime is obviously insufficient. The verification methods in the runtime phase mainly include static rule matching and fixed data set comparison. Static rule matching verifies input and output based on preset rules, but these rules are often too rigid and difficult to adapt to complex and changeable actual application scenarios. Fixed data set verification compares the current output with historical data. Although it can ensure the consistency of the output to a certain extent, it lacks the ability to respond to real-time changes and cannot detect new abnormal situations in time. Both methods have obvious limitations when processing dynamic inputs, and it is difficult to meet the needs of reliable application of AI in complex environments.

[0004] In addition, whether it is the evaluation in the training phase or the rule matching and data set verification in the operation phase, the existing technology has serious deficiencies in the traceability and explainability of AI output. It is difficult for users to judge whether the results generated by AI meet expectations, and it is impossible to trace the specific basis for AI to make a certain decision. This not only reduces the credibility of AI in high-risk scenarios, but also restricts its further application in more fields.

[0005] Therefore, an efficient, flexible and dynamically adaptable input-output verification mechanism is needed to improve the stability and security of AI in practical applications. Summary of the invention

[0006] In view of the shortcomings of the prior art mentioned above, the purpose of the present application is to provide an AI agent real-time data verification method, system, medium, program and terminal based on dynamic mapping to solve the above problems.

[0007] To achieve the above and other related objectives, the first aspect of this application provides a method for real-time data verification of an AI agent based on dynamic mapping, including: obtaining a number of historical data of the AI agent, where the historical data includes historical input data and its corresponding historical output data; extracting features from each historical input data to obtain its corresponding input feature set; using a clustering algorithm to group historical input data with similar input feature sets and their corresponding historical output data into a category set, and assigning a unique mapping identifier to each category set; establishing a dynamic mapping table according to all category sets and their corresponding mapping identifiers; statistically analyzing the feature range of historical input data and the result range or pattern of historical output data within each category set; obtaining the real-time input data of the AI agent; extracting the features of the real-time input data to obtain its corresponding input feature set; querying the dynamic mapping table for a matching mapping identifier according to the input feature set corresponding to the features of the real-time input data, and determining whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier. If not, it is determined that the real-time input data is abnormal.

[0008] In an embodiment of the first aspect of this application, according to the obtained real-time input data, the corresponding real-time output data is output, and it is determined whether the real-time output data conforms to the result range or pattern of the output data within the category set corresponding to the matching mapping identifier in the dynamic mapping table. If not, it is determined that the real-time output data is abnormal.

[0009] In an embodiment of the first aspect of this application, when determining whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier, if the input feature set of the real-time input data does not belong to any category set in the existing dynamic mapping table, a new category set is created for the real-time data and its corresponding real-time output data, a unique mapping identifier is assigned, and the category set and its corresponding mapping identifier are incorporated into the dynamic mapping table.

[0010] In an embodiment of the first aspect of this application, the result range or pattern of the output data is comprehensively modeled through rule templates, vector space ranges, and multimodal matching logics to support unified verification of various types of output results such as structured text, natural language text, and images.

[0011] In an embodiment of the first aspect of this application, the input feature set includes numerical features, and / or text features, and / or categorical features.

[0012] In an embodiment of the first aspect of the present application, when performing feature extraction on historical input data and / or real-time input data respectively, feature enhancement is performed in combination with the context information of the historical input data and / or real-time input data, and / or interaction history, and / or user profile information.

[0013] To achieve the above object and other related objects, the second aspect of the present application provides a real-time data verification system for an AI intelligent agent based on dynamic mapping, including: a dynamic mapping table establishment module, configured to obtain a plurality of historical data of the AI intelligent agent, wherein the historical data includes historical input data and its corresponding historical output data; perform feature extraction on each historical input data respectively to obtain its corresponding input feature set; use a clustering algorithm to classify the historical input data with similar input feature sets and their corresponding historical output data into a category set, and assign a unique mapping identifier to each category set; establish a dynamic mapping table according to all category sets and their corresponding mapping identifiers; statistically analyze the feature range of the historical input data and the result range or pattern of the historical output data within each category set; a real-time data analysis module, configured to obtain the real-time input data of the AI intelligent agent; extract the features of the real-time input data to obtain its corresponding input feature set; query the matching mapping identifier in the dynamic mapping table according to the input feature set corresponding to the features of the real-time input data, and determine whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier, if not, determine that the real-time input data is abnormal.

[0014] To achieve the above object and other related objects, the third aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any one of the foregoing is implemented.

[0015] To achieve the above object and other related objects, the fourth aspect of the present application provides a computer program product, which includes computer program code, and when the computer program code runs on a computer, the computer is caused to implement the method described in any one of the foregoing.

[0016] To achieve the above object and other related objects, the fifth aspect of the present application provides an electronic terminal, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the method described in any one of the foregoing.

[0017] As described above, the present application has the following beneficial effects:

[0018] This application constructs a dynamic mapping table by using historical data, aggregates historical input data and output data, and establishes a one-to-one correspondence with mapping identifiers. When real-time input data is obtained, the system can determine which category set the real-time input data belongs to by matching the mapping identifier, and make a judgment in combination with the feature range of the historical input data corresponding to the set to determine whether the real-time input data conforms to the feature pattern of the category. If it conforms, it indicates that the input is reasonable and within the expected range, and the system can process it normally; if it does not conform, potential abnormal input can be detected in a timely manner, thereby improving the data stability, security, and response reliability of the AI agent during operation. Moreover, after obtaining the real-time input data, the system can generate corresponding real-time output data, and determine which category set the output should belong to through the matching mapping identifier. Subsequently, the system compares the real-time output data with the result range or pattern of the historical output data in the category set to determine whether it meets the output expectation of the category. If it conforms, it indicates that the current output is reasonable semantically or logically and can be regarded as a valid response; if it does not conform, potential output anomalies or model deviations can be identified in a timely manner, thereby improving the output accuracy, stability, and business controllability of the AI agent during operation. Brief Description of the Drawings

[0019] Figure 1 It shows a schematic flowchart of the real-time data verification method for an AI agent based on dynamic mapping in an embodiment of this application.

[0020] Figure 2 It shows a schematic flowchart of the real-time data verification method for an AI agent based on dynamic mapping in an embodiment of this application.

[0021] Figure 3 It shows a schematic structural diagram of the real-time data verification system for an AI agent based on dynamic mapping in an embodiment of this application.

[0022] Figure 4 It shows a schematic structural diagram of an electronic terminal in an embodiment of this application. Detailed Embodiment

[0023] The following uses specific specific examples to illustrate the implementation manners of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific implementation manners, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0024] In the embodiments of the present application, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and effects. For example, the first XX and the second XX are only used to distinguish different XX, and do not limit their sequence. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different.

[0025] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific manner.

[0026] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (s) or plural items (s). For example, at least one (item) of a, b or c can represent: a, b, c, a - b, a - c, b - c or a - b - c, where a, b, c can be single or multiple.

[0027] As Figure 1-2 shown, the first aspect of the present application provides a method for real - time data verification of an AI agent based on dynamic mapping, including:

[0028] S1: Obtain a number of historical data of the AI agent, where the historical data includes historical input data and its corresponding historical output data.

[0029] Preferably, the historical data can be sourced from user interaction logs, system call records or other forms of input - output samples recorded during the actual deployment of the AI agent. The historical input data includes natural language inputs of users, structured instructions, etc., and the output data is the response or operation result generated by the AI agent based on this input.

[0030] Preferably, historical data covering the main input types and output modes of the target application scenario are collected to ensure that subsequent modeling has sufficient representativeness and breadth. In practical applications, according to the specific task complexity and input diversity, no less than thousands to tens of thousands of input-output sample pairs can be collected. When new data cannot significantly improve the category clustering quality or mapping stability, the data volume can be regarded as basically meeting the modeling requirements.

[0031] S2: Feature extraction is performed on each historical input data respectively to obtain its corresponding input feature set.

[0032] It should be understood that when the historical input data and / or real-time input data are text data, feature extraction is directly performed. When they are voice data, the voice data is first converted into text data by ASR automatic speech recognition technology and then feature extraction is performed.

[0033] In an embodiment of the first aspect of the present application, when performing feature extraction on historical input data and / or real-time input data respectively, feature enhancement is performed by combining the context information, and / or interaction history, and / or user portrait information of the historical input data and / or real-time input data.

[0034] It should be understood that by introducing context information of the input data, user interaction history, user portrait information and other context-enhanced features, the limitations of a single input data in semantic expression can be effectively compensated. In practical applications, the user's current input is often closely related to their previous multi-round conversations, operation behaviors or long-term preferences. Feature extraction based only on the current input content may not accurately reflect their true intentions. By integrating the context dialogue content, semantic coherence can be retained; introducing the interaction history helps to identify the user's behavior pattern; combining user portrait information (such as domain preferences, common vocabulary styles, etc.) can improve the system's adaptability to individual differences. The fusion processing of the above information can significantly enhance the expression ability of the input features, improve the accuracy of merging the same categories in the clustering stage, and also help to improve the accuracy and robustness of the real-time input matching the historical categories, especially having significant advantages when facing semantic ambiguity or boundary inputs.

[0035] Preferably, after obtaining the input feature set of the historical input data, preprocessing is performed on the input feature set. Among them, the process of the preprocessing includes data cleaning and feature scaling. Data cleaning is to detect, correct or remove possible missing values and outliers in the input feature set to ensure the integrity and validity of the input data. Feature scaling is to normalize or standardize the original numerical features. For example, the feature values can be scaled to the interval [0,1], or standardized to a distribution with a mean of 0 and a variance of 1, to prevent features of different scales from causing interference in the matching calculation.

[0036] S3: Use a clustering algorithm to group historical input data with similar input feature sets and their corresponding historical output data into a category set, and assign a unique mapping identifier to each category set.

[0037] Preferably, the clustering algorithm can adopt methods such as K-means, DBSCAN, hierarchical clustering, etc., to group and classify historical input data with similar features, and associate the corresponding historical output results. Assign a unique mapping identifier to each clustered category set as the index basis for subsequent input-output matching and verification.

[0038] S4: Establish a dynamic mapping table based on all category sets and their corresponding mapping identifiers.

[0039] It should be understood that the dynamic mapping table is used to record the mapping relationship between historical input data, historical output data, and their category identifiers. This mapping table can be stored in a database, cache, or embedded data structure, and has the capabilities of querying and updating. It is the core data structure of the entire verification process.

[0040] S5: Statistically analyze the feature range of historical input data and the result range or pattern of historical output data within each category set.

[0041] It should be understood that by establishing the value boundaries and semantic distributions of the features of each historical input data to determine the feature range, and extracting the typical expressions or behavioral patterns of the corresponding output results, it constitutes the basis for subsequent comparison. The result range of historical output data can be modeled using methods such as rule templates, vector space ranges, example sets, etc., so as to adapt to different output forms.

[0042] S6: Obtain the real-time input data of the AI agent; extract the features of the real-time input data to obtain its corresponding input feature set.

[0043] It should be understood that when the AI agent receives new input, the system extracts its features and adopts the same feature extraction (and enhancement strategy) as the historical input data, so as to maintain the consistency and comparability of input features.

[0044] S7: Query the matching mapping identifier in the dynamic mapping table according to the input feature set corresponding to the features of the real-time input data.

[0045] In an embodiment of the first aspect of the present application, the input feature set includes numerical features, and / or text features, and / or categorical features.

[0046] Preferably, adopt corresponding matching strategies for different types of features:

[0047] When the system uses numerical features as the input feature set, matching is achieved by comparing the numerical features in the real-time input data with the numerical feature ranges in the category set corresponding to the mapping identifier. For example, the mapping table stipulates that ages between 18 and 30 years old form an input feature set, corresponding to the mapping identifier A. If the age feature value in the new data is 22 years old, it falls within this range, and it is initially determined that it may match the identifier A. The system predefines the value ranges of the numerical features covered by each category set in the dynamic mapping table as the basis for matching judgment. For example, the mapping table stipulates that input data with the "age" feature between 18 and 30 years old is classified into a certain input feature set, and the corresponding mapping identifier is A. When the system receives a new piece of real-time input data with the "age" field value of 22 years old, the system compares this value with the corresponding value range in the mapping table. Since 22 years old falls within the range of 18 - 30 years old, the numerical features of this real-time input data meet the range criteria set by category set A. Based on this, the system can initially determine that this data may match the category set represented by the mapping identifier A.

[0048] Preferably, to enhance the flexibility and accuracy of matching, the system can also be set according to business requirements: closed interval or open interval matching rules (such as whether to include boundary values); allowable numerical tolerance ranges (such as ±5% floating); and priority discrimination strategies (when multiple category sets are all matched, how to select the optimal match).

[0049] When using categorical features as the input feature set, the matching process is based on an exact match of the category values. That is, the categorical feature values carried in the real-time input data are directly compared with the category values included in each category set in the dynamic mapping table to determine their attribution relationships. For example, suppose the mapping table defines a certain category set that includes color feature values of "red", "blue", and "green", and associates this set with the mapping identifier B. At this time, if the color feature value in the real-time input data is "blue", it can be determined that this value is within the existing categorical input feature set in the mapping table, so it matches the category set represented by the identifier B, thus establishing an association relationship. In practical applications, categorical features can include but are not limited to: discrete attributes (such as gender: male / female, user type: ordinary / member / enterprise); label fields (such as product categories, failure types, behavior labels); multi-select or enumeration-type information (such as hobbies, industries, functional modules, etc.).

[0050] Preferably, the present invention supports both the matching of single-category feature values and the matching of multi-feature combinations. In a multi-feature scenario, the system will simultaneously examine whether multiple category fields satisfy the matching conditions of a certain category set. For example, if a certain category set stipulates that "gender is female and user type is member" corresponds to the mapping identifier C, the system will only determine its belonging identifier C on the premise that these two fields of the new data match simultaneously. Further, in addition, to improve flexibility, the system can support: partial matching (such as any value included in the multiple-choice field is considered a match); matching priority rules (select the optimal one when multiple category sets can be matched); and a matching fault tolerance mechanism (such as supporting synonymous value mapping: "female student" can be regarded as "female").

[0051] When using text-based features as the input feature set, a text similarity algorithm is usually used to match and judge the text content in the real-time input data with the existing text feature set in the mapping table. Due to the characteristics of text-based features such as openness, diverse expressions, and semantic ambiguity, it is impossible to directly perform precise matching like numerical or categorical features. Therefore, it is necessary to use a similarity algorithm to quantitatively compare texts that are semantically or literally similar. Preferably, text matching methods such as cosine similarity algorithm, word embedding similarity, and edit distance can be used to calculate the similarity between the real-time text and the historical text. For example, if the text feature corresponding to a certain category set in the mapping table is "unable to start the system", and the real-time input text is "cannot boot", although the surface words are different, their semantics are similar. After being calculated by the BERT model, the similarity is 0.87, which exceeds the system-set matching threshold of 0.8. Therefore, it can be determined that this real-time input should be classified into the "unable to start the system" category and associated with its corresponding mapping identifier.

[0052] It should be understood that in some scenarios, the mapping identifier (i.e., the category number) is not determined simply by feature similarity, numerical range, or exact matching, but is generated by a specific business logic or rule system. These rules are usually formulated based on domain knowledge, business processes, policy constraints, etc., and have clear judgment logic. Therefore, preferably, a matching rule is established, that is, for the case where the generation method of some mapping identifiers is driven by specific business rules, the system needs to preset a set of executable matching logic rules and apply them to the second feature set composed of real-time input data. Such rules are usually formulated based on business requirements, industry experience, or strategies, and have a clear conditional judgment structure, such as "if condition A and condition B are satisfied, then classify it as mapping identifier X". This rule-based mapping method is applicable to scenarios where it is difficult to accurately classify input features through a single similarity or range judgment, especially in systems with fixed business hierarchies, label divisions, and behavior rules, etc., and has wide applicability.

[0053] Preferably, the categorical features include keyword features, and the numerical features include semantic vector features.

[0054] It should be understood that keyword features are used to capture representative important words in the input data. Usually, through technical means such as word frequency statistics, TF-IDF, and named entity recognition (NER), the core expression content in the input is extracted, which helps to reflect the explicit semantic information of the input. Semantic vector features, on the other hand, map the input content to a low-dimensional semantic space through deep semantic modeling methods such as word embedding and sentence vectors, so as to capture the implicit semantic associations and context dependencies in the text. Keyword features focus on interpretability and keyword coverage, while semantic vector features emphasize overall semantic understanding and generalization ability.

[0055] S8: Determine whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier. If not, determine that the real-time input data is abnormal.

[0056] It should be understood that the input feature set of the real-time input data is compared with the feature range of the historical input data that has been modeled in the corresponding category set. The feature range may include keyword distribution, semantic vector space boundary, context semantic coverage range, etc. When the feature set of the real-time input data significantly deviates from this range in multiple dimensions, or cannot form an effective match with any existing category set, it indicates that the input is not covered by the known patterns of the current system and may belong to abnormal input, out-of-bounds requests, or new semantic scenarios. At this time, the system can determine that there are potential risks in this input, such as misleading questions, illegal content, requests outside the model's ability boundary, etc., and trigger a preset security response mechanism, such as alarm prompts, rejection processing, transfer to manual review, or recording samples to be learned, etc., to ensure the robustness and controllability of the AI system during operation. This mechanism can effectively prevent the AI model from generating incorrect responses or out-of-control behaviors when facing uncertain inputs and is a key part of improving the system's security and robustness.

[0057] In an embodiment of the first aspect of the present application, the following steps are further included:

[0058] S9: Output corresponding real-time output data according to the obtained real-time input data, and determine whether the real-time output data conforms to the result range or pattern of the output data within the category set corresponding to the mapping identifier that matches in the dynamic mapping table. If not, determine that the real-time output data is abnormal.

[0059] It should be understood that after the system generates the real-time output data, it compares the real-time output data with the result range or pattern of the historical output data within the category set corresponding to the mapping identifier matched in the dynamic mapping table. The result range or pattern can be modeled based on the semantic vector distribution, format template, keyword set, logical structure features of the historical output data, and even statistical models of multimodal expression methods such as images and audio. When the current output result significantly deviates from the output pattern of this category in terms of semantic expression, content structure, or output form, or contains unexpected content such as logical conflicts and semantic errors, the system can determine that this output is an abnormal result. Such an abnormality may mean that the model generates an unreasonable, misleading, or low-confidence response in the current context, or indicates that the input exceeds the output stable region of the model. The system can trigger an exception handling mechanism accordingly, such as recording the abnormal output, refusing to display it, outputting a warning message, or guiding to transfer to manual processing, so as to avoid the transmission of incorrect information or potential risks. This mechanism not only improves the controllability of the model's output and the response quality, but also provides basic support for the traceability and credibility of the model, and is an important link to ensure the safe and stable operation of the AI agent.

[0060] Preferably, the result range or pattern of the output data is comprehensively modeled through a rule template, a vector space range, and multimodal matching logic to support the unified verification of various types of output results such as structured text, natural language text, and images.

[0061] In an embodiment of the first aspect of the present application, the following steps are further included:

[0062] S10: When determining whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier, if the input feature set of the real-time input data does not belong to any category set in the existing dynamic mapping table, a new category set is created for the real-time data and its corresponding real-time output data, a unique mapping identifier is assigned, and the category set and its corresponding mapping identifier are incorporated into the dynamic mapping table.

[0063] It should be understood that during the process of matching and judging real-time input data, if the input feature set cannot effectively match the input feature range of any existing category set in the current dynamic mapping table, it indicates that the input represents a new input mode or scenario not covered by the system. To avoid misjudging such new inputs as anomalies and to enhance the system's adaptability to a dynamically changing environment, the system can register the input and its corresponding output as new data samples, automatically create a new category set, and assign a unique mapping identifier. The feature range and output mode of the newly created category set can be automatically generated based on the initial samples and can be continuously improved by continuously supplementing data during subsequent operations. By incorporating this new category set and its mapping identifier into the dynamic mapping table, the system can achieve self-expansion and learning, possess the ability to continuously absorb new scenarios and new semantic expressions, enhance its adaptability to input diversity and complexity, contribute to maintaining the coverage and effectiveness of the verification mechanism during long-term operation, and embody the dynamic and evolvable nature of the method.

[0064] As Figure 3 shown, the second aspect of the present application provides a real-time data verification system for an AI intelligent agent based on dynamic mapping, including: a dynamic mapping table establishment module for obtaining a number of historical data of the AI intelligent agent, where the historical data includes historical input data and its corresponding historical output data; respectively extracting features from each historical input data to obtain its corresponding input feature set; using a clustering algorithm to group historical input data with similar input feature sets and their corresponding historical output data into a category set, and assigning a unique mapping identifier to each category set; establishing a dynamic mapping table according to all category sets and their corresponding mapping identifiers; statistically analyzing the feature range of historical input data and the result range or mode of historical output data within each category set; a real-time data analysis module for obtaining real-time input data of the AI intelligent agent; extracting the features of the real-time input data to obtain its corresponding input feature set; querying for a matching mapping identifier in the dynamic mapping table according to the input feature set corresponding to the features of the real-time input data, and judging whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier, and if not, determining that the real-time input data is abnormal.

[0065] It should be understood that the specific processes of each module executing the above corresponding steps have been described in detail in the above method embodiments. For the sake of brevity, they will not be repeated here.

[0066] It should also be understood that the division of modules in the embodiments of the present application is illustrative, merely a logical function division, and there may be other division methods in actual implementation. In addition, each functional module in the various embodiments of the present application may be integrated in a processor, may exist alone physically, or two or more modules may be integrated in one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0067] The third aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any one of the foregoing is implemented.

[0068] The fourth aspect of the present application provides a computer program product, which includes computer program code, and when the computer program code runs on a computer, the computer implements the method described in any one of the foregoing.

[0069] As Figure 4 shown, the fifth aspect of the present application provides an electronic terminal, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the method described in any one of the foregoing. The electronic terminal includes: at least one processor 401, a memory 402, at least one network interface 403, and a user interface 405. Each component in the device is coupled together through a bus system 404. It can be understood that the bus system 404 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 404 also includes a power bus, a control bus, and a status signal bus.

[0070] Among them, the user interface 405 may include a display, a keyboard, a mouse, a trackball, a click gun, a button, a button, a touchpad, or a touch screen, etc.

[0071] It can be understood that the memory 402 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM, StaticRandom Access Memory), synchronous static random access memory (SSRAM, Synchronous StaticRandomAccess Memory). The memory described in the embodiments of the present invention is intended to include but not limited to these and any other suitable types of memories.

[0072] In the embodiments of the present invention, the memory 402 is used to store various types of data to support the operation of the electronic terminal 400. Examples of such data include: any executable programs for operating on the electronic terminal 400, such as the operating system 4021 and application programs 4022; the operating system 4021 includes various system programs, such as the framework layer, the core library layer, the driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application programs 4022 may include various application programs, such as a Media Player, a Browser, etc., for implementing various application services. Implementing the method provided by the embodiments of the present invention may be included in the application programs 4022.

[0073] The method disclosed in the above embodiments of the present invention may be applied to or implemented by the processor 401. The processor 401 may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method may be completed by the integrated logic circuit in hardware or instructions in software form in the processor 401. The above-mentioned processor 401 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 401 may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor 401 may be a microprocessor or any conventional processor, etc. Combining the steps of the accessory optimization method provided by the embodiments of the present invention may be directly embodied as being completed by the hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in the storage medium, and this storage medium is located in the memory. The processor reads the information in the memory and combines its hardware to complete the steps of the foregoing method.

[0074] In an exemplary embodiment, the electronic terminal 400 may be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs) for executing the foregoing method.

[0075] As used in this specification, the terms "component", "module", "system", etc. are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable, an execution thread, a program, and / or a computer. By way of illustration, both an application running on a computing device and the computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on one computer and / or distributed between two or more computers. In addition, these components may execute from various computer-readable media having various data structures stored thereon. A component may communicate, for example, by signals according to one or more data packets (e.g., data from two components interacting with another component in a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals) through local and / or remote processes.

[0076] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints of the technical solution. Skilled artisans may implement the described functionality in different ways for each particular application, but such implementation should not be regarded as exceeding the scope of this application.

[0077] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0078] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other may be through some interfaces, and the indirect couplings or communication connections of devices or units may be in electrical, mechanical, or other forms.

[0079] The unit described as a separation component may or may not be physically separated, and the component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] In addition, each functional unit in various embodiments of the present application may be integrated in a processing unit, may exist physically alone for each unit, or two or more units may be integrated in one unit.

[0081] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server, data center, etc. that contains one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a high-definition digital video disc (DVD)), or a semiconductor medium (for example, a solid state disk (SSD), etc.).

[0082] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0083] As described above, the above are only the specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by this application and should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0084] In summary, this application effectively overcomes various disadvantages in the prior art and has high industrial utilization value.

[0085] The above embodiments are only used to illustrate the principle and its effects of this application by way of example, rather than to limit this application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by this application should still be covered by the claims of this application.

Claims

1. A real-time data verification method for an AI agent based on dynamic mapping, characterized in that, Including: Obtain a number of historical data of the AI agent, where the historical data includes historical input data and its corresponding historical output data; Extract features from each historical input data respectively to obtain its corresponding input feature set; Use a clustering algorithm to group the historical input data with similar input feature sets and their corresponding historical output data into a category set, and assign a unique mapping identifier to each category set; Establish a dynamic mapping table according to all category sets and their corresponding mapping identifiers; Statistically analyze the feature range of the historical input data and the result range or pattern of the historical output data within each category set; Obtain the real-time input data of the AI agent; Extract the features of the real-time input data to obtain its corresponding input feature set; Query the matching mapping identifier in the dynamic mapping table according to the input feature set corresponding to the features of the real-time input data, and determine whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier. If not, determine that the real-time input data is abnormal.

2. The real-time data verification method for an AI agent based on dynamic mapping according to claim 1, wherein Output the corresponding real-time output data according to the obtained real-time input data, and determine whether the real-time output data conforms to the result range or pattern of the output data within the category set corresponding to the matching mapping identifier in the dynamic mapping table. If not, determine that the real-time output data is abnormal.

3. A real-time data verification method for an AI agent based on dynamic mapping according to claim 1, characterized in that, When determining whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier, if the input feature set of the real-time input data does not belong to any category set in the existing dynamic mapping table, create a new category set for the real-time data and its corresponding real-time output data, assign a unique mapping identifier, and incorporate the category set and its corresponding mapping identifier into the dynamic mapping table.

4. A real-time data verification method for an AI agent based on dynamic mapping according to claim 1, characterized in that, The result range or pattern of the output data is comprehensively modeled through rule templates, vector space ranges, and multimodal matching logics to support the unified verification of various types of output results such as structured text, natural language text, images, etc.

5. A real-time data verification method for an AI agent based on dynamic mapping according to claim 1, characterized in that The input feature set includes numerical features, and / or text features, and / or categorical features.

6. The real-time data verification method of an AI agent based on dynamic mapping according to claim 1, wherein, When extracting features from historical input data and / or real-time input data respectively, feature enhancement is performed in combination with the context information, and / or interaction history, and / or user profile information of the historical input data and / or real-time input data.

7. An AI agent real-time data verification system based on dynamic mapping, characterized in that, Including: A dynamic mapping table establishment module for obtaining a number of historical data of the AI agent, where the historical data includes historical input data and its corresponding historical output data; extracting features from each historical input data respectively to obtain its corresponding input feature set; using a clustering algorithm to group the historical input data with similar input feature sets and their corresponding historical output data into a category set, and assigning a unique mapping identifier to each category set; establishing a dynamic mapping table according to all category sets and their corresponding mapping identifiers; statistically analyzing the feature range of the historical input data and the result range or pattern of the historical output data within each category set; A real-time data analysis module is used to obtain the real-time input data of the AI intelligent agent; extract the features of the real-time input data to obtain its corresponding input feature set; query the matching mapping identifier in the dynamic mapping table according to the input feature set corresponding to the features of the real-time input data, and determine whether the real-time input data conforms to the feature range of the input data within the category set corresponding to the mapping identifier. If not, it is determined that the real-time input data is abnormal.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1-6.

9. A computer program product, characterized in that, The computer program product includes computer program code. When the computer program code runs on a computer, the computer is caused to implement the method according to any one of claims 1-6.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the method according to any one of claims 1-6.

Images