Automatic report generation method and device based on artificial intelligence
Through an automated report generation method based on artificial intelligence, using artificial intelligence models to analyze and process user input, generate preset format component data and render it, solving the efficiency and flexibility of traditional report generation methods, and realizing intelligence and personalization Report generation improves user experience.
Patent Information
- Application Number
- CN202411080628.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-12-03
Smart Images

Figure CN119067090A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to an artificial intelligence-based automated report generation method and device. Background Art
[0002] In today's information age, with the rapid growth of data volume, more and more organizations and individuals need to extract useful information from large amounts of data and present it in a visual way. Traditional report generation methods often require a lot of manpower and time, and often lack flexibility and personalization. Therefore, it is necessary to propose an efficient and flexible automated report generation method. Summary of the invention
[0003] In order to solve the above problems, the present application proposes an artificial intelligence-based automated report generation method, device, computer-readable storage medium and electronic device, which can efficiently and flexibly generate automated reports based on user input.
[0004] In a first aspect, the present application provides an artificial intelligence-based automated report generation method, the method comprising: a front-end display platform obtains a first user input, which indicates an analysis requirement for target data; a back-end processing platform uses an artificial intelligence model to analyze and process the first user input, obtains N copies of component data in a preset format, and returns them to the front-end display platform; the N copies of component data are used to form an analysis report for the target data, each copy of component data includes attribute information and component text of the corresponding component; in response to receiving the N copies of component data, the front-end display platform renders the N copies of component data in a preset format in a first display interface based on a preset layout algorithm, and obtains a first display interface including N components as an analysis report; the preset layout algorithm includes determining the regional position and regional width and height of the display area of each component in the first display interface according to its attribute information.
[0005] Therefore, the present application uses an artificial intelligence model to analyze and process the first user input, obtains N copies of component data in a preset format, and renders the N copies of component data in a preset format based on a preset layout algorithm in the front-end display platform to generate an analysis report, which can improve the intelligence level and flexibility of the system's report generation.
[0006] In one possible implementation, the front-end display platform renders N copies of component data in a preset format in a first display interface based on a preset layout algorithm, including: parsing each copy of the component data according to a preset format, extracting the report template name of the analysis report to which it belongs and the component name of the corresponding component contained in the attribute information; using the preset layout algorithm, according to the report template name and the component name of the corresponding component, determining the regional position and the regional width and height of the display area of the corresponding component in the first display interface; in the first display interface, rendering the component data in a preset format according to the regional position and the regional width and height of the corresponding component.
[0007] In a possible implementation, determining the regional position and the regional width and height of the display area of the corresponding component in the first display interface includes: if it is judged according to the component name that the corresponding component is displayed in a fixed display area, then searching the report template corresponding to the report template name according to the component name to obtain the regional position and the regional width and height of the fixed display area; if it is judged according to the component name that the corresponding component is displayed in a non-fixed display area, then searching the report template corresponding to the report template name according to the component name to obtain the regional width and height of the non-fixed display area; and calculating the regional position of the non-fixed display area according to the regional width and height of the non-fixed display area; wherein the regional position and the regional width and height are defined in the report template based on the grid layout system.
[0008] In a possible implementation, the preset layout algorithm also includes, for N copies of component data, setting the area position of the non-fixed display area after the area positions of all fixed display areas, and arranging the area positions of all non-fixed display areas in sequence from left to right and from top to bottom according to the order in which the component data is received.
[0009] In one possible implementation, the front-end display platform renders N copies of component data in a preset format in a first display interface based on a preset layout algorithm, including: for each copy of component data, generating or mapping a first display interface based on the report ID of the analysis report to which the component data belongs, and rendering the component data in a preset format in the first display interface based on a preset layout algorithm.
[0010] In one possible implementation, N copies of component data in a preset format are obtained and returned to a front-end display platform, including: successively generating N copies of component data, and returning each copy of component data to the front-end display platform in real time; the front-end display platform renders the N copies of component data in a preset format in a first display interface based on a preset layout algorithm, including: successively responding to receiving one copy of the N copies of component data, the front-end display platform renders the copy of the component data in a preset format in real time in the first display interface based on a preset layout algorithm.
[0011] In one possible implementation, the analysis and processing also obtains text type and / or image type data and returns it to the front-end display platform; the method also includes: in response to receiving the text type and / or image type data, the front-end display platform displays the text type and / or image type data in the output box of the interactive interface; the text type and / or image type data is an overview of the N components data.
[0012] In one possible implementation, the front-end display platform obtains the first user input using the input box of the interactive interface, and the method also includes: after obtaining the first user input, the front-end display platform sets the input box to a prohibited input state; after receiving the report completion indication message sent by the back-end processing platform, the input box is set to an input-enabled state, and the first display interface is set to a report completed state; the report completion indication message is sent after the back-end processing platform sends all processed data corresponding to the first user input.
[0013] In a possible implementation, the method further includes: in a first display interface set to report a completed state, in response to a user dragging a display area of a component corresponding to any component data, adjusting a region position and a region width and height of the display area.
[0014] In a second aspect, the present application provides an artificial intelligence-based automated report generation device, the device comprising: a front-end display module, for obtaining a first user input indicating analysis requirements for target data; a back-end processing module, for analyzing and processing the first user input using an artificial intelligence model, and obtaining N copies of component data in a preset format and returning them to a front-end display platform; the N copies of component data are used to form an analysis report for the target data, each copy of component data including attribute information and component text of the corresponding component; the front-end display module is also used to, in response to receiving the N copies of component data, render the N copies of component data in a preset format in a first display interface based on a preset layout algorithm on the front-end display platform, and obtain a first display interface including N components as an analysis report; the preset layout algorithm includes determining the regional position and regional width and height of the display area of each component in the first display interface according to its attribute information.
[0015] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute the method described in the first aspect or any possible implementation of the first aspect.
[0016] In a fourth aspect, the present application provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory; wherein, when the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.
[0017] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0019] Figure 1 This is a framework diagram of an automated report generation provided by an embodiment of the present application;
[0020] Figure 2 This is a flow chart of an automated report generation method based on artificial intelligence provided in an embodiment of the present application;
[0021] Figure 3 It is an automatic report generation diagram based on artificial intelligence provided by an embodiment of the present application;
[0022] Figure 4 This is a schematic diagram of an artificial intelligence-based automated report generation device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0024] In the description of the embodiments of the present application, words such as "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a concrete way.
[0025] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the term "multiple" means two or more. For example, multiple systems refers to two or more systems, and multiple screen terminals refers to two or more screen terminals.
[0026] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprises", "has" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.
[0027] As mentioned earlier, traditional report generation methods often require a lot of manpower and time, and often lack flexibility and personalization.
[0028] In view of this, the front-end display platform of the embodiment of the present application first obtains the first user input, which indicates the analysis requirements for the target data; secondly, the back-end processing platform uses the artificial intelligence model to analyze and process the first user input, and returns the N copies of component data generated successively to the front-end display platform in real time, and the N copies of component data are used to form an analysis report for the target data; then the front-end display platform renders the N copies of component data in real time in the first display interface based on the preset layout algorithm, so as to automatically generate a first display interface including N components as an analysis report. Compared with the traditional manual processing method, the use of artificial intelligence models to analyze and process the first user input can improve the intelligence level of report generation; in addition, this solution returns the N copies of component data generated successively to the front-end display platform in real time for real-time rendering, which can improve the efficiency of report generation; and the N copies of component data are rendered in the first display interface based on the preset layout algorithm to obtain a personalized visual report, which can improve the flexibility of system report generation and enhance user experience.
[0029] For example, Figure 1 A diagram showing an automated report generation framework provided in an embodiment of the present application is shown.
[0030] like Figure 1 As shown, the message interaction of the automated report generation process is completed by both the back-end processing platform and the front-end display platform. The back-end processing platform and the front-end display platform can be deployed on any device, apparatus, server, or device cluster with computing and processing capabilities.
[0031] The front-end display platform provides a series of tools, frameworks and libraries for building and displaying the front-end interface, as well as interactive elements, allowing users to ask questions and explore different aspects of the data by clicking, hovering or dragging. The back-end processing platform uses artificial intelligence models to perform natural language processing on user questions, complete the establishment of communication connections and data interaction with the front-end display platform. The artificial intelligence model is a large model or AI model that is pre-trained using relevant data in the application field.
[0032] First, the front-end display platform sets the input box of the interactive interface to an input-enabled state, so that the user can ask questions in the input box manually or by converting voice into text to obtain questions, which indicate the analysis requirements for the target data.
[0033] Secondly, after obtaining the question, the front-end display platform sets the input box to a prohibited input state and establishes a server-sent events (SSE) connection for the question with the back-end processing platform.
[0034] Subsequently, the front-end display platform sends the questions to the back-end processing platform through the SSE connection, and receives the answers generated by the back-end processing platform through the SSE connection by analyzing and processing the questions using the artificial intelligence model.
[0035] On the one hand, the above answer can be component type data.
[0036] Specifically, the artificial intelligence model generates N copies of component data in a preset format and returns them to the front-end display platform. The N copies of component data are used to form an analysis report for the target data. The preset format is agreed upon in advance by the back-end processing platform and the front-end display platform based on the characteristics of the application field. Each copy of component data can be rendered as a component in the display interface of the front-end display platform. A component is an interface element that can be reused in different interfaces. Each copy of component data includes at least the attribute information and component text of the corresponding component. The attribute information of the component is used to determine the regional position and regional width and height of its display area in the display interface of the front-end display platform. The component text of the component is related to the question entered by the user.
[0037] Furthermore, in response to receiving N copies of component data, the front-end display platform is used to render the N copies of component data in a preset format in the first display interface based on a preset layout algorithm.
[0038] Specifically, when the front-end display platform receives N copies of component data, it parses them according to the preset format, extracts the report template name of the analysis report contained in the attribute information, and the component name of the corresponding component. For each copy of component data received, it is determined whether a display interface has been generated for the problem. If so, the display area of the corresponding component in the display interface is determined according to the preset layout algorithm and the attribute information of the corresponding component in the built display interface, and the component data is rendered in the display area to display the corresponding component; otherwise, a new display interface is created for the problem to display the corresponding component.
[0039] On the other hand, the above answer may also be text-type and / or picture-type data, which are overviews of the N components data.
[0040] Further, in response to receiving text type and / or image type data, the front-end display platform displays these text and / or image data in the output box of the interactive interface.
[0041] Furthermore, after all the processing data corresponding to the problem are sent, the back-end processing platform also sends a report completion indication message to the front-end display platform to prompt that the processing data corresponding to the problem has been sent.
[0042] Finally, after receiving the report completion indication message, on the one hand, the front-end display platform stops updating the display interface, sets the status of the display interface to the report completed, and obtains a display interface including N components as an analysis report. On the other hand, the front-end display platform also disconnects the SSE connection established for the problem and stops receiving data from the back-end processing platform. Thirdly, the front-end display platform sets the input box in the interactive interface to an input-enabled state so that the user can perform new input and obtain new problems.
[0043] As a result, automated report generation can be performed based on the AI model, providing an intelligent and flexible report generation solution. This solution can automatically generate beautiful and personalized report layouts based on user needs and data characteristics, thereby improving the user experience.
[0044] Figure 2 FIG. 1 shows a flow chart of an automatic report generation method based on artificial intelligence provided by an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:
[0045] Step S201: The front-end display platform obtains a first user input, which indicates an analysis requirement for target data.
[0046] In one embodiment, the front-end display platform can be any web application that supports network requests and data processing. It has a user interaction function, by providing an interactive interface for the user to enter a first user input in an input box, which indicates the analysis requirements for the target data.
[0047] For example, in the semiconductor field, the format of manual user input is set as: format key information (time + IoT id + wafer id + loop name) + user requirements, and the first user input can be:
[0048] Please analyze the defect data of Week40 TES001.100#01AA loop in the photolithography process and generate an analysis report.
[0049] The target data are: time: Week40, Iot id: TES001, wafer id: 100#01, loop name: AAloop, analysis requirements: analyze the defect data in the lithography process and generate an analysis report.
[0050] Optionally, you may also provide only the necessary target data information and set the analysis requirements as omissible attributes, and the artificial intelligence model will perform analysis and processing based on the target data information to obtain the analysis requirements.
[0051] Optionally, a prompt for commonly used user input may be provided in a drop-down prompt box of the interactive interface input box for the user to refer to for accurate input, thereby improving the efficiency of subsequent processing of analysis requirements in user input.
[0052] In one implementation, after obtaining the first user input, the front-end display platform sends an SSE network request to the back-end processing platform to establish an SSE connection for the first user input. The first user input is sent to the back-end processing platform through the SSE connection, and the back-end processing platform receives the analysis and processing result of the first user input using the artificial intelligence model.
[0053] In one implementation, after obtaining the first user input, the front-end display platform also sets the input box to a prohibited input state, and then unbans it after the back-end processing platform completes the analysis and processing of the first user input, so as to avoid mutual interference between different user inputs.
[0054] Step S202: The backend processing platform uses an artificial intelligence model to analyze and process the first user input, obtains N sets of component data in a preset format, and returns them to the frontend display platform. The N sets of component data are used to form an analysis report for the target data, and each set of component data includes attribute information and component text of the corresponding component.
[0055] In one embodiment, the backend processing platform can call the artificial intelligence model, and can establish a communication connection with the frontend display platform to exchange information, and any backend application that supports network requests and data processing. The artificial intelligence model is a large model or AI model that is pre-trained using relevant data in the application field.
[0056] The backend processing platform uses the artificial intelligence model to perform natural language processing operations on the first user input, and provides answers to the analysis requirements for the target data indicated by the first user input.
[0057] Exemplarily, the artificial intelligence model processes the first user input to obtain N components of data in a preset format. The preset format is agreed upon in advance by the backend processing platform and the frontend display platform according to the characteristics of the application field, such as a domain-specific language (DSL) format.
[0058] The N pieces of component data are used to form an analysis report for the target data, and each piece of component data includes attribute information and component text of the corresponding component. The attribute information includes the report template name of the analysis report to which the N pieces of component data belong, and the component name of the corresponding component. The attribute information of the component is used to determine the area position and area width and height of its display area in the display interface of the front-end display platform, and the component text is related to the first user input.
[0059] Each component data also includes the component structure of the corresponding component, which includes the component type and component configuration information. The effect presented by the component is to display the component text in the display interface according to the component structure, so the component is an interface element that can be reused in different interfaces. Component-based design allows developers of the front-end display platform to create reusable interface elements that can be reused in different interfaces and projects, thereby improving development efficiency and maintainability.
[0060] For example, the component type can be a title, button, form, navigation bar, card, list, image, etc. The component configuration information is the style of the component, including color, size, border, etc. The component text is the text string, number, unit symbol, etc. to be displayed by the component.
[0061] In one implementation, the backend processing platform analyzes and processes the first user input and also obtains text-type and / or image-type data, which are overviews of the N components of data.
[0062] In one implementation, since the N copies of component data are independent of each other, the backend processing platform will send the N copies of component data generated successively to the frontend display platform in real time, without having to wait until all N copies of component data are generated before sending them again.
[0063] In one implementation, after the backend processing platform sends all processed data corresponding to the first user input, it sends a report completion indication message to the frontend display platform to prompt the frontend display platform that the processed data has been sent.
[0064] Step S203, in response to receiving the N copies of component data, the front-end display platform renders the N copies of component data in a preset format in a first display interface based on a preset layout algorithm, and obtains a first display interface including N components as an analysis report. The preset layout algorithm includes determining the area position and area width and height of the display area of each component in the first display interface according to its attribute information.
[0065] In one embodiment, the front-end display platform provides an interface display for the user, and displays N components obtained by rendering N copies of component data in a first display interface based on a preset layout algorithm, and obtains an analysis report for the target data indicated by the first user input formed by the N copies of component data.
[0066] For each component data, the component data also includes the report ID of the analysis report to which it belongs. The report ID is the index number assigned by the backend processing platform to the analysis report to which it belongs, and is unique in the backend processing platform and the frontend display platform. Determine whether the first display interface has been established for the first user input according to the report ID. If so, in the first display interface obtained by mapping the report ID, determine the display area of the corresponding component in the display interface according to the preset layout algorithm and the attribute information of the corresponding component, and render the component data in the display area to display the corresponding component; if not, create a new first display interface for the first user input to display the corresponding component, and establish a mapping relationship between the report ID and the first display interface.
[0067] For example, a component data in the semiconductor field includes the report ID of the analysis report to which it belongs: ID=1, the report template name of the analysis report to which it belongs: photolithography process defect report, component name: title, component type: title, component configuration information: color and size of the title, and component text: text information to be displayed in the title.
[0068] For each component data, the front-end display platform parses it according to the preset format, extracts the report template name of the analysis report contained in the attribute information, and the component name of the corresponding component. The report template corresponding to the report template name is the template used in the first display interface. The report template includes the area position and area width and height of the preset area of multiple preset components in the report template. These preset components have one-to-one mapped component names. The back-end processing platform and the front-end display platform save these report templates in advance.
[0069] The preset layout algorithm includes: determining the area position and area width and height of the display area of the corresponding component in the first display interface according to the report template name and component name of the corresponding report.
[0070] Specifically, the first display interface uses the report template corresponding to the report template name. The properties of the display area of the corresponding component in the first display interface are determined from the relevant table according to the component name. If it is a fixed display area, the report template corresponding to the report template name is searched according to the component name to obtain the area position and area width and height of the preset area of the mapped preset component, and use them as the area position and area width and height of the fixed display area; if it is a non-fixed display area, the area width and height of the preset area are searched from the report template according to the component name, and used as the area width and height of the non-fixed display area, and the area position of the non-fixed display area is calculated according to the area width and height of the non-fixed display area; wherein the area position and area width and height are defined in the report template based on the grid layout system.
[0071] Exemplarily, commonly used static components may be set to be displayed in a fixed display area, and personalized dynamic components may be set to be displayed in a non-fixed display area.
[0072] For example, the grid layout system vue grid layout can be used in the front-end display platform to pre-design the regional position and regional width and height of the preset area of the preset components in various report templates. For example: the page is divided into a certain number of rows and columns, each grid occupies one or more row and column units, and the coordinate information x and y are used to represent the position of the preset area of the preset component in the report template, and w and h represent the width and height of the preset area. Then a one-to-one mapping relationship between various preset components and component names is established, and the regional position and regional width and height of the preset area of the mapped preset component can be obtained through the component name.
[0073] The preset layout algorithm also includes: for N copies of component data, setting the area position of the non-fixed display area after the area positions of all fixed display areas, and arranging the area positions of all non-fixed display areas from left to right and from top to bottom in the order in which the component data is received.
[0074] After determining the area position and area width and height of the display area of each component data corresponding to the component in the first display interface, the component data in a preset format is rendered in the first display interface according to the area position and area width and height of the corresponding component.
[0075] In one implementation, the front-end display platform renders each component data received successively in real time, thereby improving the rendering efficiency of each component data on the front-end display platform.
[0076] In one implementation, when the backend processing platform analyzes and processes the first user input and obtains text-type and / or image-type data, the frontend display platform displays these data in an output box of the interactive interface.
[0077] In one implementation, after the front-end display platform receives the report completion indication message sent by the back-end processing platform, the front-end display platform stops updating the first display interface and sets the first display interface to a report completed state; the front-end display platform also disconnects the SSE connection established for the first user input and stops receiving data from the back-end processing platform; the front-end display platform also sets the input box in the interactive interface to an input-enabled state, so that the user can perform new input and obtain new questions.
[0078] In one embodiment, in the first display interface set to the report completed state, in response to dragging the display area of the component corresponding to any component data, the area position and area width and height of the display area are adjusted to better display the corresponding component and facilitate users to view the report results.
[0079] For example, Figure 3 This is an automatic report generation diagram based on artificial intelligence provided by the embodiment of the present application. Figure 3 As shown, the front-end display platform includes Analysis3, a display interface provided for user input, and Insight Navigate, an interactive interface provided for all user inputs.
[0080] Exemplarily, the front-end display platform can also provide corresponding display interfaces Analysis1, Analysis2, etc. for other user inputs.
[0081] The Analysis page and the Insight Navigate interface are two different parts of the front-end display platform. The Analysis page focuses on in-depth analysis and detailed data operations, and is used to display the above component type data. The Insight Navigate interface focuses on providing quick insights and navigation, and is used to provide an input box for users to enter manually and obtain user input. The input box can also include a default prompt displayed in gray font to improve the efficiency of user manual input.
[0082] A communication connection is established between the front-end display platform and the back-end processing platform. The back-end processing platform uses an artificial intelligence model to analyze and process user input, obtains four component data and returns them to the front-end display platform for rendering according to a preset layout algorithm, and obtains a display interface AnaIysis3 including the corresponding four components as an analysis report.
[0083] like Figure 3 As shown, the display interface Analysis3 is used to display the four components corresponding to the four components, and the components are:
[0084] The first title component: used to describe the subject of the analysis report;
[0085] The second text component: describes in detail the results of the analysis report;
[0086] The third map component: displays the wafer map in the analysis report to facilitate users to view the defect distribution and film thickness of the wafer;
[0087] The fourth table component: The table header is the wafer id, and the table displays the relevant information of the wafer in the analysis report, such as defect pictures, defect distribution maps, etc.
[0088] Optionally, the backend processing platform calls the artificial intelligence model to analyze and process the user input and also obtain text type and / or image type data, which is an overview of the four component data.
[0089] like Figure 3 As shown, the interactive interface Insight Navigate also provides an output box, which is used to display text type and / or image type data. It can be understood that the output box is also used to display user input manually entered by the user.
[0090] Therefore, compared with traditional manual processing methods, this application uses an artificial intelligence model to analyze and process user input, and displays the component type data in the processed data by the front-end display platform based on a preset layout algorithm, which can improve the intelligence level and flexibility of the system's generated reports.
[0091] It should be noted that although the operations of the method of the embodiment of the present application are described in a specific order in the above embodiment, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flow chart can change the order of execution. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.
[0092] Based on the method in the above embodiment, illustratively, Figure 4 An automatic report generation device based on artificial intelligence provided by an embodiment of the present application is shown. Figure 4 As shown, the automatic report generating device 400 includes:
[0093] The front-end display module 410 is used to obtain a first user input, which indicates an analysis requirement for target data.
[0094] The backend processing module 420 is used to analyze and process the first user input using an artificial intelligence model, obtain N component data in a preset format, and return them to the frontend display platform. The N component data are used to form an analysis report for the target data, and each component data includes attribute information and component text of the corresponding component.
[0095] The front-end display module 410 is further configured to, in response to receiving N copies of component data, render the N copies of component data in a preset format in the first display interface based on a preset layout algorithm to obtain a first display interface including N components as an analysis report. The preset layout algorithm includes determining the regional position and the regional width and height of the display area of each component in the first display interface according to its attribute information.
[0096] Based on the methods in the above embodiments, the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the methods described in the above embodiments.
[0097] Based on the method in the above embodiment, an embodiment of the present application provides an electronic device. The electronic device may include: at least one memory for storing a program; at least one processor for executing the program stored in the memory. Wherein, when the program stored in the memory is executed, the processor is used to execute the method described in the above embodiment. Exemplarily, the electronic device may be a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, a server, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook, and a cellular phone, a personal digital assistant (personal digital assistant, PDA), an augmented reality (augmented reality, AR) device, a virtual reality (virtual reality, VR) device, an artificial intelligence (artificial intelligence, Al) device, a wearable device, a vehicle-mounted device, a smart home device and / or a smart city device. The embodiment of the present application does not impose any special restrictions on the specific type of the electronic device.
[0098] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.
[0099] It is understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not used to limit the scope of the embodiments of the present application. It should be understood that in the embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0100] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the present application should be included in the scope of protection of the present application.
Claims
1. An automated report generation method based on artificial intelligence, characterized in that: The method comprises: The front-end display platform obtains a first user input indicating an analysis requirement for target data; The backend processing platform uses an artificial intelligence model to analyze and process the first user input, obtains N copies of component data in a preset format, and returns them to the frontend display platform; the N copies of component data are used to form an analysis report for the target data, and each copy of component data includes attribute information and component text of the corresponding component; In response to receiving the N copies of component data, the front-end display platform renders the N copies of component data in a preset format in a first display interface based on a preset layout algorithm, and obtains a first display interface including N components as the analysis report; the preset layout algorithm includes determining the regional position and regional width and height of the display area of each component in the first display interface according to its attribute information.
2. The method according to claim 1, characterized in that: The front-end display platform renders the N copies of component data in the preset format in the first display interface based on a preset layout algorithm, including: Parsing each component data according to the preset format, extracting the report template name of the analysis report contained in the attribute information and the component name of the corresponding component; Using the preset layout algorithm, according to the report template name and the component name of the corresponding component, determine the area position and area width and height of the display area of the corresponding component in the first display interface; In the first display interface, the component data in the preset format is rendered according to the region position and region width and height of the corresponding component.
3. The method according to claim 2, characterized in that The determining of the area position and the area width and height of the display area of the corresponding component in the first display interface includes: If it is determined according to the component name that the corresponding component is displayed in a fixed display area, then according to the component name, the area position and area width and height of the fixed display area are obtained by searching the report template corresponding to the report template name; If it is determined according to the component name that the corresponding component is displayed in a non-fixed display area, then according to the component name, the width and height of the non-fixed display area are obtained by searching the report template corresponding to the report template name; and Calculating the area position of the non-fixed display area according to the area width and height of the non-fixed display area; The region position and the region width and height are defined in the report template based on a grid layout system.
4. The method according to claim 3, characterized in that The preset layout algorithm also includes, for N copies of component data, setting the area position of the non-fixed display area after the area positions of all fixed display areas, and arranging the area positions of all non-fixed display areas in sequence from left to right and from top to bottom according to the order in which the component data is received.
5. The method according to claim 1, characterized in that The front-end display platform renders the N copies of component data in the preset format in the first display interface based on a preset layout algorithm, including: For each piece of component data, the first display interface is generated or mapped according to the report ID of the analysis report to which the component data belongs, and the component data in the preset format is rendered in the first display interface based on a preset layout algorithm.
6. The method according to claim 1, characterized in that The N copies of component data in a preset format are returned to the front-end display platform, including: Generate N copies of component data successively, and return each copy of component data to the front-end display platform in real time; The front-end display platform renders the N copies of component data in the preset format in the first display interface based on a preset layout algorithm, including: In response to receiving one of the N copies of component data, the front-end display platform renders the copy of the component data in the preset format in real time in the first display interface based on a preset layout algorithm.
7. The method according to claim 1, characterized in that The analysis and processing also obtains text-type and / or picture-type data and returns it to the front-end display platform; The method further comprises: In response to receiving the text type and / or picture type data, the front-end display platform displays the text type and / or picture type data in an output box of the interactive interface; the text type and / or picture type data is an overview of the N components data.
8. The method according to claim 1, characterized in that The front-end display platform obtains the first user input by using the input box of the interactive interface, The method further comprises: After obtaining the first user input, the front-end display platform sets the input box to a prohibited input state; After receiving the report completion indication message sent by the back-end processing platform, the input box is set to an input-enabled state, and the first display interface is set to a report completed state; the report completion indication message is sent after the back-end processing platform has sent all processed data corresponding to the first user input.
9. The method according to claim 8, characterized in that The method further comprises: In the first display interface set to report the completed state, in response to the user dragging the display area of the component corresponding to any component data, the area position and the area width and height of the display area are adjusted.
10. An automatic report generation device based on artificial intelligence, characterized in that: The device comprises: A front-end display module is used to obtain a first user input, which indicates an analysis requirement for target data; A backend processing module is used to analyze and process the first user input using an artificial intelligence model, obtain N sets of component data in a preset format, and return them to the frontend display platform; the N sets of component data are used to form an analysis report for the target data, and each set of component data includes attribute information and component text of the corresponding component; The front-end display module is also used to respond to receiving the N copies of component data. The front-end display platform renders the N copies of component data in a preset format in a first display interface based on a preset layout algorithm to obtain a first display interface including N components as the analysis report; the preset layout algorithm includes determining the regional position and regional width and height of the display area of each component in the first display interface according to its attribute information.
