{
  "docId": "019dd923-5e88-73ef-bd58-45ee3d7c1969",
  "docSlug": "a22c365fb8b31ee6",
  "documentTitle": "Accenture Tech Vision 2025",
  "authorId": "Accenture",
  "authorName": "Accenture",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "strategy_consulting",
  "sourceTypeLabel": "Strategy consulting",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.778,
  "pageNumber": 29,
  "pageCount": 67,
  "prevPage": 28,
  "nextPage": 30,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "overcrowded",
  "nDataPoints": 5,
  "notes": "The slide uses a bar chart to illustrate the 19x growth in research papers between 2021 and 2024.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "bar_chart_horizontal",
    "callout_box",
    "footnote"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd58-45ee3d7c1969/29",
  "deckHref": "/decks/019dd923-5e88-73ef-bd58-45ee3d7c1969",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd58-45ee3d7c1969.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd58-45ee3d7c1969#slide-29",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Research into multimodal models has increased significantly.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-0a6b-775b-a1dd-3c599ff4cefd",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.405,
        "x": 0.55,
        "y": 0.36
      },
      "kind": "chart",
      "text": "Number of research papers relating to Multimodal Foundation Models, 2020 - 2024*",
      "attrs": null,
      "subkind": "bar-horizontal",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "fd93de09-1e0d-401c-8e41-94e10be20a91",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Number of research papers: 2,834",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-0a6b-775b-a1dd-42ff923cce2d",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.21,
        "x": 0.047,
        "y": 0.5
      },
      "kind": "paragraph",
      "text": "How does it connect to the trend? While text-based chatbots are becoming increasingly common, the addition of audio, image, and video input/output will vastly expand the customer-facing ways AI can be used.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "471009ce-cabb-48b0-9661-c7492b85af1c",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.21,
        "x": 0.275,
        "y": 0.23
      },
      "kind": "paragraph",
      "text": "Who is doing it today? Runway's Gen-3 Alpha is an AI model that can produce realistic videos from simple text prompts or still images.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "85973df9-d473-4297-a4b0-4febcb241df8",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.21,
        "x": 0.047,
        "y": 0.23
      },
      "kind": "paragraph",
      "text": "What is it? Companies are rapidly expanding the range of modalities foundation models can accept as inputs and produce as outputs.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "fdb742f3-5dce-495f-8ce7-0f5c55f7f050",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.3,
        "x": 0.55,
        "y": 0.85
      },
      "kind": "source-note",
      "text": "Note: *2024 contains partial data through Oct 2024. Source: Accenture Research analysis on ArXiv papers; Jan 2020 - Oct 2024",
      "attrs": null,
      "subkind": null,
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "721026d8-22ea-49e8-bd02-2a19b0dc4ada",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.035,
        "w": 0.405,
        "x": 0.55,
        "y": 0.23
      },
      "kind": "title",
      "text": "Research into multimodal models has increased significantly",
      "attrs": null,
      "subkind": "action-title",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "05027e3c-8fec-4f51-9b5c-c0f58ee56f78",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.028,
        "w": 0.233,
        "x": 0.047,
        "y": 0.158
      },
      "kind": "title",
      "text": "Multimodal AI models",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "b481c5d6-de69-4898-bb6a-17a0f39fc3bc",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-0bbb-77da-b1d3-607bbf56d97f",
      "evidence": "Action title 'Research into multimodal models has increased significantly'",
      "confidence": 75
    },
    {
      "name": "Concrete Language",
      "slug": "concrete-language",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "019dd95a-0bbb-77da-b1d3-5e8bae851379",
      "evidence": "'2,834' multimodal-AI papers",
      "confidence": 80
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 46,
      "from": 14,
      "beatId": "019dd95a-0680-7418-8208-ad7bcff99346",
      "arcName": "The Consultant's Gambit",
      "arcSlug": "consultants-gambit",
      "beatName": "Solution & Approach",
      "beatSlug": "consultants-gambit-solution-approach",
      "evidence": "Trends 1-3 lay out Accenture's framework: agentic, personified, embodied AI",
      "position": 3,
      "confidence": 72,
      "parentBeatName": "Turn",
      "parentBeatSlug": "turn"
    }
  ],
  "loops": [
    {
      "to": 33,
      "from": 22,
      "name": "So What Cascade",
      "slug": "41-so-what-cascade",
      "bestFor": "Data presentations, executive summaries, driving to recommendations",
      "matchId": "019dd95a-07fd-712f-b772-76ae1331d8f2",
      "evidence": "Big Picture -> 4x/2,834/76% stats -> Implications -> What's Next -> Portrait of the Future.",
      "position": 3,
      "objective": "Cascade Personified-AI evidence into customer-experience action",
      "structure": "The Data -> So What? (Insight 1) -> So What? (Insight 2) -> So What? (The Action)",
      "confidence": 78,
      "description": "Chain insights together, each answering 'so what?' until you reach the actionable conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}