Chart generation method and apparatus, device, and storage medium

Abstract

The present disclosure relates to the technical field of artificial intelligence, and specifically to the technical fields such as large models and natural language understanding, and provides a chart generation method and apparatus, a device, and a storage medium. The chart generation method comprises: acquiring target text content and target prompt information; on the basis of the target text content and the target prompt information, using a first pre-trained language model to generate structured information, wherein the structured information is used for generating a target chart; on the basis of the structured information, using a second pre-trained language model to generate the target chart; and displaying the target chart. The present disclosure can improve the chart generation efficiency and accuracy.

Description

Chart generation method, device, equipment and storage medium

[0001] This application claims priority to a Chinese patent application filed on October 23, 2023, with application number 202311378535.8 and invention name “Graphic Generation Method, Apparatus, Device and Storage Medium”. Technical Field

[0002] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as large models and natural language understanding, and more particularly to a chart generation method, apparatus, device, and storage medium. Background Art

[0003] Converting text-based document reports into chart-based presentation reports is a common requirement at work.

[0004] In related technologies, users can use presentation creation tools (such as PPT) to convert text content into charts.

[0005] Summary of the Invention

[0006] The present disclosure provides a chart generation method, apparatus, device, and medium.

[0007] According to one aspect of the present disclosure, a chart generation method is provided, comprising: obtaining target text content and target prompt information; using a first pre-trained language model to generate structured information based on the target text content and the target prompt information, wherein the structured information is used to generate a target chart; using a second pre-trained language model to generate the target chart based on the structured information; and displaying the target chart.

[0008] According to another aspect of the present disclosure, a chart generation device is provided, including: an acquisition module for acquiring target text content and target prompt information; a first generation module for using a first pre-trained language model to generate structured information based on the target text content and the target prompt information, wherein the structured information is used to generate a target chart; a second generation module for using a second pre-trained language model to generate the target chart based on the structured information; and a display module for displaying the target chart.

[0009] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any one of the methods described in any one of the above aspects.

[0010] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods according to any one of the above aspects.

[0011] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of the above aspects.

[0012] According to the technical solution disclosed in the present invention, the efficiency and accuracy of chart generation can be improved.

[0013] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0015] FIG1 is a schematic diagram of a first embodiment of the present disclosure;

[0016] FIG2 is a schematic diagram of an application scenario provided according to an embodiment

[0017] FIG3 is a schematic diagram of the overall architecture of a chart generation system according to an embodiment of the present disclosure;

[0018] FIG4 is a schematic diagram according to a second embodiment of the present disclosure;

[0019] FIG5 is a schematic diagram according to a third embodiment of the present disclosure;

[0020] FIG6 is a schematic diagram of an electronic device for implementing the chart generating method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0022] In related technologies, presentation tools (such as PowerPoint) can be used to convert text into charts. However, this approach requires users to design the interface and content themselves and cannot automatically convert text into charts, resulting in poor conversion efficiency and accuracy.

[0023] In order to improve the efficiency and accuracy of chart generation, the present disclosure provides the following embodiments.

[0024] FIG1 is a schematic diagram according to a first embodiment of the present disclosure. This embodiment provides a chart generation method, which includes:

[0025] 101. Obtain target text content and target prompt information.

[0026] 102. Use a first pre-trained language model to generate structured information based on the target text content and the target prompt information, where the structured information is used to generate a target chart.

[0027] 103. Use a second pre-trained language model to generate the target graph based on the structured information.

[0028] 104. Display the target chart.

[0029] The target text content refers to the text content of the chart to be generated. The user can input the target text content in the interactive interface provided by the chart generation system (hereinafter referred to as the system), or select the target text content from the existing text content.

[0030] The target prompt information refers to the required information for the generated chart. The system may pre-provide a variety of optional prompt information, and the user may select the target prompt information from the various optional prompt information according to their needs. Alternatively, the user may input the target prompt information in the interactive interface provided by the system.

[0031] The target prompt information includes, for example, the style and color of the target chart; and may also include the type of the target chart, such as a framework diagram, a flow chart, a diagram, and the like.

[0032] Target chart refers to a chart generated based on target text content.

[0033] A chart refers to a graphic structure that can intuitively display the attributes of statistical information (temporality, quantity, etc.) and plays a key role in knowledge mining and intuitive and vivid perception of information.

[0034] In this embodiment, the target diagram may include: a framework diagram, a flow chart, a table, etc.

[0035] Graphs can be represented with structured information.

[0036] Structured information refers to information that, after analysis, can be broken down into multiple, interconnected components, each with a clear hierarchy. Structured information typically consists of clearly defined fields and records. Fields describe the attributes of the data, while records represent specific instances of the data. By organizing data into a predefined structure, structured information makes data processing more convenient and efficient.

[0037] Different structured information can be obtained based on the type of target diagram. For example, if the target diagram is a flowchart, the structured information includes the text content of each process node and the logical relationship between each process node.

[0038] In this embodiment, a pre-trained language model is used to obtain structured information and a target graph. For the sake of distinction, the pre-trained language model that obtains structured information is referred to as a first pre-trained language model, and the pre-trained language model that obtains the target graph is referred to as a second pre-trained language model.

[0039] The pre-trained language model is a deep neural network model that can be specially trained by the system itself or an existing model.

[0040] In this embodiment, by generating structured information and then generating a target graph based on the structured information, the target graph can be automatically generated, which improves generation efficiency compared to manually configuring the target graph. Furthermore, by generating the structured information and target graph using a pre-trained language model, the excellent performance of the pre-trained language model is leveraged to improve the accuracy of the target graph, thereby improving both the efficiency and accuracy of graph generation.

[0041] In order to better understand the embodiments of the present disclosure, the application scenarios of the embodiments of the present disclosure are described below.

[0042] As shown in Figure 2, a user can interact with the chart generation system via a user terminal 201 to obtain a target chart. The user terminal can be a personal computer (PC), a laptop, a mobile device (e.g., a cell phone), etc. The main functional components of the chart generation system can be located on a server 202, which can be a local server or a cloud server, and can be a single server or a server cluster.

[0043] The user can send the target text content and target prompt information to the chart generation system through the user terminal. The chart generation system converts the target text content into a target chart based on the target prompt information. After the chart generation system generates the target chart, it displays it to the user through the user terminal.

[0044] The graph generation system uses a pre-trained language model to generate target graphs.

[0045] A pre-trained language model is a pre-trained deep learning neural network model that performs a specific function. A pre-trained language model can be specially trained by the system or an existing model.

[0046] In order to improve efficiency and accuracy, the pre-trained language model uses an existing model, specifically a large language model (LLM).

[0047] LLM has been a hot topic in the field of artificial intelligence in recent years. LLM is a pre-trained language model that has learned a wealth of language knowledge and world knowledge through pre-training on massive amounts of text data, enabling it to achieve amazing results in various natural language processing (NLP) and image processing tasks. Wenxin Yiyan, ChatGPT, and others are applications developed based on LLM. They can generate fluent, logical, and creative text content, and can even have natural conversations with humans. Specifically, taking text conversations as an example, large models can be general pre-trained Transformer (Generative Pre-trained Transformer, GPT) models based on Transformer, Enhanced Representation through Knowledge Integration (ERNIE) models based on knowledge integration, and so on.

[0048] In this embodiment, the pre-trained language model includes a first pre-trained language model and a second pre-trained language model. Taking the pre-trained language model as a large model as an example, these two pre-trained language models can be called the first large model and the second large model.

[0049] The first model is used to process the input target text content and target prompt information to output structured information.

[0050] Among them, the first model can extract key sentences in the target text content according to the target prompt information, analyze the logical relationship of the target text content, and generate structured information based on the key sentences and logical relationship.

[0051] For example, if the target prompt information includes the type of the target chart, such as a flowchart, the first model can extract the text content in each process node and the relationship between each process node, and form the text content and mutual relationship of each process node into structured information.

[0052] In this embodiment, by extracting key sentences and analyzing the logical relationships between the key sentences, and generating structured information based on the key sentences and their logical relationships, the accuracy of the structured information can be improved, thereby improving the accuracy of the target graph.

[0053] Since the target text content and structured information are both text, the first large model can specifically be a large model for generating text from text, such as the GPT model or ERNIE model mentioned above.

[0054] The second largest model is used to process the input structured information to output the target graph.

[0055] Among them, target charts may include: framework diagrams, flow charts, tables, etc.

[0056] Since the structured information is text and the target chart is a graph, the second pre-trained language model can be specifically a large model for generating graphs from text.

[0057] After the system generates the target chart, it can be displayed to the user through the interactive interface.

[0058] Taking the generation of a target chart from a large model as an example, as shown in Figure 3, the chart generation system includes an application display module, a data service module, a first large model interface, and a second large model interface. The application display module is located in the data display layer, the data service module is located in the data interface layer, and the first and second large model interfaces are located in the data provision layer.

[0059] The chart generation system can open an interface to users. Users can use this interface to send chart generation requests to the data service module. The data service module then sends the target text content and target prompt information included in the chart generation request to the first large model via the first large model interface. The first large model generates structured information based on the target text content and target prompt information and feeds it back to the data service module.

[0060] After receiving the structured information fed back by the first model, the data service module sends it to the second model through the second model interface. The second model generates the target chart based on the structured information and feeds it back to the data service module.

[0061] The data service module sends the target chart to the application display module, and the application display module displays the target chart to the user.

[0062] In combination with the above application scenarios, the present disclosure also provides a chart generation method.

[0063] FIG4 is a schematic diagram according to a second embodiment of the present disclosure. This embodiment provides a chart generation method, the method comprising:

[0064] 401. Obtain target text content and target prompt information.

[0065] In conjunction with the system shown in FIG3 , the user can send a request to the data service module through the interface provided by the system. The request includes the target text content and target prompt information, so that the data service module can obtain the target text content and target prompt information from the request.

[0066] 402. Using a first large model, obtain structured information based on the target text content and the target prompt information.

[0067] Specifically, the target text content and the target prompt information are sent to the first large model through the first interface between the first large model, so that the first large model generates the structured information based on the target text content and the target prompt information; and the structured information sent by the first large model is received through the first interface.

[0068] In combination with the system shown in Figure 3, after the data service module obtains the target text content and target prompt information, it can send the target text content and target prompt information to the first large model through the first large model interface. The first large model processes the input target text content and target prompt information, outputs structured information, and feeds it back to the data service module through the first large model interface.

[0069] In this embodiment, by obtaining structured information through the first large model, the excellent performance of the existing large model can be utilized to obtain more accurate structured information and improve the accuracy of the target graph.

[0070] 403. Use the second largest model to obtain a target graph based on the structured information.

[0071] Specifically, the structured information is sent to the second large model through the second interface between the second large model and the second large model, so that the second large model generates the target chart based on the structured information; and the target chart sent by the second large model is received through the second interface.

[0072] Combined with the system shown in Figure 3, after the data service module obtains the structured information, it can send the structured information to the second largest model through the second largest model interface. The second largest model processes the input structured information, outputs the target chart, and feeds it back to the data service module through the second largest model interface.

[0073] In this embodiment, by generating the target graph through the second largest model, the excellent performance of the existing large model can be utilized to obtain a more accurate target graph.

[0074] 404. Display the target chart.

[0075] In conjunction with the system shown in FIG3 , after the data service module obtains the target chart, it can be presented to the user through the application presentation module.

[0076] Through the above steps, the large model can be applied to the scenario of converting text content into charts, realizing automatic chart generation and improving conversion efficiency and accuracy.

[0077] In order to obtain a target chart that satisfies the user more, the generated target chart may be modified. That is, this embodiment may further include:

[0078] 405. Receive a modification statement for the target chart.

[0079] In conjunction with the system shown in FIG3 , the user can send a modification statement to the data service module through an interface provided by the system, so that the data service module can obtain the modification statement.

[0080] 406. Use the second large model to modify the target chart based on the modification statement to generate a modified target chart.

[0081] Combined with the system shown in Figure 3, after the data service module obtains the modification statement, it can send the modification statement to the second largest model through the second largest model interface. The second largest model modifies the target chart based on the modification statement, obtains the modified target chart, and feeds it back to the data service module through the second largest model interface.

[0082] 407. Display the modified target chart.

[0083] In conjunction with the system shown in FIG3 , after the data service module obtains the modified target chart, it can be presented to the user through the application presentation module.

[0084] In this embodiment, by modifying the target chart, user needs can be better met and the accuracy of the chart can be improved.

[0085] FIG5 is a schematic diagram according to a third embodiment of the present disclosure. This embodiment provides a chart generating device. The device 500 includes: an acquisition module 501 , a first generation module 502 , a second generation module 503 and a display module 504 .

[0086] The acquisition module 501 is used to acquire the target text content and target prompt information; the first generation module 502 is used to use a first pre-trained language model to generate structured information based on the target text content and the target prompt information, and the structured information is used to generate a target chart; the second generation module 503 is used to use a second pre-trained language model to generate the target chart based on the structured information; the display module 504 is used to display the target chart.

[0087] In this embodiment, by generating structured information and then generating a target graph based on the structured information, the target graph can be automatically generated, which improves generation efficiency compared to manually configuring the target graph. Furthermore, by generating the structured information and target graph using a pre-trained language model, the excellent performance of the pre-trained language model is leveraged to improve the accuracy of the target graph, thereby improving both the efficiency and accuracy of graph generation.

[0088] In some embodiments, the first generation module 502 is further used to: use the first pre-trained language model to extract key sentences in the target text content based on the target prompt information, and determine the logical relationship between the key sentences, and generate the structured information based on the key sentences and the logical relationship.

[0089] In this embodiment, by extracting key sentences and analyzing the logical relationships between the key sentences, and generating structured information based on the key sentences and their logical relationships, the accuracy of the structured information can be improved, thereby improving the accuracy of the target graph.

[0090] In some embodiments, the first pre-trained language model is a first large model; the first generation module 502 is further used to: send the target text content and the target prompt information to the first large model through a first interface between the first large model, so that the first large model generates the structured information based on the target text content and the target prompt information; and receive the structured information sent by the first large model through the first interface.

[0091] In this embodiment, by obtaining structured information through the first large model, the excellent performance of the existing large model can be utilized to obtain more accurate structured information and improve the accuracy of the target graph.

[0092] In some embodiments, the second pre-trained language model is a second large model; the second generation module 503 is further used to: send the structured information to the second large model through a second interface between the second large model, so that the second large model generates the target chart based on the structured information; and receive the target chart sent by the second large model through the second interface.

[0093] In this embodiment, by generating the target graph through the first large model, the excellent performance of the existing large model can be utilized to obtain a more accurate target graph.

[0094] In some embodiments, the device 500 further includes: a modification module for receiving a modification statement for the target chart; using the second pre-trained language model to modify the target chart based on the modification statement to generate a modified target chart; and displaying the modified target chart.

[0095] In this embodiment, by modifying the target chart, user needs can be better met and the accuracy of the chart can be improved.

[0096] It can be understood that in the embodiments of the present disclosure, the same or similar contents in different embodiments can be referenced to each other.

[0097] It can be understood that the terms “first”, “second”, etc. in the embodiments of the present disclosure are only used for distinction and do not indicate the degree of importance, time sequence, etc.

[0098] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0099] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0100] FIG6 shows a schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure. Electronic device 600 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 600 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0101] As shown in Figure 6, electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In RAM 603, various programs and data required for the operation of electronic device 600 can also be stored. Computing unit 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0102] Multiple components in the electronic device 600 are connected to the I / O interface 605, including an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0103] The computing unit 601 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the chart generation method. For example, in some embodiments, the chart generation method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the chart generation method described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the chart generation method by any other suitable means (e.g., by means of firmware).

[0104] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0105] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable load balancing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0106] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0107] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0108] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0109] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship is established by computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and VPS services ("Virtual Private Servers" or simply "VPS"). The server may also be a server in a distributed system or a server integrated with blockchain.

[0110] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0111] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for generating a chart, comprising: Get the target text content and target prompt information; Using a first pre-trained language model, generating structured information based on the target text content and the target prompt information, wherein the structured information is used to generate a target chart; Using a second pre-trained language model, generating the target graph based on the structured information; The target chart is displayed.

2. The method according to claim 1, wherein: The adopting of the first pre-trained language model to generate structured information based on the target text content and the target prompt information includes: The first pre-trained language model is used to extract key sentences in the target text content based on the target prompt information, and logical relationships between the key sentences are determined, and the structured information is generated based on the key sentences and the logical relationships.

3. The method according to claim 1, wherein: The first pre-trained language model is a first large model; The adopting of the first pre-trained language model to generate structured information based on the target text content and the target prompt information includes: Sending the target text content and the target prompt information to the first large model through a first interface with the first large model, so that the first large model generates the structured information based on the target text content and the target prompt information; The structured information sent by the first large model is received through the first interface.

4. The method according to claim 1, wherein: The second pre-trained language model is the second largest model; The adopting the second pre-trained language model to generate the target graph based on the structured information includes: Sending the structured information to the second large model through a second interface between the second large model and the second large model, so that the second large model generates the target graph based on the structured information; The target chart sent by the second large model is received through the second interface.

5. The method according to any one of claims 1 to 4, further comprising: receiving a modification statement for the target graph; Using the second pre-trained language model, modifying the target graph based on the modification sentence to generate a modified target graph; The modified target graph is displayed.

6. A chart generating device, comprising: An acquisition module is used to acquire target text content and target prompt information; A first generating module, configured to use a first pre-trained language model to generate structured information based on the target text content and the target prompt information, wherein the structured information is used to generate a target chart; A second generating module, configured to generate the target graph based on the structured information by using a second pre-trained language model; A display module is used to display the target chart.

7. The device according to claim 6, wherein: The first generating module is further used for: The first pre-trained language model is used to extract key sentences in the target text content based on the target prompt information, and logical relationships between the key sentences are determined, and the structured information is generated based on the key sentences and the logical relationships.

8. The device according to claim 6, wherein: The first pre-trained language model is a first large model; The first generating module is further used for: Sending the target text content and the target prompt information to the first large model through a first interface with the first large model, so that the first large model generates the structured information based on the target text content and the target prompt information; The structured information sent by the first large model is received through the first interface.

9. The device according to claim 6, wherein: The second pre-trained language model is the second largest model; The second generating module is further used for: Sending the structured information to the second large model through a second interface between the second large model and the second large model, so that the second large model generates the target graph based on the structured information; The target chart sent by the second large model is received through the second interface.

10. The device according to any one of claims 6 to 9, further comprising: A modification module, configured to receive a modification statement for the target chart; and modify the target chart based on the modification statement using the second pre-trained language model to generate a modified target chart; And, displaying the modified target chart.

11. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

13. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images