Large model data attribution method and device, equipment, medium and product

Abstract

One or more of the scenarios herein provide a large model data attribution method and device, equipment, medium and product, the large model data attribution method comprises: in response to a first operation triggered at a first document page, presenting a first area; in response to a second operation triggered in the first area, presenting a second area; in response to a third operation triggered in the second area, receiving first configuration information; in the first document page, presenting a content mark block generated based on the first configuration information. Support users to add content mark blocks for processing chart data in the document in an interactive manner, without manual analysis and processing of chart data by the user, realize multi-dimensional, comprehensive and flexible processing of chart data in the document, and improve the processing and data attribution efficiency of chart data in the document.

Description

Technical Field

[0001] One or more of the scenarios described herein relate to a large model data attribution method, a large model data attribution device, an electronic device, a computer-readable storage medium, and a computer program product. Background Technology

[0002] A document processing system can be understood as a software system used to manage documents. Users can use a document processing system to perform document-related operations, such as writing analysis reports.

[0003] In the process of writing analysis reports, operations related to charts and graphs are often involved, so improving the efficiency of chart-related operations in documents is particularly important. Summary of the Invention

[0004] This content section is provided to briefly introduce the concepts, which will be described in detail in the subsequent detailed description section. This content section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] This paper provides at least one scenario of a large model data attribution method, comprising: presenting a first region in response to a first operation triggered on a first document page, wherein the first region is used to select a tag block type; presenting a second region in response to a second operation triggered on the first region, wherein the second region is used to configure content tag blocks, the tag block type of the content tag blocks matching the tag block type indicated by the second operation; receiving first configuration information in response to a third operation triggered on the second region; and presenting the content tag blocks generated based on the first configuration information on the first document page; wherein the tag block type of the content tag blocks includes at least one of the following: a first tag block for interpreting chart data, a second tag block for rendering chart data, and a third tag block for attribution analysis of chart data.

[0006] At least one embodiment of this document provides a large model data attribution apparatus, comprising: a presentation module configured to: present a first region in response to a first operation triggered on a first document page, wherein the first region is used to select a tag block type; the presentation module is further configured to: present a second region in response to a second operation triggered in the first region, wherein the second region is used to configure content tag blocks, the tag block type of the content tag blocks matching the tag block type indicated by the second operation; a receiving module configured to: receive first configuration information in response to a third operation triggered in the second region; the presentation module is further configured to: present the content tag blocks generated based on the first configuration information on the first document page; wherein the tag block type of the content tag blocks includes at least one of the following: a first tag block for interpreting chart data, a second tag block for rendering chart data, and a third tag block for attribution analysis of chart data.

[0007] At least one scenario of this paper provides an electronic device including: at least one processor; and at least one memory including one or more computer program instructions; wherein the one or more computer program instructions are executed by the processor to perform the large model data attribution method provided in at least one scenario of this paper.

[0008] At least one aspect of this paper provides a computer-readable storage medium that non-transitory stores computer-readable instructions, wherein the large model data attribution method provided by at least one aspect of this paper is implemented when the computer-readable instructions are executed by a processor.

[0009] At least one aspect of this document provides a computer program product, including a computer program that, when executed by a processor, implements the large model data attribution method provided by at least one aspect of this document.

[0010] In one of the large model data attribution methods provided in this paper, users are supported in interactively adding content tag blocks for processing chart data in documents. The content tag blocks include interpretation blocks, chart blocks, and attribution blocks. Users configure the configuration information of the content tag blocks, and the corresponding content tag blocks are presented in the document. Users do not need to manually analyze and process the chart data, which enables multi-dimensional, comprehensive, and flexible processing of chart data in the document and improves the efficiency of chart data processing and data attribution in the document. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the various scenarios herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0012] Figure 1 This paper illustrates an application scenario of at least one of the large model data attribution methods presented in this paper.

[0013] Figure 2 The diagram illustrates a flowchart of a large model data attribution method provided in at least one of the cases presented in this paper.

[0014] Figure 3 The illustration shows a schematic diagram of a content marker block provided in at least one scenario of this article;

[0015] Figures 4A to 4F The illustration shows a schematic diagram of a document page provided in at least one scenario herein;

[0016] Figure 5 The schematic diagram illustrates the structure of a large model data attribution device provided in at least one of the cases presented in this paper.

[0017] Figure 6 A schematic diagram of the structure of an electronic device suitable for implementing at least one of the scenarios described herein is shown. Detailed Implementation

[0018] One or more scenarios described herein will now be described in more detail with reference to the accompanying drawings. While some scenarios are shown in the drawings, it should be understood that this document can be implemented in various forms and should not be construed as limited to the scenarios set forth herein; rather, these scenarios are provided to provide a more thorough and complete understanding of this document. It should be understood that the accompanying drawings and scenarios are for illustrative purposes only and are not intended to limit the scope of this document.

[0019] It should be understood that the steps described in the method embodiments herein may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this document is not limited in this respect.

[0020] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one situation" means "at least one situation"; the term "another situation" means "at least one additional situation"; the term "some situations" means "at least some situations". Definitions of other terms will be given in the following description.

[0021] It should be noted that the concepts of "first" and "second" mentioned in this article are only used to distinguish different devices, modules or units, and are not used to limit the order of the functions performed by these devices, modules or units or their interdependencies.

[0022] It should be noted that the terms "one" and "more" used in this document are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0023] The names of the messages or information exchanged between the various devices in the embodiments herein are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0024] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0025] It is understood that before using the technical solutions disclosed in each scenario in this article, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this article and their authorization should be obtained through appropriate means in accordance with relevant laws and regulations. Relevant users may include any type of rights holder, such as individuals, enterprises, or groups.

[0026] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require obtaining and using the user's information, thereby enabling the relevant user to choose whether to provide information to the software or hardware such as electronic devices, applications, servers, or storage media that perform the operation of any of the technical solutions described herein.

[0027] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide information to the electronic device.

[0028] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation method described in this article. Other methods that comply with relevant laws and regulations may also be applied to the implementation method described in this article.

[0029] A document processing system can be understood as a software system used to manage documents. It is widely used in various scenarios such as office work, study, and creation. Users can use the document processing system to perform document-related operations, such as creating, editing, and viewing documents.

[0030] In some application scenarios, users can use document processing systems to write analysis reports. For example, users can query and export data from multiple heterogeneous data sources, add charts to the document, and then combine their own business knowledge to analyze the chart data, write analysis results and interpretation text, and form analysis reports (such as weekly reports, monthly reports, etc.).

[0031] To improve the efficiency of chart-related operations in documents, such as data attribution, some document processing systems offer auxiliary tools. For example, some systems provide report template tools that allow users to predefine report templates and periodically retrieve data from data sources to populate fixed locations within the template. However, these report template tools lack chart interpretation capabilities, still requiring manual result writing, and offer limited flexibility in chart-related processing.

[0032] To at least partially solve the aforementioned technical problem, this paper provides a large model data attribution method in at least one scenario. The method includes: in response to a first operation triggered on a first document page, presenting a first region for selecting a tag block type; in response to a second operation triggered on the first region, presenting a second region for configuring content tag blocks, wherein the tag block type of the content tag blocks matches the tag block type indicated by the second operation; in response to a third operation triggered on the second region, receiving first configuration information; and presenting content tag blocks generated based on the first configuration information on the first document page. The tag block type of the content tag blocks includes at least one of the following: a first tag block for interpreting chart data, a second tag block for rendering chart data, and a third tag block for attribution analysis of chart data.

[0033] Based on the large model data attribution method provided in at least one of the embodiments of this paper, at least one of the embodiments of this paper also provides a large model data attribution device, electronic device, computer-readable storage medium, and computer program product.

[0034] In one of the large model data attribution methods provided in this paper, users are supported in interactively adding content tag blocks for processing chart data in documents. The content tag blocks include interpretation blocks, chart blocks, and attribution blocks. Users configure the configuration information of the content tag blocks, and the corresponding content tag blocks are presented in the document. Users do not need to manually analyze and process the chart data, which enables multi-dimensional, comprehensive, and flexible processing of chart data in the document and improves the efficiency of chart data processing and data attribution in the document.

[0035] For example, in at least one of the cases presented in this paper, data attribution can be understood as attributing chart data to data in a document by adding content tag blocks.

[0036] The following detailed description, with reference to the accompanying drawings, illustrates one or more scenarios and some examples thereof.

[0037] Figure 1 The illustration shows an application scenario of at least one of the large model data attribution methods presented in this paper.

[0038] like Figure 1 As shown, the application scenario provided in this case may include user 101, terminal device 102, and server 103. Terminal device 102 can be various electronic devices capable of providing interactive pages, such as smart wearable devices, smart appliances, smart cars, mobile phones, tablets, laptops, or desktop computers.

[0039] In one or more of the scenarios described herein, a client may be installed in the terminal device 102. This client may be a client of a document processing system. The server 103 may be a server that provides support for the operation of the client installed in the terminal device 102. That is, the server 103 may be a server of a document processing system. For example, the server 103 may be a server for a local area network or a wide area network, or it may be a cloud server, etc. The scenarios described herein do not limit this.

[0040] User 101 can be a user of a client installed on terminal device 102. For example, user 101 can be an editor who edits documents in a document processing system.

[0041] In one or more scenarios described herein, the document processing system can be deployed in different ways. In some cases, the document processing system can be deployed locally; for example, it can be a document processing application (APP), document processing tool, or document processing plugin installed on terminal device 102. Alternatively, it can be deployed in the cloud, providing document management services as a cloud service; for example, it can be an online document processing tool. Furthermore, the document processing system can be integrated into other systems as a functional module, providing document processing functionality. For instance, it can be integrated into an office collaboration system, providing document processing services (e.g., cloud document processing services) within that system.

[0042] The server 103 can communicate with the terminal device 102, for example, by providing the client installed on the terminal device 102 with relevant data (such as document content) required by the terminal device to run the client; or, for example, the server 103 can also receive relevant data returned by the terminal device 102 during the running of the client (such as operation data on the document triggered by user 101 on the client).

[0043] For example, the large model data attribution methods provided in one or more scenarios in this paper can be implemented in software, hardware, firmware, or any combination thereof.

[0044] For example, the large model data attribution method provided in one or more scenarios of this paper is applicable to a terminal device that can load and execute the large model data attribution method. This paper does not impose any limitations on this. For instance, the terminal device may include other forms of processing units with data processing capabilities and / or instruction execution capabilities, such as a central processing unit (CPU), graphics processing unit (GPU), digital signal processor (DSP), neural network processing unit (NPU), or storage units. The server or terminal device may also have an operating system and various types of application programming interfaces (APIs) installed, implementing the large model data attribution method provided in this paper by running code or instructions.

[0045] The following will combine Figure 2 , Figure 3 and Figures 4A to 4F This paper provides a detailed description of at least one of the large model data attribution methods presented in this paper.

[0046] Figure 2 The diagram illustrates a flowchart of a large model data attribution method provided in at least one scenario of this paper.

[0047] like Figure 2 As shown, the large model data attribution method in this scenario includes steps S201 to S204. The executing entity of this large model data attribution method can be an electronic device with a client deployed, an electronic device with a server deployed, or any electronic device that connects the client and server. This document does not limit the scope of this scenario. The steps included in this large model data attribution method are explained below:

[0048] Step S201: In response to the first operation triggered on the first document page, present the first area.

[0049] Step S202: In response to the second operation triggered in the first region, present the second region.

[0050] Step S203: In response to the third operation triggered in the second region, receive the first configuration information.

[0051] In one or more contexts of this article, the first document page can be understood as any document page, for example, the first document page can be a document page that is currently open and being viewed.

[0052] The first document page can hold the first document, which users can process. For example, users can edit the content of the first document on the first document page. The first document can be of different types; for example, it can be an analysis report. The content of the first document can include various types of content such as text, images, tables, videos, files, whiteboards, and code blocks.

[0053] In one or more scenarios described herein, users are supported in configuring content tag blocks on the first document page. Content tag blocks can be understood as the relevant areas of the first document related to the chart data. In other words, users can define the processing areas related to the chart data on the first document page through interactive tagging, thereby enabling automatic chart data processing on the first document page.

[0054] By triggering a configuration operation on the first document page, a content tag block is added to the first document page. The configuration operation can be understood as an operation to add configuration information for the content tag block. That is, by triggering the configuration operation, the logic for adding the content tag block is enabled. For example, the first document page can provide configuration controls, and the configuration operation triggered on the first document page can be an operation to trigger the configuration controls; or, for example, the triggering logic of the configuration operation can be pre-set, and when the operation triggered on the first document page is detected to meet the triggering logic of the configuration operation, the configuration operation is triggered.

[0055] The first area can be used to select the type of markup block. That is, the first area can be understood as the area used to add a specific type of markup block. For example, the first area can be a floating window area that appears above the first document page, or the first area can be a window area that appears in the first document page.

[0056] The second operation can be understood as the operation of selecting a marker block type. For example, the first area can present selectable marker block types (including the first marker block, the second marker block, and the third marker block), and the second operation can be the operation of selecting one of the marker block types.

[0057] The second area can be used to configure content tag blocks. The tag block type of the content tag block matches the tag block type of the second operation instruction. In other words, the second area can be understood as the area used to obtain the configuration information of the content tag block. Since the configuration information required for content tag blocks of different tag block types is different, the second area corresponding to content tag blocks of different tag block types can be different. For example, the second area corresponding to the first tag block can be used to obtain configuration information A and configuration information B, the second area corresponding to the second tag block can be used to obtain configuration information A and configuration information C, and the second area corresponding to the third tag block can be used to obtain configuration information D and configuration information E.

[0058] For example, when the second operation is to select one of the tag block types, the tag block type indicated by the second operation is the selected tag block type, and the second area can be used to configure the content tag block of the selected tag block type.

[0059] The third operation can be understood as the operation of inputting the first configuration information. For example, the second area may include multiple sub-areas, each of which corresponds to multiple configuration information. The third operation may be the operation of inputting information in multiple sub-areas, and the information input in multiple sub-areas forms the first configuration information.

[0060] In this way, the user first selects the marker block type and provides the configuration area corresponding to the marker block type. The user then interacts with the first document page to dynamically mark the first document page, reducing the user's learning curve and enabling automatic chart data processing on the first document page in an intuitive and interactive way.

[0061] The first configuration information for a content tag block can be understood as the configuration information required to generate the content tag block. For example, the first configuration information for a content tag block may include the chart data involved in the content tag block, the chart data processing logic, etc.

[0062] This document does not restrict the manner in which the first configuration information for the content tag block is received, such as by the user inputting the first configuration information for the content tag block via information input.

[0063] Step S204: On the first document page, a content tag block generated based on the first configuration information is presented.

[0064] Since the first configuration information can indicate the configuration information required to generate the content tag block, representing the user's processing needs for the chart data, the content tag block can be generated based on the first configuration information, such as the content to be presented in the content tag block, and then the content tag block is presented in the first document page.

[0065] In this way, to meet users' chart data processing needs, users do not need to manually analyze the chart data. By triggering the configuration operation and entering the first configuration information, the chart data can be automatically processed on the first document page, and the content markup blocks can be dynamically assembled on the first document page.

[0066] Figure 3 The illustration shows a schematic diagram of a content marker block provided in at least one scenario herein.

[0067] In one or more scenarios described herein, content marker blocks may include multiple marker block types, and different marker block types can represent different processing methods for chart data. For example, such as Figure 3 As shown, the tag block type of the content tag block may include at least one of the following: a first tag block for interpreting chart data, a second tag block for rendering chart data, and a third tag block for attribution analysis of chart data.

[0068] In other words, the first marker block can be understood as an interpretation block, which can be used for preliminary, shallow interpretation of chart data. For example, the first marker block can analyze the chart data in a single chart. The second marker block can be understood as a chart block, which can be used to render chart data. For example, the second marker block can render chart data on the first document page, presenting the chart data in the form of a chart. Alternatively, the second marker block can also render external charts on the first document page, adjusting the presentation of the external charts (such as changing the theme color of the external charts) to match the overall style of the first document page. The third marker block can be understood as an attribution block, which can be used for deep, complex attribution analysis of chart data. For example, the third marker block can perform joint analysis of chart data in multiple charts, breaking down any anomalies that arise.

[0069] Thus, by providing a rich variety of marker block types, users can select and configure content marker blocks of the corresponding marker block type to meet their different chart data processing needs. This enables automatic processing of chart data in different aspects on the first document page. Furthermore, by providing content marker blocks, different chart processing needs can be modified and reused independently, providing users with modular chart data processing functions on the document page.

[0070] Furthermore, the user's interactive behavior triggered on the first document page can also be associated with the presentation position of the content markup block. For example, in response to a first operation triggered on the first document page, the first area is presented, including: in response to a first operation triggered at a first position on the first document page, the first area is presented.

[0071] The first position can be understood as any position on the first document page. The first position can be represented by positional information. For example, the first position can be the Xth line of the first document page, where X is an integer greater than 0.

[0072] For example, the trigger logic for the first operation can be pre-set. For instance, the trigger logic for the first operation is to input a specific character. The user can input a specific character on the 4th line of the first document page to trigger the first operation. In this case, the first position is the 4th line of the first document page.

[0073] Correspondingly, in the first document page, a content tag block generated based on the first configuration information is presented, including: presenting the content tag block generated based on the first configuration information at a first position on the first document page.

[0074] In other words, when a user triggers the first action at the first position, it indicates that the user has a need to add a content marker block at the first position to process the chart data. Therefore, after generating the content marker block based on the first configuration information, the content marker block is presented at the first position to match the user's interactive behavior with the presented content.

[0075] In this way, the first action triggered by the user can bind the content marker block to the location. That is, the first action can not only be used to trigger the addition of the content marker block (such as the selection of the marker block type), but also to locate it in the first document page, indicating the position where the user wants to perform chart data processing in the first document page, so that the content marker block is presented in the position desired by the user, thereby improving the user's experience of automatically processing chart data in the first document page.

[0076] The following section introduces the first configuration information for content tag blocks of different tag block types.

[0077] In some cases, the tag block type of the content tag block includes a first tag block, that is, the content tag block is used to interpret chart data. In this case, the first configuration information for the content tag block is received, including: receiving first chart information and first reference content, the content tag block interprets the chart data associated with the first chart information, and the presentation content of the content tag block matches the style of the first reference content.

[0078] In other words, for the first tag block, the first configuration information may include first chart information and first reference content. The first chart information can be used to represent the chart, for example, the first chart information can be used to represent an external chart or an internal chart in the first document page, and the first chart information may be a chart link, chart identifier, etc.; the first reference content can serve as a style reference for imitating the content tag block, for example, the first reference content may be a natural language interpretation example, content that needs to be interpreted, etc.

[0079] For example, the first chart information could be an external chart named Chart A, and the first reference content could be "X problems were generated this quarter, and Y problems were reduced".

[0080] By configuring the first chart information, the interpretation object of the content marker block is indicated (e.g., a data source). By configuring the first reference content, the interpretation content of the content marker block is indicated. In this way, for the first marker block that interprets the chart data, the interpretation object and interpretation content of the content marker block are clarified, so that the presentation content of the content marker block matches the user's chart data interpretation needs.

[0081] Furthermore, for the first marker block, the first configuration information may also include interpretation requirement description information. For example, the interpretation requirement description information may describe the user's specific interpretation requirements for the chart data associated with the first chart information in natural language. In this way, by configuring the interpretation requirement description information, the relationship between the presented content of the content marker block and the user's interpretation requirements for the chart data is made closer.

[0082] In some cases, the tag block type of the content tag block includes a second tag block, that is, the content tag block is used to render chart data. In this case, receiving the first configuration information for the content tag block includes: receiving second chart information, and the content tag block rendering the chart data associated with the second chart information.

[0083] In other words, for the second marker block, the first configuration information may include the second chart information. The second chart information can be used to represent charts or data. For example, the second chart information can be used to represent external charts or external data, and the second chart information may be chart links, chart identifiers, data links, etc.

[0084] For example, the second chart information can be an external chart named Chart A, or the second chart information can be external data named Data Table B.

[0085] On the one hand, content tags belonging to the second tag block can render external charts on the first document page. For example, the external chart can be rendered in the first document page in a style that matches the first document. On the other hand, content tags belonging to the second tag block can also render external data as charts on the first document page. For example, the external data can be rendered as line charts, pie charts, etc. In this case, by identifying the data structure of the external data, the chart type that matches the data structure of the external data can be selected for rendering.

[0086] By configuring the second chart information, the rendering object of the content marker block (such as a data source) is indicated. In this way, for the second marker block that renders the chart data, the rendering object of the content marker block is clarified, so that the content presented by the content marker block matches the user's chart data rendering requirements.

[0087] In some cases, the tag block type of the content tag block includes a third tag block, that is, the content tag block is used for attribution analysis of chart data. In this case, the first configuration information for the content tag block is received, including: receiving orchestration information for multiple process nodes, and the content tag block performs attribution analysis on the chart data associated with the multiple process nodes.

[0088] In other words, for the third marker block, the first configuration information may include the orchestration information of multiple process nodes. The first configuration information can be used to characterize the attribution analysis logic. For example, the orchestration information of multiple process nodes may include the configuration information of multiple different types of process nodes and the relationship information between multiple different types of process nodes.

[0089] Since attribution analysis of chart data is usually quite complex, the attribution analysis logic is broken down into multiple process nodes. Users only need to configure each process node and the execution order between them to form the orchestration information of multiple process nodes and obtain the first configuration information.

[0090] For example, a canvas-style orchestration interface is provided, allowing users to define the execution order and data flow between process nodes by dragging and dropping process nodes and connecting them with lines, gradually building attribution analysis logic and forming a workflow for executing the attribution analysis logic.

[0091] By configuring the orchestration information of multiple process nodes, the attribution analysis logic of the content tag block is indicated. In this way, for the third tag block that performs attribution analysis on chart data, the attribution analysis logic of the content tag block is clarified, so that the content presented by the content tag block matches the user's chart data attribution analysis needs, and the chart data processing includes in-depth attribution, multi-dimensional decomposition and other analysis content, thereby improving the chart data processing effect.

[0092] In some possible implementations, various types of process nodes are pre-configured for users to choose from. Process nodes may include at least one of the following: condition nodes, intermediate data generation nodes, attribution conclusion generation nodes, and parallel nodes.

[0093] For example, a condition node can be used to: judge at least one of the chart data associated with the condition node and the intermediate data generated by the intermediate data generation node based on filtering conditions, in order to execute different process branches.

[0094] For example, an intermediate data generation node can be used to: calculate at least one of the chart data associated with the intermediate data generation node and other intermediate data generated by other intermediate data generation nodes, based on generation logic, to generate intermediate data.

[0095] For example, the attribution conclusion generation node can be used to: perform attribution analysis on at least one of the chart data associated with the attribution conclusion generation node and the intermediate data generated by the intermediate data generation node, based on attribution logic, to generate attribution analysis results.

[0096] For example, a parallel node can be used to execute at least two process nodes in parallel.

[0097] In other words, the configuration information of a condition node can include chart information and filtering conditions. Based on the filtering conditions, the chart data indicated by the chart information is filtered, thereby determining the direction of subsequent process nodes. The configuration information of an intermediate data generation node can include chart information, other intermediate data, and generation logic. Based on the generation logic, the chart data indicated by the chart information and other intermediate data are analyzed to obtain intermediate data, such as descriptive conclusions. The configuration information of an attribution conclusion generation node can include chart information, intermediate data, and attribution logic. Based on the attribution logic, attribution analysis is performed on the chart data indicated by the chart information and intermediate data. For example, attribution analysis is performed on the reasons for anomalies in the chart data and intermediate data indicated by the chart information to obtain in-depth analysis conclusions. The configuration information of a parallel node can include node information of at least two process nodes, such as node identifiers.

[0098] In this way, by providing different types of process nodes, users can gradually break down complex attribution analysis logic into simple and independent sub-logics by arranging different types of process nodes. Users can select the corresponding type of process node according to the sub-logic, input the configuration information of the process node, reduce the difficulty of attribution analysis of chart data, and configure complex attribution analysis processes through a graphical canvas.

[0099] The content of different tag types has different generation methods. For example, the content of different tag types can be generated based on artificial intelligence models, which will be introduced below.

[0100] In some cases, the content tag block is of the first tag block type. In this case, the content of the content tag block is generated as follows: the first chart information and the first reference content are sent to the first model, the first code returned by the first model is received, the first code is executed, and the content of the content tag block is obtained.

[0101] The first code can be used to generate interpretation content that is associated with the chart data of the first chart information and matches the style of the first reference content. Thus, by executing the first code, interpretation content can be generated, and the interpretation object of the interpretation content is the chart data associated with the first chart information. The style of the interpretation content is similar to that of the first reference content.

[0102] The first model can be understood as any artificial intelligence model with code generation capabilities. The first model can be a large model; for example, it can include any one or a combination of several large language models, speech models, vision models, and multimodal models. For instance, the first model can be a model built on a transformer architecture, a model built on a recurrent neural network, a model built on an attention mechanism, etc. Alternatively, the first model can also be a model improved upon the transformer architecture, such as a mixture of experts (MoE) model.

[0103] This paper does not restrict the way the first model is obtained in one or more scenarios. For example, the first model can be an existing, open-source artificial intelligence model. Alternatively, the first model can be an artificial intelligence model obtained by fine-tuning the pre-trained artificial intelligence model using training data related to code generation (such as chart information, reference content, and execution code corresponding to the chart information and reference content).

[0104] The first model can generate initial code and prompts based on prompt learning. In generative tasks (such as text generation, question answering, and dialogue tasks), these prompts can guide the AI ​​model to produce specific outputs. By configuring prompts, the AI ​​model can understand the background and requirements of the task, enabling it to handle different types of processing tasks without retraining, thus increasing the scalability and flexibility of the AI ​​model.

[0105] For example, a first prompt word is generated, the first prompt word is sent to a first model, and a first code is received from the first model. The first prompt word may include: first chart information, first reference content, and prompt information for indicating that the first code is generated based on the first chart information and the first reference content.

[0106] By sending the first prompt word to the first model, the first model can analyze the first chart information and the first reference content with the prompt word's prompting capability, and then generate the first code.

[0107] Thus, on the one hand, by using the first model to analyze the first chart information and the first reference content, the first code is automatically generated, thereby automatically generating the content of the content marker block. On the other hand, considering that interpreting chart data often involves relatively complex interpretation logic, if the interpretation content is directly generated using the first model, it is difficult to guarantee the accuracy of the interpretation content. When there are errors in the interpretation content, it is also difficult to find out the cause of the error and to modify the interpretation content. Therefore, the first code is generated using the first model, and the generation logic of the interpretation content is reflected in the first code, which facilitates adjustment and modification and improves the accuracy of the interpretation content.

[0108] Furthermore, it can also receive modification operations on the first code, and update the first code based on the modification operations.

[0109] In other words, users can check the execution logic of the first code. For example, they can check whether the first code can accurately generate interpretation content that matches the style of the first reference content and the chart data associated with the first chart information. If an error is found in the execution logic of the first code, a modification operation is triggered to modify the first code so that the modified first code can generate accurate interpretation content that meets the user's chart data interpretation needs.

[0110] Thus, since the first code can reflect the generation logic of the interpreted content, by checking and analyzing the first code, it is possible to locate the erroneous parts of the first code, and then quickly modify the execution logic of the first code, reducing the possibility that the inaccurate output of the first model will lead to inaccurate interpretation content, and realizing rapid adjustment of the interpreted content.

[0111] In some cases, the content tag block is of the second tag block type. In this case, the content of the content tag block is generated as follows: the second chart information is sent to the second model, the second code returned by the second model is received, the second code is executed, and the content of the content tag block is obtained.

[0112] The second code can be used to render the chart data associated with the second chart information into a chart type that matches the second chart information.

[0113] The second model can be understood as any artificial intelligence model with code generation capabilities. The second model can be a large model; for example, it can include any one or a combination of several large language models, speech models, vision models, and multimodal models. For instance, the second model can be a model built on a transformer architecture, a model built on a recurrent neural network, a model built on an attention mechanism, etc. Alternatively, the second model can also be a model improved upon the transformer architecture, such as a mixture of experts (MoE).

[0114] It should be noted that the second model can be the same artificial intelligence model as the first model, or the second model can be a different artificial intelligence model from the first model. This article does not impose any restrictions on one or more of these cases.

[0115] This paper does not restrict the way the second model is obtained in one or more scenarios. For example, the second model can be an existing, open-source artificial intelligence model. Alternatively, the second model can be an artificial intelligence model obtained by fine-tuning the pre-trained artificial intelligence model using training data related to code generation (such as chart information and the execution code corresponding to the chart information).

[0116] The second model can generate a second code based on prompt learning. For example, it can generate a second prompt word, send the second prompt word to the second model, and receive the second code returned by the second model. The second prompt word may include: second chart information and prompt information for indicating that the second code is generated based on the second chart information.

[0117] By sending a second prompt word to a second model, the second model can analyze the information in the second chart and generate the second code by leveraging the prompt word's capabilities.

[0118] Thus, on the one hand, the second model is used to analyze the information in the second chart, thereby automatically generating the second code and ultimately automatically generating the content to be displayed in the content marker block. On the other hand, considering that rendering the chart data requires converting the text data into an image chart, it would be difficult to guarantee the accuracy of the rendered chart if the second model is used to directly generate the rendered chart. Therefore, the second model is used to generate the second code, which contains the chart rendering logic. By executing the second code, the chart is rendered, thus improving the accuracy of the rendered chart.

[0119] In some cases, the content tag block is a third tag block. In this case, the content of the content tag block is generated as follows: execute the first task flow obtained based on the orchestration information of multiple process nodes, obtain the output results of each process branch in the first task flow, and generate the content of the content tag block based on the output results of each process branch in the first task flow.

[0120] In other words, based on the orchestration information of multiple process nodes, multiple process nodes are orchestrated to form the first task process. Since multiple process nodes may include condition nodes, the first task process may include multiple process branches. By executing the first task process, the output results of each process branch in the first task process are obtained. Then, the output results of each process branch are assembled into complete attribution analysis content to obtain the content of the content tag block.

[0121] For example, during the execution of the first task process, an artificial intelligence model is used to process the execution logic (i.e., generation logic or attribution logic) of the intermediate data generation node and the attribution conclusion generation node to obtain the execution results of the intermediate data generation node and the attribution conclusion generation node. For example, the artificial intelligence model is used to generate execution code, and by executing the execution code, intermediate data or attribution analysis results are obtained.

[0122] In this way, during the execution of the first task process, complex and cross-functional attribution analysis logic is applied to different chart data from different charts, and then the results of each execution are integrated into the final attribution analysis result, making the attribution analysis of the chart data more comprehensive and complete.

[0123] The following section uses specific page examples to introduce the large model data attribution methods provided in this article for one or more scenarios.

[0124] Figures 4A to 4F The illustration shows a schematic diagram of a document page provided in at least one scenario herein.

[0125] like Figure 4A As shown, the first document page 400 can display the document content of the first document. For example, the first document can be "XXX Weekly Report". The document content of the first document can include three subheadings: Progress Synchronization, Special Project Synchronization, and Quality Construction. Under the subheading of Quality Construction, there are further two subheadings: Issues and Overall Trends. The user can trigger the first action on the line below the subheading "3.2 Overall Trends". In response to the first action, the first area 401 is displayed. The first area 401 can be used to select the type of marker block, such as "Add Interpretation Block", "Add Chart Block", or "Add Attribution Block".

[0126] like Figure 4BAs shown, in response to a second operation triggered in the first area 401 to select "Add Interpretation Block", the first document page 400 can be divided into two areas. The left area can be a document content presentation area 410, which presents the document content of the first document. The right area can be an area 420 for configuring content marker blocks belonging to the first marker block. The user can trigger a third operation in the area 420 for configuring content marker blocks belonging to the first marker block, such as selecting an external chart or a chart within the document, selecting a chart name, or entering reference content to input the first configuration information. In addition, the area 420 for configuring content marker blocks belonging to the first marker block can also present the first code and preview the results. The user can view or modify the generated first code in the area 420 for configuring content marker blocks belonging to the first marker block, and can also preview the generated interpretation content in the area 420 for configuring content marker blocks belonging to the first marker block.

[0127] like Figure 4C As shown, in response to a second operation triggered in the first area 401 to select "Add Chart Block", the first document page 400 can be divided into two areas. The left area can be a document content presentation area 410, which presents the document content of the first document. The right area can be an area 430 for configuring content marker blocks belonging to the second marker block. The user can trigger a third operation in the area 430 for configuring content marker blocks belonging to the second marker block, such as selecting a chart name to input the first configuration information. In addition, the area 430 for configuring content marker blocks belonging to the second marker block can also present a preview result. The user can view the preview rendered chart in the area 430 for configuring content marker blocks belonging to the second marker block.

[0128] like Figure 4D As shown, in response to a second operation triggered in the first area 401 to select "Add Attribution Block", the first document page 400 can be divided into two areas. The left area can be a document content presentation area 410, which presents the document content of the first document. The right area can be an area 440 for configuring content tag blocks belonging to the third tag block. The user can trigger a third operation in the area 440 for configuring content tag blocks belonging to the third tag block, such as an operation to orchestrate a task flow, to input the first configuration information. In addition, the area 440 for configuring content tag blocks belonging to the third tag block can also present a preview result. The user can view the preview of the generated attribution analysis result in the area 440 for configuring content tag blocks belonging to the third tag block.

[0129] like Figure 4E As shown, in response to a trigger operation on the attribution canvas in area 440 for configuring content tag blocks belonging to the third tag block, the first document page 400 can switch to the attribution canvas 450. The attribution canvas 450 includes a process node selection area, a process node arrangement area, and a process node configuration area. Users can select different types of process nodes in the process node selection area, arrange multiple process nodes in the process node arrangement area (e.g., arrange the execution order between multiple process nodes), and enter configuration information for the selected process node in the process node configuration area (e.g., enter chart data and generation logic associated with the process node). Users can also view the generated execution code or modify the execution code in the process node configuration area.

[0130] like Figure 4F As shown, after receiving the first configuration information for the content tagging block, the content tagging block is presented on the first document page 400, for example, the interpretation content 402 belonging to the first tagging block is presented, the rendered chart 403 belonging to the second tagging block is presented, and the attribution analysis content 404 belonging to the third tagging block is presented.

[0131] In this way, users can quickly and conveniently add document content related to chart data processing to the document content by triggering interactive operations on the first document page. On the one hand, users do not need to perform manual chart data processing, achieving efficient chart data processing in document editing scenarios; on the other hand, the chart data processing results (i.e., the content presented by the content marker block) are embedded in the first document page in the form of document content, and users do not need to perform additional operations such as copying or adjusting, improving the efficiency of users in writing documents such as analysis reports.

[0132] Based on the large model data attribution method provided in at least one aspect of this paper, this paper also provides a large model data attribution device in at least one aspect. The following will combine... Figure 5 A detailed description of the large model data attribution device is provided.

[0133] Figure 5 The schematic diagram illustrates the structure of a large model data attribution device provided in at least one of the cases presented in this paper.

[0134] like Figure 5As shown, the large model data attribution device 500 in this scenario includes a presentation module 501 and a receiving module 502. For example, the presentation module 501 and the receiving module 502 can be implemented using hardware (e.g., circuit) modules or software modules, as are the cases described below. For example, the presentation module 501 and the receiving module 502 can be implemented using a central processing unit (CPU), a general-purpose graphics processing unit (GPGPU), a graphics processing unit (GPU), a tensor processor (TPU), a field-programmable gate array (FPGA), or other forms of processing units with data processing capabilities and / or instruction execution capabilities, along with corresponding computer instructions.

[0135] The presentation module 501 is configured to: in response to a first operation triggered on the first document page, present a first area, wherein the first area is used to select a marker block type; wherein the marker block type of the content marker block includes at least one of the following: a first marker block for interpreting chart data, a second marker block for rendering chart data, and a third marker block for attribution analysis of chart data. For example, the presentation module 501 can be configured to execute step S201 described above; its specific implementation principle can be referred to the relevant description of step S201, and will not be repeated here.

[0136] The presentation module 501 is further configured to: in response to a second operation triggered in the first region, present a second region, wherein the second region is used to configure content marker blocks, the marker block type of the content marker blocks matching the marker block type indicated by the second operation. For example, the presentation module 501 can be configured to execute step S202 described above; its specific implementation principle can be found in the relevant description of step S202, and will not be repeated here.

[0137] The receiving module 502 is configured to receive first configuration information in response to a third operation triggered in the second region. For example, the receiving module 502 can be configured to execute step S203 as described above; its specific implementation principle can be found in the relevant description of step S203, and will not be repeated here.

[0138] The presentation module 501 is further configured to: present the content tag block generated based on the first configuration information in the first document page. For example, the presentation module 501 can be configured to execute step S204 as described above; its specific implementation principle can be found in the relevant description of step S204, and will not be repeated here.

[0139] In at least one embodiment of this document, the presentation module 501 is further configured to: present the first region in response to the first operation triggered at a first location on the first document page; the presentation module 501 is further configured to: present the content tag block generated based on the first configuration information at the first location on the first document page.

[0140] In at least one of the embodiments described herein, the content tag block type includes the first tag block, and the receiving module 502 is further configured to receive first chart information and first reference content, wherein the content tag block interprets the chart data associated with the first chart information, and the presentation content of the content tag block matches the style of the first reference content.

[0141] In at least one of the embodiments described herein, the large model data attribution device 500 further includes a generation module configured to: send the first chart information and the first reference content to the first model; receive the first code returned by the first model, wherein the first code is used to generate interpretation content for the chart data associated with the first chart information and matching the style of the first reference content; and execute the first code to obtain the presentation content of the content marker block.

[0142] In at least one embodiment of this document, the generation module is further configured to: receive a modification operation on the first code; and update the first code based on the modification operation.

[0143] In at least one instance of this document, the tag block type of the content tag block includes the second tag block, and the receiving module 502 is further configured to: receive second chart information, wherein the content tag block renders chart data associated with the second chart information.

[0144] In at least one of the embodiments described herein, the generation module is further configured to: send the second chart information to the second model, receive the second code returned by the second model, wherein the second code is used to render the chart data associated with the second chart information into a chart type matching the second chart information; execute the second code to obtain the presentation content of the content tag block.

[0145] In at least one instance of this document, the tag block type of the content tag block includes the third tag block, and the receiving module 502 is further configured to: receive orchestration information for multiple process nodes, wherein the content tag block performs attribution analysis on the chart data associated with the multiple process nodes.

[0146] In at least one embodiment of this document, the process node includes at least one of the following: a condition node, an intermediate data generation node, an attribution conclusion generation node, and a parallel node; the condition node is used to: judge at least one of the chart data associated with the condition node and the intermediate data generated by the intermediate data generation node based on filtering conditions, so as to execute different process branches; the intermediate data generation node is used to: calculate at least one of the chart data associated with the intermediate data generation node and the intermediate data generated by other intermediate data generation nodes based on generation logic, so as to generate intermediate data; the attribution conclusion generation node is used to: perform attribution analysis on at least one of the chart data associated with the attribution conclusion generation node and the intermediate data generated by the intermediate data generation node based on attribution logic, so as to generate attribution analysis results; the parallel node is used to: execute at least two of the process nodes in parallel.

[0147] In at least one embodiment of this document, the generation module is further configured to: execute a first task flow obtained based on the orchestration information of the plurality of process nodes, and obtain the output results of each process branch in the first task flow; and generate the presentation content of the content tag block based on the output results of each process branch in the first task flow.

[0148] It should be noted that, for clarity and brevity, at least one scenario herein does not present all the constituent units of the large model data attribution device 500. To achieve the necessary functions of the large model data attribution device 500, those skilled in the art can provide or configure other constituent units (not shown) according to specific needs, and one or more scenarios herein do not impose any limitations on this.

[0149] The large model data attribution device 500 provided in at least one scenario of this paper is based on the same concept as the large model data attribution method provided in at least one scenario of this paper. It can achieve the same technical effect and the same technical purpose as the large model data attribution method provided in at least one scenario of this paper. For details, please refer to the relevant description above, which will not be repeated here.

[0150] This document also provides, in at least one embodiment, an electronic device including a processing device and a storage device, the storage device including one or more computer program modules; wherein the one or more computer program modules are stored in the storage device and configured to be executed by the processing device, the one or more computer program modules being used to implement the large model data attribution method provided in any embodiment of this document.

[0151] For example, the processing device may be a processor, such as a central processing unit (CPU), digital signal processor (DSP), image processor (GPU), general-purpose graphics processor (GPGPU), or other form of processing unit with data processing capabilities and / or instruction execution capabilities. It may be a general-purpose processor or a dedicated processor and may control other components in the electronic device to perform the desired functions.

[0152] For example, the storage device may be a memory, and may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and a processing device may execute the program instructions to implement the functions described in at least one of the embodiments herein (implemented by the processing device) and / or other desired functions. Various application programs and various data may also be stored on the computer-readable storage medium, which is not limited in the embodiments described herein.

[0153] The following is for reference. Figure 6 The diagram illustrates a structural schematic of an electronic device (e.g., a terminal device or a server) 600 suitable for implementing at least one of the embodiments described herein. The terminal device in at least one embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, personal digital assistants (PDAs), tablet computers (PADs), portable multimedia players (PMPs), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital televisions and desktop computers. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of at least one scenario described herein.

[0154] like Figure 6 As shown, the electronic device 600 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory 602 or a program loaded from a storage device 608 into a random access memory 603. The random access memory 603 also stores various programs and data required for the operation of the electronic device 600. The processing unit 601, the read-only memory 602, and the random access memory 603 are interconnected via a bus 604. An input / output interface 605 is also connected to the bus 604.

[0155] Typically, the following devices can be connected to the input / output interface 605: input devices 606 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 608 including, for example, magnetic tape, hard disk, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0156] In particular, according to one or more embodiments herein, the processes described in the above-referenced flowcharts can be implemented as computer software programs. For example, one or more embodiments herein include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via communication device 609, or installed from storage device 608, or installed from read-only memory 602. When the computer program is executed by processing device 601, it performs the functions defined in the methods of at least one embodiment herein.

[0157] The electronic device 600 provided in at least one scenario of this paper is based on the same concept as the large model data attribution method provided in at least one scenario of this paper. It can achieve the same technical effect and the same technical purpose as the large model data attribution method provided in at least one scenario of this paper. For details, please refer to the relevant descriptions above, which will not be repeated here.

[0158] It should be noted that the computer-readable medium described above can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this document, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, radio frequency (RF), etc., or any suitable combination thereof.

[0159] The computer-readable storage medium provided in at least one scenario of this paper is based on the same concept as the large model data attribution method provided in at least one scenario of this paper. It can achieve the same technical effect and the same technical purpose as the large model data attribution method provided in at least one scenario of this paper. For details, please refer to the relevant descriptions above, which will not be repeated here.

[0160] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol, such as the Hypertext Transfer Protocol (HTTP), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0161] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0162] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the aforementioned large model data attribution method.

[0163] Computer program code for performing the operations described herein may be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0164] One or more scenarios described herein also provide a computer program product comprising one or more computer instructions. When these computer instructions are loaded and executed on a computing device, all or part of the flow or function described in any of these scenarios is generated.

[0165] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0166] When the computer program product is executed by a computer, the computer executes any of the aforementioned large model data attribution methods. The computer program product can be a software installation package; when any of the aforementioned large model data attribution methods needs to be used, the computer program product can be downloaded and executed on the computer.

[0167] The computer program product provided in at least one scenario of this paper is based on the same concept as the large model data attribution method provided in at least one scenario of this paper. It can achieve the same technical effect and the same technical purpose as the large model data attribution method provided in at least one scenario of this paper. For details, please refer to the relevant descriptions above, which will not be repeated here.

[0168] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of the systems, methods, and computer program products according to the various scenarios described herein. In this respect, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the figures. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0169] The units or modules described in at least one of the cases herein can be implemented in software or hardware. The names of the units or modules do not, in some cases, constitute a limitation on the unit or module itself.

[0170] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0171] In the context of this document, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0172] Based on one or more scenarios presented in this paper, Example 1 provides a large model data attribution method, including:

[0173] In response to a first operation triggered on a first document page, a first area is presented, wherein the first area is used to select a marker block type;

[0174] In response to a second operation triggered in the first region, a second region is presented, wherein the second region is used to configure content tag blocks whose tag block type matches the tag block type indicated by the second operation;

[0175] In response to a third operation triggered in the second region, first configuration information is received;

[0176] The content tag block generated based on the first configuration information is presented on the first document page;

[0177] The content tagging block includes at least one of the following tagging block types: a first tagging block for interpreting chart data, a second tagging block for rendering chart data, and a third tagging block for attribution analysis of chart data.

[0178] Based on one or more scenarios described herein, Example 2 provides the response to the first action triggered on the first document page in Example 1, rendering a first area, including:

[0179] In response to the first operation triggered at a first location on the first document page, the first area is rendered; and

[0180] The step of presenting the content tag block generated based on the first configuration information on the first document page includes:

[0181] At the first location on the first document page, the content tag block generated based on the first configuration information is presented.

[0182] According to one or more scenarios in this document, Example 3 provides that the tag block type of the content tag block in Example 1 or Example 2 includes the first tag block, and the receiving of the first configuration information includes:

[0183] The system receives first chart information and first reference content, wherein the content marker block interprets the chart data associated with the first chart information, and the presented content of the content marker block matches the style of the first reference content.

[0184] Based on one or more scenarios in this article, Example 4 provides a way to generate the content of the content markup block in Example 3 in the following manner:

[0185] The first chart information and the first reference content are sent to the first model, and the first code returned by the first model is received. The first code is used to generate interpretation content that is associated with the chart information and matches the style of the first reference content.

[0186] Executing the first code yields the rendered content of the content tag block.

[0187] Based on one or more scenarios in this article, Example 5 provides the method from Example 4, and also includes:

[0188] Receive modification operations for the first code;

[0189] Based on the modification operation, update the first code.

[0190] According to one or more scenarios in this document, Example 6 provides that the tag block type of the content tag block in Example 1 or Example 2 includes the second tag block, and the receiving of the first configuration information includes:

[0191] Receive second chart information, wherein the content tag block renders the chart data associated with the second chart information.

[0192] Based on one or more scenarios in this paper, Example 7 provides a way to generate the content of the content markup block in Example 6 in the following manner:

[0193] The second chart information is sent to the second model, and the second code returned by the second model is received. The second code is used to render the chart data associated with the second chart information into a chart type that matches the second chart information.

[0194] Execute the second code to obtain the rendered content of the content tag block.

[0195] According to one or more scenarios in this document, Example 8 provides that the tag block type of the content tag block in Example 1 or Example 2 includes the third tag block, and the receiving of the first configuration information includes:

[0196] The system receives orchestration information for multiple process nodes, wherein the content tagging block performs attribution analysis on the chart data associated with the multiple process nodes.

[0197] Based on one or more scenarios in this paper, Example 9 provides that the process nodes in Example 8 include at least one of the following: condition nodes, intermediate data generation nodes, attribution conclusion generation nodes, and parallel nodes;

[0198] The condition node is used to: judge at least one of the chart data associated with the condition node and the intermediate data generated by the intermediate data generation node based on the filtering conditions, so as to execute different process branches;

[0199] The intermediate data generation node is used to: calculate at least one of the chart data associated with the intermediate data generation node and the intermediate data generated by other intermediate data generation nodes based on the generation logic, so as to generate intermediate data;

[0200] The attribution conclusion generation node is used to: perform attribution analysis on at least one of the chart data associated with the attribution conclusion generation node and the intermediate data generated by the intermediate data generation node, based on attribution logic, so as to generate attribution analysis results.

[0201] The parallel node is used to execute at least two of the process nodes in parallel.

[0202] Based on one or more scenarios in this paper, Example 10 provides a way to generate the content of the content markup block in Example 8 in the following manner:

[0203] Execute the first task flow obtained based on the orchestration information of the multiple process nodes, and obtain the output results of each process branch in the first task flow;

[0204] Based on the output results of each process branch in the first task flow, the presentation content of the content tag block is generated.

[0205] Based on one or more scenarios described herein, Example 11 provides a large model data attribution apparatus, comprising:

[0206] The rendering module is configured to: in response to a first operation triggered on a first document page, render a first area, wherein the first area is used to select a marker block type;

[0207] The presentation module is further configured to: in response to a second operation triggered in the first region, present a second region, wherein the second region is used to configure content marker blocks, the marker block type of the content marker blocks matching the marker block type indicated by the second operation;

[0208] The receiving module is configured to receive first configuration information in response to a third operation triggered in the second region;

[0209] The presentation module is further configured to: present the content tag block generated based on the first configuration information on the first document page;

[0210] The content tagging block includes at least one of the following tagging block types: a first tagging block for interpreting chart data, a second tagging block for rendering chart data, and a third tagging block for attribution analysis of chart data.

[0211] According to one or more of the scenarios described herein, Example Twelve provides an electronic device comprising:

[0212] At least one processor; and

[0213] At least one memory, including one or more computer program instructions;

[0214] Among them, the one or more computer program instructions are executed by the processor at runtime, and the large model data attribution method provided in at least one case of this article is provided.

[0215] According to one or more scenarios described herein, Example Thirteen provides a computer-readable storage medium that non-transitory stores computer-readable instructions, wherein the large model data attribution method provided by at least one scenario of this article is implemented when the computer-readable instructions are executed by a processor.

[0216] According to one or more scenarios herein, Example Fourteen provides a computer program product including a computer program that, when executed by a processor, implements the large model data attribution method provided by at least one scenario herein.

[0217] The above description is merely a preferred embodiment and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure herein is not limited to technical solutions formed by specific combinations of the above-described technical features, but also includes other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed herein that have similar functions.

[0218] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain contexts, multitasking and parallel processing may be advantageous. Similarly, while some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of this paper. Certain features described in the context of a single case can also be implemented in combination within that single case. Conversely, various features described in the context of a single case can also be implemented individually or in any suitable sub-combination in multiple cases.

[0219] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A large model data attribution method, comprising: In response to a first operation triggered on a first document page, a first area is presented, wherein the first area is used to select a marker block type; In response to a second operation triggered in the first region, a second region is presented, wherein the second region is used to configure content tag blocks whose tag block type matches the tag block type indicated by the second operation; In response to a third operation triggered in the second region, first configuration information is received; The content tag block generated based on the first configuration information is presented on the first document page; The content tagging block includes at least one of the following tagging block types: a first tagging block for interpreting chart data, a second tagging block for rendering chart data, and a third tagging block for attribution analysis of chart data.

2. The method according to claim 1, wherein, The response to the first operation triggered on the first document page, displaying the first area, includes: In response to the first operation triggered at a first location on the first document page, the first area is rendered; and The step of presenting the content tag block generated based on the first configuration information on the first document page includes: At the first location on the first document page, the content tag block generated based on the first configuration information is presented.

3. The method according to claim 1 or 2, wherein, The content tagging block's tagging block type includes the first tagging block, and receiving the first configuration information includes: The system receives first chart information and first reference content, wherein the content marker block interprets the chart data associated with the first chart information, and the presented content of the content marker block matches the style of the first reference content.

4. The method according to claim 3, wherein, The content of the content marker block is generated in the following way: The first chart information and the first reference content are sent to the first model, and the first code returned by the first model is received. The first code is used to generate interpretation content that is associated with the chart information and matches the style of the first reference content. Executing the first code yields the rendered content of the content tag block.

5. The method according to claim 4, further comprising: Receive modification operations for the first code; Based on the modification operation, update the first code.

6. The method according to claim 1 or 2, wherein, The content tagging block's tagging block type includes the second tagging block, and receiving the first configuration information includes: Receive second chart information, wherein the content tag block renders the chart data associated with the second chart information.

7. The method according to claim 6, wherein, The content of the content marker block is generated in the following way: The second chart information is sent to the second model, and the second code returned by the second model is received. The second code is used to render the chart data associated with the second chart information into a chart type that matches the second chart information. Execute the second code to obtain the rendered content of the content tag block.

8. The method according to claim 1 or 2, wherein, The content tagging block's tagging block type includes the third tagging block, and receiving the first configuration information includes: The system receives orchestration information for multiple process nodes, wherein the content tagging block performs attribution analysis on the chart data associated with the multiple process nodes.

9. The method according to claim 8, wherein, The process nodes include at least one of the following: condition nodes, intermediate data generation nodes, attribution conclusion generation nodes, and parallel nodes; The condition node is used to: judge at least one of the chart data associated with the condition node and the intermediate data generated by the intermediate data generation node based on the filtering conditions, so as to execute different process branches; The intermediate data generation node is used to: calculate at least one of the chart data associated with the intermediate data generation node and the intermediate data generated by other intermediate data generation nodes based on the generation logic, so as to generate intermediate data; The attribution conclusion generation node is used to: perform attribution analysis on at least one of the chart data associated with the attribution conclusion generation node and the intermediate data generated by the intermediate data generation node, based on attribution logic, so as to generate attribution analysis results. The parallel node is used to execute at least two of the process nodes in parallel.

10. The method according to claim 8, wherein, The content of the content marker block is generated in the following way: Execute the first task flow obtained based on the orchestration information of the multiple process nodes, and obtain the output results of each process branch in the first task flow; Based on the output results of each process branch in the first task flow, the presentation content of the content tag block is generated.

11. A large model data attribution device, comprising: The rendering module is configured to: in response to a first operation triggered on a first document page, render a first area, wherein the first area is used to select a marker block type; The presentation module is further configured to: in response to a second operation triggered in the first region, present a second region, wherein the second region is used to configure content marker blocks, the marker block type of the content marker blocks matching the marker block type indicated by the second operation; The receiving module is configured to receive first configuration information in response to a third operation triggered in the second region; The presentation module is further configured to: present the content tag block generated based on the first configuration information on the first document page; The content tagging block includes at least one of the following tagging block types: a first tagging block for interpreting chart data, a second tagging block for rendering chart data, and a third tagging block for attribution analysis of chart data.

12. An electronic device, comprising: At least one processor; as well as At least one memory, including one or more computer program instructions; The one or more computer program instructions are executed by the processor to perform the method according to any one of claims 1 to 10.

13. A computer-readable storage medium for non-transitory storage of computer-readable instructions, wherein, The method of any one of claims 1 to 10 is implemented when the computer-readable instructions are executed by a processor.

14. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 10.

Images