Information processing system

Abstract

The application provides an information processing system. An information processing system, characterized by comprising: a processor; wherein the processor is configured to: monitor the validity period of a digital certificate, when the validity period is approaching, generate a prompt for obtaining a new certificate using a generative artificial intelligence model; set the obtained digital certificate to the information processing device, and generate a prompt for indicating the execution of the procedures necessary for completing an electronic transaction using a generative artificial intelligence model; analyze the emotional state of a user, and generate a prompt for indicating the adjustment of notification time and notification content based on the emotional state using a generative artificial intelligence model.

Description

Technical Field

[0001] The technology disclosed herein relates to an information processing system. Background Technology

[0002] Japanese Patent Application Publication No. 2022-180282 discloses a method for controlling a role-based chatbot executed by at least one processor. The method includes the following steps: receiving a user's speech; adding the user's speech to a prompt word, the prompt word containing instruction statements associated with an explanation of the chatbot's role; encoding the prompt word; and inputting the encoded prompt word into a language model to generate a chatbot response to the user's speech.

[0003] Existing digital certificate management and electronic transaction systems have several shortcomings in certificate validity management and user notification. First, traditional systems typically only periodically check the validity of digital certificates using fixed rules. When a certificate is nearing expiration, they only provide a simple reminder or trigger a renewal process, lacking flexibility to handle complex business scenarios. This makes them prone to expiration due to configuration oversights or operational errors, leading to interruptions in information services or electronic transactions. Second, in existing technologies, the control logic used to guide certificate acquisition, deployment, and the execution of procedures related to electronic transactions is mostly a pre-set, fixed process, making it difficult to dynamically adjust according to changes in the system environment or service requirements. Its automation and intelligence levels are limited. Third, when notifying users of certificate status, transaction progress, or risk information, existing systems generally use uniform notification content and timing, failing to consider the user's current emotional state. This insufficient attention to user experience and notification effectiveness may cause users to miss crucial notifications when stressed or distracted, or lead to fatigue from excessive notifications, affecting decision-making efficiency. In summary, it is necessary to provide a system that can automatically generate prompts for certificate acquisition, certificate configuration, electronic transaction execution, and notification control using generative artificial intelligence models, and can dynamically adjust notification strategies based on user emotional states, in order to reduce the risk of certificate expiration, improve the stability of electronic transactions, and enhance the user interaction experience. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides an information processing system comprising a processor configured to: monitor the expiration date of a digital certificate; when the expiration date approaches, generate a prompt using a generative artificial intelligence model to instruct the acquisition of a new certificate; drive subsequent certificate application, issuance, and renewal processes through the prompt to reduce the risk of certificate non-renewal due to human error; set the acquired digital certificate into an information processing device and generate a prompt using a generative artificial intelligence model to instruct the execution of procedures necessary to complete electronic transactions, enabling identity authentication, encrypted communication configuration, and transaction process control related to electronic transactions to be automatically completed under unified intelligent instructions, thereby improving the automation and security of the transaction process; and analyze the user's emotional state and generate a prompt using a generative artificial intelligence model to instruct the adjustment of notification time and content based on the emotional state, enabling the system to dynamically select appropriate notification timing, frequency, and information presentation methods according to the user's current level of tension, anxiety, or focus, thereby improving the acceptability and effectiveness of notifications. Furthermore, the processor is configured to: generate prompts using a generative artificial intelligence model to instruct the execution of notification operations to prevent information service interruptions due to digital certificate expiration, enabling the system to proactively and promptly trigger multi-channel notifications when certificates are nearing expiration or anomalies occur, ensuring the continuity of information services; and generate prompts using a generative artificial intelligence model to instruct the optimization of notification priorities based on the user's emotional state, enabling the system to prioritize notifications involving key information such as certificate security and transaction risks based on the user's current emotional state when multiple notifications coexist, thereby improving user experience while ensuring system security and business continuity. Through the above structure and control methods, this invention can simultaneously achieve intelligence and personalization at three levels: certificate lifecycle management, electronic transaction execution, and user notification strategy, effectively solving problems such as high certificate expiration risk, rigid process control, and insufficient notification experience in existing technologies.

[0005] "System" refers to a whole consisting of one or more hardware devices and / or software modules, used to perform functions such as digital certificate monitoring, certificate acquisition and configuration, electronic transaction control, and user notification control.

[0006] "Processor" refers to a hardware component capable of executing program code to perform data processing and logical judgments, including but not limited to a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), and any combination thereof.

[0007] A "digital certificate" is an electronic document issued by a certificate authority to identify an entity and support encrypted communication and / or electronic signatures, such as a public key certificate conforming to the X.509 standard.

[0008] "Validity period" refers to the time interval between the issuance of a digital certificate by the certificate authority and its expiration date. During this time interval, the digital certificate is considered to be in a normal working state.

[0009] "Generative AI models" refer to AI models trained through machine learning or deep learning that can automatically generate text, instructions, or other output content based on input, including but not limited to large language models, text generation models, and multimodal models with prompt generation capabilities.

[0010] "Prompts" refer to instructional or guiding text information generated by generative artificial intelligence models to instruct systems or external components to perform specific processing steps, including content for instructing certificate acquisition, certificate configuration, electronic transaction procedures, and notification control.

[0011] "Information processing device" refers to electronic equipment used for processing, storing and transmitting data, including but not limited to servers, terminal devices, network devices and computing nodes with applications deployed.

[0012] "Electronic transactions" refer to the process of trading goods, services or other rights and obligations through electronic means in a network environment, including but not limited to online payment, electronic contract signing and related authentication and settlement operations.

[0013] "User's emotional state" refers to characteristic information that reflects the user's current psychological state or emotional tendency, such as tension, anxiety, calmness, and focus, which can be inferred through physiological signals, behavioral characteristics, or interaction data.

[0014] "Notification time" refers to the specific moment or time interval at which the system sends notification information to users related to the status of digital certificates, electronic transactions, or system risks.

[0015] "Notification content" refers to the text, images, icons, or combinations thereof presented to users by the system in relation to digital certificates, electronic transactions, or system status, used to alert users to risks, progress, or operational suggestions.

[0016] "Notification operation" refers to the sending or display behavior performed by the system to convey certificate status, transaction status or risk information to users, including notifications via email, push notifications, interface pop-ups, SMS and other means.

[0017] "Notification priority" refers to the level or weight used to determine the relative importance and sending order of multiple notifications to be sent or displayed, in order to control which notifications are pushed to the user first. Attached Figure Description

[0018] Figure 1 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the first embodiment.

[0019] Figure 2 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and smart device according to the first embodiment.

[0020] Figure 3 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the second embodiment.

[0021] Figure 4 This is a conceptual diagram illustrating an example of the main functions of the data processing device and smart glasses according to the second embodiment.

[0022] Figure 5 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the third embodiment.

[0023] Figure 6 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and head-mounted terminal according to the third embodiment.

[0024] Figure 7 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the fourth embodiment.

[0025] Figure 8 This is a conceptual diagram illustrating an example of the main functions of the data processing device and robot according to the fourth embodiment.

[0026] Figure 9 This represents an emotion map that maps multiple emotions.

[0027] Figure 10 This represents an emotion map that maps multiple emotions.

[0028] Figure 11 This is a sequence diagram illustrating the processing flow of the data processing system of the first embodiment.

[0029] Figure 12 This is a sequence diagram illustrating the processing flow of the data processing system in Application Example 1.

[0030] Figure 13 This is a sequence diagram illustrating the processing flow of the data processing system of the second embodiment.

[0031] Figure 14This is a sequence diagram illustrating the processing flow of the data processing system in Application Example 2. Detailed Implementation

[0032] Hereinafter, an example of an implementation of the system according to the present disclosure will be described with reference to the accompanying drawings.

[0033] First, let me explain the terminology used in the following instructions.

[0034] In the following embodiments, the processor (hereinafter referred to as "processor") with reference numerals may be a single computing device or a combination of multiple computing devices. Furthermore, the processor may be a single computing device or a combination of multiple computing devices. Examples of computing devices include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0035] In the following embodiments, RAM (Random Access Memory), as indicated in the figures, is a memory that temporarily stores information and is used as working memory by the processor.

[0036] In the following embodiments, the memory, as indicated by the reference numerals, is one or more non-volatile storage devices that store various programs and parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), disks (e.g., hard disks), or magnetic tapes.

[0037] In the following embodiments, the communication I / F (Interface) with reference numerals is an interface that includes a communication processor and an antenna, etc. The communication I / F is responsible for communication between multiple computers. As an example of a communication specification applicable to the communication I / F, wireless communication specifications such as 5G (5th Generation Mobile Communication System), Wi-Fi (wireless fidelity) (registered trademark), or Bluetooth (registered trademark) can be listed.

[0038] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it can be only A, only B, or a combination of A and B. Furthermore, in this specification, when "and / or" connects to express more than three items, the same interpretation as "A and / or B" applies.

[0039] First Implementation Method Figure 1 An example of the configuration of the data processing system 10 according to the first embodiment is shown.

[0040] like Figure 1 As shown, the data processing system 10 includes a data processing device 12 and an intelligent device 14. A server can be cited as an example of the data processing device 12.

[0041] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0042] The smart device 14 includes a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. In addition, the receiving device 38, output device 40, camera 42, and communication I / F 44 are also connected to the bus 52.

[0043] The receiving device 38 includes a touchscreen 38A and a microphone 38B, and receives user input. The touchscreen 38A receives user input via touch by detecting contact with an indicator (e.g., a pen or finger). The microphone 38B receives user input via sound by detecting the user's voice. The control unit 46A in the processor 46 sends data representing the user input received by the touchscreen 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data representing the user input.

[0044] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting data in a form perceptible to the user 20 (e.g., sound and / or text). The display 40A displays visual information such as text and images according to instructions from the processor 46. The speaker 40B outputs sound according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0045] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for sending and receiving various information between processor 46 and processor 28 via network 54.

[0046] Figure 2 The diagram shows an example of the main functions of the data processing device 12 and the smart device 14.

[0047] like Figure 2 As shown, in the data processing apparatus 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the memory 32. The specific processing program 56 is an example of a "program" as understood in this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0048] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. In the emotion inference function (emotion-specific function) using the emotion-specific model 59, various inferences and predictions related to the user's emotions are performed, including inferences and predictions of the user's emotions, but this is not limited to this example. Furthermore, emotion inference and prediction may also include, for example, emotion analysis (parsing).

[0049] In the smart device 14, the processor 46 performs the acceptance output processing. The memory 50 stores the acceptance output program 60. The acceptance output program 60 is used in conjunction with the data processing system 10 and the specific processing program 56. The processor 46 reads the acceptance output program 60 from the memory 50 and executes the read acceptance output program 60 on the RAM 48. The acceptance output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance output program 60 executed on the RAM 48. Furthermore, the smart device 14 has the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and these models can also be used to perform the same processing as the specific processing unit 290. The acceptance output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance output program 60 executed on the RAM 48.

[0050] Alternatively, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. Furthermore, the data processing device 12 may be a server device or a user-held terminal device (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of the processing of the data processing system 10 of the first embodiment will be described.

[0051] Example 1 The flow of a specific process in Example 1 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart device 14. Furthermore, the data processing device 12 is referred to as the "server," and the smart device 14 is referred to as the "terminal."

[0052] In network services, to provide information to terminals via secure communication, it is typically necessary to configure and maintain digital certificates for encrypted communication on servers. In existing technologies, the monitoring, renewal application, payment settlement, server configuration updates, and notification processing of digital certificates are often implemented using fragmented scripts or manual operations, which presents the following problems: First, the acquisition and calculation of certificate validity information largely rely on simple timed scripts, lacking coordination with system-level functions such as configuration management and service control. This results in the server being unable to perform fast and reliable automatic processing under a unified control framework when certificates are about to expire or have already expired, easily causing information service interruptions and affecting system availability and security. Second, the steps involved in certificate renewal, such as domain name ownership verification, certificate issuance request generation, electronic settlement service invocation, configuration file updates, and service reloading, lack end-to-end automated orchestration. Error handling and rollback mechanisms are insufficient, requiring frequent intervention from maintenance personnel, which increases maintenance costs and the risk of human error. Third, existing notification mechanisms typically rely solely on simple time thresholds or single state conditions for triggering, failing to intelligently adjust notification priority, content, and medium based on user state information. This makes it prone to pushing high-priority alerts when users are under pressure or unsuitable for receiving information, impacting user experience and reducing the probability of critical notifications being addressed promptly. Fourth, while generative AI models possess powerful capabilities in code generation and process design, existing systems lack mechanisms to systematically integrate them into the certificate lifecycle management process. They fail to drive the model to generate automated execution steps and control programs tailored to the system through structured prompts, thus failing to improve the computer system's adaptability and scalability for certificate management tasks at the architectural level.

[0053] Therefore, a technical solution is needed that can uniformly manage digital certificate validity monitoring, certificate update request generation, electronic settlement processing, configuration updates and service reload, and notification control within the system. This solution should automatically generate or optimize control processes and program logic by collaborating with generative artificial intelligence models and using prompt statements as intermediaries. It should also adaptively adjust notification behavior based on user status information such as the user's emotional state, thereby improving the management efficiency of secure communication-related resources, reducing the risk of information service interruption, and enhancing the overall intelligent operation and maintenance capabilities of the system at the computer technology level.

[0054] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Embodiment 1 is achieved by the following means.

[0055] In this invention, the server includes a processing unit that periodically acquires the validity period of encrypted authentication information registered on the communication control function using a time management function and generates validity period management information; a processing unit that automatically generates and sends authentication information acquisition request data based on the validity period management information and performs verification processing to initiate authentication information update processing; a processing unit that generates and sends settlement request data through electronic settlement service using a billing processing function and updates encrypted authentication information status management information based on settlement result data; and a processing unit that automatically saves new encrypted authentication information and corresponding secret information and updates communication service control program settings information using configuration management and service provision functions, and performs setting verification processing and start control processing to enable information delivery. The system includes a processing unit that reflects new encrypted authentication information, a processing unit that generates and sends notification data using status monitoring and notification control functions, and generates prompts indicating this generation and sending as prompt statements for a generative artificial intelligence model, determining the content and timing of notification data based on response information obtained from the generative artificial intelligence model, and a processing unit that obtains user emotional state estimation information using user state estimation information, generates prompts adjusting notification priority and notification medium based on this emotional state estimation information as prompt statements for a generative artificial intelligence model, and updates the control parameters of the notification control function based on response information obtained from the generative artificial intelligence model. This allows for an end-to-end automated processing chain within the server, from monitoring the validity period of encrypted authentication information, updating authentication information and electronic settlement, to configuring automatic updates and intelligent notification scheduling. The system dynamically generates or optimizes control flows and program logic through a prompt statement mechanism driven by a generative artificial intelligence model, and incorporates adaptive notification control based on user emotional state. This enhances the automation, robustness, and user interaction intelligence of the computer system in digital certificate lifecycle management, reduces the risk of information service interruptions due to improper certificate management, and ultimately improves computer technology itself.

[0056] A "system" refers to an overall device or group of devices consisting of multiple functional modules, hardware resources, and software programs, used to perform processes such as encrypted authentication information management, service provision, and notification control in a network environment.

[0057] "Server" refers to an electronic computing device in a network that provides computing, storage, and communication control functions, and is the main body used to execute the programs in this invention related to encrypted authentication information management, settlement processing, configuration updates, and notification control.

[0058] A "processing unit" refers to a functional module implemented by a processor and the control program running on it, which is a logical entity used to perform operations such as data acquisition, calculation, control and output for a specific processing target.

[0059] "Time management function" refers to the program and control mechanism used to trigger task execution, obtain the current time and manage time-related parameters based on a predetermined schedule or periodic conditions.

[0060] "Communication control functions" refer to the programs and logic used to control the establishment, maintenance, and termination of network connections, and to manage the data sent and received, in order to realize data communication with terminals or external services.

[0061] "Encrypted authentication information" refers to digital information used to achieve identity authentication and data encryption during communication, including but not limited to digital certificates, public keys, private keys and their related certificate chains.

[0062] "Validity Management Information" refers to a data set generated based on parameters such as the expiration time and remaining days of encrypted authentication information, used to represent and manage the validity period status of encrypted authentication information.

[0063] "Attribute information" refers to parameters or metadata related to validity period, issuer, and user, which are parsed from encrypted authentication information.

[0064] "Connection identification information" refers to identification data used to distinguish and identify specific communication connections or service endpoints, including domain names, network addresses, or service identifiers.

[0065] "Certificate information issuance function" refers to the processing capability provided by external authentication services or internal modules for generating and issuing encrypted authentication information, including the functions of receiving requests, performing verification, and returning issuance results.

[0066] "Authentication information acquisition request data" refers to the data generated by the server and sent to the authentication information issuance function, which is a structured request message used to request the issuance or update of encrypted authentication information.

[0067] "Verification information" refers to data returned by the verification information issuance function to prove whether domain name ownership, key legality, or other authentication conditions are met, including challenge data or verification results.

[0068] "Resource management functions" refer to the programs and control mechanisms used to manage the allocation and use of computer resources such as processors, memory, and network bandwidth.

[0069] "Configuration management function" refers to the functional module used to manage system configuration parameters, service configuration files and runtime environment settings, and to support the modification, backup and rollback of configurations.

[0070] "Authentication information update processing" refers to a series of automated processes from detecting that the encrypted authentication information is about to expire, initiating an update request, passing verification, to obtaining the new encrypted authentication information.

[0071] "Billing processing function" refers to the programs and logic used to generate, send and manage billing requests related to service use or resource consumption, and to process the billing results.

[0072] "Electronic settlement services" refer to automatic payment and deduction services provided through the internet, which are external service systems used to complete the transfer of currency or credit based on settlement requests and return settlement results.

[0073] "Settlement request data" refers to structured data containing information such as fee amount, payment method, and transaction identifier, used to initiate settlement operations to electronic settlement services.

[0074] "Settlement result data" refers to information returned by the electronic settlement service that characterizes the status of the settlement processing result, including transaction success or failure status, error codes, and transaction identifiers.

[0075] "Transaction completion information" refers to management data generated based on settlement result data, used to record and indicate that a settlement process associated with an authentication information update has been completed and its results.

[0076] "Status management information" refers to the recorded data used to represent the current status of encrypted authentication information (such as valid, about to expire, being updated, expired, etc.) and its history of change.

[0077] "Service provisioning functionality" refers to programs and modules used to provide application services or information content to terminals over a network, including the ability to process requests and return responses.

[0078] "Secret information" refers to sensitive data that is used in conjunction with encrypted authentication information and needs to be kept confidential, including private keys or other authentication data that cannot be disclosed.

[0079] "Storage device" refers to a hardware device used to permanently or temporarily store programs, configurations and data, including semiconductor memory, disk drives or other storage media.

[0080] "Communication service control program" refers to a collection of programs that run on a server and are used to control the behavior of network services, including communication protocol stack configuration, port listening, and security parameter settings.

[0081] "Configuration information" refers to the configuration data used to determine how the communication service control program operates, including parameters such as certificate path, port number, protocol version, and security policy.

[0082] "Configuration verification processing" refers to the process of performing syntax checks, logic checks, and consistency verification on relevant configurations before applying or reloading configuration information.

[0083] "Startup control processing" refers to the process used to start, stop, or reload service processes, as well as to control the running status of services.

[0084] "Information provision function" refers to the overall function of outputting web pages, interface data or other forms of content to users in a network environment, realizing data provision and response to terminals.

[0085] "Status monitoring function" refers to a functional module used to acquire and analyze the system's operating status, encrypted authentication information status, and processing result status in real time or periodically.

[0086] "Notification control function" refers to the control logic used to determine whether to generate a notification, how to combine the notification content, and through which channels to send the notification based on the status monitoring results.

[0087] "Display control function" refers to the programs and logic used to present notification information, status information, or operation results on a display device or graphical user interface.

[0088] "Message sending function" refers to programs and interfaces used to send message data via email, instant messaging interfaces or other communication channels.

[0089] "Notification data" refers to structured data that includes notification content, recipients, sending method, and sending time information, used to send status or alarms to users or administrators.

[0090] "Prompt information" refers to textual information used to describe the target task or expected output, and to provide this description to the generative artificial intelligence model to trigger it to generate a response.

[0091] "Generative artificial intelligence models" refer to artificial intelligence models that are trained on large-scale data based on machine learning and deep learning technologies, and can automatically generate text, code or other content based on input prompts.

[0092] "Prompt statements" refer to prompts expressed in natural or structured language, which are used as input to generative artificial intelligence models to guide them in generating corresponding outputs.

[0093] "Response information" refers to the result information generated and output by the generative artificial intelligence model after receiving a prompt statement, including text descriptions, code snippets, or configuration suggestions.

[0094] "User status acquisition function" refers to a functional module used to acquire user-related status data from sensor data, interaction records or external interfaces, and infer the user's emotional state based on this data.

[0095] "Emotional state presumption information" refers to presumption data that represents the category, intensity, or tendency of a user's emotions, obtained through analysis of user behavior, voice, text, or other signals.

[0096] "Notification priority" refers to hierarchical information used to sort and allocate resources among multiple notifications, representing the importance and urgency of each notification.

[0097] "Notification medium" refers to the specific channel or carrier used to deliver notification information to users, including email, SMS, instant messaging tools, in-app messages, or system pop-ups.

[0098] "Control parameters" refer to adjustable parameters used to control the behavior of notification control functions, status monitoring functions, or other functional modules, including thresholds, weights, time intervals, and enable flags.

[0099] "Scheduling management function" refers to the functional module used to register, manage and trigger timed tasks or event-driven tasks, so as to realize the automatic scheduling of monitoring, update, settlement and notification processing.

[0100] "Automatic execution step information" refers to procedural data that describes the sequence, conditions, and dependencies of each processing step when the system performs a specific task, and is used to drive the automatic execution of the task.

[0101] "Control program information" refers to program code, scripts, or configuration fragments used to actually execute control logic in the processing unit, in order to achieve specific operations such as monitoring, updating, settlement, configuration changes, and notifications.

[0102] In this invention, the server acts as the core execution entity, configured to manage the lifecycle of encrypted authentication information (e.g., digital certificates), process settlements, update configurations, and control intelligent notifications, in collaboration with computer hardware and system software. The terminal, acting as an access node, interacts with the server via a secure communication protocol. Users input prompts into a generative artificial intelligence model, thereby assisting in the generation or optimization of automated control processes and program logic.

[0103] At the hardware level, servers can utilize general-purpose rack-mount or cloud computing nodes, including multi-core central processing units (CPUs), semiconductor memory (main memory), non-volatile storage devices (such as solid-state drives), network interface controllers, and optional graphics processing units (GPUs). At the software level, servers run operating systems (such as Linux-based server operating systems) and install network service software (such as reverse proxies and application servers), encryption library software (such as the OpenSSL library), task scheduling software (such as cron-like scheduled task management programs), database management systems (such as relational database management programs), email and messaging programs, and generative artificial intelligence model inference service frameworks (such as inference engines based on deep learning frameworks).

[0104] The server implements the various functional modules of this invention through control programs deployed in the operating system. The server instantiates these modules as a series of processes or threads in main memory, including a time management module, a communication control module, an encryption and authentication management module, a configuration management module, a settlement control module, a notification control module, a status monitoring module, a user status acquisition module, a scheduling management module, and a generative artificial intelligence interaction module, etc.

[0105] With the support of the operating system's scheduling service, the server uses a time management module to maintain multiple scheduled task entries. Each entry includes a task identifier, execution period (e.g., daily, hourly), next execution timestamp, and entry identifier of the associated processing module. The server maintains this scheduled task data in main memory in a table structure, such as storing it as a record array. Each record includes fields such as "Task ID," "Scheduled Time," and "Associated Certificate ID." The time management module periodically reads the system clock, and when the current time exceeds the "Scheduled Time" of a certain record, it pushes that record to the task queue of the scheduling management module.

[0106] In the encryption authentication management module, the server uses encryption library software (such as the OpenSSL library) to parse the encryption authentication information files on the storage device. The server stores the certificate file path and certificate identifiers (such as domain name and service name) in a database table, which includes fields such as certificate ID, file path, issuer information, and expiration time. The server reads these records from main memory, calls encryption library functions to parse the certificate structure for each record, and extracts time fields such as "notBefore" and "notAfter," as well as attribute information such as certificate fingerprint and signature algorithm. In the time management module, the server obtains the current timestamp, converts "notAfter" to a unified time format, and calculates the remaining days using integer subtraction. The server compares this to a preset threshold (e.g., 30 days). If the remaining days are less than or equal to the threshold, the server updates the status field of the corresponding certificate ID to "expiring soon" in the status management table and generates a validity period management information record, which includes flags such as certificate ID, remaining days, last check time, and whether an update request has been initiated.

[0107] In the communication control module, the server filters certificate records with statuses such as "expiring soon" or "retrying after update failure" from the database based on validity management information, and obtains their associated connection identification information (e.g., hostname, virtual host configuration identifier). The server constructs an authentication information retrieval request data structure in main memory, which includes fields such as request type, target service identifier, domain name list, and public key fingerprint. The server constructs an encrypted network request message through the network protocol stack, calls the application interface of an external proof information issuance service (e.g., an interface based on the ACME protocol), and appends locally generated key proof data or challenge response path information to the message.

[0108] When the server receives the verification information returned by the certification information issuance service, it parses the response data into a structured object in main memory, extracting fields such as challenge type, challenge token, target verification path, and expected content. The server selects different specific processing methods based on the challenge type in the configuration management module. For example, when the challenge type is "verification via hypertext transfer path," the server creates a specific file in the root directory of the corresponding website (e.g., a specified directory) on the storage device, with the filename set to the challenge token and the file content set to the verification string specified by the issuance service. The server updates the network service configuration (e.g., ensuring the corresponding path is not redirected or cached) and checks the external reachability of the path through the status monitoring module. When the challenge type is "verification via domain name resolution record," the server constructs a data structure containing host records, record types, and text content in the communication control module that interacts with the domain name resolution service, calls the domain name resolution service interface to create the corresponding text record, and then uses a query interface to repeatedly check whether the record has taken effect, thereby controlling the timing of the next verification step.

[0109] The server utilizes the electronic settlement service interface within the settlement control module to perform billing processing for paid authentication information update procedures. The server maintains a settlement template table in the database, containing fields such as billing scheme ID, currency, amount, and payment method identifier. When settlement is required, the server loads the corresponding template from the table and generates a settlement request data structure based on the current certificate update request. This structure includes the transaction ID (generated by the server according to certain rules), amount, currency type, account identifier, and service item code. The server sends an encrypted communication request to the electronic settlement service through the network interface controller and, upon receiving the settlement result data, extracts fields such as transaction status code, transaction serial number, and timestamp. The server records the corresponding transaction completion information for this certificate update process in the status management table and simultaneously writes the results in a predefined format to the log file for subsequent auditing.

[0110] After receiving the new encrypted authentication information and its corresponding secret information in the configuration management module, the server writes it to the specified directory on the storage device and updates the certificate path field in the configuration database. The server loads the current network service configuration file text content from main memory, replacing the old certificate path and key path with the new path. The server then calls the configuration check command provided by the network service software, performs the check operation in a subprocess, and captures the return code and output text. If the check passes, the server calls the service reload interface (e.g., through the system service management program or the service's own control command) to achieve uninterrupted loading of the new certificate. If the check fails, the server automatically restores the backed-up old configuration file through the configuration management module, rolls the configuration state back to a secure state, and adds a "configuration update failed" status and error code to the certificate record in the status management table.

[0111] The server continuously tracks the status fields of encrypted authentication information, settlement status fields, and configuration update status fields in the status monitoring module, forming a comprehensive status view. The server generates notification data based on these statuses and preset rules in the notification control module. The notification data is internally represented in a structured form, including fields such as notification ID, target user identifier, notification level, notification content template ID, sending channel, and scheduled sending time. In the display control module, the server can display these notification contents to operations and maintenance personnel through the management control panel; in the message sending module, notifications can be sent via email, instant messaging interface, or system log channel.

[0112] In the generative AI interaction module, the server organizes the prompts describing the target task into prompt statements. These prompt statements express the task intent and constraints in natural language text. For example, the server can generate the following prompt statements: "Based on the following certificate status table fields (certificate ID, domain name, expiration date, remaining days, last update status), generate a list of processing steps for automatically renewing expiring certificates and reloading network services. The steps must include error handling and rollback strategies." "Please provide a control flow description for implementing the periodic checking and updating of encrypted authentication information in a Linux-based server environment using an encryption library and an automated task scheduler, and indicate the configuration files and log files that need to be accessed at each step." "Please design a unified certificate management solution for multiple domains and multiple service instances, explaining how to organize storage paths, how to abstract configuration templates, and how to batch reload related services after certificate updates without affecting online connectivity." Users can also actively input prompts into the generative artificial intelligence model on the terminal, for example: "Please help me generate a script description for automatically renewing certificates and reloading network services using a certificate management tool in a Linux environment. The script should include logging and error handling." "Generate a detailed step-by-step guide on how to automatically apply for and renew certificates using a high-level programming language to invoke the certificate issuance protocol, and explain how this works in conjunction with configuration file updates and service reloads." "How to integrate an electronic payment interface to enable automatic deduction for certificate renewal? Please provide a description of the processing flow, including the logic for handling payment failure retries and alarms." The server encapsulates prompts as model input through a generative AI interaction module, invoking a generative AI model inference service deployed locally or remotely. This generative AI model employs a multi-layer self-attention network architecture (e.g., the Transformer architecture), including an input embedding layer, a multi-head self-attention layer, a feedforward network layer, and an output generation layer. When sending input text, the server first segments and encodes the prompts, converting the text into a sequence of integer tokens, and then converting it into a vector sequence using an embedding matrix. The model performs weighted summation and linear transformations on these vectors within the multi-layer self-attention network, calculates the dependencies between different tokens, performs non-linear transformations in the feedforward network layer, and selects the next token to be generated using a probability distribution in the output layer.

[0113] This generative AI model is trained beforehand using a large-scale pre-training corpus and a fine-tuning dataset of instructions. During training, the server or training device uses the cross-entropy loss function to measure the difference between the model output and the target text, calculates the gradient using the backpropagation algorithm, and updates the network weights using stochastic gradient descent or its variants (such as adaptive moment estimation). To enhance the model's robustness to control flow generation, text samples related to system configuration, error handling, rollback mechanisms, and concurrent scheduling can be added to the training data. Furthermore, data augmentation strategies (e.g., replacing parameter names, path names, and service names with templates) are employed to expand the training set, thereby enabling the model to better adapt to the technical text generation required by this invention.

[0114] After receiving the response information from the generative artificial intelligence model, the server parses the output text in main memory, extracting the processing step descriptions, configuration parameter suggestions, and state machine design points, and converting them into an intermediate representation of internally usable automated execution step information and control program information. This intermediate representation can take the form of structured data, such as a list of records consisting of fields like "Step ID," "Preconditions," "Execution Action," "Error Branch," and "Rollback Action." The server registers this step information as executable task definitions in the scheduling management module and associates it with a specific certificate ID or service instance ID.

[0115] By leveraging the high-dimensional semantic reasoning capabilities of generative artificial intelligence models, servers use prompts as an interface to transform complex control flow design tasks into structured, machine-executable task definition data. This goes beyond simply replacing human operations; it dynamically generates and optimizes control logic within the system. Compared to traditional manual scripting, this approach offers improvements at the following computer technology levels: First, by simultaneously weighing multiple error scenarios and configuration combinations in a high-dimensional space, server-generated flows tend to have more comprehensive error handling branch coverage and rollback strategy design, thus reducing the probability of unpredictable errors in edge scenarios and improving overall robustness. Second, servers can repeatedly call the model to generate targeted, optimized flows based on real-time status and the latest certificate combinations, rather than using fixed scripts, reducing redundant steps and thus lowering average processing latency and resource consumption.

[0116] In the user status acquisition module, the server can obtain user-related data from various data sources, such as the interaction frequency reported by the terminal, operation behavior logs, error confirmation time, and language input content. The server uses feature extraction algorithms (such as statistical feature calculation and word vector-based text feature calculation) to convert this raw data into emotion-related feature vectors. The emotion state inference model can employ a multilayer perceptron or an attention-based sequence model to infer from these feature vectors, outputting emotion state inference information representing the emotion category (e.g., tense, calm, busy) and intensity (e.g., numerical scale). In the notification control module, the server uses these numerical values ​​as input, combining them with indicators such as notification level and system urgency as input features for the generative artificial intelligence model. For example, the server can send the following prompt statement to the model: "The current user is under high pressure and is frequently processing alarms. Please design a reordering and grouping strategy based on the following notification queue (including notification level, content summary, and deadline), prioritizing security-related and non-urgent notifications, and postponing or combining non-urgent notifications." After receiving the model's response, the server parses the output into priority adjustment rules and media selection rules (e.g., email, instant messaging, or display only on the console), and updates the control parameter table in the notification control module. This dynamic adaptation process based on model-generated rules ensures that the notification strategy maintains a better signal-to-noise ratio and balance point under different user and system states, thereby reducing the waste of attention and system resources caused by invalid notifications.

[0117] The server, through the aforementioned hardware and software configurations, implements data and control flows, forming a complete end-to-end automated chain: from monitoring the validity period of encrypted authentication information supported by an underlying time management mechanism, to encrypted communication with external authentication and electronic settlement services; from the automatic generation and checking of configuration files, to the controlled reloading of service processes; and then to intelligent notification strategies based on state and emotion, supplemented by process generation and optimization driven by generative artificial intelligence models. This chain is essentially an improvement on the internal resource management and control logic generation methods of computer systems, rather than simply a mechanical replacement of manual operation and maintenance steps. By introducing a prompting statement mechanism oriented towards generative artificial intelligence models, this invention utilizes the large-scale parameter space and attention mechanism within the model to achieve higher coverage and adaptability in control logic generation than traditional rule engines, thereby achieving technical benefits in system stability, processing efficiency, and error rate control.

[0118] In this invention, the terminal can be of various types, including mobile terminals, desktop terminals, or dedicated terminals. The terminal includes at least a processor, memory, a display device, and a network interface in its hardware, and runs a client application or browser in its software. The terminal establishes a session with the server through a secure communication protocol and automatically completes the server certificate verification process. With the support of the operating system's security module, the terminal calls the local certificate store to check the encrypted authentication information returned by the server. If the server automatically updates the certificate and reloads the configuration according to this invention, the terminal can continuously obtain valid certificates in subsequent connections, avoiding connection interruptions and security alarms, thereby improving the overall availability of the network system and the security of data transmission.

[0119] Users input prompts into a server or remote generative AI service via a graphical user interface or command-line interface on their terminal to obtain best practice configuration and strategy suggestions for specific deployment environments and business scales. Based on these suggestions, users optimize system parameters and deployment structures on the server. This human-machine collaborative mechanism, centered on prompts, combines user experience, the model's semantic reasoning capabilities, and the server's automated execution capabilities. This allows the invention to move beyond fixed processes and continuously self-optimize under different environments and constraints, thus representing a structural improvement to computer system operation and maintenance.

[0120] use Figure 11 The processing procedure is explained.

[0121] Step 1: The server retrieves the certificate list and reads the certificate files. The server, acting as the processing entity, loads the list of currently managed encrypted authentication information from storage devices and configuration databases.

[0122] Input: Certificate configuration table (including certificate ID, domain name, certificate file path, last check time, etc.), certificate file in storage device.

[0123] The server reads records one by one from the certificate configuration table to obtain the file path and associated domain name of each certificate; the server calls the file system interface to read the binary data of the certificate file from the specified path and stores it in memory as a buffer.

[0124] Output: A list of raw certificate data (each entry includes the certificate ID, domain name, and certificate binary content).

[0125] Step 2: The server parses the certificate validity period and generates validity period management information. The server uses cryptographic library software (such as the OpenSSL library) to parse the raw certificate data obtained in step 1.

[0126] Input: List of raw certificate data (certificate binary content, certificate ID, domain name).

[0127] The server calls the encryption library's parsing function to convert the binary certificate into a structured object, extracting time fields such as notBefore and notAfter, as well as issuer information and fingerprint information. The server obtains the current system time through the time management module, converts notAfter into a unified timestamp format, and performs a subtraction operation to calculate the "remaining days". The server compares the "remaining days" with a preset threshold (e.g., 30 days) to generate a boolean flag indicating whether it is "about to expire".

[0128] Output: A list of validity period management information (each entry includes certificate ID, domain name, expiration date, remaining days, and a "expiring soon" flag).

[0129] Step 3: The server updates certificate status and filters certificates that need updating. The server updates its internal status management table based on the validity period management information and selects the target certificate that needs to be updated.

[0130] Input: Validity management information list, current status management table (records certificate ID and status field).

[0131] The server iterates through each certificate ID. If the "expiring soon" flag is true and the current status is not "updating", the status field is updated to "pending update". The server collects all certificate IDs with the status "pending update" into the target set and records the domain name, remaining days, and status change in the log.

[0132] Output: Target certificate set (list of certificate IDs to be updated), updated status management table.

[0133] Step 4: The server generates authentication information for the target certificate and retrieves the request data. The server constructs an authentication information retrieval request for each certificate in the target certificate set in preparation for interaction with the external authentication information issuance service.

[0134] Input: Target certificate set, certificate configuration table (including domain name list, public key information, service identifier, etc.).

[0135] The server reads the list of domain names and service types corresponding to each target certificate, constructs a request data structure in memory, and fills in fields such as request type (new issuance or renewal), domain name array, public key fingerprint, and account identifier. The server serializes the request data structure (e.g., converts it to JSON or protocol buffer format) and adds necessary authentication header information and timestamps.

[0136] Output: A list of authentication information retrieval request data (each request message corresponds to a certificate ID).

[0137] Step 5: The server sends a request to an external certificate issuance service and receives challenge information. The server uses the communication control module to send the request generated in step 4 to an external certificate information issuance service over the network, and receives the returned challenge information.

[0138] Input: Authentication information retrieval request data list, network connection parameters (target service address, port, security protocol version).

[0139] The server establishes an encrypted connection through a transport layer security protocol and sends request messages one by one. The server reads response data from the receive buffer, decodes the response, and extracts fields such as challenge type (e.g., HTTP verification or DNS verification), challenge token, verification path, and expected content. The server then associates this challenge information with the certificate ID and writes it into the challenge information table.

[0140] Output: A list of challenge information (each entry includes certificate ID, challenge type, token, and verification parameters).

[0141] Step 6: The server performs domain ownership verification preparation operations based on the challenge type. The server automatically prepares the verification environment locally or through an external service, depending on the type of challenge information.

[0142] Input: Challenge information list, certificate configuration table, web service configuration, DNS service access parameters.

[0143] When the server detects that the challenge type is based on hypertext path verification, it creates a verification file in the root directory of the corresponding site in the file system. The file name is set to the challenge token, and the file content is written with the verification string. The server updates or checks the web service configuration to ensure that the verification path can be accessed externally and is not interfered with by redirection. When the challenge type is based on domain name resolution record verification, the server calls the domain name resolution service interface through the communication control module, submits a request to add a new text record, sets the record name to the specified prefix + domain name, writes the record value into the verification string, and periodically checks whether the record is effective.

[0144] Output: A list of verification preparation results (each entry includes the certificate ID, challenge type, preparation success flag, and error message fields).

[0145] Step 7: The server notifies the issuance service to begin verification and receives the verification result. After completing the verification preparation, the server proactively sends a verification ready signal to the external signing service and obtains the verification result.

[0146] Input: Verification preparation result list, challenge information list.

[0147] For each successfully prepared certificate ID, the server generates verification confirmation request data, including the certificate ID, challenge identifier, and preparation status. The server sends this request to the issuance service and parses the verification status code and explanatory text in the returned data. For records that pass verification, the server updates the certificate status to "verification passed" in the status management table. For records that fail verification, the server records the reason for the failure and marks them as "verification failed, to be retried" according to a preset strategy.

[0148] Output: A list of verification results (certificate ID, whether verification passed, reason for failure), and an updated status management table.

[0149] Step 8: The server performs settlement processing related to certificate renewal. After successful verification, the server invokes the electronic settlement service to settle the payment for the certificate renewal process that requires payment.

[0150] Input: Verification result list, settlement template table (including pricing scheme, currency, etc.), account information.

[0151] For certificate IDs that have passed verification and require payment, the server selects the corresponding scheme from the settlement template table, constructs a settlement request data structure, and the fields include transaction ID (generated by the server), certificate ID, amount, currency, payment account identifier, etc.; the server sends an encrypted request to the electronic settlement service through the network interface, receives the settlement result message, parses the status field and serial number field in the result and writes them into the transaction completion information table; the server updates the certificate status to "pending issuance" or "settlement failed" according to the settlement success or failure.

[0152] Output: A list of settlement result records (each record includes certificate ID, transaction status, and transaction number), and an updated status management table.

[0153] Step 9: The server downloads the new certificate and stores it in the specified path. After verification and settlement are completed, the server obtains new encrypted authentication information from the external issuance service and saves it.

[0154] Input: Updated status management table (certificate IDs with status "pending issuance"), external issuance service interface parameters.

[0155] The server generates certificate download request data for each "to be issued" certificate ID and sends it to the issuance service; the server receives the new certificate content and related intermediate certificate chains as well as secret information (such as private key or key identifier), and checks the certificate format and basic field validity in memory; the server creates a new directory or overwrites existing files for each certificate on the storage device, writes the certificate file and secret information file to the specified path, and updates the corresponding path field in the certificate configuration table.

[0156] Output: New certificate file and secret information file, updated certificate configuration table.

[0157] Step 10: The server updates the network service configuration and performs configuration verification. After obtaining the new certificate, the server automatically modifies the network service configuration file and performs syntax and logic checks.

[0158] Input: Updated certificate configuration table (new certificate path), current network service configuration file content, backup directory path.

[0159] The server first backs up the existing configuration file by copying it to the specified backup directory. The server then parses the configuration file text in memory, locates the certificate path configuration item associated with the target domain name, and replaces the old path with the new certificate path and the new secret information path. The server writes the modified configuration text back to the configuration file and calls the configuration check command provided by the network service software, executes it in a subprocess, and captures the return code and error output. The server sets the configuration verification status field based on the check results.

[0160] Output: Updated network service configuration file, configuration verification results (success / failure and error messages).

[0161] Step 11: The server reloads the network service and verifies the validity of the new certificate. After the server successfully verifies the configuration, it performs a service reload operation and checks whether the new certificate is effective.

[0162] Input: Configuration verification result, network service control interface parameters (service name, control command).

[0163] When the server detects that the configuration verification is successful, it calls the system service management program or the control command provided by the service to perform a smooth reload, so that the network service reloads the configuration file and certificate file. After the reload is completed, the server accesses its own service port through local or remote commands (such as test requests based on encrypted communication), parses the returned certificate chain information, and verifies that the certificate fingerprint, expiration time and new certificate record are consistent. The server writes the verification result to the log and status management table and updates the certificate status to "deployed".

[0164] Output: Service reload result (success / failure), new certificate activation verification result, and updated status management table.

[0165] Step 12: The server generates a notification message and invokes a generative artificial intelligence model. The server automatically constructs prompt statements based on certificate status, settlement results, and configuration update results, which are then used by the generative artificial intelligence model to generate notification content and strategies.

[0166] Input: Status management table (including certificate status, remaining days, and error records), notification policy template.

[0167] The server selects the events to be notified (such as successful update, failed update, unprocessed certificate about to expire, etc.) from memory, fills in key fields (domain name, expiration date, reason for failure, etc.) into a preset natural language template according to the event type, and generates prompt text, such as: "Please generate an alarm message for operations and maintenance personnel based on the following certificate status, including the domain name, current status, suggested operation steps, and keep it within 200 characters." The server packages these prompts as model input and sends them to the inference service interface of the generative artificial intelligence model.

[0168] Output: List of prompt statements, request data sent to the generative artificial intelligence model.

[0169] Step 13: The server receives the response from the generative artificial intelligence model and generates notification data. The server receives response information from the generative artificial intelligence model and converts it into sendable notification data.

[0170] Input: The response text returned by the generative artificial intelligence model (including suggested notification content, sorting suggestions, and sending method suggestions).

[0171] The server parses the response text in memory, identifying the notification body paragraphs, priority suggestions, and suggested notification media (e.g., email, instant messaging). The server maps this content to an internal notification data structure, populating it with notification ID, recipient identifier, content field, priority field, and media field. The server writes the notification data to a notification queue list for subsequent processing by the notification control module.

[0172] Output: Notification data queue (structured notification records).

[0173] Step 14: The server optimizes notification priority and delivery method based on the user's emotional state. The server uses the emotional state estimation information provided by the user state acquisition module to reorder the notification data queue and optimize the media selection.

[0174] Inputs: notification data queue, emotional state estimation information (such as user's current stress index, busyness level classification), and established business priority rules.

[0175] The server combines the sentiment status value with the notification priority value and applies a predefined weighted formula or rule table to calculate a comprehensive priority score. The server sorts the notification queue according to the comprehensive score, placing notifications with high comprehensive scores at the top. Based on the media suggested in the response information and the sentiment status (e.g., reducing the frequency of instant push notifications and using summary emails in response to high stress), the server sets a specific sending channel field for each notification. The server updates the relevant fields in the notification queue list.

[0176] Output: Optimized notification data queue (including overall priority and final media selection).

[0177] Step 15: The server sends a notification and records the sending result. The server sends notifications to the corresponding users or administrators through different channels based on the optimized notification data queue, and records the results.

[0178] Inputs: Optimized notification data queue, mail server configuration, and instant messaging interface parameters.

[0179] The server iterates through the notification queue, calls the corresponding sending module for each notification based on the media field, for example, constructs an email message and sends it to the target mailbox through the email sending module, or constructs a text message and calls an external interface through the instant messaging module; the server reads the return code and response content of each sending operation, determines whether the sending was successful, updates the sending status field in the notification record, and writes the sending result to the log.

[0180] Output: Notification sending result record (each record includes notification ID, sending medium, success / failure flag, and error message).

[0181] Step 16: Users can input prompts via the terminal to optimize automated processes. Users interact with generative artificial intelligence models on the terminal and propose improvements to automated processes.

[0182] Input: The prompts entered by the user on the terminal interface, for example: "Please help me design an automated certificate management process, including a failure retry strategy and concurrency control specifications for multiple service instances." "Based on the following error log snippet, analyze the reason for the certificate update failure and provide suggested steps to improve the configuration and process." Users type the aforementioned natural language text into a browser or client application on the terminal and send it to a server or remote generative artificial intelligence service via the network; users receive the instructions, suggested steps, or configuration schemes returned by the model on the terminal and view and understand them on the interface.

[0183] Output: User-confirmed improvement suggestions (which can be used for subsequent manual adjustments or further automation).

[0184] Step 17: The server updates the automatic execution step information and control parameters based on the model's recommendations. After receiving the process suggestions generated by the model, the server converts them into information on automatically executed steps and control parameters that can be executed within the system.

[0185] Input: Suggested text output by the generative AI model in response to user prompts, and existing scheduling management configuration.

[0186] The server parses the suggested text, extracts the described steps, conditional judgments, retry intervals, rollback conditions, and other elements, and maps them into structured step records. The server inserts or updates the new step records into the task definition table of the scheduling management module, while adjusting relevant thresholds and weight parameters, such as the certificate check cycle, maximum number of retries, and timeout. The server thus dynamically changes the execution method of subsequent processing steps, achieving technical optimization of the entire certificate management process.

[0187] Output: Updated automatic execution step information, updated control parameters, and scheduling configuration.

[0188] Application Example 1 The process flow corresponding to the specific processing in Use Case 1 will be described below. The various parts of the system described below are implemented by the data processing device 12 and the intelligent device 14. Furthermore, the data processing device 12 is referred to as the "server" and the intelligent device 14 is referred to as the "terminal".

[0189] With the expansion of network services and the increasing security requirements, encrypted communication and authentication based on digital certificates have become key technologies in computer network infrastructure. However, in existing technologies, the lifecycle management of digital certificates still faces the following technical challenges: First, servers typically rely solely on simple expiration time check scripts, failing to automate various computer processing steps such as certificate expiration detection, certificate application, external settlement processing, certificate deployment, and service reloading within a unified framework. This results in a highly fragmented certificate renewal process at the implementation level, complex system maintenance, and a susceptibility to configuration inconsistencies and security vulnerabilities. Second, while servers can generate status logs, there is a lack of mechanisms to structure this low-level status data into high-level semantic information and link it with the terminal. Terminals cannot perceive changes in certificate status in a human-friendly manner, making it difficult to... First, existing notification mechanisms are mostly fixed templates or hard-coded texts, which cannot dynamically adjust the content and priority of notifications based on digital certificate status, transaction results, and user emotional state. This makes it impossible to fully utilize the intelligent processing capabilities of computers to reduce the cognitive burden and decision-making costs of operation and maintenance personnel. Second, although generative artificial intelligence models have been widely used in the field of natural language generation, there is still a lack of a systematic technical solution in the certificate management scenario that can automatically convert the underlying structured state data into high-level semantic prompts, thereby driving the generative artificial intelligence model to generate notification texts that are adapted to users with different technical backgrounds and emotional states.

[0190] In summary, current technologies cannot yet achieve, within a single computer system: fine-grained monitoring of digital certificate validity periods, automatic invocation of external certificate issuance and settlement service interfaces, automatic control of certificate deployment and service reload processes, and generation of prompts based on structured state information and user state information for generative artificial intelligence models, thereby achieving intelligent optimization in notification content, timing, and priority. Therefore, it is necessary to propose a new computer implementation method and system architecture to improve the automation, reliability, and human-computer interaction experience of digital certificate lifecycle management, thereby substantially improving the technical performance of computer systems in terms of secure operation and management.

[0191] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is achieved by the following means.

[0192] In this invention, the server includes: a processing unit for acquiring the validity period information and current time information of a digital certificate, calculating the remaining time until the validity period expires, and determining whether the remaining time is within a predetermined threshold; a processing unit for, when determining that the remaining time is within the predetermined threshold, using a certificate issuance communication function to call the application programming interface of a certificate issuance external device, generating and sending new digital certificate issuance request data, and managing the certificate issuance processing progress based on certificate issuance status data received in response; a processing unit for, based on the certificate issuance status data, using a settlement communication function to call the application programming interface of a settlement processing external device, generating and sending settlement request data containing fee information related to the acquisition of the digital certificate, and recording the transaction completion status based on settlement result data received in response; and a processing unit for storing the new digital certificate in an information processing device. The system includes: a storage area for updating certificate-related parameters in the configuration file of the communication processing device and applying the new digital certificate by reloading the operation of the communication processing device; a processing unit for generating status information containing the validity period information of the digital certificate, the certificate issuance status data, and the settlement result data, and implementing a status information providing interface for providing the status information to an external terminal device; a processing unit for extracting element information of notification content based on the status information, setting conditions for generating prompt information containing the element information, and generating a prompt statement representing the prompt information generation conditions as input data for a generative artificial intelligence model; and a processing unit for acquiring the natural language text output by the generative artificial intelligence model based on the prompt statement and sending the natural language text to the external terminal device as notification information. This enables the formation of an integrated computer processing flow within the server, encompassing everything from automatic invocation of certificate validity period checks, external certificate issuance and settlement services, automatic certificate deployment and service reloading, to automatic construction of prompt statements based on structured state information and driving a generative artificial intelligence model to generate personalized natural language notifications. This reduces delays and errors caused by manual intervention, improves the automation and reliability of digital certificate lifecycle management, and enhances the human-computer interaction experience and decision-making efficiency for users during operation and maintenance management through intelligent optimization of notification content and priorities.

[0193] A "system" refers to a set of hardware and software components consisting of one or more information processing devices, communication devices, and programs running on them, used to implement digital certificate management, external interface calls, and notification generation and output.

[0194] A "digital certificate" is an electronic data structure used to provide identity authentication and data encryption capabilities during communication. It includes at least subject information, public key information, signature information, and validity period information.

[0195] "Validity period information" refers to a set of time parameters used to indicate when a digital certificate begins to take effect and when it ends to take effect, including at least the expiration date.

[0196] "Current time information" refers to the time data obtained by the system clock or time service to represent the current moment, which is used for comparison and calculation with the validity period information.

[0197] "Remaining Time" refers to the time difference between the current time and the expiration date of the digital certificate, used to determine whether the certificate is nearing its expiration.

[0198] "Preset threshold" refers to the time length threshold set in the system to determine whether a digital certificate is nearing its expiration date, such as a certain number of days.

[0199] A “processing unit” refers to one or more program modules executed by a processor to perform a specific data processing function. This logical unit can be implemented through software, hardware, or a combination of both.

[0200] "Certificate issuance communication function" refers to the network communication capability used to establish a communication connection and exchange data between the system and an external certificate issuance device, including at least the functions of sending request data and receiving response data.

[0201] "External device for certificate issuance" refers to an external computing device or service system that provides digital certificate issuance services, receives certificate application requests through a predetermined interface and returns certificate issuance status or certificate data.

[0202] An "Application Programming Interface" is an interface specification disclosed by an external device for function calls and data exchange between programs, which can be accessed through network protocols.

[0203] "Issuance request data" refers to a set of data generated by the system and sent to an external device for certificate issuance, used to request the external device to issue a new digital certificate, and includes at least the identification information required for the certificate application.

[0204] "Certificate issuance status data" refers to a set of data returned by an external device used for certificate issuance to indicate the progress and results of certificate application processing, and includes at least processing status information.

[0205] "Settlement communication function" refers to the network communication capability used to exchange data related to cost settlement between the system and external devices used for settlement processing.

[0206] "External devices for settlement processing" refers to external computing devices or service systems that provide transaction settlement or payment processing services, used to receive settlement requests and return settlement results.

[0207] "Settlement request data" refers to the data set generated by the system and sent to the external device used for settlement processing to request the execution of transaction settlement processing, which includes at least fee information and transaction identification information.

[0208] "Fee information" refers to price-related data such as the amount of money required to obtain a digital certificate and the type of currency.

[0209] "Settlement result data" refers to the set of data returned by the external device used for settlement processing to indicate the settlement processing result, which at least includes status information of payment success or failure.

[0210] "Transaction completion status" refers to the status information determined based on settlement result data regarding whether the settlement process for obtaining a certain certificate has been successfully completed.

[0211] "Information processing device" refers to a computing device equipped with a processor, memory, and communication interface, used to execute programs and process data related to digital certificates.

[0212] "Storage area" refers to the storage resources in an information processing device used to store programs, certificate data and related configuration information, including persistent storage and volatile storage.

[0213] "Communication processing device" refers to a device or software module used to execute network protocols and process network data transmission and reception, which may be a network server, gateway or other network communication component.

[0214] "Configuration file" refers to a collection of files that record the operating parameters and behavioral configurations of the communication processing device, and is used to control the working mode of the communication processing device.

[0215] "Certificate-related parameters" refers to the configuration items in the configuration file used to specify the storage location of digital certificates, certificate types, and other information related to certificate applications.

[0216] "Status information" refers to a set of data generated by the system that comprehensively represents various operational statuses such as the validity period of a digital certificate, the certificate issuance status, and the settlement result.

[0217] "Status information provider interface" refers to a program interface or network access interface used to provide status information to external terminal devices, and can be implemented in the form of application programming interface.

[0218] "External terminal device" refers to a user-side or management-side computing terminal device that is connected to the system via a network and is able to receive notification information, such as a mobile terminal or workstation.

[0219] "Element information of the notification content" refers to the key information units extracted from the status information that constitute the core semantics of the notification text, such as certificate status, expiration time, settlement result, etc.

[0220] "Prompt message generation conditions" refers to a set of rules, parameters, or templates used to guide how to combine and express element information to generate prompt messages, and to control the structure and tone of the generated content.

[0221] "Prompt information" refers to intermediate-level text information generated based on element information and prompt information generation conditions, used to summarize the current state of the system or provide operational suggestions.

[0222] "Prompt statements" refer to natural language or semi-structured text instructions used as input to generative artificial intelligence models to describe the generation goals and constraints.

[0223] "Generative AI models" refer to AI models that can automatically generate natural language text or other data content based on input prompts.

[0224] "Natural language text" refers to string data expressed in human natural language, output by generative artificial intelligence models, which is used to directly display to users or terminal devices.

[0225] "Notification message" refers to a message containing natural language text that is sent to an external terminal device to indicate the status of a digital certificate or the result of related operations.

[0226] "User status information" refers to a set of data collected or generated by external terminal devices to reflect the user's current status (including emotional state), which can be obtained through interactive behavior or sensor data.

[0227] "Emotional state index" refers to a set of parameters or parameters that are calculated based on user state information and used to quantitatively represent the emotional characteristics of users.

[0228] "Notification priority" refers to a hierarchy of information used to indicate the importance of different notifications in terms of their sending order, display prominence, or reminder intensity.

[0229] "Presentation" refers to how notification information is presented on external terminal devices, including text length, tone, display position, or whether it is accompanied by sound and vibration.

[0230] In this embodiment of the invention, the server operates as the core information processing device. The server includes a processor, storage device, and network interface. The server runs multiple software modules on a general-purpose operating system (e.g., a Linux-based server operating system). These modules include: a certificate management module, an external interface call module, a configuration management module, a status information generation module, a prompt statement generation module, and a generative artificial intelligence model call module. The terminal operates as an external terminal device on a mobile communication device or desktop computing device. The terminal communicates with the server via a network and displays natural language notification text generated or co-generated by the server to the user.

[0231] The server uses an encryption library (such as the general OpenSSL library or an equivalent cryptographic algorithm library) in its certificate management module to read digital certificate files from the storage area. The server performs syntax parsing and time format conversion on fields such as "NotBefore" and "NotAfter" in the certificate data structure, converting this time data into a unified timestamp format and storing it in an in-memory data structure. The server obtains the current time information using the system clock or network time protocol service. It calculates the difference between the current time and the expiration time using an arithmetic operation module to obtain a numerical representation of the remaining time, and compares this remaining time with a predetermined threshold. The server maintains a mapping relationship of "certificate identifier → remaining time → status flag" in memory using a key-value structure, and persistently records this mapping in the storage device in the form of a relational data table or key-value database for subsequent access by the certificate issuance and settlement modules.

[0232] The server utilizes a standard HTTP / HTTPS communication stack in its external interface call module to communicate with external devices via an application programming interface. When calling an external device for certificate issuance, the server constructs an issuance request data structure containing fields such as a list of domain names, certificate type, applicant identifier, and challenge method. This data structure is serialized into a text format (e.g., JSON or XML) and the communication is encrypted using a transport layer security protocol. Upon receiving certificate issuance status data, the server parses the returned message according to a predetermined pattern, mapping fields such as status code, challenge information, and certificate chain data to an internal object representation. The server maintains multiple discrete states in its internal state machine, such as "not applied for → applied for → challenging → issued," and drives subsequent settlement requests and certificate deployment processing based on these states.

[0233] In settlement processing, the server calls the interface of the external device used for settlement processing. The server generates settlement request data containing transaction identifier, fee amount, currency type, customer identifier, and security token. The server signs or calculates a message authentication code for this data to ensure data integrity and authentication during transmission. After receiving the settlement result data, the server writes the payment status, error code, transaction time, and transaction serial number into the transaction record table. The server uses an index structure to accelerate subsequent query and verification operations, thereby achieving structured management of the settlement process within the computer. Because the server associates and stores the certificate issuance status with the settlement result, the server can automatically determine whether the entire certificate acquisition process is complete without manual intervention and control the certificate deployment logic accordingly.

[0234] The server parses and updates the configuration files of the communication processing devices within the configuration management module. The server maintains a set of templated configuration fragments for different types of communication processing programs (such as common web server software or reverse proxy software). Internally, the server represents the configuration file content in the form of an abstract syntax tree or key-value mapping. When updating certificate-related parameters, the server does not simply replace text but performs syntax-level node updates to ensure the structural correctness of the configuration file and the consistency of parameters. After completing the configuration file update, the server sends a reload command through the system service manager interface (such as a general service management framework). The server applies the new certificate file without completely interrupting existing connections, thereby ensuring service continuity while reducing the risk of certificate switching. This configuration management method, through structured analysis and automatic updates of the configuration files, reduces the risk of syntax errors and service interruptions caused by manual editing, substantially improving the reliability of the computer system during certificate deployment.

[0235] In the status information generation module, the server structurally aggregates data from multiple sources. It obtains validity period information and remaining time from the certificate management module, certificate issuance status data from the external interface call module, and settlement result data from the settlement processing module. The server organizes this data into a multi-layered status information object, assigning a unique identifier and timestamp to each layer. The server maintains a collection of status information indexed by domain name, certificate fingerprint, or service identifier in storage. It provides query services to terminals through a status information provision interface. This interface can be an HTTP-based application programming interface, allowing terminals to request status information for a specific certificate or service group as needed. By pre-aggregating and indexing status information, the server improves the response speed of status queries and reduces the overall system load caused by repetitive calculations by terminals.

[0236] In the prompt statement generation module, the server transforms the internally used structured state data into natural language or semi-structured text descriptions suitable for use as input to generative artificial intelligence models. The server first extracts key information about the notification content based on the state information, such as whether a certificate is about to expire, the validity period of a new certificate, whether the settlement was successful, whether there is an error code, and whether manual intervention is required. Then, according to predefined prompt statement generation conditions, the server combines this key information into a prompt statement with explicit instructions and constraints. In this process, the server uses a combination of a rule base and a template library. The rule base specifies the elements to be emphasized, the tone, and the length requirements for different state combinations, while the template library provides basic sentence structures. The server fills the placeholder positions in the template with the key information and adds constraints such as language requirements, output length limits, and tone requirements to the generated prompt statement.

[0237] In the generative AI model invocation module, the server uses a deep learning-based generative AI model, which can be a sequence-to-sequence neural network with a multi-layer self-attention structure. The server configures a multi-layer encoder and a multi-layer decoder in the model structure. The encoder vectorizes the input prompt sequence, and the decoder progressively generates the output natural language text based on the encoding results. Within the model, the server uses word embedding layers to map words or sub-words to a high-dimensional vector space, utilizes multi-head self-attention to capture long-distance dependencies within sentences, and employs a feedforward network to perform non-linear transformations on the features at each position. During model training, the server uses large-scale text corpora and synthetic certificate scenario dialogue data as training samples. The server uses cross-entropy as a loss function to quantify the difference between the model output and the target text, and updates the network weights using stochastic gradient descent or its variants (such as adaptive learning rate optimization algorithms). During training, the server can employ data augmentation strategies, such as diversifying the replacement of time expressions, monetary expressions, and service names, to improve the model's generalization ability and robustness in certificate management scenarios.

[0238] After receiving the prompt statement during the inference phase, the server segments or breaks it down into sub-words, encodes it into a vector sequence, and inputs it into the model. During decoding, the server uses beam search or temperature-controlled sampling strategies to generate multiple candidate texts and selects the optimal candidate as the natural language text output based on evaluation metrics such as length penalty and keyword coverage. Before output, the server can apply a filtering module to remove or replace content that may not comply with the enterprise's security policy, thereby ensuring the security and professionalism of the notification text. In this way, the server transforms the underlying structured state information into natural language notifications that are adaptable to different users and scenarios, rather than being limited to fixed template text. This introduces a new information representation and generation mechanism within the computer, improving the flexibility and interpretability of notification expression.

[0239] In this embodiment of the invention, the terminal obtains status information and natural language notification text from the server via a network interface. The terminal runs a lightweight user interface module locally and directly displays the text provided by the server in the graphical interface or system notification area. The terminal can also group and sort notifications according to user preferences. In some embodiments, the terminal may additionally run a local natural language processing library (e.g., a general-purpose word segmentation and syntactic analysis library). The terminal performs local reprocessing on the natural language text returned by the server, such as simplifying terminology or adding supplementary explanations according to the user's language level. However, the terminal does not need to perform complex deep generation operations, thereby saving the terminal's computing resources.

[0240] In this embodiment of the invention, users receive notification information and perform query operations through a terminal interface. Users can view the certificate status, latest update time, and settlement records of various services or domains on the terminal interface. When needed, users can send additional requests to the server through the terminal, such as requesting the generation of a certificate update report for a specific time period. Upon receiving such a request, the server can construct a new prompt statement through the prompt statement generation module, for example: "Please generate a simple and easy-to-understand notification text based on the following system status information to inform the website operators:" 1. The website's SSL certificate has been automatically renewed; 2. The new certificate is valid until February 1, 2026; 3. The renewal fee has been successfully paid automatically through the online payment interface; 4. The entire process does not require manual intervention, but you can log in to the management backend to view detailed transaction records.

[0241] Please output in Simplified Chinese, using a formal yet easily understandable tone, and keep the length under 150 characters. The server inputs the prompt statement into the generative artificial intelligence model, and then returns the model's output text to the terminal, which displays it to the user. In another example, the server could construct more technically sophisticated prompt statements, such as: "Assuming the server uses web service software and a general certificate issuance interface to manage SSL certificates, please describe in detail the complete process of automatically ordering a new certificate, completing payment through the payment interface, and automatically updating the web service configuration and reloading the service after the certificate is issued when the certificate expires within 30 days. Please provide examples of the interface types that need to be called in each step, the data fields that need to be processed, and possible error handling strategies." Through the aforementioned generation and invocation process, the server establishes a reusable mechanism for constructing prompt statements within the computer. Combined with the deep generation capabilities of generative artificial intelligence models, this enables automatic mapping between low-level technical states and high-level natural language descriptions. This mechanism not only reduces the burden on manual maintenance personnel in writing notifications and reports but also improves the information expression methods of computer systems at the data structure and processing flow levels, thereby enhancing the representational and interactive capabilities of computer technology itself.

[0242] The server achieves several technical benefits through the overall architecture of this invention. By automatically calculating and determining the validity period of certificates and applying thresholds, the server reduces omissions caused by manual polling and script configuration errors, thereby lowering the frequency of service interruptions due to certificate expiration. Through structured management of certificate issuance status and settlement results, and by optimizing internal data access paths using state machines and indexing mechanisms, the server enables rapid updates and queries of a large number of certificate states in high-concurrency scenarios, improving processing speed. By parsing and updating configuration files at the syntax level and applying new certificates through a controlled reload mechanism, the server reduces the risk of configuration errors and service interruptions, improving the overall stability and reliability of the system. By converting status information and user status information into prompt statements and generating adaptive natural language text using a generative artificial intelligence model, the server improves the relevance and understandability of notification content without increasing manpower costs, thereby reducing the probability of operational misjudgments and delayed responses.

[0243] In various implementations, the server can employ different types of generative AI model structures, such as a hybrid network structure combining convolutional layers and self-attention layers, or a sequence model with gated recurrent units. The server can also construct multiple specialized sub-models based on different languages ​​and domains, selecting the appropriate sub-model for inference through a routing mechanism. In terms of feature design, the server can extend input features beyond certificate status and time information, incorporating contextual metrics such as service access volume and recent fault records, allowing the model to comprehensively consider risk levels and business impact when generating notifications. These extensions enable the invention to be applicable not only to single-certificate scenarios but also to large-scale service clusters and multi-tenant environments, thus leveraging its technological advantages in more complex computer systems.

[0244] Through the above implementation, the server, terminal, and user work collaboratively under the framework of this invention. Internally, the server implements an integrated data flow encompassing certificate status detection, external interface calls, configuration updates, prompt statement construction, and generative artificial intelligence model inference. The terminal handles display and lightweight processing, and the user makes decisions based on high-quality natural language notifications provided by the system. This structure does not simply automate manual work; rather, it transforms the technical behavior of computer systems in three areas—security management, configuration control, and human-computer interaction—through specific data structures, algorithmic processes, and model architectures, thereby achieving comprehensive technical improvements in processing speed, error rate, maintenance costs, and interaction quality.

[0245] use Figure 12 The processing procedure is explained.

[0246] Step 1: The server retrieves the certificate and time information and calculates the remaining time. The inputs are the digital certificate file in the storage device and the current system time. The server calls the encryption library to parse the expiration date field in the certificate, converting the expiration time into a unified timestamp format; simultaneously, the server obtains the current timestamp from the system clock. The server performs a subtraction operation on the two timestamps to obtain the remaining time value, compares the remaining time with a predetermined threshold, and generates a status flag indicating whether the expiration is imminent as output. The server writes the certificate identifier, remaining time, and status flag to a memory structure and persistent storage.

[0247] Step 2: The server generates certificate issuance request data based on the remaining time status flag. The inputs are the certificate identifier, remaining time, and "near expiration" status flag output from step 1. When the server detects that the status flag is "near expiration," it reads parameters such as the domain name list, certificate type, and applicant information from the configuration store, assembling these parameters into a structured data object. The server uses a serialization library to encode this object into text format and adds metadata such as authentication tokens and request headers for subsequent network calls. The output is a certificate issuance request message to be sent and its corresponding internal order record.

[0248] Step 3: The server invokes the interface of the external certificate issuance device and processes the response. The input consists of the certificate issuance request message generated in step 2 and the order record. The server sends the request message to the external certificate issuance device via the network interface and waits for a response. After receiving the response message, the server uses a parsing module to convert the message into an internal data structure, extracting fields such as the certificate issuance status code, order identifier, and challenge information. Based on the status code, the server updates the status field of the internal order record, writes the new status (e.g., "Accepted," "Pending Verification," "Issued") as output to the database, and provides the updated order status object for subsequent processes.

[0249] Step 4: The server determines whether to trigger a settlement request based on the certificate issuance status. The input is the order status object output in step 3. When the server detects a status of "issued" or "settlement available," it reads the fee standard and currency type from the configuration and the certificate type and validity period information from the order record. The server calculates the amount due according to predetermined rules and assembles fields such as amount, order identifier, and customer identifier into a settlement request data structure. The server serializes this data structure into a transmission format and outputs it as a settlement request message to be sent. If the status does not meet the settlement conditions, the server outputs a "settlement not required" status and ends the current round of settlement processing.

[0250] Step 5: The server invokes the external device interface for settlement processing and records the transaction results. The input is the settlement request message generated in step 4. The server sends the settlement request to the external settlement device through a secure communication channel, and signs or calculates a message authentication code before sending the message. After receiving the settlement response message, the server parses the payment status, error code, transaction serial number, and settlement time in the response, mapping these fields to internal transaction record objects. The server marks the transaction as "successful" or "failed" according to the payment status, writes the transaction record to the transaction data table, and outputs the transaction completion status and settlement result data associated with the order.

[0251] Step 6: After successful settlement, the server downloads and stores the new digital certificate. The input consists of the order information in the "Issued" status from step 3 and the settlement result data of "Payment Successful" output from step 5. The server calls the certificate download function through the certificate issuance interface and receives response data containing the new certificate chain. The server performs format validation and integrity checks on the response content, writes the certificate chain and key data to the specified storage path of the information processing device, and sets access permissions. Internally, the server generates a Certificate Deployment Object indicating the path to the new certificate file and its metadata, serving as input and output for subsequent configuration updates.

[0252] Step 7: The server updates the configuration file of the communication processing device and reloads the service. The input is the certificate deployment object output from step 6 and the contents of the existing configuration file. The server uses the configuration parsing module to parse the configuration file into a structured representation, locating the certificate path and key path parameter nodes. The server replaces these parameter nodes with the new certificate path, reserializes it into a text configuration file, and writes it back to disk. The server then sends a "reload" control command to the communication processing device, causing it to reread the configuration and load the new certificate. The server determines whether the reload was successful based on the status information returned by the service and outputs the certificate deployment status result.

[0253] Step 8: The server aggregates certificate and transaction statuses and generates unified status information. Inputs include the remaining time and status flags from step 1, the certificate issuance status from step 3, the settlement result from step 5, and the certificate deployment status from step 7. The server combines this data into a multi-field status object, including certificate identifier, current status, remaining time, issuance stage status, payment status, deployment status, and last update time. The server stores this status object in a status information storage area and prepares it for external queries through a status information interface, outputting a standardized status information record accessible to terminals.

[0254] Step 9: The server generates prompt information elements and constructs prompt statements based on the status information. The input is the status information record output in step 8. The server first analyzes the status information according to the rule base, such as determining conditions like "approaching expiration," "successful automatic renewal," and "payment or deployment failure." The server extracts elements such as domain name, expiration time, new certificate validity period, payment result, and error description from the status information. The server then selects an appropriate sentence template based on the prompt information generation conditions, such as preparing different explanatory structures for operations and maintenance personnel or administrators. The server fills the elements into the template, while adding conditions such as language requirements, length constraints, and tone descriptions, generating a text-based prompt statement, which serves as the input and output of the generative artificial intelligence model.

[0255] Step 10: The server invokes a generative AI model to generate natural language notification text. The input is the prompt statement generated in step 9. The server encodes the prompt statement into a sequence of inputs for the model and performs inference using the deployed generative AI model. Internally, the server generates multiple candidate texts using a self-attention mechanism and decoding strategy. The server selects candidates that meet the length and keyword coverage requirements as the output natural language text. The server can apply filtering rules at the output stage to remove content that does not meet security or style requirements, ultimately obtaining a notification text optimized for the current state conditions. This text, along with the corresponding certificate identifier, is then stored as output in the sending queue list.

[0256] Step 11: The server sends a notification text to the terminal and provides a status query interface. The input consists of the natural language notification text output in step 10 and the status information record from step 8. The server sends the notification text to the target terminal via a push notification service or application programming interface; simultaneously, the server allows the terminal to retrieve the corresponding status information by certificate identifier or service identifier in the status query interface. When responding to a terminal query request, the server reads the corresponding record from the status information storage area and returns it to the terminal, outputting a terminal-oriented notification data packet and a status data packet.

[0257] Step 12: The terminal receives the notification and presents it to the user. The input consists of the notification data packet and status data packet sent by the server in step 11. The terminal parses the received natural language text and status fields, displays the notification text in the system notification bar or application interface, and determines whether to add highlighting, sound, or vibration alerts based on the status fields. When necessary, the terminal structures the status data into tables or graphs, providing information such as certificate expiration date, most recent renewal date, and payment status. The terminal locally generates user-interactive interface elements, such as controls for "View Details," "Recheck," and "Generate Report," and outputs a visual interface for user interaction and a local status cache.

[0258] Step 13: The user triggers an additional request based on the terminal interface. The input consists of the interface and notification text presented by the terminal in step 12. The user selects a certificate or service by clicking or typing, and issues instructions such as "Check certificate again immediately," "View payment records," or "Generate this month's certificate renewal report." The terminal converts the user's actions into structured request parameters and sends them to the server via the network interface. After receiving these requests, the server re-executes the processing related to status checks, transaction queries, or prompt statement generation, outputs new status information and notification text, and then feeds back to the user through steps 11 and 12, achieving a closed-loop interaction.

[0259] Alternatively, an emotion engine for inferring user emotions can be combined. That is, the specific processing unit 290 can also use the emotion-specific model 59 to infer user emotions and perform specific processing using user emotions.

[0260] Example 2 The flow of a specific process in Example 2 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 as the "terminal."

[0261] With the widespread adoption of encrypted communication-based network services, e-commerce, and cloud services, the number of deployed digital certificates and the structure of certificate chains are becoming increasingly complex. Current technologies rely heavily on static scripts, fixed rules, or manual ledger management for monitoring and updating certificate validity, presenting the following technical problems: First, in a distributed service environment, servers need to periodically call underlying encryption components to obtain certificate information and perform time calculations and status determinations. Relying solely on simple scripts makes it difficult to manage the certificate status of multiple domains and systems in a timely and unified manner, easily leading to monitoring blind spots and delays, affecting system security and availability. Second, traditional alarm mechanisms often use fixed templates and thresholds, failing to automatically differentiate risk levels based on the specific range of remaining certificate validity, nor can they dynamically adjust notification frequency based on historical notification records. This results in missed or delayed reports, and the possibility of repeated notifications to the same object within a short period, increasing the management burden. Third, existing systems typically do not utilize user actions or interactive content to estimate user psychological states. Alert content and timing can only be delivered using a uniform strategy, failing to differentiate scheduling based on different users' stress levels, workloads, and attention spans. This results in some notifications being ignored at critical moments or further disrupting users under significant stress. Fourth, existing solutions utilizing generative AI models primarily focus on natural language generation itself, lacking deep coupling with underlying certificate status calculations, risk grading, historical records, and user psychological state estimations. The generated text struggles to balance technical accuracy, risk expression levels, and the controllability of notification strategies, failing to truly optimize system operation and maintenance interactions and reduce the incidence of security incidents.

[0262] Therefore, designing a unified technical architecture at the computer system level that enables servers to automatically acquire and parse the validity period attributes of digital certificates, combine time calculation and threshold judgment to achieve refined status classification, and link with generative artificial intelligence models to generate prompt statements in a structured manner, and then adaptively control the content, presentation, sending channel and sending timing of notifications based on the user's psychological state and notification history, thereby reducing operation and maintenance costs and improving the overall reliability and human-computer interaction efficiency while ensuring security, has become a technical challenge that needs to be solved.

[0263] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Embodiment 2 is achieved by the following means.

[0264] In this invention, the server includes a processing unit for automatically acquiring validity period attribute information of electronic proof information used for encrypted communication in an information processing device, calculating the remaining time to the validity period based on the current time information and determining the status according to a preset threshold, a generation control unit for generating structured data containing monitoring object identifier, validity period, remaining time, status distinction and business impact information based on the status determination result, encapsulating it into a prompt statement and inputting it into a generative artificial intelligence model, causing the generative artificial intelligence model to generate a prompt statement for indicating certificate update or acquisition operations and notification sending conditions, and a generation control unit for outputting information based on the generative artificial intelligence model. The notification text and sending conditions are processed through an electronic communication channel or interface display channel, and the monitoring results and notification records are recorded in the storage unit. The notification control unit controls the notification frequency and priority for the same monitored object based on the records. The psychological state analysis unit infers the user's psychological state based on the operation record information or interaction content information from the user terminal and dynamically changes the prompt statement conditions input to the generative artificial intelligence model to generate prompt statements for adjusting the presentation, detail and timing of the notification text. The task scheduling unit sets and executes a series of control information for periodically and automatically repeating the above monitoring, prompt statement generation and notification processing. This enables the formation of an integrated technical chain on the server side, encompassing everything from collecting underlying data on certificate validity periods, accurately calculating remaining time, determining risk levels, generating structured prompts using generative artificial intelligence models, to adaptively optimizing notification content and sending strategies based on user psychological states and historical records. This improves the automation and precision of certificate lifecycle management, reduces human intervention and errors, lowers the probability of service interruptions and security incidents caused by certificate expiration, and significantly improves the human-computer interaction experience for operations and maintenance through intelligent scheduling of notification channels, frequency, and text style, thereby achieving technical improvements in the overall reliability and operational efficiency of the computer system.

[0265] "Information processing device" refers to a general-purpose or special-purpose computing device that includes a processor, memory and input / output interfaces, and is used to execute program instructions and process electronic data, including but not limited to servers, terminal devices or combinations thereof.

[0266] "Electronic authentication information used for encrypted communication" refers to electronic authentication data used to identify the identity of communication entities and establish secure sessions during encrypted communication, including but not limited to digital certificates, public key certificates, or other authentication data structures containing validity period information.

[0267] "Validity period attribute information" refers to the time interval data associated with electronic certificate information that indicates its trustworthiness and usability in the time dimension, including start time, end time, and the remaining validity period derived therefrom.

[0268] "Current time information" refers to time data representing the current moment obtained by an information processing device based on a system clock or time service, including local time, Coordinated Universal Time, or time calibrated by a time synchronization service.

[0269] "Remaining Time" refers to the time difference between the expiration date of the electronic certificate information and the current time, indicating the length of time that the electronic certificate information can still be trusted and used in the future.

[0270] "Preset threshold" refers to a time parameter that is pre-set in the system for classifying the remaining time or triggering specific processing, including a single threshold or multiple threshold ranges of different levels.

[0271] "Electronic certificate information status" refers to the result of classifying the availability of electronic certificate information in the time dimension based on validity period attribute information and predetermined thresholds, including but not limited to security status, warning status, soon-to-expire status, and expired status.

[0272] "Monitoring object identifier" refers to identification information used to uniquely or distinguishably identify the monitored electronic certificate information or its associated communication target, including domain name, network address, system name, service identifier, etc.

[0273] "Structured information" refers to a combination of information organized according to a predetermined data format, with clearly defined field names and data types, which is used to be parsed and processed by programs, including but not limited to key-value pair collections, records, objects, or document structures.

[0274] "Prompt statements" refer to text data or a combination of text and structured data that are provided as input to a generative artificial intelligence model to instruct the model to perform a specific generative task or to constrain the generated results.

[0275] "Generative artificial intelligence models" refer to data processing models that are based on machine learning algorithms, especially deep learning and large-scale corpus training, and can automatically generate natural language text or other content based on input prompts.

[0276] "Notification text" refers to natural language content generated by a generative artificial intelligence model or a pre-defined template based on the status of electronic certificate information, structured information, and prompts, used to inform users of certificate status, risk information, and suggested actions.

[0277] "Sending conditions" refers to the set of parameters associated with the notification text that control whether and how the notification is sent, including sending time, sending channel, target user, resend strategy, and priority.

[0278] "Electronic communication device" refers to software and hardware components used to send or receive notification texts through electronic communication networks, including but not limited to email sending modules, message push modules, instant messaging interfaces, etc.

[0279] "Interface display device" refers to a human-computer interaction interface component used to present notification text or monitoring results to users in a visual form, including displays, web interfaces, mobile application interfaces and their rendering software.

[0280] "Notification processing" refers to the entire process of providing information prompts to users through electronic communication devices or interface display devices based on notification text and sending conditions, including notification content generation, sending, display, and reception.

[0281] "Storage device" refers to a hardware or logical unit used to persistently or temporarily store electronic data, including hard disks, solid-state storage, memory units and their management software.

[0282] "Monitoring results" refers to the set of status information related to each monitored object obtained after acquiring, calculating, and determining the validity period of electronic certificate information.

[0283] "Notification processing execution records" refer to historical data that saves information such as the time, target, channel, content, and result of each notification processing, which is used for subsequent statistics and strategy adjustments.

[0284] "Notification frequency" refers to the number of times or intervals that notifications are sent to the same monitored object or the same user within a given time period.

[0285] "Notification priority" refers to a ranking parameter used to distinguish the importance and order of sending among multiple notifications to be sent.

[0286] "User terminal" refers to information devices operated by users and interacting with servers through a network, including but not limited to personal computers, mobile terminals, tablet terminals or other smart devices.

[0287] "Operation log information" refers to the recorded data about user operation behavior generated and collected during the interaction between the user's terminal and the system, including clicks, inputs, access paths, dwell time, etc.

[0288] "Interactive content information" refers to the specific content data generated when users interact with the system through text, voice, or graphics, including dialogue text, command content, feedback information, etc.

[0289] "User psychological state" refers to the state information about a user's emotions, stress level, concentration, and other psychological characteristics inferred from operation record information and interaction content information.

[0290] The "Psychological State Analysis Department" is a functional module that analyzes operation records and interaction content to infer the user's psychological state and output parameters for adjusting notification strategies.

[0291] The "Generation Control Department" refers to the functional module responsible for constructing structured information and prompts, calling generative artificial intelligence models, and controlling the types and constraints of their generated results.

[0292] The "Notification Control Department" refers to the functional module that determines whether and how to send a notification based on the notification text, sending conditions, monitoring results, and execution records, and performs corresponding notification processing.

[0293] The "Task Scheduling Department" refers to the functional module used to set and manage periodic or trigger-based task execution plans, and to automatically execute steps such as certificate monitoring, prompt statement generation, and notification processing according to predetermined control information.

[0294] In a preferred embodiment, the server operates as an information processing device in a data center environment, deployed on a computing device with a multi-core central processing unit, main memory, persistent storage, and network interface. The server runs a general-purpose operating system, such as a Unix-like operating system, and installs encryption communication libraries (e.g., an encryption tool implementing transport layer security protocols and certificate parsing functions), a script execution environment (e.g., an interpreted language environment supporting standard libraries), and network service components (e.g., a web server and application framework providing hypertext transfer services). The server works in conjunction with the storage device, power management unit, and network controller via an internal bus, supporting continuous reading and writing of certificate data, monitoring results, and user interaction records.

[0295] The server stores certificate monitoring and notification generation programs in its storage device. These programs are implemented in an interpreted language and are periodically activated through the operating system's task scheduling function. After these programs are loaded into main memory, the server uses its processing unit to execute parsing logic, time calculation logic, structured data construction logic, and generative artificial intelligence model invocation logic. The server maintains a list of monitored objects in its configuration file, which is stored as a hierarchical data structure containing monitored object identifiers, network connection parameters, threshold configurations, and notification policy configurations. At runtime, the server reads this configuration through a parsing library to form a memory-based mapping structure, facilitating subsequent rapid retrieval and calculation.

[0296] The server uses the command-line interface or programming interface provided by the encrypted communication tool to obtain electronic certificate information from the remote service node. The server initiates an encrypted handshake request to the target network address via the network interface and receives certificate chain data sent by the peer during the handshake process. The server buffers the returned certificate text into a byte sequence in memory and uses a regular expression module to parse the byte sequence, extracting the field containing the validity period. After extracting the validity period string, the server uses a time processing module to convert the string into a unified time object, and the result is serialized into an internal timestamp for subsequent arithmetic operations.

[0297] Based on the current time and the certificate's expiration timestamp, the server uses internal arithmetic logic to calculate the remaining time. The server subtracts the timestamp to generate a time difference object in days, hours, or other units. The server maps the time difference to intervals based on predetermined thresholds (e.g., greater than a certain value, within a certain range, less than or equal to a certain value), classifying the status of each monitored object into multiple discrete levels, such as a security level interval, a warning level interval, and a high-risk level interval. The server stores these classification results in memory as multi-field records, each containing at least the monitored object identifier, expiration timestamp, remaining time value, status level, and the time of the most recent notification.

[0298] After receiving the status classification results, the server reorganizes them into structured information. Using key-value pairs or record structures, the server combines the monitored object identifier, validity period, remaining days, status level, and predefined business impact descriptions into a unified data structure, and serializes this structure into textual content. When generating prompt statements, the server embeds this textual content into natural language descriptions, forming conditions that constrain the output of the generative artificial intelligence model. The server can construct prompt statements in the following forms: "You are the enterprise operations and maintenance notification copywriting assistant. Please generate a Chinese alert email to be sent to the system administrator based on the following information, with a formal and clear tone."

[0299] The information is as follows: - Domain name: www.example.com - Belongs to: Customer Portal Website - Certificate expiration date: 2026-04-01 12:00:00 - Remaining days: 30 - Alarm Level: Red (Requires immediate attention) - Potential risks: After the certificate expires, HTTPS access may fail or security warnings may appear, affecting customer access and data security.

[0300] Require: 1. The title must include the phrase 'Certificate validity period is about to expire'; 2. The main text should specify the domain name, expiration date, remaining days, and associated risks; 3. Finally, provide clear recommendations for handling the issue (e.g., renew the certificate as soon as possible). In another example of a prompt statement, the server can also request the generation of multi-level templates: Please design three different levels of Chinese notification templates for the certificate monitoring system: - Green: Certificate has more than 60 days of remaining validity; this is only used for status reporting. - Yellow: The certificate has 30 to 60 days of remaining validity and requires the administrator to arrange an update plan; - Red: The certificate has less than or equal to 30 days of remaining validity, and the administrator needs to handle it as soon as possible.

[0301] Each level should output a template email body, using placeholders to represent the domain name, expiration date, remaining days, and risk description. The server uses the aforementioned prompt as input text and sends it to the inference service where the generative AI model resides via network protocol. In one implementation, the generative AI model employs a neural network structure based on a multi-layer attention mechanism. Its core consists of multiple encoding and decoding layers, each containing multi-head self-attention sublayers and feedforward sublayers. The server loads pre-trained parameter weights during model initialization; these weights are obtained during the pre-training and fine-tuning phases. The pre-training phase uses a large-scale general corpus for self-supervised learning, updating the model parameters using gradient descent by minimizing the cross-entropy loss function. The fine-tuning phase uses a specialized corpus related to operational notification scenarios to perform transfer learning on the model, making the generated content more consistent with system requirements in terms of terminology accuracy and tone control.

[0302] During training, the server updates the weights of each layer of the neural network using stochastic gradient descent or its variants (e.g., optimization algorithms with adaptive learning rate adjustment). In the pre-training phase, the server can employ a masked language modeling task to enable the model to learn contextual representations. In the fine-tuning phase, it calculates the difference between the generated sequence and the target sequence by providing prompt statements and target notification text pairs, and uses this difference as the loss for backpropagation. The server incorporates data augmentation strategies, such as synonym substitution and sentence structure transformation, into the training data construction to enhance the model's robustness to different expression forms, thereby generating more technically accurate and structurally clear notification text more stably during the inference phase.

[0303] During inference, the server takes the prompt statement as input, encodes it into a high-dimensional vector sequence, and generates the notification text progressively during decoding. The server can apply temperature parameters, sampling strategies, and length penalty factors during the decoding stage to control text diversity and length. Furthermore, the server performs post-processing on the generated results at the program level, such as checking whether required fields (monitored object identifier, remaining days, etc.) are included. If the conditions are not met, it automatically returns to the local template generation path to ensure the integrity and usability of the notification content.

[0304] In this invention, the server not only uses a generative artificial intelligence model to generate notification text, but also indirectly controls the structure and style of the model's output by controlling the content of the prompt statements. The server injects security level or warning level differentiation fields into the prompt statements, enabling the model to automatically adopt different levels of risk language and recommended countermeasures during generation. Through this structured prompt statement design, the server leverages the model's language generation capabilities to construct a multi-level notification system, rather than relying solely on fixed templates, thereby achieving greater expressive flexibility while maintaining the accuracy of technical information.

[0305] The server stores monitoring results and notification processing records for each monitored object in the storage device. These records include a timestamp, status level, the channel through which the notification was sent, a summary of the notification content, and whether the user has acknowledged it. During subsequent operations, the server queries these records to determine whether to resend the notification. For example, if a monitored object is at a high-risk level but has already received multiple notifications within a short period without any status change, the server can suppress duplicate notifications based on preset rules, or simply update the status in the dashboard without sending emails. This reduces network load and user interference without compromising security, achieving a technical optimization of notification frequency.

[0306] To adjust notification strategies based on user psychological states, the server collects operation logs and interaction content information from the terminal. When a user interacts with the system interface, the terminal sends operation behaviors such as click counts, page dwell time, and scrolling behavior to the server in the form of event logs. In conversational interfaces, the terminal can also send user-input text or speech-to-text results. The server uses this data to construct feature vectors, such as operation density per unit time, erroneous operation ratio, dwell time on key function pages, and message response latency. The server can use traditional machine learning models (such as gradient boosting tree-based classifiers) or lightweight neural networks to train these features and output psychological state labels, such as "high stress," "distracted," and "normal workload."

[0307] The server defines specific judgment criteria in its psychological state analysis. For example, frequent repetitive operations and high error rates correspond to a high-stress state, while prolonged lingering on the same error page may correspond to a confused state. The server combines these non-standard, specific rules with learned classification boundaries to infer the user's psychological state. Based on these inferences, the server dynamically adjusts the prompts in the input generative AI model. For instance, when the user is under high stress, constraints such as "Please use concise, step-by-step instructions" and "Avoid using too much technical jargon" are added to the prompts; when the user's attention is distracted, prompts such as "Please highlight the most important risks and operational steps, and control the word count" are added. In this way, the server explicitly encodes psychological state characteristics into the prompts, thereby influencing the model's output and making the notification text more suitable for the current user's state.

[0308] After receiving the notification text and sending conditions generated by the model, the server sends the message via electronic communication devices or displays the content on an interface device. The server interacts with an external mail transfer agent through the mail protocol stack, encapsulating the notification text into email data units and sending them to the configured recipient address. Simultaneously, the server returns monitoring data and notification content to the web-based dashboard through interfaces provided by the application framework, which are then rendered as charts and lists in the browser. The terminal displays the certificate status, remaining days, and historical alarm records for each monitored object to the user through a graphical user interface. Users can select to mark an alarm as processed on the terminal. Upon receiving this feedback, the server updates the processing status field in the alarm record to processed and considers this information in subsequent judgments to reduce repeated alerts for the same issue.

[0309] In a typical use case, users only need to configure the list of services to be monitored and notification preferences on their terminal. Afterward, all certificate validity monitoring and notification text generation are handled automatically by the server. When users access the dashboard through a browser on their terminal, the server provides aggregated monitoring data and predicted risks in real time, allowing users to intuitively understand the certificate health status of different services and immediately take certificate renewal actions upon receiving high-risk notifications. Because the server performs precise time calculations and classifications of certificate status in advance and generates highly targeted alert text through generative artificial intelligence models, users can more easily understand the risk level and operational steps, thereby reducing misconfigurations or delays in processing.

[0310] The technical solution of this invention does not simply automate the manual notification writing process, but rather introduces a structured data flow and intelligent generation mechanism specifically for certificate lifecycle management within the computer. The server avoids errors caused by inconsistent time formats and improper handling of boundary conditions in traditional script implementations through precise time arithmetic and state determination algorithms. Furthermore, the server reduces network traffic and storage overhead while minimizing invalid alarms through hierarchical state differentiation and notification frequency control logic, thereby improving overall system efficiency. The server further models user psychological states, transforming user behavior data into technical features that influence notification strategies. This enables priority delivery of critical notifications to the appropriate users at the most suitable time and through the most appropriate channels, even with limited network and computing resources, resulting in substantial improvements in computing resource scheduling and communication efficiency.

[0311] In optional implementations, the server can employ generative AI models of varying sizes to adapt to resource-constrained or time-critical environments. For example, in environments with ample computing resources, a model with a large number of parameters can be used to obtain more natural and richer notification text; in edge computing environments, a smaller, distilled model can be used to reduce inference latency by decreasing the number of layers or attention heads. The server can also select different inference configurations based on the urgency of the notification, using a more granular sampling strategy for high-priority notifications and a faster greedy decoding for low-priority notifications, to achieve a dynamic balance between accuracy and speed.

[0312] In another implementation, the server can deploy the generative AI model on a local computing node instead of relying on an external inference service, thereby reducing latency and security risks associated with cross-network calls. In this case, the server uses a local high-performance computing library to call matrix operations, accelerating the model's forward inference, and batch-processes multiple notification statements to improve throughput, thus achieving efficient parallel notification generation in large-scale monitoring scenarios.

[0313] Therefore, by introducing collaborative modules such as precise calculation of certificate validity period, state differentiation logic, structured prompt statement construction, generative artificial intelligence model control, user psychological state inference and adaptive scheduling of notification strategy into the server, the present invention has achieved technical improvements in the entire system in terms of processing speed, notification accuracy, data management and communication load. Compared with simple manual process automation or fixed rule systems, it has achieved higher reliability and scalability.

[0314] use Figure 13 The processing procedure is explained.

[0315] Step 1: The server loads the configuration and initializes the environment.

[0316] Input: Configuration files in the storage device (including a list of monitored objects, threshold configurations, notification policies, generative artificial intelligence model interface information, etc.).

[0317] Output: In-memory configuration data structures (e.g., a list / mapping of records for multiple monitored objects), an initialized log module, and a database connection.

[0318] The server reads the configuration file content, uses a parsing library to convert the text configuration into an internal data structure, and maps the domain name, port number, system name, alarm threshold, notification policy, etc. of each monitored object into key-value pairs. At the same time, the server initializes the logger, opens the log file or log pipeline, and establishes a connection to the database so that monitoring results and notification records can be written later.

[0319] Step 2: The server iterates through the monitored objects and retrieves the original certificate information.

[0320] Input: The list of monitored objects generated in step 1, the underlying encrypted communication tools, and network connectivity capabilities.

[0321] Output: Certificate text information or error status markers for each monitored object.

[0322] For each monitored object, the server constructs an encrypted handshake command or calls an interface to establish a communication session with the target service through the network interface based on the domain name and port. When communication is successful, the server extracts the certificate chain text from the returned data stream and caches it as a string. When communication fails, the server generates an error record containing the error type (timeout, connection refused, etc.) and uses this error status as a temporary output for the current monitored object for subsequent exception handling.

[0323] Step 3: The server parses the validity period information from the certificate text.

[0324] Input: The certificate text information output in step 2.

[0325] Output: The certificate expiration date (a time object in a uniform format) or a parsing error status.

[0326] The server applies regular expressions to the certificate text to find the field representing the expiration date. After matching the time string, the server calls a time parsing function to convert the string into an internal time object according to a predetermined time format. If the time field is missing or the format is incorrect, the server generates a parsing error flag and records the reason for the error in the monitoring results. The data processing procedure is: string matching → field truncation → string to time object conversion.

[0327] Step 4: The server calculates the remaining time and determines the certificate status level.

[0328] Input: The validity period object obtained in step 3, the current system time, and the threshold configuration.

[0329] Output: Remaining time value (e.g., number of days) and the corresponding status level (e.g., green, yellow, red, or expired).

[0330] The server reads the current time from the system clock, calculates the expiration time, and subtracts the current time to obtain the time difference. The server converts the time difference into an integer number of days as the remaining time value. Based on multiple threshold ranges in the configuration, the server maps the remaining time to a predefined status level, such as green for greater than the first threshold, yellow for between two thresholds, red for less than or equal to the lowest threshold, or a negative value indicating expiration. The server combines the remaining time and status level into a structured record for subsequent notification generation.

[0331] Step 5: The server constructs structured information and generates basic prompt statements.

[0332] Input: The monitoring object identifier, validity period, remaining time, status level, and predefined business impact description output from step 4.

[0333] Output: Structured information text and corresponding prompts used as input to the generative artificial intelligence model.

[0334] The server combines the monitored object identifier (such as domain name), the name of the system to which it belongs, the validity period, the remaining time, the status level, and the potential business impact into an organized text, and concatenates it according to the field order. The server then wraps this text with natural language descriptions to form a prompt statement containing specific instructions, such as requesting the generation of a formal alarm email or a multi-level template. The server then prepares this prompt statement as input for subsequent calls to the generative artificial intelligence model.

[0335] Step 6: The server determines whether to invoke the generative artificial intelligence model based on the notification requirements.

[0336] Input: The prompt statement generated in step 5, the current status level, and the usage policy in the system configuration (whether to enable generative artificial intelligence models).

[0337] Output: The result of the generation method selection for the notification text to be generated (calling the model or using a local template) and the corresponding input data.

[0338] The server checks whether the current scenario requires generating notification text using a generative AI model based on the status level and configuration. For example, it enables intelligent generation for red and yellow statuses and uses a short template for green statuses. If the configuration does not enable the model, the server directly enters the local template path. If the model is enabled, the prompt statement is marked as model input, and network request parameters (such as temperature, maximum length, and language requirements) are prepared.

[0339] Step 7: The server invokes a generative artificial intelligence model to generate notification text.

[0340] Input: The prompt statement determined in step 6, the address of the generative artificial intelligence model interface, and the inference parameters.

[0341] Output: Notification text generated by a generative artificial intelligence model and optional notification title or multi-level template content.

[0342] The server encapsulates the prompt statement into a request message and sends it to the inference service that deploys the generative artificial intelligence model via a network protocol. The inference service uses a neural network based on a multi-layer attention mechanism to encode and decode the prompt statement and output a sequence of candidate notification texts. After receiving the inference response, the server performs a structural check on the generated text to verify whether it contains key fields such as the monitoring object identifier, validity period, and remaining time. If the check passes, the text is used as the final notification content; otherwise, an exception is recorded and the server falls back to the local fixed template generation path.

[0343] Step 8: The server generates notification text using a local template when there is no call or rollback.

[0344] Input: The result of the generation method selection in step 6, the local predefined template, and the status information in step 4.

[0345] Output: Notification text and title generated based on the template.

[0346] The server reserves placeholders for domain name, validity period, remaining days, status level, etc. in the local template; the server replaces the specific values ​​and strings from step 4 into the template, performs string concatenation and formatting on the template, and obtains a notification title and body that can be sent directly; the server ensures that the length and format of the generated text meet the requirements of email or messaging channels.

[0347] Step 9: The server determines the conditions for sending the notification and constructs the sending instruction.

[0348] Input: Status level in step 4, notification text in step 7 or 8, notification channel policy in configuration, and historical notification records in the database.

[0349] Output: Specific sending channel selection (email, interface display, or both), recipient list, and sending time schedule.

[0350] The server queries the database for the most recent notification time and frequency for the current monitored object, and decides whether to send it immediately or only update it in the dashboard based on the status level and preset frequency control rules (such as not repeating high-risk emails within 24 hours). The server selects different channels according to different levels of configuration. For example, high-risk uses email + dashboard, while low-risk uses only dashboard display. The server constructs a sending command, which includes a list of target addresses, notification title, body and sending strategy (send immediately or delay sending).

[0351] Step 10: The server sends the notification and records the execution result.

[0352] Input: The sending command and notification text output from step 9.

[0353] Output: Email sending result status, interface display update status, and updated notification records.

[0354] The server establishes a connection with the email service through the email sending module, sends the notification title and body as email content to the designated receiving address, and receives the returned success or failure status; the server also pushes the notification content and status to the interface display module to update the terminal dashboard display; the server writes the sending result, timestamp, channel information and notification text summary into the database as a new execution record for subsequent frequency control and auditing.

[0355] Step 11: The server receives user operation information and interaction content from the terminal.

[0356] Input: User operation records (clicks, dwell time, etc.) and interaction content information (dialogue text, etc.) uploaded by the terminal.

[0357] Output: A set of feature data used for mental state estimation.

[0358] When a user browses the dashboard or reads a notification, the terminal sends the user's interface operation events to the server in the form of logs; the terminal also sends the user's input text to the server in the conversational interface; the server preprocesses these raw logs, including sorting by time, filtering noise, and extracting fields, and converts them into numerical features, such as the number of operations per unit time, error rate, page switching frequency, response latency, etc., to provide input for subsequent psychological state inference.

[0359] Step 12: The server estimates the user's psychological state and adjusts subsequent prompts accordingly.

[0360] Input: The feature data set from step 11, and a pre-trained mental state classification model or rule set.

[0361] Output: User's mental state label and subsequent prompts with mental state constraints.

[0362] The server inputs feature data into a psychological state classification model or rule-based judgment logic, and outputs psychological state labels (such as high stress, distracted, normal state) through feature weighting and threshold comparison. Based on different psychological states, the server sets enhancement parameters for prompt statements for subsequent generative artificial intelligence model calls, such as requiring simplified expression or highlighting key information. The server appends these parameters to structured information so that conditions such as "tone requirements" and "length limits" can be automatically added when generating prompt statements in the future.

[0363] Step 13: In subsequent monitoring cycles, the server generates new prompts by combining the overall status and psychological information.

[0364] Input: The latest certificate status obtained in step 4, the mental state label and its parameters obtained in step 12.

[0365] Output: Optimized prompts based on the current technical and user status.

[0366] When the server constructs a new round of prompts, it not only includes the status of the monitored object, the remaining time, and a risk description, but also adjusts the explanation method according to the user's psychological state. For example, when the stress is high, it reduces technical details and increases step-by-step guidance, while providing more comprehensive technical information when the state is normal. The server writes these differentiated requirements into the prompt text, thereby guiding the generative artificial intelligence model to generate notification text that is more suitable for the current user's cognitive load.

[0367] Step 14: The terminal displays notifications and monitoring results, and the user responds.

[0368] Input: The server displays the notification text and monitoring status data pushed through the channel via the interface.

[0369] Output: User's viewing behavior and processing feedback on the terminal.

[0370] After receiving notification text and status data from the server, the terminal renders them into a dashboard page or pops up a prompt, presenting the user with the remaining days, status level, and history of the certificate. The user can click on the terminal to mark an alarm as processed or jump to the certificate management interface to perform an update operation. After the user's operation, the terminal feeds back the processing status to the server to update the alarm records and subsequent notification policies on the server side.

[0371] Step 15: The server updates alarm status and controls subsequent notification policies.

[0372] Input: User feedback from step 14, and existing monitoring and notification records in the database.

[0373] Output: Updated alarm log status and adjusted notification control parameters.

[0374] Based on user feedback, the server updates the alarm record field of the corresponding monitored object to "processed" or "ignored" and records the processing time. When calculating subsequent notification strategies, the server refers to this status to suppress or reduce the priority of repeated reminders for the same problem, thereby reducing unnecessary notifications. At the same time, the server uses historical data to statistically analyze the response latency and processing success rate under different strategies, providing a basis for adjusting thresholds and parameters, and forming an adaptive improvement of the notification strategy.

[0375] Application Example 2 The process flow corresponding to the specific processing in Use Case 2 will be described below. The various parts of the system described below are implemented by the data processing device 12 and the intelligent device 14. In addition, the data processing device 12 is referred to as the "server" and the intelligent device 14 is referred to as the "terminal".

[0376] In network communication environments, encrypted communication authentication and encryption are widely used to ensure the confidentiality and integrity of data transmission. However, the management of such authentication information (e.g., digital certificates) in existing technologies mainly relies on static scripts or manual configuration, which has the following technical shortcomings: (1) At the system level, the validity period monitoring of proof information is usually implemented through a simple timed script, which only compares the expiration date and cannot dynamically adjust the renewal strategy according to complex operating status and multi-source configuration. This may lead to problems such as renewal omission, service interruption or temporary decrease in security level in high load or multi-node environments, making it difficult to guarantee the reliability and availability of the computer system.

[0377] (2) At the communication process level, updating the proof information often requires calling the certificate issuance interface, payment interface and server configuration interface respectively. These calling logics are solidified in the program code. When the business strategy or external service interface changes, the program needs to be manually modified and redeployed. The lack of adaptive control logic results in poor scalability and maintainability of the computer system when the protocol evolves and services change.

[0378] (3) At the configuration management level, when applying new proof information to communication control functions (such as network service processes and reverse proxy processes), existing systems often rely on manual editing of configuration files and manual restarts, or simply execute fixed commands. They lack integrated automatic control over configuration updates, process restarts, and health checks, which can easily lead to "silent failures" when overload fails, affecting the overall stability of the system.

[0379] (4) At the information notification level, existing systems usually send alarms or reminders to the management terminal using fixed templates and at fixed times, ignoring the user’s usage context and attention state. High-priority notifications may pop up frequently when the user is busy or under great pressure, thereby interfering with the user’s operation, reducing the efficiency of human-computer interaction, and making it difficult to guide the user to handle critical security events in a timely manner within the optimal time window.

[0380] (5) In terms of intelligence, although natural language processing and sentiment analysis technologies exist, existing proof information management systems do not make full use of generative artificial intelligence models to dynamically describe and drive the operation process through prompt statements. That is, there is a lack of an architecture that uses generative artificial intelligence models to automatically generate, adjust and optimize control instruction texts (prompt statements) to indirectly control the underlying automated process. This makes it difficult for the system to iteratively optimize notification and automation strategies based on user feedback and historical response data. Computer technology is insufficient in terms of adaptability and intelligent collaboration.

[0381] Therefore, how can we build a system at the computer system level that can: (a) Automatically monitor the validity period of the authentication information used for encrypted communication and perform updates, orders, and payments; (b) Automatically and reliably apply new certification information to communication control functions and perform health checks; (c) Intelligently adjust the timing, content and priority of notifications based on the user's emotional state and historical response behavior; (d) Using generative artificial intelligence models and prompting mechanisms, the above-mentioned automated processing logic is abstracted, driven, and continuously optimized. The technical improvement of the overall information processing, communication control, and human-computer interaction processes is the problem that this invention aims to solve.

[0382] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Application Example 2 is achieved by the following means.

[0383] In this invention, the server includes a generative artificial intelligence model processing module for periodically acquiring the validity period of encrypted communication proof information by a computing device and calculating the remaining period, and generating a prompt statement to instruct automatic execution of proof information update or acquisition processing when the remaining period is lower than a threshold; a communication control module for controlling order processing and payment processing between the server and an external processing device based on the prompt statement generated by the generative artificial intelligence model; a configuration control module for associating and storing the updated proof information in the communication control function and automatically rewriting the setting information and restarting or reloading the communication control function; a notification generation and sending module for generating a prompt statement to instruct the execution of sending a notification to the information prompting terminal device based on the proof information status and processing progress, and generating and sending notification data accordingly; a sentiment estimation and notification control module for performing sentiment estimation processing based on operation history information and input information from the terminal device and generating a prompt statement to instruct the adjustment of notification sending time and content according to sentiment status, thereby controlling notification scheduling and content; and a model adaptation module for updating the prompt statement structure and expression style input to the generative artificial intelligence model based on user evaluation information and notification response status, and automatically adjusting control parameters to improve the automation level of proof information management and notification processing. This allows for the formation of an adaptive control closed loop within the computer system, centered on a generative artificial intelligence model and prompt statements. This enables end-to-end automated control of the monitoring, updating, ordering, payment, configuration, and notification of encryption communication proof information. By employing a unified prompt statement-driven mechanism at the underlying level, the control logic can be adjusted without significant modifications to the underlying program code when external interfaces, business strategies, or user behavior patterns change, thereby improving the system's scalability and maintainability. Simultaneously, the notification strategy is dynamically optimized using sentiment estimation results, ensuring that notifications are more timely and relevant to the user's state, reducing interference with user operations, and improving the user's response efficiency to critical security events. Overall, this improves the performance and reliability of computer technology in secure communication management, human-computer interaction, and intelligent operation and maintenance.

[0384] A "system" refers to a collection of devices consisting of at least one computing device, a storage device, and a communication interface, which work together through program instructions to perform processes such as managing encrypted communication authentication information, communication control, and notification control.

[0385] "Computing device" refers to an electronic hardware unit that can execute program instructions and perform logical operations, judgments and control processing on input data, such as a central processing unit or its equivalent circuit.

[0386] "Authentication information for encrypted communication" refers to electronic authentication information used to achieve identity authentication and communication encryption in network communication, including digital certificates with validity periods and their equivalent electronic authentication data.

[0387] "Validity period" refers to the time interval during which the proof information used for encrypted communication is recognized as valid by the certification authority. This time interval is defined by the start time and the end time.

[0388] "Remaining validity period" refers to the time difference between the current time and the expiration time of the validity period of the proof information used for encrypted communication, and is used to characterize the length of time that the certificate has left before it expires.

[0389] "Preset threshold" refers to a time threshold set in the system to determine whether the proof information used for encrypted communication needs to be updated or retrieved, such as a value expressed in days or hours.

[0390] "Update processing" refers to the process of re-issuing or renewing existing encrypted communication proof information through an authentication service before its validity period expires or is close to its expiration.

[0391] "Acquisition processing" refers to the process of issuing or reissuing corresponding proof information for encrypted communication that has not yet been configured or needs to be added, through the authentication service.

[0392] "Prompt statements" refer to natural language or structured text used as input to generative artificial intelligence models to indicate or describe the target processing content, constraints, and output requirements.

[0393] "Generative artificial intelligence model" refers to a text generation model based on machine learning, which is an artificial intelligence model that can automatically generate corresponding natural language text or control command text based on input prompts.

[0394] The “Generative Artificial Intelligence Model Processing Module” refers to a software functional unit that uses a generative artificial intelligence model to generate prompt statements and target text based on the system status and input data, and uses them to drive or adjust subsequent automated processing procedures.

[0395] "External processing device" refers to an information processing device that is configured outside this system, connected to this system through a communication network, and has functions such as issuing certification information, processing orders, or processing payments.

[0396] "Order processing" refers to the process of sending a request to an external processing device to create a service order for the issuance of authentication information for encrypted communication and to determine the service terms.

[0397] "Payment processing" refers to the process of automatically settling and confirming payments in a payment platform or external processing device to complete the service corresponding to the order.

[0398] The "communication control module" refers to the program functional unit that controls data exchange, session management, and error handling between this system and external processing devices.

[0399] The "configuration control module" refers to a program functional unit that reads, writes, and modifies the settings information of the information processing device for providing communication services, and triggers service restarts or reloads to make the new encrypted communication authentication information effective.

[0400] "Information processing device for providing communication services" refers to information processing hardware or virtual computing environment that executes network service processes and provides encrypted communication services to external parties.

[0401] "Communication control function" refers to the program components or service processes on the information processing device for providing communication services that are used to handle network connections, protocol handshakes, and encrypted communication.

[0402] "Setup information" refers to the parameters, paths, policies, and their combinations in configuration files or configuration storage that are defined to control the operation of communication control functions.

[0403] "Reboot or reload process" refers to the control process that makes updated settings effective by stopping and restarting the communication control function, or by reloading the configuration without completely stopping the service.

[0404] "Information notification terminal device" refers to a terminal device used to display notification information to users and receive user input, including mobile terminals, fixed terminals, or browser clients.

[0405] "Notification data" refers to structured information or message content generated by the server and sent to the terminal device for information prompting, used to prompt the status, processing progress or countermeasures of the encrypted communication proof information.

[0406] The "notification generation and sending module" refers to the program function unit that generates notification data based on the internal state of the system and sends the notification data to the information prompt terminal device through the communication interface.

[0407] "Operation history information" refers to data recorded on the terminal device used for information prompts, such as timestamps, operation types, interface switching, and interactive behaviors related to user operations.

[0408] "Input information" refers to text, options, instructions, or other data that users input via a terminal device through information prompts and that can be used for sentiment estimation.

[0409] "Emotional state" refers to the psychological or emotional characteristics of a user during a specific period of time, inferred from historical operation information and input information, such as tension, relaxation, positivity, or negativity.

[0410] "Sentiment estimation processing" refers to the process of using sentiment analysis algorithms or models to analyze operation history information and input information in order to infer the user's emotional state.

[0411] The “Sentiment Estimation and Notification Control Module” refers to the program functional unit that performs sentiment estimation processing and generates and applies control strategies for the timing and content of notifications based on the estimated sentiment state.

[0412] "Sending time" refers to the specific point in time or time interval at which the system sends notification data to the terminal device used for information prompting.

[0413] The "model adaptation module" refers to a program functional unit that adjusts or updates the prompt statement structure, expression style, and related control parameters of the input generative artificial intelligence model based on user evaluation information and notification response status, in order to optimize the model output and system behavior.

[0414] "Evaluation information" refers to subjective feedback data such as ratings, comments, or other forms given by users regarding notification content, notification frequency, system behavior, etc.

[0415] "Response status" refers to the behavioral characteristics exhibited by users after receiving notification data, including whether they view the notification, the duration of viewing, whether they perform the recommended action, and the response time.

[0416] "Control parameters" refer to a set of adjustable values ​​or rules used to influence the behavior of automated processing flows, including notification frequency, importance threshold, prompt statement length limit, tone selection strategy, etc.

[0417] "Relative importance" refers to the weight value used for ranking and scheduling among multiple notification requests, obtained by comprehensively evaluating factors such as event type, time sensitivity, and emotional state.

[0418] "Sending order" refers to the order in which multiple notifications are sent, determined by their relative importance or other strategies, when there are multiple notifications to be sent.

[0419] "Sending frequency" refers to the number of times or intervals in which notification data is sent to users within a certain time interval, and is used to control the overall rhythm and density of notifications.

[0420] In various embodiments of this invention, the server, terminal, and user each assume different technical roles. The server primarily handles the monitoring, updating, ordering, payment, configuration, and notification control of encryption communication proof information (e.g., digital certificates); the terminal is mainly used to display notifications, collect user operation and sentiment-related information, and interact with the server; the user primarily confirms, provides feedback, and performs necessary manual intervention through the terminal interface. This invention achieves technical improvements to the internal communication security management and human-computer interaction process of computer systems by introducing a generative artificial intelligence model and prompt statement-driven mechanism on the server side, and closely integrating it with traditional cryptographic libraries, network service programs, and sentiment analysis algorithms.

[0421] The server can be a general-purpose information processing device with a multi-core central processing unit, main memory, non-volatile memory, and network interface, such as a rack server or a virtual machine node in a cloud computing environment. The terminal can be a mobile terminal with a processor, display unit, touch input unit, and wireless communication module, or a fixed terminal device with browser functionality. The server and terminal communicate via a local area network (LAN) or wide area network (WAN), using transmission control protocols and secure socket protocols to implement encrypted connections.

[0422] The server runs a general-purpose operating system (such as a Unix-based operating system) on its software and installs multiple software components, including: encryption libraries (such as encrypted communication libraries implementing X.509 parsing), network service programs (such as reverse proxy services or Hypertext Transfer Protocol servers), task scheduling services (such as time-triggered task managers), database management systems, mail transfer agents, push notification interface clients, sentiment analysis tools, and client modules for accessing generative artificial intelligence models. The terminal runs a mobile or desktop operating system on its software and installs applications for communicating with the server, or client programs capable of executing scripts and rendering web pages.

[0423] In this embodiment of the invention, the server divides the processing logic for managing the proof information used in encrypted communication into multiple functional modules. The server maintains an internal "certificate status table" through a configured task scheduling service. This table stores fields such as certificate identifier, certificate path, validity start time, validity end time, remaining validity period, update status, order status, payment status, configuration status, and the result of the last health check in a structured manner. The server periodically calls the encryption library to parse the certificate file, converting the termination time recorded in the certificate into a unified timestamp format and comparing it with the system clock to obtain the remaining validity period and update the corresponding fields in the certificate status table. The server uses a fixed time difference calculation formula and a unified time base in this process to ensure that the remaining validity calculation results for the same certificate are consistent across nodes in a multi-node deployment scenario, thereby improving the accuracy and consistency of certificate status management.

[0424] When the server detects that the remaining validity period of a certificate used for encrypted communication is lower than a predetermined threshold, it triggers the control logic for update processing. Instead of hard-coding all update steps directly into the program code, the server constructs one or more prompt statements that describe the current certificate status, the target operation, and external interface constraints in natural language or semi-structured text. For example, the server can generate the following prompt statements: "Please design an automatic renewal process based on the following conditions: The current certificate will expire in 30 days, and a new certificate needs to be obtained through the certificate issuance service interface. After updating the configuration in the network service program, the service will be reloaded." The server passes the prompt to the generative AI model. In one implementation, the generative AI model employs a deep neural network based on a transformer structure. This network contains multiple layers of self-attention encoders and decoders, each layer including a multi-head attention sublayer and a feedforward sublayer. The parameters are pre-trained on a large-scale natural language corpus. When the server invokes the model, it encodes the prompt as a sequence of words, generates a high-dimensional representation using embedding matrices and positional encoding, calculates context-related representations through a multi-layer attention mechanism, and generates the target text on the decoding side using an autoregression approach. Internally, the server uses cross-entropy as the training error function and updates the weights through backpropagation and gradient descent optimization algorithms. During the inference phase, the server no longer updates the parameters but instead selects output sequences with higher probabilities from the probability distribution using a beam search strategy, thus achieving a text result that balances stability and diversity.

[0425] After receiving the output of the generative AI model, the server parses the text generated by the model, extracting the sequence of executable operations, calling parameters, and conditional constraints. For example, the server can extract operations such as "call the certificate renewal interface," "check the return status code," "write the new certificate path to the configuration file," and "reload the network service program" from the text and map them to the local execution module. This method of indirectly driving the underlying processing through prompt statements and generated text allows the server to change the control logic by adjusting the prompt statements when the external interface changes, without directly modifying the underlying program structure, thereby reducing maintenance complexity.

[0426] During the update process, the server invokes the certificate issuance service interface to construct a request data structure including domain name information, public key request data, and authentication method, and sends the request to the external processing device via a secure transmission protocol. The server performs format and integrity verification on the returned data, stores the newly generated certificate chain and private key in protected storage, and updates the certificate status table with the new expiration date and fingerprint value. The server then reads the network service program's configuration file through the configuration control module, aligns the configuration items related to the encrypted communication proof information, such as paths, protocol versions, and cipher suites, with the new certificate information, and seamlessly reloads the network service program through the execution control interface. During this process, the server uses a health check mechanism to initiate an encrypted communication request to itself, verifying the handshake process and the integrity of the certificate chain, thereby technically ensuring the correctness of the configuration update and preventing service interruptions or the use of incorrect certificates.

[0427] During order processing and payment processing, the server maintains order and payment tables, associating each order request with a payment voucher. When a renewal payment is required, the server constructs control text based on prompts generated by a generative artificial intelligence model, instructing operations such as "create order," "calculate fee," and "call payment interface and handle failure retry strategy," and drives the communication logic with external payment services accordingly. In this way, the server can flexibly adjust the payment process according to different business strategies or external platform requirements, thereby refactoring business logic without changing the underlying module structure, reducing coupling, and improving the system's adaptability during protocol evolution.

[0428] In terms of notification processing, the server manages the notification queue in the form of a structured table. Each record contains a notification identifier, associated certificate identifier, notification type, priority, target terminal identifier, scheduled sending time window, notification content template identifier, and sending status. When the certificate status changes, the server writes the new notification task to this table and calls the notification generation and sending module to generate the terminal-oriented notification text or message body. The server can also utilize generative artificial intelligence models to automatically generate notification content based on prompt statements. For example, the server can use the following prompt statements: "Please use no more than 50 Chinese characters to generate a system notification about 'Your SSL certificate will expire in 7 days. Please renew it as soon as possible.' The tone should be calm and concise." After obtaining the notification text output by the model, the server embeds it into the message body and sends it to the terminal via push notification or email services. Compared to traditional fixed templates, this approach, based on prompts and generated text, can automatically adjust its length, tone, and information density according to different contexts, thereby reducing reading burden and improving the effective information delivery rate, and technically improving the interaction efficiency of the user interface and notification system.

[0429] In this invention, the terminal runs a client application. Upon startup, this application retrieves the user identifier and device identifier from the server and generates or updates the message channel identifier locally. After receiving a notification from the server, the terminal displays the text to the user via the operating system's notification mechanism, and the user clicks to open the corresponding management interface. In this interface, the terminal obtains certain fields from the certificate status table via secure communication, such as certificate name, expiration time, and update status, and displays them in a table or graphical format. The user can perform operations such as "confirm update complete" and "request manual retry" on the terminal. The terminal converts these operations into structured requests and sends them to the server, thus forming a closed-loop control.

[0430] The terminal can also collect operation history and input information, including interface dwell time, click frequency, and feedback text content, with the user's permission. In this embodiment, the terminal can use a lightweight feature extraction algorithm to convert continuous operation sequences into behavior vectors, and combine the text input into a feature set after word segmentation and vectorization, and then transmit it to the server via network communication.

[0431] In sentiment estimation, the server can employ a specialized sentiment classification model. In one implementation, this model is a multi-layer bidirectional recurrent neural network or a transformer-based text classification network. It uses user input text and behavior vectors as features, mapping them to multiple sentiment category labels (e.g., "relaxed," "tense," "positive," "negative"). When training this model, the server can use historical data labeled with sentiment tags, employing cross-entropy as the loss function and updating parameters through stochastic gradient descent or adaptive learning rate algorithms. During the inference phase, the server inputs the feature sequence obtained from the terminal into the model, predicts the current sentiment state and corresponding confidence level, and writes the results into the user's sentiment state table.

[0432] After assessing the user's emotional state, the server uses its emotion estimation and notification control module to reorder and reschedule tasks in the notification queue. For example, when the server detects that a user is under high stress, it will delay sending non-urgent notifications or compress the notification text into a shorter, more direct format to reduce interference; when it detects that the user is in a relatively relaxed or focused state, it will prioritize sending high-priority notifications related to security risks. The server can construct the following prompts for this purpose: "The user is currently under mild stress. Please generate a calm SSL certificate update reminder with no more than 40 Chinese characters to avoid causing additional stress." After parsing the notification text provided by the generative artificial intelligence model, the server writes the text along with the adjusted sending time into the notification queue, thereby achieving notification control based on emotional state adaptive optimization. This invention, through this technical means, allows the notification system to move away from fixed rules and instead form a scheduling strategy internally based on model predictions and historical response data. This technically improves the matching degree between notification arrival time and user processing capacity, reduces accidental touches and neglect, and improves the response speed to critical security events.

[0433] In the model adaptation module of this invention, the server continuously collects user evaluation information on the content and frequency of notifications, as well as specific response behaviors, including whether the notification was read, reading duration, whether a recommended action was performed, and execution delay time. The server associates and stores this data with the currently used prompt statements, forming a "prompt statement—output text—user response" triple dataset. The server periodically uses this dataset to optimize the use of the generative artificial intelligence model, including: adjusting the structure of the prompt statements, reducing easily overlooked lengthy pre-explanations, and strengthening the explicit expression of key information. The server can generate the following prompt statements to request suggestions for improvement on the prompt statement pattern: "The following is some user feedback regarding certificate update notifications: 'Notifications are too frequent,' 'The text is too long.' Based on this feedback, please provide three specific suggestions for improving the frequency and length of notifications." After receiving suggestions from the generative artificial intelligence model, the server rewrites its internal prompt template and updates control parameters such as notification interval, maximum character count, and priority threshold. Through this closed-loop tuning mechanism, the server not only automates the certificate management process but also continuously improves its control strategies, thereby achieving adaptive performance optimization at the computer technology level.

[0434] In the system of this invention, users can observe certificate status, notification content, and adaptive emotion effects through a terminal interface and intervene manually when necessary. For example, when a user believes that the automatic renewal result of a certificate is abnormal, they can trigger a "manual check and retry" operation with one click through the interface. After receiving the instruction, the server will construct a new prompt statement based on the current status, such as "Please generate a step-by-step troubleshooting and retry strategy for the failed certificate update process," and call a generative artificial intelligence model to obtain a more detailed troubleshooting solution. Based on this, the server will perform further inspection and recovery steps, such as verifying network connectivity, checking for changes in the certificate issuance service interface, and verifying local configuration paths, thereby shortening the fault location time and improving the system recovery speed.

[0435] Through the synergy of the aforementioned modules, the system of this invention achieves the following technical improvements: The server manages certificate status and notification tasks using a unified data structure, reducing redundant access and inconsistency issues and improving data management efficiency; the server drives the underlying control logic through a generative artificial intelligence model and prompt statements, decoupling the control layer from the execution layer. When external interfaces change, the system can quickly adapt by modifying prompt statements, thereby reducing recompilation and deployment time; the server incorporates user status into scheduling decisions through a specialized sentiment estimation model and notification scheduling algorithm, avoiding notification strategies based solely on time rules and reducing false interference and neglect rates; the server continuously improves text generation quality and overall system automation at the model usage level through closed-loop optimization of the "prompt statement-response result" process. The combined effect of these technical features makes this invention not merely a simple automated replacement of manual work, but a substantial improvement to the communication security management and notification system at the levels of computer internal structure, data flow, and control flow, resulting in significant improvements in processing speed, configuration accuracy, notification effectiveness, and overall reliability.

[0436] use Figure 14 The processing procedure is explained.

[0437] Step 1: The server reads the certificate status table and local certificate file information from the storage device.

[0438] Input: Certificate identifier stored in the database, certificate file path, validity period information of the last record, and certificate file in the file system.

[0439] The server's specific data processing and operations are as follows: The server opens each certificate file in the file system using the file path, uses the encryption library to parse the certificate structure, extracts the start and end times of the certificate's validity period, and converts the text-formatted time into a unified timestamp format; the server compares this timestamp with the existing records in the database, and updates the records if they do not match; the server also establishes a mapping relationship between the certificate identifier and the certificate file path and caches it in memory.

[0440] Output: The updated certificate status table record set, which includes a standardized validity period timestamp and an in-memory mapping structure of "certificate identifier → certificate file path and validity period".

[0441] Step 2: The server calculates the remaining validity period of each certificate and determines whether it is below a predetermined threshold.

[0442] Input: Certificate expiration timestamp from step 1, current system timestamp, and preset time threshold (e.g., 30 days).

[0443] The server's specific data processing and calculation: The server performs the calculation "remaining seconds = expiration time stamp - current timestamp" on each certificate record and converts the result into days; the server compares the remaining days with a time threshold. If it is less than the threshold, the server sets the "required update flag" field of the certificate to true and records the trigger reason and time; if it is not less than the threshold, the flag is kept false.

[0444] Output: A certificate status table updated with the "Remaining Term" and "Update Required" fields.

[0445] Step 3: The server generates prompts to guide the update process for certificates marked as needing to be updated, and calls a generative artificial intelligence model to generate update strategy text.

[0446] Input: Records in the certificate status table where the "Need to be updated" flag is true (including certificate identifier, remaining days, service type, current configuration status, etc.), and a predefined prompt statement template.

[0447] The server's specific data processing and computation: The server embeds parameters such as the remaining days of the certificate, the service importance level, and the current configuration status into the prompt statement template, for example, generating a natural language description such as "The current certificate will expire in 30 days and needs to be automatically renewed and the network service program configuration updated through the certificate service interface"; the server encodes the prompt statement into a text sequence and sends it to the generative artificial intelligence model interface, receiving the natural language update strategy text returned by the model; the server parses the text content, identifies the operation steps, dependency order, and condition judgments, and converts it into an internally executable task list.

[0448] Output: A list of update tasks for internal control, along with the corresponding original prompts and update strategy text returned by the generative AI model.

[0449] Step 4: The server calls an external certificate issuance service to perform certificate renewal or acquisition processing based on the update task list.

[0450] Input: The task list from step 3, including information such as "calling the certificate renewal interface" and "new certificate parameter requirements", as well as the certificate service interface configuration (interface address, authentication credentials).

[0451] The server's specific data processing and operations are as follows: The server constructs a certificate service request data structure for each update task, writing fields such as domain name, public key request data, and verification method into the request body; the server sends the request through a secure transmission protocol and waits for the external certificate issuance service to return the result; the server performs format and integrity checks on the returned data, extracts the new certificate chain and related metadata; the server adds or updates the corresponding certificate record in the database, and writes the validity period and fingerprint information of the new certificate into the certificate status table.

[0452] Output: Successfully acquired new certificate data (certificate chain, private key or private key path, etc.) and updated certificate status record.

[0453] Step 5: In scenarios where payment is required, the server performs order processing and payment processing based on the output of the generative artificial intelligence model.

[0454] Input: Update the payment-related step information in the task list, the price and validity period configuration of the certificate in the order table, the payment interface configuration, and the "ordering and payment strategy" text generated by the generative artificial intelligence model.

[0455] The server's specific data processing and calculation: The server extracts elements such as "create order", "calculate total amount" and "set retry count" based on the policy text, constructs order records and writes them into the order table; The server then constructs a payment request, encapsulates fields such as order amount, currency type, and payment token into a request body, and calls the payment service through a secure interface; The server receives the payment result, parses the result code and transaction number, marks the order status as "paid" for successful transactions, otherwise records the reason for failure and decides whether to retry or issue an alarm based on the policy.

[0456] Output: Updated order and payment tables, including payment status, transaction number and possible error codes, as well as payment result status associated with the certificate update task.

[0457] Step 6: The server configures the new certificate into the communication service program and performs a reload and health check.

[0458] Input: The path to the new certificate or certificate data from step 4, the path to the configuration file of the network service program, and the current configuration status.

[0459] The server's specific data processing and operations are as follows: The server reads the existing configuration file, locates the configuration items related to the proof information used for encrypted communication (certificate path, key path, protocol version, cipher suite, etc.), replaces the path with the new certificate path, and constructs the new configuration content in memory; the server writes the updated configuration back to the file system and commands the network service program to perform a reload operation through the control interface; the server then automatically initiates an encrypted communication request to itself, records whether the handshake is successful, the certificate chain verification result, and the response time; the server writes the health check result to the certificate status table and the health check record table.

[0460] Output: The status of network service instances with the new certificate applied, and health check logs reflecting the reload results and communication availability.

[0461] Step 7: The server generates notification tasks based on certificate status changes and processing progress, and constructs prompt statements for notification generation.

[0462] Input: The latest record in the certificate status table (including remaining validity period, update status, configuration status, and health check status), notification policy configuration, and the correspondence between users and terminals.

[0463] The server's specific data processing and calculation: The server calculates the scenarios in which notifications need to be generated based on the notification policy (e.g., less than 30 days remaining, update failure, reload failure, etc.) and creates a notification task record for each scenario; The server embeds the certificate status summary information (expiration time, update result) into the notification template to generate a prompt statement, such as "Please generate a system notification with no more than 50 Chinese characters about 'The SSL certificate will expire in 7 days, please complete the update as soon as possible'"; The server sends the prompt statement to the generative artificial intelligence model and receives the generated notification text; The server writes the notification text and the target terminal identifier together into the notification task queue.

[0464] Output: A queue of notification tasks with generated text, where each record contains the target terminal, notification content, scheduled sending time, and priority.

[0465] Step 8: The terminal receives notification data from the server and displays the notification content to the user.

[0466] Input: Notification data sent by the server, including notification text, notification type, certificate identifier, and possible action links.

[0467] The terminal's specific data processing and calculation: The terminal receives notification data through message push channels or in-application pull requests, and parses the notification text and additional data; The terminal calls the operating system notification interface to display the notification title and content to the user in the form of a system notification bar or pop-up window; When the user clicks on the notification, the terminal requests relevant certificate details from the server based on the certificate identifier, and renders fields such as certificate name, expiration time, and update status in the application interface.

[0468] Output: The notification interface and certificate details interface displayed on the terminal screen, as well as the record of the certificate details request sent to the server.

[0469] Step 9: The terminal collects the user's operation history and input information and sends it to the server.

[0470] Input: User click events on the terminal interface (such as turning on notifications, ignoring notifications, clicking the "Act Now" button), dwell time, scrolling behavior, and feedback content entered by the user through text boxes or forms.

[0471] The terminal's specific data processing and operations: The terminal timestamps and encodes operation events, organizing continuous action sequences into an operation list sorted by time; the terminal performs basic cleaning of the user-input text (removing meaningless characters and controlling length) and combines it with the operation list to form a sentiment analysis feature data packet; the terminal sends this data packet to the server through a secure communication protocol.

[0472] Output: Raw sentiment-related feature data sent to the server, including operation sequences and text feedback.

[0473] Step 10: The server performs sentiment estimation processing and generates prompts for adjusting notification strategies.

[0474] Input: The sentiment feature data package from step 9, historical sentiment model parameters, and the user's past notification response records.

[0475] The server's specific data processing and operations are as follows: The server extracts behavioral features such as operation frequency, dwell time, and ignore rate from data packets, and performs word segmentation and vectorization on the text feedback; the server inputs these features into a sentiment classification model, calculates the probability distribution of the user's current emotional state for each emotion category, selects the emotion category with the highest probability as the current emotional state, and records the confidence level; the server then constructs a prompt statement based on the emotional state and historical responses, such as "The user is currently under mild stress. Please generate an SSL certificate update reminder using no more than 40 Chinese characters in a brief and calm tone"; the server sends this prompt statement to a generative artificial intelligence model to obtain new notification text.

[0476] Output: Current user sentiment state label and confidence level, new prompts for generative AI models, and sentiment-adaptive notification text returned by the model.

[0477] Step 11: The server optimizes the timing, order, and frequency of notification sending based on emotional state and historical responses, and updates the notification task queue.

[0478] Input: Emotional state results from step 10, user history of notification response records, notification tasks that have not yet been sent in the current queue, and system notification policy parameters.

[0479] The server's specific data processing and calculations: The server calculates the relative importance of each notification to be sent, mapping the security risk level, the urgency of the remaining deadline, and the user's current emotional state into a weight value; the server sorts the notification queue according to the weight, determines the sending order, and adjusts the notification sending interval based on emotional state and feedback records to avoid pushing non-urgent notifications intensively during periods of high user stress; the server replaces the original fixed template text with the notification text output by the generative artificial intelligence model, and writes the updated content and planned sending time back to the notification task queue.

[0480] Output: A queue of notification tasks updated in an optimized order and time schedule, along with sentiment-adaptive text content associated with each notification.

[0481] Step 12: Users can view notifications and certificate status on the terminal and initiate manual intervention requests when necessary.

[0482] Input: The notification content displayed on the terminal, certificate details, and operation options provided by the terminal (such as "Confirm Update", "Retry Automatic Renewal", "Report Problem").

[0483] User-specific data processing and computation (from a system perspective): The user selects the corresponding operation based on the notification content and interface prompts; the terminal converts the user's selection into structured instructions, such as "perform manual retry for the specified certificate" or "confirm the current result", and sends it to the server through a secure channel; after receiving the instruction, the server uses it as new input to update the task status, and if necessary, regenerates the prompt statement, such as "please generate troubleshooting steps for the failed certificate renewal process", and calls the generative artificial intelligence model again to obtain troubleshooting strategies.

[0484] Output: Manual intervention request instructions sent from the terminal to the server, and a new list of update or troubleshooting tasks and corresponding policy text generated by the server based on the instructions.

[0485] The specific processing unit 290 sends the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires sound representing user input regarding the result of the specific processing. The control unit 46A sends the sound data representing user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the sound data.

[0486] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be performed partially or entirely by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0487] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or external devices.

[0488] For example, the collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the smart device 14 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0489] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the smart device 14.

[0490] Second Implementation Method Figure 3 An example of the configuration of the data processing system 210 according to the second embodiment is shown.

[0491] like Figure 3 As shown, the data processing system 210 includes a data processing device 12 and smart glasses 214. A server can be cited as an example of the data processing device 12.

[0492] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0493] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and communication I / F 44 are also connected to the bus 52.

[0494] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0495] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the user 20's surroundings (e.g., the field of view defined by an angle equivalent to the field of vision of an average healthy person).

[0496] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0497] Figure 4 This illustrates an example of the main functions of the data processing device 12 and the smart glasses 214. For example... Figure 4 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0498] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0499] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. In the emotion inference function (emotion-specific function) using the emotion-specific model 59, various inferences and predictions related to the user's emotions are performed, including inferences and predictions of the user's emotions, but this is not limited to this example. Furthermore, emotion inference and prediction may also include, for example, emotion analysis (parsing).

[0500] In the smart glasses 214, the processor 46 performs reception and output processing. The memory 50 stores the reception and output program 60. The processor 46 reads the reception and output program 60 from the memory 50 and executes the read reception and output program 60 on the RAM 48. The reception and output processing is implemented by the processor 46 operating as a control unit 46A according to the reception and output program 60 executed on the RAM 48. Furthermore, the smart glasses 214 has the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and these models can also be used to perform the same processing as the specific processing unit 290.

[0501] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart glasses 214. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0502] Example 1 The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0503] Application Example 1 The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0504] Example 2 The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0505] Application Example 2 The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0506] The specific processing unit 290 sends the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A outputs the result of the specific processing to the speaker 240. The microphone 238 acquires sound input representing the user's input regarding the result of the specific processing. The control unit 46A sends the sound data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the sound data.

[0507] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be performed partially or entirely by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0508] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or external devices.

[0509] For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the smart glasses 214 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0510] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the smart glasses 214.

[0511] Third Implementation Method Figure 5 An example of the configuration of the data processing system 310 according to the third embodiment is shown.

[0512] like Figure 5 As shown, the data processing system 310 includes a data processing device 12 and a head-mounted terminal 314. A server can be cited as an example of the data processing device 12.

[0513] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0514] The head-mounted terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, display 343, and communication I / F 44 are also connected to the bus 52.

[0515] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0516] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the user 20's surroundings (e.g., the field of view defined by an angle equivalent to the field of vision of an average healthy person).

[0517] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0518] Figure 6 This illustrates an example of the main functions of the data processing device 12 and the head-mounted terminal 314. For example... Figure 6 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0519] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0520] The memory 32 stores the data generation model 58 and the emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290.

[0521] In the head-mounted terminal 314, the processor 46 performs the acceptance / output processing. The memory 50 stores the acceptance / output program 60. The processor 46 reads the acceptance / output program 60 from the memory 50 and executes the read acceptance / output program 60 on the RAM 48. The acceptance / output processing is implemented by the processor 46 operating as a control unit 46A according to the acceptance / output program 60 executed on the RAM 48.

[0522] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the head-mounted terminal 314. In the following description, the data processing device 12 will be referred to as the "server" and the head-mounted terminal 314 will be referred to as the "terminal".

[0523] Example 1 The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0524] Application Example 1 The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0525] Example 2 The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0526] Application Example 2 The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0527] The specific processing unit 290 sends the result of the specific processing to the head-mounted terminal 314. In the head-mounted terminal 314, the control unit 46A outputs the result of the specific processing to the speaker 240 and the display 343. The microphone 238 acquires sound input representing the user's input regarding the result of the specific processing. The control unit 46A sends the sound data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the sound data.

[0528] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 includes prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be performed partially or entirely by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0529] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the head-mounted terminal 314, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the head-mounted terminal 314. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the head-mounted terminal 314 or external devices, and the head-mounted terminal 314 acquires or collects information required for processing from the data processing device 12 or external devices.

[0530] For example, the collection unit is implemented by the control unit 46A of the head-mounted terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the head-mounted terminal 314 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 to analyze the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 to generate a menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the head-mounted terminal 314 or the specific processing unit 290 of the data processing device 12 to provide the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0531] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the head-mounted terminal 314.

[0532] Fourth Implementation Method Figure 7 An example of the configuration of the data processing system 410 according to the fourth embodiment is shown.

[0533] like Figure 7 As shown, the data processing system 410 includes a data processing device 12 and a robot 414. A server can be cited as an example of the data processing device 12.

[0534] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0535] Robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, controlled object 443, and communication I / F 44 are also connected to the bus 52.

[0536] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0537] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, to photograph the area around robot 414 (e.g., the field of view defined by a perspective equivalent to the field of vision of an average healthy person).

[0538] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0539] The controlled object 443 includes a display device, LEDs (light-emitting diodes) for the eyes, and motors for driving the arms, hands, and feet. The posture or movement of the robot 414 is controlled by controlling the motors in the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. In addition, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0540] Figure 8 This illustrates an example of the main functions of the data processing device 12 and the robot 414. For example... Figure 8 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0541] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0542] The memory 32 stores the data generation model 58 and the emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290.

[0543] In robot 414, the processor 46 performs the acceptance and output processing. The memory 50 stores the acceptance and output program 60. The processor 46 reads the acceptance and output program 60 from the memory 50 and executes the read acceptance and output program 60 on RAM 48. The acceptance and output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance and output program 60 executed on RAM 48.

[0544] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal".

[0545] Example 1 The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0546] Application Example 1 The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0547] Example 2 The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0548] Application Example 2 The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0549] The specific processing unit 290 sends the result of the specific processing to the robot 414. In the robot 414, the control unit 46A outputs the result of the specific processing to the speaker 240 and the controlled object 443. The microphone 238 acquires sound input representing the result of the specific processing. The control unit 46A sends the sound data representing the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the sound data.

[0550] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be performed partially or entirely by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0551] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or external devices, and the robot 414 acquires or collects information required for processing from the data processing device 12 or external devices.

[0552] For example, the collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the robot 414 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the speaker 240 of the robot 414 and the control object 443 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0553] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the robot 414.

[0554] Furthermore, the emotion-specific model 59, acting as an emotion engine, can determine a user's emotion based on a specific mapping. Specifically, the emotion-specific model 59 can determine a user's emotion based on an emotion graph that serves as a specific mapping (see [reference]). Figure 9 The emotion-specific model 59 can also determine the robot's emotion, and the specific processing unit 290 performs specific processing based on the robot's emotions.

[0555] Figure 9 This is a diagram representing an emotion map 400 that maps multiple emotions. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotion is. On the outer side of the concentric circles, emotions representing states or behaviors arising from mood are arranged. Emotions are concepts that include feelings and mental states. Emotions generated by reactions occurring in the brain are arranged roughly to the left of the concentric circles. Emotions derived from situational judgments are arranged roughly to the right of the concentric circles. Emotions generated by reactions occurring in the brain and derived from situational judgments are arranged roughly above and below the concentric circles. Furthermore, "pleasant" emotions are arranged above the concentric circles, and "unpleasant" emotions are arranged below them. Thus, in the emotion map 400, multiple emotions are mapped based on the structure that generates emotions, and emotions that are likely to occur simultaneously are mapped close to each other.

[0556] These emotions are distributed at the three o'clock position of the emotion map 400, typically fluctuating between peace and anxiety. In the right half of the emotion map 400, situational awareness dominates over internal sensation, thus resulting in an impression of calm.

[0557] The inner side of the emotion map 400 represents the inner state, while the outer side represents behavior. Therefore, the further outward you are from the emotion map 400, the more visible the emotion becomes (manifested in behavior).

[0558] Here, human emotions are based on various balances such as posture and blood sugar levels. When these balances deviate from an ideal state, it indicates an unpleasant state; when they approach the ideal state, it indicates a pleasant state. Emotions in robots, cars, motorcycles, etc., can also be created in the following way: based on various balances such as posture and remaining battery power, when these balances deviate from an ideal state, it indicates an unpleasant state; when they approach the ideal state, it indicates a pleasant state. Emotion maps can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a Brain Physiological Signal Analysis System for Voice Emotion Recognition and Emotion, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). In the left half of the emotion map, emotions belonging to the sensory-dominated region, called "response," are arranged. Furthermore, in the right half of the emotion map, emotions belonging to the situational cognition-dominated region, called "situation," are arranged.

[0559] In the emotion map, two types of emotions that promote learning are defined. One is a negative emotion on the situational side, in the middle or peripheral region of "repentance" or "reflection." This occurs when the robot experiences negative emotions such as "I don't want to experience this feeling again" or "I don't want to be blamed again." The other is a positive emotion on the response side, near the "desire" region. This occurs when there are positive feelings such as "wanting more" or "wanting to know more."

[0560] The emotion-specific model 59 inputs user input into a pre-trained neural network to obtain emotion values ​​representing each emotion shown in the emotion map 400, thereby determining the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network... Figure 10 As shown in the sentiment graph 900, it was trained in a way that sentiments that are configured close to each other have similar values. Figure 10 The text shows examples of emotions such as "peace of mind", "stability", and "reassurance" that have similar emotion values.

[0561] The above description focuses on the functions of the data processing device 12, but the system of this disclosure is not necessarily installed on a server. The system of this disclosure can also be installed as a general information processing system. This disclosure can also be installed, for example, as a software program running on a personal computer, an application running on a smartphone, etc. The method of this disclosure can also be provided to users in the form of SaaS (Software as a Service).

[0562] In the above embodiments, an example of a specific process being performed by a single computer 22 is given. However, the technology disclosed herein is not limited to this, and the specific process can also be distributed among multiple computers, including computer 22. For example, the data generation model 58 can be located on an external device of the data processing apparatus 12, where data is generated based on the input data.

[0563] In the above embodiments, examples of storing a specific processing program 56 in the memory 32 have been described, but the technology disclosed herein is not limited thereto. For example, the specific processing program 56 may also be stored in a portable computer-readable non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed into the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0564] Alternatively, a specific processing program 56 may be pre-stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 according to the requirements of the data processing device 12.

[0565] In addition, it is not necessary to store all the specific processing program 56 in the storage device such as the server connected to the data processing device 12 via the network 54 or in the memory 32; a portion of the specific processing program 56 may be stored in advance.

[0566] As hardware resources for performing specific processes, various processors, as shown below, can be used. For example, a CPU can be listed as a processor, which functions as a general-purpose processor that performs specific processes by executing software, i.e., a program. Furthermore, processors can be listed as special-purpose circuits such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application-Specific Integrated Circuits), which are processors with circuitry specifically designed to perform specific processes. Each processor has built-in or connected memory, and each processor executes specific processes using that memory.

[0567] The hardware resources for performing a specific process can consist of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resources for performing a specific process can be a single processor.

[0568] As an example of a single processor, there are two approaches: First, a processor is composed of a combination of one or more CPUs and software, which functions as a hardware resource to perform a specific process; second, as represented by a SoC (System-on-a-chip), a processor is used to implement the functionality of the entire system, which includes multiple hardware resources for performing a specific process, using a single IC (Integrated Circuit) chip. In this way, the specific process is implemented by using one or more of the aforementioned processors as hardware resources.

[0569] Furthermore, the hardware architecture of these various processors, more specifically, can utilize circuits that combine semiconductor elements and other circuit components. Moreover, the specific process described above is just one example. Therefore, without departing from the main point, unnecessary steps can certainly be deleted, new steps added, or the processing order changed.

[0570] The descriptions and illustrations above are detailed explanations of a portion of the technology disclosed herein, and are merely one example of the technology disclosed herein. For example, the above descriptions of the structure, function, effect, and results are just one example of the structure, function, effect, and results of a portion of the technology disclosed herein. Therefore, without departing from the spirit of the technology disclosed herein, unnecessary parts may be deleted, new elements added, or replacements may be made to the descriptions and illustrations above. Furthermore, to avoid confusion and facilitate understanding of a portion of the technology disclosed herein, explanations of common technical knowledge that do not require special explanation under the premise of being able to implement the technology disclosed herein have been omitted from the descriptions and illustrations above.

[0571] All documents, patent applications and technical specifications set forth in this specification are incorporated herein by reference to the same extent that each document, patent application and technical specification is specifically and individually described therein and referenced by reference.

[0572] In addition, the following notes are provided in response to the above explanation.

[0573] Example 1 (Note 1) An information processing system, characterized in that it comprises: A processing unit for periodically obtaining the validity period of encrypted authentication information registered on the communication control function using the time management function, parsing attribute information related to the validity period from the encrypted authentication information using the encryption processing function, calculating the remaining time until the validity period, and generating validity period management information; The processing unit is used to extract connection identification information corresponding to encrypted authentication information that is determined to be about to expire within a predetermined time period based on the validity period management information, generate and send authentication information acquisition request data using communication control function and proof information issuance function, and perform verification processing on the verification information received from the proof information issuance function using resource management function and configuration management function, thereby starting the authentication information update processing. A processing unit for generating and sending settlement request data related to authentication information updates via the communication function of electronic settlement service using the billing processing function, parsing the settlement result data obtained as a response to generate transaction completion information, and updating the status management information of the encrypted authentication information based on the transaction completion information; This unit is used to utilize configuration management and service provision functions to save newly acquired encrypted authentication information and its corresponding secret information to the storage area on the storage device, update the setting information of the communication service control program, and automatically perform setting verification processing and startup control processing, thereby reflecting the new encrypted authentication information in the information provision function. This processing unit is used to utilize status monitoring and notification control functions to generate and send notification data based on the validity period management information of encrypted authentication information, the update processing result information of authentication information, and the transaction completion information through display control functions or message sending functions. It also generates prompt information used to instruct the generation and sending of the notification data into prompt statements for generative artificial intelligence models and determines the content of the notification data and the timing of sending based on the response information obtained from the generative artificial intelligence model. A processing unit for acquiring presumed emotional state information about a user using a user state acquisition function, generating prompts for adjusting the priority of notifications executed by the notification control function and the prompts for the notification medium based on the presumed emotional state information into prompt statements for a generative artificial intelligence model, and updating the control parameters of the notification control function based on response information obtained from the generative artificial intelligence model.

[0574] (Note 2) According to the information processing system described in Appendix 1, the aforementioned processing unit is further configured to: generate expiration prediction information from the expiration management information of encrypted authentication information using a status monitoring function; associate the prediction information with user status estimation information to determine notification priority information; and generate prompt information for optimizing the sending order and sending method of notification data sent by the notification control function based on the notification priority information as a prompt statement for a generative artificial intelligence model.

[0575] (Note 3) According to the information processing system described in Appendix 1, the aforementioned processing unit is further configured to: generate automatic execution step information and control program information for monitoring processing of encrypted authentication information, authentication information update processing, settlement processing, configuration update processing, and notification processing based on response information obtained from a generative artificial intelligence model; and register the automatic execution step information and the control program information to the scheduling management function, thereby continuously automating the entire process from managing the validity period of encrypted authentication information to its reflection in the information provision function and notification to users.

[0576] Application Example 1 (Note 1) An information processing system, characterized in that it comprises: A unit that obtains the validity period information and current time information of a digital certificate, calculates the remaining time until the validity period expires, and determines whether the remaining time is within a predetermined threshold. If the remaining time is determined to be within the predetermined threshold, the unit uses the certificate issuance communication function to call the application programming interface of the certificate issuance external device to generate and send new digital certificate issuance request data, and manages the certificate issuance processing progress based on the certificate issuance status data received as a response. Based on the certificate issuance status data, the unit uses the settlement communication function to call the application programming interface of the settlement processing external device to generate and send settlement request data containing fee information related to the acquisition of the digital certificate, and records the transaction completion status based on the settlement result data received as a response. The unit that stores the new digital certificate in the storage area of ​​the information processing device, updates the certificate-related parameters in the configuration file of the communication processing device, and applies the new digital certificate by reloading the operation of the communication processing device; A unit that generates status information including the validity period information of the digital certificate, the certificate issuance status data, and the settlement result data, and implements a status information providing interface for providing the status information to external terminal devices; Based on the status information, extract the element information of the notification content, set the conditions for generating prompt information containing the element information, and generate a prompt statement representing the prompt information generation conditions as a unit of input data for the generative artificial intelligence model. The generative artificial intelligence model obtains the natural language text output by the prompt statement and sends the natural language text to the external terminal device as a unit for providing notification information.

[0577] (Note 2) The information processing system according to Appendix 1 is characterized in that, The status information provided by the status information provision interface determines the likelihood of information service termination due to the expiration of the digital certificate's validity period, generates a prompt statement for instructing the generative artificial intelligence model to generate a notification containing attention prompts based on the determination result, and uses the natural language text output by the generative artificial intelligence model to execute the notification.

[0578] (Note 3) The information processing system according to Appendix 1 is characterized in that, The user's state information obtained from the external terminal device is parsed to calculate the user's emotional state index. Based on the emotional state index and the state information, conditional data for determining the notification priority and presentation form is generated. A prompt statement containing the conditional data is generated as input data for a generative artificial intelligence model. The priority and content of the notification are optimized based on the natural language text output by the generative artificial intelligence model.

[0579] Example 2 (Note 1) An information processing system, characterized in that it comprises: An apparatus for acquiring validity period attribute information of electronic proof information used for encrypted communication in an information processing device, calculating the remaining time to the validity period based on the current time information, and determining the status of the electronic proof information according to a predetermined threshold. An apparatus for generating structured information containing a monitored object identifier, the validity period, the remaining time, the status distinction, and the business impact that may result from the expiration of the electronic certificate information, based on the status of the electronic certificate information; inputting a prompt statement containing the structured information into a generative artificial intelligence model; and causing the generative artificial intelligence model to generate a prompt statement for instructing the updating or acquisition of the electronic certificate information and the conditions for sending the notification text. An apparatus for informing a user via an electronic communication device or an interface display device, based on the notification text generated by the generative artificial intelligence model and the sending conditions, and prompting the implementation of operations related to the setting or updating of the electronic certificate information; A device for storing the monitoring results of the validity period of the electronic certificate information and the execution record of the notification process in a storage device, and for controlling the notification frequency or priority for the same monitored object based on the record information stored in the storage device; An apparatus for inferring a user’s psychological state based on operation log information or interaction content information obtained from the user’s terminal, and for changing the conditions of the prompt statements input to the generative artificial intelligence model according to the psychological state, so that the generative artificial intelligence model generates prompt statements for instructing adjustments to the presentation, level of detail or timing of the notification text. A device for setting control information for automatically repeating the electronic certificate information validity period monitoring process, the prompt statement generation process, and the notification process at a predetermined period, and for autonomously executing a series of processes based on the control information.

[0580] (Note 2) The information processing system according to Appendix 1 is characterized in that, The device for generating prompt statements is further configured to include security level distinctions or warning level distinctions in the prompt statements input to the generative artificial intelligence model based on the status determination result related to the validity period of the electronic certificate information, thereby generating prompt statements that instruct the generative artificial intelligence model to generate multiple notification texts with different risk level descriptions and different recommended processing content according to the remaining time range.

[0581] (Note 3) The information processing system according to Appendix 1 is characterized in that, The device for generating prompt statements is further configured to generate prompt statements for instructing optimization of at least one of the following: the notification recipient, the notification channel, the notification retransmission interval, and the notification importance level distinction, based on the inference result of the user's psychological state and the notification processing execution record stored in the storage device, and to control the notification processing according to the optimized conditions.

[0582] Application Example 2 (Note 1) An information processing system, characterized in that it comprises: A generative artificial intelligence model processing module is used to periodically obtain the validity period of the proof information for encrypted communication by the computing device, calculate the remaining period based on the validity period and the current time, and generate a prompt statement to indicate the automatic execution of the proof information update or acquisition process when the remaining period is less than a predetermined threshold. The communication control module is used to perform order processing and payment processing through an external processing device with proof information issuance communication function for updating or obtaining the proof information for encrypted communication, and to control the communication processing based on prompt statements generated by a generative artificial intelligence model to instruct the automatic execution of the order processing and payment processing. A configuration control module is used to associate the encrypted communication proof information obtained through the update or acquisition with the communication control function on the information processing device providing communication services and store it in a storage area; to rewrite the setting information of the communication control function so that the encrypted communication proof information takes effect; and to perform a restart or reload process on the communication control function after the setting information is changed. The configuration control module controls the process based on prompt statements generated by a generative artificial intelligence model to instruct the automatic execution of the setting and enabling processes. A notification generation and sending module is used to generate a prompt statement for instructing the execution of communication processing to send a notification to an information prompting terminal device based on the remaining expiration time of the encrypted communication proof information and the progress status of the update processing and setting processing, and to generate and send notification data to the information prompting terminal device based on the prompt statement. An emotion estimation and notification control module is used to perform emotion estimation processing on the user's emotional state based on the operation history information and input information obtained from the information prompting terminal device, and to generate a prompt statement to indicate at least one of the sending time and content of the notification data according to the emotional state, and to control the notification scheduling and notification content based on the prompt statement. And a model adaptation module for updating the sentence structure and expression style of the prompt statements input to the generative artificial intelligence model based on the evaluation information obtained from the user and the user's response to the notification data, and for automatically adjusting the control parameters for improving the automation of the management and processing of proof information for encrypted communication and notification processing.

[0583] (Note 2) According to the information processing system described in Appendix 1, the computing device is further configured to: generate notification data containing countermeasures to avoid information service interruption or security degradation when the validity period of the encrypted communication proof information is less than or equal to the predetermined threshold, and to process the notification data using a generative artificial intelligence model with a tone and amount of information appropriate to the emotional state, and to generate corresponding notification data based on the prompting statement.

[0584] (Note 3) According to the information processing system described in Appendix 1, the computing device is further configured as follows: a generative artificial intelligence model processing module that calculates the relative importance of multiple notification requests based on the user's emotional state obtained through the emotion estimation processing and the user's historical response records to the notification data, and generates a prompt statement for instructing the optimization of the sending order and frequency of the notification data according to the importance, and controls the sending order and frequency of notifications based on the prompt statement.

Claims

1. An information processing system, characterized in that, include: processor; The processor is configured to: monitor the validity period of digital certificates, and when the validity period is approaching, use a generative artificial intelligence model to generate a prompt indicating the acquisition of a new certificate; The acquired digital certificate is set into the information processing device, and a generative artificial intelligence model is used to generate prompts to indicate the execution of procedures necessary to complete the electronic transaction; The system analyzes the user's emotional state and uses a generative artificial intelligence model to generate prompts that indicate adjustments to the notification time and content based on the emotional state.

2. The information processing system according to claim 1, characterized in that, The processor is also configured to use a generative artificial intelligence model to generate a prompt indicating the execution of a notification operation to prevent information services from being interrupted due to the expiration of a digital certificate.

3. The information processing system according to claim 1, characterized in that, The processor is also configured to use a generative artificial intelligence model to generate prompts that indicate the optimization of notification priorities based on the user's emotional state.

Images