AI-driven pan-screen operation method and device and electronic equipment

Abstract

The invention relates to an AI-driven pan-screen operation method and device and electronic equipment. The method comprises the steps that an operation instruction input by an operator is received in response, the operation instruction is analyzed, an operation intention is recognized, and the operation instruction is an instruction based on a natural language; calling at least one AI service based on the operation intention to generate an operation sequence corresponding to the operation intention; and adaptively executing the operation sequence on at least one target terminal pan-screen service system to realize a cross-terminal operation task. According to the method and the device, the operation instruction is identified and the AI service is called, so that a cross-terminal operation task can be realized for a plurality of target terminal pan-screen service systems.

Description

Technical Field

[0001] This disclosure generally relates to the field of terminal operation, and in particular to an AI-driven method, device, and electronic device for operating screens across the entire network. Background Technology

[0002] Currently, with the widespread adoption of smart TVs, tablets, mid-screen speakers, and in-vehicle smart screens, the multi-screen ecosystem has become a core carrier for users to obtain information and enjoy entertainment. The accompanying multi-screen operation scenarios also exhibit complex characteristics of multi-terminal collaboration, multi-content format integration, and interwoven operational steps. Its operational scope not only covers holiday / film / seasonal theme planning, multi-terminal desktop layout configuration, and real-time media asset content updates, but also requires refined operations such as content security verification and precise user segmentation and targeting, placing higher demands on the efficiency and intelligence of the operation system. However, current multi-screen operation systems still face multi-dimensional technical bottlenecks. On the one hand, the system's functional modules are scattered, and the operation links are lengthy, requiring operators to spend a significant amount of time learning the system logic. The time required for a single operational task far exceeds that of traditional tools, resulting in low daily efficiency. On the other hand, operational planning heavily relies on human experience and lacks intelligent auxiliary tools. Holiday templates need to be designed manually, and hot topics need to be searched manually, leading to inconsistent planning quality and hot topic response cycles often exceeding 24 hours, resulting in missed operational opportunities. Furthermore, operational knowledge is scattered across multiple channels such as local documents and shared drives, lacking structured integration and semantic retrieval capabilities. New employees require 3-6 months to master core skills, resulting in a lengthy training cycle and difficulties in knowledge transfer. Therefore, the existing system can no longer meet the operational needs of "efficiency, intelligence, and refinement," nor can it adapt to the diverse scenario requirements of multi-terminal, ubiquitous screen operations. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides an AI-driven method, apparatus and electronic device for operating ubiquitous screens.

[0004] According to some embodiments of this disclosure, an AI-driven pan-screen operation method is provided, comprising: responding to receiving an operation instruction input by an operator, parsing the operation instruction and identifying the operation intent, wherein the operation instruction is a natural language-based instruction; invoking at least one AI service based on the operation intent to generate an operation operation sequence corresponding to the operation intent; and adapting the operation operation sequence to be executed on at least one target terminal pan-screen business system to realize cross-terminal operation tasks.

[0005] In some embodiments, the step of invoking at least one AI service based on the operational intent to generate an operational operation sequence corresponding to the operational intent includes: performing visual orchestration on a workflow platform based on the operational intent to generate an intelligent agent that reflects the operational intent; and responding to the interaction between the workflow platform and the AI ​​big model, invoking at least one AI service through the intelligent agent to generate an operational operation sequence corresponding to the operational intent.

[0006] In some embodiments, the invocation of at least one AI service through the intelligent agent includes at least one of the following methods: invoking a dedicated operation tool in the intelligent quick toolbox to map the operational intent to a predefined and reusable standardized operation sequence; invoking an intelligent scheduling service and triggering and generating an initial operational plan based on the hot topic tags provided by the intelligent scheduling service; and invoking an intelligent planning service to generate a structured theme planning scheme based on at least one of the hot topic tags, user profiles, and operational strategies.

[0007] In some embodiments, invoking the dedicated operation tools in the intelligent shortcut toolbox includes invoking at least one of the following tools: invoking a tag expression generation tool to convert natural language segmentation intents into structured user segmentation rules; invoking a desktop focus setting tool to intelligently configure the desktop focus navigation logic of the target terminal business system according to interactive instructions; invoking an intelligent media asset replacement tool to batch identify and replace specified media assets based on image recognition or metadata matching; and invoking a content deduplication retrieval tool to retrieve historical operational content based on content fingerprint and similarity calculation to avoid duplicate delivery.

[0008] In some embodiments, the step of invoking the intelligent scheduling service and triggering and generating an initial operation plan based on the real-time hot topics provided by the intelligent scheduling service includes: collecting raw hot topic data from a preset Internet data source through a scheduled task; performing semantic analysis and clustering on the raw hot topic data to generate structured hot topic tags; generating a creation prompt containing execution suggestions based on the time-sensitive attributes of the hot topic tags and pushing it to the operation personnel; and, in response to the confirmation instruction of the operation personnel, invoking the content generation service to automatically generate a preliminary operation plan.

[0009] In some embodiments, an intelligent knowledge base is constructed to store, parse, and quantify historical operational knowledge, and to provide intelligent retrieval and support for the operational tasks.

[0010] In some embodiments, constructing an intelligent knowledge base includes: collecting historical operation documents from multiple heterogeneous data sources, the historical operation documents including at least one of text, tables, presentations, and images; parsing and extracting key information from the historical operation documents, and converting them into high-dimensional vector representations to construct a knowledge vector base; semantically associating and fusing the extracted information based on knowledge graph technology; and, in response to receiving natural language queries, retrieving matching knowledge content from the knowledge vector base through intent recognition and vector similarity calculation.

[0011] In some embodiments, the method further includes: adapting the operation sequence to be executed on at least one target terminal screen-based service system to realize cross-terminal operation tasks, including: adapting the operation sequence to an execution instruction that conforms to the interface specification of the at least one target terminal screen-based service system through service encapsulation; and distributing the execution instruction to the at least one target terminal screen-based service system to complete the cross-terminal operation task.

[0012] According to some embodiments of this disclosure, an AI-driven pan-screen operation device is provided, comprising: a parsing unit, configured to parse the operation instruction input by an operator and identify the operation intent in response to receiving the operation instruction, wherein the operation instruction is a natural language-based instruction; an invocation unit, configured to invoke at least one AI service based on the operation intent to generate an operation operation sequence corresponding to the operation intent; and an execution unit, configured to adapt the operation operation sequence to execute on at least one target terminal pan-screen business system to realize cross-terminal operation tasks.

[0013] According to some embodiments of this disclosure, an electronic device is provided, including: a processor; a memory for storing computer programs or instructions executable by the processor; wherein the processor is configured to execute the computer programs or instructions to implement the AI-driven pan-screen operation method in any of the above embodiments.

[0014] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: By identifying operational instructions and calling AI services, this disclosure can realize cross-terminal operation tasks for multiple target terminal pan-screen business systems. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of this disclosure, the embodiments of this disclosure will be further explained and described with reference to the following drawings. These drawings are only used to more conveniently and specifically describe the embodiments of this disclosure and are not intended to limit this disclosure.

[0016] Figure 1 This is a flowchart illustrating an AI-driven pan-screen operation method according to some embodiments of the present disclosure;

[0017] Figure 2 This is a flowchart illustrating a method for invoking AI services based on operational intent, according to some embodiments of this disclosure;

[0018] Figure 3 This is a schematic diagram illustrating the process of invoking the Smart Shortcut Toolbox according to some embodiments of this disclosure;

[0019] Figure 4 This is a flowchart illustrating a method for invoking an intelligent scheduling service and generating an initial operation plan, based on some embodiments of this disclosure.

[0020] Figure 5 This is a block diagram of an AI-driven ubiquitous screen operation device shown according to some embodiments of the present disclosure;

[0021] Figure 6 This is a schematic diagram of the architecture of an AI-driven pan-screen operation platform shown according to some embodiments of the present disclosure;

[0022] Figure 7 This is a block diagram illustrating an apparatus for AI-driven ubiquitous screen operation according to some embodiments of the present disclosure; and

[0023] Figure 8 This is another block diagram illustrating an apparatus for AI-driven ubiquitous screen operation according to some embodiments of the present disclosure. Detailed Implementation

[0024] Some embodiments of this disclosure will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. Various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become readily apparent upon understanding this disclosure. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but can be changed as will become readily apparent upon understanding this disclosure, except for operations that must be performed in a particular order. Furthermore, for clarity and brevity, descriptions of features known in the art may be omitted.

[0025] The embodiments described in the following examples of this disclosure are not representative of all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0026] This disclosure provides an AI-driven pan-screen operation method in some embodiments, which is used for pan-screen operation of multiple target terminals. By parsing and recognizing operation instructions, it calls artificial intelligence (AI) services to realize cross-terminal operation tasks.

[0027] In the current field of related technologies, the operation of multi-screen platforms still relies heavily on traditional manual operation methods, with the entire process dependent on manual operation by operators. Content selection requires manual searching of internet platforms and media asset libraries to select film and television materials and posters that meet the needs from massive resources. Theme planning requires building a framework based on personal experience, manually designing the theme structure, matching corresponding content, and even repeatedly adjusting the layout to adapt to different terminal screens. Desktop configuration and content updates require navigating through multi-level system menus and manually inputting parameters to complete operations such as focus settings and media asset replacement.

[0028] Among the related technologies, the multi-dimensional technical pain points caused by the lack of human-led and intelligent support in the field of pan-screen operation include: (1) The operation chain of pan-screen operation under pure manual drive is long and inefficient. The core business links of pan-screen operation such as content selection, theme planning, desktop layout configuration, and media content update all rely on manual operation by the operators. A single complete operation task covering "theme planning-content configuration-review and verification" takes more than two hours on average, which is difficult to match the business needs of high-frequency operation updates of multiple terminals (such as Internet Protocol Television (OTT), Interactive Personality TV (IPTV), in-vehicle screens, etc.). Moreover, during the operation, it is necessary to repeatedly jump between multiple levels of menus in the system and manually input configuration parameters (such as desktop focus position, tag grouping rules, etc.), which further increases the complexity of operation, resulting in continuous loss of operation efficiency and failing to meet the timeliness requirements of large-scale pan-screen operation. (2) Currently, the quality of pan-screen operation planning is unstable and the response to hot topics is lagging. At present, the operation planning work relies heavily on the individual experience of personnel. The theme framework construction, content material matching, and scenario-based layout design are all manually led, resulting in significant differences in the logic and attractiveness of the planning results between newly hired operators and senior operators, and the output quality is difficult to standardize. At the same time, the operation response to internet hot topics (such as festival nodes, movie hits, and sports events) requires a multi-stage process of "manual monitoring of hot topics - manual retrieval of related materials - item-by-item design of planning schemes". The complete response cycle often exceeds 24 hours, which is very easy to miss the best operation window period when pan-screen users' attention is at its peak. (3) The current system lacks the ability to gain a global insight and intelligent analysis of historical operation content. Due to the isolation of data and the lack of a unified feature library, it is impossible to conduct efficient cross-terminal and cross-theme content comparison before executing new operation actions. This leads to the system relying heavily on manual experience for deduplication, which is inefficient and prone to omissions. As a result, the same or highly similar media assets and themes are repeatedly deployed, causing multiple wastes of material storage, production costs and push traffic, directly increasing the unnecessary costs of pan-screen operation. (4) The unstructured knowledge transfer and high dependence on experience restrict operational efficiency and business continuity. The current system lacks a unified operational knowledge base, and the formats of historical operational documents are complex (including pictures, text, Doc, Excel, PPT, online documents, etc.). Traditional technical means are difficult to achieve efficient and accurate file parsing and content extraction. As a result, the knowledge system of pan-screen operation (such as system operation manuals, business rules, classic cases and solutions) and core practical experience have long relied on oral transmission and decentralized local storage (such as shared cloud drives and personal computers), and cannot be effectively structured and integrated and intelligently retrieved.

[0029] In view of this, some embodiments of this disclosure provide an AI-driven pan-screen operation method, which can realize cross-terminal operation tasks based on operation intentions through AI services provided by a large AI model.

[0030] Figure 1 This is a flowchart illustrating an AI-driven pan-screen operation method 100 according to some embodiments of this disclosure, such as... Figure 1 As shown, the method 100 includes steps S102, S104 and S106.

[0031] In step S102, in response to receiving an operation instruction input by the operator, the operation instruction is parsed and the operation intent is identified, wherein the operation instruction is a natural language-based instruction.

[0032] In this embodiment, when operators input operational instructions based on natural language, the system automatically responds and receives the instructions, then parses and processes them. During the parsing process, the system uses natural language processing technology to identify the operator's operational intent, including intent to plan a theme, intent to configure content, and intent to segment operations. This natural language-based interaction method allows operators to trigger corresponding operational processes directly through everyday language without needing to learn complex system operation logic.

[0033] In step S104, at least one AI service is invoked based on the operational intent to generate an operational operation sequence corresponding to the operational intent.

[0034] In this embodiment, an AI service is invoked based on operational intent, generating an operational operation sequence corresponding to that intent. For example, an operations staff member inputs a natural language command on the work interface, such as "Remove all expired event posters from the homepage." The identified operational intent is: the core intent is "media asset management," the specific operation is "batch removal," and the object is "expired event posters on the homepage." The "intelligent" part is completed by invoking corresponding AI services, such as calling an image recognition service to scan all posters on the homepage; calling an Optical Character Recognition (OCR) or metadata reading service to identify the event date information on the posters, making a comprehensive judgment, and filtering out a list of all "expired" posters. The generated executable, structured operational operation sequence is: [Operation: Remove, Target ID: Poster 005, Position: Homepage Recommendation].

[0035] In step S106, the operation sequence is adapted and executed on at least one target terminal pan-screen service system to realize cross-terminal operation tasks.

[0036] The target terminal multi-screen business system in this embodiment can be understood as the "execution end" that ultimately controls the screen display. It may include a Content Operation System (COS), an Application Management System (AMS), Value-Added Services (VAS), a Short Video System (SVS), a Topic Operation System, and a User Center System (UCS). Because the technical interfaces, data structures, and capabilities of different terminal business systems are completely different, the operational operation sequence needs to be adapted and executed on these terminal business systems. Through a single planning, it can be deployed simultaneously and automatically to multiple screen ecosystems, eliminating the need for operators to perform separate operations on different terminal business systems, thus achieving cross-terminal operational tasks.

[0037] As described above, this disclosed AI-driven pan-screen operation method achieves end-to-end intelligent operation from operational instructions to cross-terminal execution, significantly improving operational efficiency, planning quality, and reducing operational costs. This method frees operations personnel from tedious manual operations, allowing them to focus on creative and strategic work, while ensuring the quality and consistency of operational content.

[0038] Figure 2 This is a flowchart illustrating a method 200 for invoking AI services based on operational intent, as shown in some embodiments of this disclosure. Figure 2 As shown, the method 200 includes steps S202 and S204.

[0039] In step S202, based on the operational intent, a visual orchestration is performed on the workflow platform to generate an intelligent agent that reflects the operational intent.

[0040] In this embodiment, the workflow platform can be an agent-based artificial intelligence (Agentic) workflow development platform, also known as a GAIA platform. By dragging and dropping pre-defined functional modules (such as large model call blocks, conditional judgment blocks, and Application Programming Interface (API) connection blocks) onto the workflow platform, a flowchart can be drawn on a graphical interface to form an executable workflow that reflects the operational intent. This visually orchestrated and runnable workflow can be called an agent. The workflow platform provides the AI ​​capability modules, logical judgments, and API connectors required to build these agents. This visual orchestration method allows operators to intuitively design and adjust workflows, building complex operational logic without writing code.

[0041] The workflow platform disclosed herein provides efficient and flexible intelligent solutions for operational scenarios. The workflow platform supports visual construction and deployment of intelligent agents, deeply integrates multi-source large-scale model capabilities and business system data, and features an open data access architecture that can quickly connect to various databases and API interfaces. The workflow platform provides end-to-end AI empowerment, achieving intelligent support across the entire operational chain, from strategy generation and task execution to data feedback.

[0042] In step S204, in response to the interaction between the workflow platform and the AI ​​big model, at least one AI service is invoked through the intelligent agent to generate an operational operation sequence corresponding to the operational intent.

[0043] In this embodiment, the workflow platform interacts with the AI ​​big data model. The workflow platform is responsible for coordinating data exchange and instruction transmission between the AI ​​big data model and the target terminal's multi-screen business system, ensuring that operational intentions can be accurately translated into an executable operational sequence. The AI ​​big data model may include, but is not limited to, Tongyi Qianwen, DeepSeek, Doubao, and Jiutian. Following a pre-arranged process, the intelligent agent invokes one or more underlying, specialized AI services (such as image recognition, data querying, and text generation) at the correct time and with the correct parameters, and integrates and transmits their results, ultimately generating a structured operational sequence that can be executed by the target terminal's multi-screen business system.

[0044] In this embodiment, the intelligent agent invokes at least one AI service, including at least one of the following methods: invoking a dedicated operation tool in the intelligent quick toolbox to map operational intentions to a predefined and reusable standardized operation sequence; invoking an intelligent scheduling service and triggering and generating an initial operational plan based on hot topic tags provided by the intelligent scheduling service; and invoking an intelligent planning service to generate a structured topic planning scheme based on at least one of hot topic tags, user profiles, and operational strategies. In this embodiment, the dedicated operation tool encapsulates one or more operational operations for specific high-frequency scenarios. The dedicated operation tool can be considered an intelligent agent visually orchestrated on a workflow platform. The workflow of the dedicated operation tool is pre-designed, debugged, and saved on the GAIA canvas. Each step in the workflow uses standardized interfaces and data processing methods, and the intelligent agent can be published to the intelligent quick toolbox for any user to invoke in any scenario. In this embodiment, by invoking the intelligent scheduling service, a high-value hot topic is monitored and identified. By understanding and processing the hot topic, a highly structured tag package, i.e., hot topic tags, is generated. This method integrates elements from trending topic tags, such as event type, core subject, and popularity level, to trigger the generation of an initial operational plan. This complete and well-structured initial operational plan, ready for evaluation and use by operations personnel, is then pushed to them. In this embodiment, a structured topic planning scheme is generated based on at least one of trending topic tags, user profiles, and operational strategies by invoking an intelligent planning service. The trending topic tags may be generated by an intelligent scheduling service, the user profile may be, for example, a target customer profile, and the operational strategy may be, for example, a company brand strategy and production standards. By integrating the above information and utilizing the vast knowledge and contextual understanding of a large model, reasoning and creation are performed to generate a structured text that meets the requirements, ultimately forming a machine-readable, human-reviewable, and executable structured topic planning scheme for downstream systems.

[0045] In this embodiment, upon receiving an operational instruction, the required combination of AI services is determined based on the type of identified operational intent. For example, for the intent to "create a special feature on Spring Festival films," the intelligent scheduling service, intelligent quick toolbox, and intelligent planning service are activated simultaneously. Subsequently, requests are sent to each AI service sequentially according to the preset service call order and parameter specifications. The intelligent scheduling service analyzes current hot topics related to the Spring Festival films; the intelligent quick toolbox uses a content deduplication tool to automatically find high-quality film resources related to the Spring Festival films in the system; and the intelligent planning service generates a complete theme planning scheme, including a theme framework, content materials, and layout design, based on the output results of the first two services. These AI services work collaboratively to ultimately generate a series of structured operational operation sequences, such as "create a special feature - set the special feature name - configure the special feature cover - add a content list - set the recommendation algorithm - publish and launch," etc. This method of generating operational operation sequences based on AI services decomposes complex operational tasks into standardized and executable operational steps, significantly improving operational efficiency.

[0046] In this embodiment, the intelligent planning service serves as the system's strategy generation hub, deeply integrating external hot topics, internal data, and human intent to construct the decision-making foundation for intelligent operation planning. First, it accesses hot topic tags based on the intelligent scheduling service, and simultaneously calls multiple sources of content and historical plans for knowledge retrieval. Simultaneously, it performs multi-dimensional data fusion and correlation analysis on user profiles, content assets, and operational history to form quantifiable and reusable data insights. Furthermore, through natural language processing technology, it accurately parses unstructured instructions from operational personnel, identifying their core objectives, scenarios, and constraints, ensuring alignment of intentions and consistency of goals in human-machine collaboration.

[0047] Based on the integration of diverse information, and by combining trending hashtags, data insights, and operational strategies, a comprehensive and complete theme planning scheme is generated using a large language model, encompassing content creation and visual planning. Subsequently, based on the group differences in user profiles, the unified scheme is personalized and scenario-based, outputting customized operational themes and execution strategies for different user groups, achieving a precise strategy mapping from a "one-size-fits-all" approach to "a thousand different strategies."

[0048] Intelligent planning services enable end-to-end automated planning processes from "perception-understanding-generation-adaptation," systematically solving problems such as delayed response, reliance on manual labor, and difficulty in scaling and personalization in traditional operations. By organically combining trend perception, data-driven approaches, and intent understanding, the system can dynamically output highly structured, immediately implementable segmented operational plans, significantly improving planning efficiency and accuracy. Ultimately, it constructs a new paradigm of modern operational planning centered on intelligent decision-making and aiming for "one person, a thousand faces."

[0049] In this embodiment of the disclosure, calling dedicated operation tools in the intelligent shortcut toolbox includes calling at least one of the following tools: calling a tag expression generation tool to convert natural language segmentation intent into structured user segmentation rules; calling a desktop focus setting tool to intelligently configure the desktop focus navigation logic of the target terminal business system according to interactive instructions; calling an intelligent media asset replacement tool to perform batch identification and replacement of specified media assets based on image recognition or metadata matching; and calling a content deduplication retrieval tool to retrieve historical operational content based on content fingerprint and similarity calculation to avoid duplicate delivery.

[0050] The tag expression generation tool, based on natural language processing technology, automatically transforms unstructured user segmentation intentions input by operators into executable structured rule expressions, enabling precise and efficient generation of user segmentation strategies. For example, when operators input a natural language description such as "filter male users who have watched sports events in the past 30 days and prefer high-definition content," the system can automatically convert it into an executable structured expression. The desktop focus setting tool analyzes operators' interaction commands and intelligently configures the focus position and navigation logic of the target terminal's multi-screen business system desktop according to preset UI rules, achieving automated optimization of view navigation. This allows operators to adjust the focus position of the user interface with simple commands, improving the user experience. The intelligent media asset replacement tool, based on image recognition and feature matching algorithms, supports batch identification and replacement of posters, videos, and other media assets within a specified range based on visual features or metadata. When updating a large number of content posters or video covers, the system can automatically identify and replace the relevant media assets without manual intervention. The intelligent quick toolbox also includes an intelligent topic analysis tool and a one-click system troubleshooting tool. The intelligent topic analysis tool utilizes data mining and visualization technologies to perform multi-dimensional, in-depth analysis of the algorithm configuration, clustering effects, and content composition of deployed topics, providing data-driven decision support for operational strategy optimization. The one-click system troubleshooting tool combines real-time log collection and anomaly pattern recognition to automatically diagnose system operating status, accurately pinpoint the root causes of typical problems such as strategy failures and distribution failures, and generate troubleshooting reports, enabling rapid discovery and delimitation of system problems.

[0051] This disclosure integrates multiple dedicated operation tools through a modular architecture, enabling automated conversion of natural language commands into multi-step operational procedures. The system parses user-input operational requests, automatically invokes the corresponding toolchain, and executes complex configuration processes, ultimately achieving an intelligent operation mode where "conversational commands complete multi-step operational procedures." Figure 3 This is a schematic diagram of the process 300 for invoking the Smart Shortcut Toolbox, as shown in some embodiments of this disclosure. Figure 3As shown, process 300 includes: Step 302, the operator inputs a natural language command, such as "remove all expired activity posters from the homepage"; Step S304, the natural language is processed; Step 306, intent parsing and recognition, such as recognizing the core intent as "media asset management" through natural language understanding, the specific operation as "batch removal", and the target as "expired activity posters on the homepage"; Step S308, tool routing, the system routes the task to the "intelligent media asset replacement tool" accordingly; Step S310, execution engine, calling standardized business interfaces, after the intelligent media asset replacement tool is activated, it will call the corresponding AI service based on the workflow platform to complete the "intelligent" part: calling the image recognition service to scan all posters on the homepage, calling OCR... Alternatively, the metadata reading service identifies the activity date information on the posters, makes a comprehensive judgment, and filters out a list of all "expired" posters; Step S312, execution result feedback and progress display, providing feedback on the execution results and progress to the operations personnel, along with an operation summary (e.g., "5 expired posters have been successfully removed"). If an API call fails, the "one-click system troubleshooting tool" is automatically triggered, which collects error logs, analyzes patterns, locates the root cause of the problem (e.g., IPTV system interface timeout), and generates a report; Step S314, task completion and data feedback, regardless of success or failure, the instructions, results, time consumed, and any anomalies encountered in this operation will be recorded and fed back to the intelligent knowledge base and intelligent planning module for optimizing future strategies and knowledge accumulation.

[0052] In this embodiment, when calling dedicated operation tools in the intelligent shortcut toolbox, multiple dedicated operation tools are automatically called and chained together to complete complex instructions based on the parsing of operational instructions and the identification of operational intentions. For example, if the operational instruction is "Update the homepage theme to a Mid-Autumn Festival reunion style and push it to users who are recently interested in mooncakes; check if there are any problems after the update," then the following tools are called sequentially: content deduplication tool, intelligent media asset replacement tool, desktop focus setting tool, tag expression generation tool, and one-click system troubleshooting tool. Based on the workflow orchestration capabilities of the GAIA platform, the above tools are called in sequence.

[0053] Figure 4 This is a flowchart illustrating a method 400 for generating an initial operation plan by invoking an intelligent scheduling service, based on some embodiments of this disclosure. Figure 4 As shown, the method 400 includes steps S402, S404, S406 and S408.

[0054] In step S402, raw hotspot data is collected from a preset Internet data source through a timed task.

[0055] In step S404, semantic analysis and clustering are performed on the original hotspot data to generate structured hotspot topic tags.

[0056] In this embodiment, raw hot topic information data is automatically collected periodically from a specified internet data source through a pre-set scheduled task and data crawling interface, constructing a real-time information input layer. Based on natural language processing and clustering analysis algorithms, deep semantic analysis and correlation calculation are performed on the raw unstructured hot topic data, automatically extracting and generating high-value hot topic tags, completing the transformation from data noise to semantic topics. Suppose a niche art film, *Coffee Under the Stars*, suddenly becomes popular on social media due to word-of-mouth. The data crawling interface continuously scans various media platforms, acquiring a large amount of raw information such as "The Last Stand of *Coffee Under the Stars*", "Director Interview", "Coffee Shop Check-in", and "Box Office Comeback," among other massive amounts of messy, unstructured text data. Clustering analysis is performed on the raw data, outputting highly structured hot topic tags: Topic Type: Film Popularity, Core Object: *Coffee Under the Stars*, Related Elements: Coffee, Art, Comeback, Popularity Trend: Rapidly Rising. This completes the precise transformation from "internet noise" to "operable topics."

[0057] In step S406, based on the time-sensitive attributes of trending topic tags, a creation prompt containing execution suggestions is generated and pushed to the operations staff.

[0058] In step S408, in response to the confirmation instruction from the operations personnel, the content generation service is invoked to automatically generate a preliminary operations plan.

[0059] In this embodiment, based on the output trending topic tags and their time-sensitive attributes, structured creation prompts and execution suggestions are proactively pushed to operations personnel to achieve instant access to trending information. By calling external large-scale models and content generation services, combined with pre-set design rules and operational strategies, preliminary topic schemes containing visual elements and content lists are automatically generated, providing actionable alternative content for operational decisions. As in the example above, the time attributes of the trending topic tags are: burst speed: a steep heat curve indicates that it is a "burst" trending topic with a potentially short lifespan; time decay factor: the model calculates that if a response is not made within 24 hours, the expected value of the heat will decay by 60%. Combined with the pre-set rules in the "rule engine," such as "film and television-related bursting hot topics have the highest priority," structured creation prompts are generated, such as: trending topic: the movie "Café Under the Stars" has achieved a word-of-mouth comeback; core keywords: art, coffee, emotion, comeback, check-in; response window: it is recommended to launch related operational content within 24 hours. This is then proactively pushed to operations personnel or downstream intelligent planning services. By calling external large-scale models and content generation services, several complete and visualized alternative schemes are generated. Each solution includes: a theme name (e.g., "A Healing Moment, Accompanied by Starlight"); a visual poster (automatically generated promotional image featuring starry skies and coffee elements); a content list (automatically linked to a list of similarly styled movies); and a compelling promotional copy. Multiple alternative theme solutions are presented visually for comparison, providing data reference for operations personnel's final decision-making and assisting them in quickly selecting the optimal solution. Once the optimal solution is determined, the structured solution data is automatically injected into the downstream content assembly, review, and release processes, significantly shortening the overall response cycle from the emergence of a trending topic to content launch, achieving a systematic improvement in operational efficiency.

[0060] In this embodiment of the disclosure, in order to continuously optimize future operational strategies and knowledge accumulation, an intelligent knowledge base can also be constructed to store, parse, and quantify historical operational knowledge, providing intelligent retrieval and support for operational tasks.

[0061] Building an intelligent knowledge base requires collecting historical operational documents from multiple heterogeneous data sources. These documents include at least one of text, tables, presentations, and images. Heterogeneous data sources include, but are not limited to, internal enterprise document libraries, third-party knowledge websites, API interface data streams, structured databases, and unstructured text libraries, supporting both scheduled polling and real-time monitoring collection modes. The historical operational documents are parsed and key information is extracted, then converted into high-dimensional vector representations to build a knowledge vector library. First, preprocessing and deep parsing (covering entities, relationships, topics, and sentiment analysis) achieve a structured understanding of the enterprise's multimodal operational knowledge. Then, using vectorization technology based on pre-trained models, the parsed key knowledge elements (paragraphs, sentences, etc.) are embedded into high-dimensional vectors, constructing the infrastructure knowledge vector library that supports the entire system's intelligent retrieval capabilities, transforming historical operational documents into a unified semantic representation that is machine-understandable and computable. The parsed knowledge is transformed from isolated information points into an organic intelligent entity, performing association, deduplication, and merging operations to proactively build a unified and coherent knowledge graph. Based on this knowledge graph, the extracted information is semantically associated and fused. Leveraging the powerful generation and reasoning capabilities of large language models, knowledge graphs are deeply processed. By querying natural language input from operations personnel and performing intent recognition and semantic parsing, precise matching and intelligent retrieval of knowledge content are achieved based on vector similarity calculation. Finally, real-time knowledge services are provided to operations personnel through a natural language interaction interface, thereby realizing the structured integration and efficient utilization of operational knowledge. This significantly improves the efficiency of new employee training and the ability to solve problems on the current network, greatly enriches the connotation of knowledge, and fundamentally enhances the usability and empowering value of knowledge in operational scenarios.

[0062] In this embodiment, the operational operation sequence generated based on operational intent is adapted and executed on at least one target terminal screen-based business system to achieve cross-terminal operational tasks. This can include: adapting the operational operation sequence into execution instructions that conform to the interface specifications of at least one target terminal screen-based business system through business encapsulation; and distributing the execution instructions to at least one target terminal screen-based business system to complete the cross-terminal operational tasks. In this embodiment, because the technical interfaces, data structures, and capabilities of different target terminal screen-based business systems (such as smart TVs, in-vehicle screens, tablets, etc.) are completely different, it is necessary to adapt the operational operation sequence into execution instructions that conform to the interface specifications of each target terminal screen-based business system through business encapsulation. This means "translating" the general operational operation sequence into API call execution that the target terminal screen-based business system can understand, ensuring that the instructions can be correctly executed on each terminal. The execution instructions are then distributed to each target terminal screen-based business system through a gateway service to achieve unified cross-platform operational management.

[0063] Based on the same concept, this disclosure also provides an AI-driven ubiquitous screen operation device 500. It is understood that the AI-driven ubiquitous screen operation device 500 provided in this disclosure includes hardware structures and / or software modules corresponding to each function in order to achieve the above-mentioned functions. Combining the units and algorithm steps of the various examples disclosed in this disclosure, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of this disclosure.

[0064] Figure 5 This is a block diagram illustrating an AI-driven ubiquitous screen operation device 500 according to some embodiments of this disclosure. (Refer to...) Figure 5 The device 500 includes a parsing unit 502, a calling unit 504, and an execution unit 506.

[0065] The parsing unit 502 is configured to parse and identify the operational intent in response to receiving an operational instruction input by an operations personnel, wherein the operational instruction is a natural language-based instruction. The invocation unit 504 is configured to invoke at least one AI service based on the operational intent to generate an operational operation sequence corresponding to the operational intent. The execution unit 506 is configured to adapt and execute the operational operation sequence on at least one target terminal universal screen business system to achieve cross-terminal operational tasks.

[0066] Regarding the apparatus in the above embodiments, the specific manner in which each unit performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0067] Figure 6 This is a schematic diagram of the architecture 600 of an AI-driven pan-screen operation platform shown according to some embodiments of this disclosure, such as... Figure 6As shown, the architecture 600 adopts a layered architecture, including an interaction layer 602, a service layer 604, a scheduling layer 606, a gateway layer 608, and a business layer 610, achieving effective separation of technical concerns. Specifically, the interaction layer 602 is used for front-end interaction and receiving operational instructions; the service layer 604 centrally handles AI capability invocation and logical calculations, and may include an intelligent quick toolbox 6042, an intelligent scheduling module 6044, an intelligent planning module 6046, and an intelligent knowledge base 6048, each corresponding to its respective AI service; the scheduling layer 606 is responsible for task coordination and resource allocation, and can serve as a workflow platform, interacting with the AI ​​large model 612 to invoke the large model; the gateway layer 608 uniformly handles protocol conversion and security control, performing security verification, protocol conversion, and distribution of operational instructions to the corresponding terminal business systems; and the business layer 610 focuses on business encapsulation for specific operational scenarios. This layered architecture decouples AI capability access, business logic execution, task scheduling management, and front-end interactive display, preventing them from interfering with each other. This fundamentally improves the system's maintainability, scalability, and operational stability. Specifically, it allows for independent upgrades of AI models or expansion of new terminal business systems without requiring any modifications to other modules.

[0068] This disclosure brings significant optimizations across three core dimensions: operational efficiency, quality, and cost, helping to upgrade pan-screen operations to achieve "high efficiency, standardization, and low cost." In terms of efficiency, AI tools compress traditional multi-step operations into "one-line commands," packaged into dedicated operation tools. Combined with automated process integration, this significantly shortens the time required for a single operational task. Simultaneously, relying on intelligent scheduling services for scheduled operations and automatic hotspot capture, the hotspot response cycle is reduced from over 24 hours manually managed to within one hour, efficiently matching the high-frequency update needs of 3-5 times daily across multiple terminals such as smart TVs, in-vehicle screens, and tablets. In terms of quality, the scenario-based templates and large-scale models assisted in creation by intelligent planning services reduce the discrepancy rate between planning results from newcomers and experienced operators from over 40% to less than 10%, reducing reliance on personnel experience. In terms of cost, on the one hand, the knowledge structure management of the intelligent knowledge base can shorten the new employee training cycle from about 3-6 months to within two weeks, reducing human resource training costs. On the other hand, the standardized business encapsulation of the Navigation & Desktop Management System (NDMS) tool supports the reuse of multi-terminal capabilities, avoiding the repeated investment in single-terminal customized development, and is expected to reduce system development and maintenance costs by 30%. By leveraging AI capabilities to improve module reuse capabilities, resource utilization can be improved simultaneously.

[0069] Figure 7This is a block diagram illustrating an apparatus 700 for AI-driven ubiquitous screen operation according to some embodiments of the present disclosure. The apparatus 700 can be provided as a terminal. For example, the apparatus 700 can be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0070] Reference Figure 7 The device 700 may include one or more of the following components: processing component 702, memory 704, power component 706, multimedia component 708, audio component 710, input / output (I / O) interface 712, sensor component 714, and communication component 716.

[0071] Processing component 702 typically controls the overall operation of device 700, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 702 may include one or more modules to facilitate interaction between processing component 702 and other components. For example, processing component 702 may include a multimedia module to facilitate interaction between multimedia component 708 and processing component 702.

[0072] Memory 704 is configured to store various types of data to support the operation of device 700. Examples of this data include instructions for any application or method operating on device 700, contact data, phonebook data, messages, pictures, videos, etc. Memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0073] The power supply component 706 provides power to the various components of the device 700. The power supply component 706 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device 700.

[0074] Multimedia component 708 includes a screen that provides an output interface between the device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 708 includes a front-facing camera and / or a rear-facing camera. When the device 700 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0075] Audio component 710 is configured to output and / or input audio signals. For example, audio component 710 includes a microphone (MIC) configured to receive external audio signals when device 700 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 704 or transmitted via communication component 716. In some embodiments, audio component 710 also includes a speaker for outputting audio signals.

[0076] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0077] Sensor assembly 714 includes one or more sensors for providing state assessments of various aspects of device 700. For example, sensor assembly 714 may detect the on / off state of device 700, the relative positioning of components such as the display and keypad of device 700, changes in the position of device 700 or a component of device 700, the presence or absence of user contact with device 700, the orientation or acceleration / deceleration of device 700, and temperature changes of device 700. Sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 714 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0078] Communication component 716 is configured to facilitate wired or wireless communication between device 700 and other devices. Device 700 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 716 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 716 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0079] In an exemplary embodiment, the apparatus 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0080] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, which can be executed by a processor 720 of the device 700 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0081] Figure 8 This is another block diagram illustrating an apparatus 800 for AI-driven ubiquitous screen operation according to some embodiments of this disclosure. For example, apparatus 800 may be provided as a server. See also... Figure 8 The device 800 includes a processing component 822, which further includes one or more processors, and memory resources represented by memory 832 for storing instructions, such as application programs, that can be executed by the processing component 822. The application programs stored in memory 832 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 822 is configured to execute instructions to perform the aforementioned antenna tuning method.

[0082] Device 800 may also include a power supply component 826 configured to perform power management of device 800, a wired or wireless network interface 850 configured to connect device 800 to a network, and an input / output (I / O) interface 858. Device 800 may operate on an operating system stored in memory 832, such as Windows Server™, MacOSX™, Unix™, Linux™, FreeBSD™, or similar.

[0083] In some embodiments of this disclosure, a storage medium is provided, which may be a non-transitory computer-readable storage medium.

[0084] In some embodiments of this disclosure, when instructions in the storage medium are executed by the processor of an electronic device, the electronic device is able to perform the AI-driven pan-screen operation method described above.

[0085] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the AI-driven pan-screen operation method involved in any of the above embodiments.

[0086] In this description, "multiple" means at least two, referring to two or more, such as two, three, etc., unless otherwise explicitly specified. Other quantifiers are similar. The singular forms "a," "the," and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. Furthermore, unless otherwise specified or clearly indicated from the context, the articles "a" and "an" as used in this disclosure and the appended claims are generally understood to mean "one or more."

[0087] It should be understood that, unless otherwise specifically indicated, features of various embodiments of this disclosure described herein can be combined with each other. As used herein, the term "and / or" includes any one of the related listed items and any combination of two or more; "and / or" describes the association relationship between related objects, indicating that three relationships may exist, for example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Similarly, "at least one of..." includes any one of the related listed items and any combination of two or more.

[0088] It is further understood that the terms "first," "second," etc., are used to describe various types of information, but this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and do not indicate a specific order or degree of importance. In fact, the expressions "first," "second," etc., are completely interchangeable. For example, without departing from the scope of this disclosure, first information can also be referred to as second information, and similarly, second information can also be referred to as first information.

[0089] Furthermore, the term "exemplary" is used herein to indicate that it serves as an example, instance, or illustration. Any aspect or design described herein as "exemplary" is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term "exemplary" is intended to present concepts in a concrete manner. As used herein, the term "or" is intended to indicate an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X applies A or B" is intended to indicate any of the natural inclusive permutations. That is, if X applies A; X applies B; or X applies both A and B, then applying A or B satisfies the condition under any of the foregoing instances.

[0090] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding the specification and drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in this disclosure, such terms are intended to be inclusive in a manner similar to the term “including.”

[0091] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed in the embodiments of this disclosure.

[0092] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. An AI-driven method for operating a screen, characterized in that, include: In response to receiving an operational instruction input by an operations personnel, the operational instruction is parsed and the operational intent is identified, wherein the operational instruction is a natural language-based instruction; Based on the operational intent, at least one AI service is invoked to generate an operational operation sequence corresponding to the operational intent; as well as The operational sequence is adapted and executed on at least one target terminal screen service system to achieve cross-terminal operational tasks.

2. The method according to claim 1, characterized in that, The step of invoking at least one AI service based on the operational intent to generate an operational operation sequence corresponding to the operational intent includes: Based on the stated operational intent, a visual orchestration is performed on the workflow platform to generate an intelligent agent that reflects the stated operational intent; and In response to the interaction between the workflow platform and the AI ​​big model, the intelligent agent calls at least one AI service to generate an operational operation sequence corresponding to the operational intent.

3. The method according to claim 2, characterized in that, The invocation of at least one AI service through the intelligent agent includes at least one of the following methods: The dedicated operation tools in the intelligent quick toolbox are invoked to map the operational intent into a predefined and reusable standardized operation sequence; Invoke the intelligent scheduling service, and based on the hot topic tags provided by the intelligent scheduling service, trigger and generate an initial operation plan; as well as The intelligent planning service is invoked to generate a structured theme planning scheme based on at least one of the aforementioned hot topic tags, user profiles, and operational strategies.

4. The method according to claim 3, characterized in that, The invocation of dedicated operation tools in the intelligent shortcut toolbox includes invoking at least one of the following tools: Invoke the label expression generation tool to transform natural language grouping intents into structured user grouping rules; Invoke the desktop focus setting tool to intelligently configure the desktop focus navigation logic of the target terminal business system according to the interaction instructions; Invoke the intelligent media asset replacement tool to perform batch identification and replacement of specified media assets based on image recognition or metadata matching; as well as Use content deduplication detection tools to retrieve historical content based on content fingerprints and similarity calculations to avoid duplicate distribution.

5. The method according to claim 3, characterized in that, The invocation of the intelligent scheduling service, and the triggering and generation of an initial operation plan based on the real-time hot topics provided by the intelligent scheduling service, includes: Raw hotspot data is collected from preset internet data sources via scheduled tasks; Semantic analysis and clustering are performed on the original hotspot data to generate structured hotspot topic tags; Based on the time-sensitive attributes of the aforementioned trending hashtags, a creation prompt containing execution suggestions is generated and pushed to the operations staff; and In response to the confirmation instruction from the operations personnel, the content generation service is invoked to automatically generate a preliminary operations plan.

6. The method of claim 1, wherein, The method further includes: Build an intelligent knowledge base to store, parse, and quantify historical operational knowledge, and provide intelligent retrieval and support for the operational tasks.

7. The method according to claim 6, characterized in that, The construction of the intelligent knowledge base includes: Collecting historical operation documents from multiple heterogeneous data sources, the historical operation documents including at least one of text, table, presentation and picture; Analyzing and key information extraction are performed on the historical operation documents, and are converted into high-dimensional vector representation to construct a knowledge vector library; Based on knowledge graph technology, the extracted information is associated and fused semantically; and In response to receiving a natural language query, through intent recognition and vector similarity calculation, the matching knowledge content is recalled from the knowledge vector library.

8. The method of claim 1, wherein, The method further comprises: The method further comprises: The method further comprises: The method further comprises:

9. An AI-driven panopticon operating device, characterized by, The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises:

10. An electronic device, comprising: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises

Images