Research report generation method and device, electronic equipment and storage medium

Abstract

The invention provides a research report generation method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence and the like. According to the specific implementation scheme, text information and other types of information input by a user when the research report is to be generated are obtained; the other types of information comprise at least one of pictures, charts, formulas and documents in specified formats; capturing effective information in the other types of information by adopting a data processing agent module to obtain effective text information; and based on the text information and the effective text information, adopting an outline agent module, an information index agent module and a content agent module to generate a research report. According to the technology disclosed by the invention, the generation efficiency of the research report can be effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to the field of artificial intelligence and other technical fields, and in particular to a method, device, electronic device and storage medium for generating a research report. Background Art

[0002] The research report is mainly completed through a large amount of preliminary research on the corresponding subject area, statistical analysis of the data, and finally integrating it into a highly professional report.

[0003] In the prior art, considering the professionalism of research reports, professional practitioners in the field usually screen out highly relevant information based on the report topic through their understanding of the field and analysis of a large amount of factual information and data in the field, and conduct statistical drawing and in-depth analysis, etc., and finally write a complete report. Summary of the invention

[0004] The present disclosure provides a method, device, electronic device and storage medium for generating a research report.

[0005] According to one aspect of the present disclosure, a method for generating a research report is provided, comprising:

[0006] Acquire text information and other types of information input by a user when generating a research report; the other types of information include at least one of pictures, charts, formulas, and documents in a specified format;

[0007] Using a data processing agent module to capture valid information from the other types of information to obtain valid text information;

[0008] Based on the text information and the effective text information, an outline intelligent agent module, an information index intelligent agent module and a content intelligent agent module are used to generate a research report.

[0009] According to another aspect of the present disclosure, there is provided a device for generating a research report, comprising:

[0010] An information acquisition module, used to acquire text information and other types of information input by a user when generating a research report; the other types of information include at least one of pictures, charts, formulas, and documents in a specified format;

[0011] An information capture module, used to capture valid information from the other types of information using a data processing agent module to obtain valid text information;

[0012] A report generation module is used to generate a research report based on the text information and the effective text information, using an outline intelligent agent module, an information index intelligent agent module and a content intelligent agent module.

[0013] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] 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 of any possible implementation manner and the aspects described above.

[0017] According to yet 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 cause the computer to execute the method of the above-mentioned aspect and any possible implementation manner.

[0018] According to yet another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements the above-mentioned aspects and any possible implementation method.

[0019] According to the technology disclosed in the present invention, the efficiency of generating research reports can be effectively improved.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0023] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0024] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure;

[0025] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0026] Figure 5 The block diagram is a block diagram of an electronic device for implementing the method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art 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.

[0028] Obviously, the described embodiments are only part of the embodiments of the present disclosure, but not all of them. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present disclosure.

[0029] It should be noted that the terminal devices involved in the embodiments of the present disclosure may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers and other smart devices; display devices may include but are not limited to personal computers, televisions and other devices with display functions.

[0030] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0031] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure; Figure 1 As shown, this embodiment provides a method for generating a research report, which may specifically include the following steps:

[0032] S101, obtaining text information and other types of information input by a user when generating a research report; the other types of information include at least one of pictures, charts, formulas, and documents in a specified format;

[0033] S102, using a data processing agent module to capture valid information from other types of information to obtain valid text information;

[0034] S103. Based on text information and effective text information, an outline intelligent agent module, an information index intelligent agent module and a content intelligent agent module are used to generate a research report.

[0035] In the application scenario of this embodiment, when a user wants to generate a research report, the input information includes not only the input text information, but also other types of information. For example, the other types of information in this embodiment may include at least one of pictures, charts, formulas, and documents in a specified format. The other types of information in this embodiment also limit the research report to be generated. For example, the generated research report may be required to refer to the content of other types of information.

[0036] In this embodiment, when generating a research report, multiple agent modules are mainly used to implement it. For example, a data processing agent module can be used to capture valid information in other types of information to obtain valid text information.

[0037] For example, other types of information in this embodiment, such as pictures, charts, formulas, and documents in a specified format, etc., may include other information in addition to text information, such as format information. When generating a research report, text information is the most important reference information, and other information such as format information can assist in the extraction of text information from other types of information. For example, some format information is used to limit the form and display style of text information. Based on this, only the text information included in other types of information can be captured, and the valid information in the captured text information can be further filtered to obtain valid text information. In other words, when capturing valid information in other types of information, other information such as format information in other types of information can be referred to to obtain more accurate and valid text information.

[0038] Moreover, in this embodiment, when capturing valid information, some stop words and words that do not contribute to the generation of the research report can also be removed, such as you, me, he (she), you, we, he (she), and words such as of, to, and etc. That is, some professional words that can contribute to the generation of the research report are mainly captured as valid text information.

[0039] In this embodiment, the outline intelligent agent module, the information index intelligent agent module and the content intelligent agent module can refer to the text information and the valid file information together and work together to generate a research report.

[0040] In this embodiment, four intelligent agent modules are used to realize the generation of the research report. As intelligent entity modules, the intelligent agent modules can realize the generation of the research report efficiently, quickly and accurately.

[0041] The method for generating a research report in this embodiment uses a data processing agent module to capture valid text information from other types of information input by the user, and uses an outline agent module, an information index agent module, and a content agent module to intelligently, efficiently, and quickly generate a research report based on the text information and valid text information input by the user. Compared with the manually generated research report of the prior art, it can effectively shorten the time spent on generating a research report and effectively improve the efficiency of generating a research report. Moreover, by referring to the text information input by the user and the valid text information captured from other types of information input by the user, the research report is generated, which can effectively ensure the accuracy and rationality of the generated research report.

[0042] Figure 2 is a schematic diagram of a second embodiment of the present disclosure; the method for generating a research report of this embodiment, in the above Figure 1 Based on the technical solutions of the embodiments shown in the figure, the technical solutions of the present disclosure are further described in more detail. Figure 2 As shown, the method for generating a research report in this embodiment may specifically include the following steps:

[0043] S201, obtaining text information and other types of information input by a user when generating a research report; the other types of information include at least one of pictures, charts, formulas, and documents in a specified format;

[0044] For example, in this embodiment, the document in the specified format is a document in word format, a document in excel format, or a document in pdf format.

[0045] In this embodiment, no matter which type of document in the specified format is used, a corresponding research report can be generated based on the document in the specified format, which can effectively enrich the usage scenarios of the research report generation.

[0046] S202, using a data processing agent module to extract text content from other types of information;

[0047] S203, using a data processing agent module to extract valid information from text content in other types of information to obtain valid text information;

[0048] For example, when other types of information include images, optical character recognition (OCR) can be used to identify all the text in the image to obtain the text content. Then, effective information in the text content is extracted, that is, meaningless words that do not contribute to the generation of the research report are removed from the text content to obtain effective text information.

[0049] When other types of information include charts, the text content in the charts can be extracted based on the format of the charts. For example, during text recognition, the text describing the structure and / or format of the charts may not be extracted. Similarly, valid information in the text content is further extracted to obtain valid text information.

[0050] Similarly, for other types of information including formulas, the text description corresponding to the formula can be extracted based on the structure and physical meaning of the formula to obtain the text content corresponding to the formula. Similarly, effective information in the text content can be further extracted to obtain effective text information.

[0051] For a document of a specified format, the text content in the document can be extracted based on the document format. For example, during text recognition, the text describing the format in the document does not need to be extracted. Similarly, valid information in the text content can be further extracted to obtain valid text information.

[0052] The data processing agent module of this embodiment can be configured with a corresponding data processing strategy, or implemented using a neural network model. Therefore, by using the data processing agent module, effective text information can be accurately, efficiently and intelligently acquired.

[0053] S204, mining the title of the research report based on the text information and the effective text information;

[0054] For example, in this embodiment, a pre-trained information mining model can be used to mine the title of the research report. The information mining model is implemented using a neural network model. When used, text information and valid text information are input into the information mining model, and the information mining model can mine the title of the research report based on the input text information and valid text information.

[0055] Optionally, the title of the research report may also be mined from the text information and the valid text information based on a pre-configured information mining strategy.

[0056] S205, using an outline agent module to analyze text information and valid text information to generate an outline of the research report;

[0057] The outline of the research report of this embodiment may include a plurality of chapter titles having a sequential relationship.

[0058] Further optionally, in this embodiment, an outline intelligent agent module may be further used to enrich the generated outline according to the text information and the valid text information, as well as the generated outline, so that the final generated outline structure is more delicate and more accurate.

[0059] S206, using an information indexing agent module to search at least one of a preset professional knowledge base, a search engine system on a public network, and a third-party database according to the text information and the valid text information to obtain relevant knowledge;

[0060] It should be noted that, before the research report is generated in this embodiment, the field of the research report to be generated is already known, and the preset professional knowledge base in the field can be called. In other words, the technical solution of this embodiment can be limited to a specific field when used.

[0061] Preferably, in this embodiment, search results can be obtained from three search channels, namely, professional knowledge base, public network and third-party database, to form the relevant knowledge obtained by the search. Specifically, the more search channels there are, the richer the content of the relevant knowledge is, which can provide rich data support for the generation of subsequent research reports.

[0062] The third-party database in this embodiment may be any other accessible database, which is not limited here.

[0063] S207, using a content agent module to generate the contents of each chapter in the research report according to the outline of the research report and relevant knowledge;

[0064] Specifically, the content intelligence module can generate the content of each chapter in the research report based on the titles of each chapter in the outline of the report and related knowledge.

[0065] It should be noted that the generation of the content of each chapter can be independent or can influence each other, so that the context of the research report is more coherent. For example, the content of each chapter can be generated in sequence according to the order of the position of each chapter from front to back in the outline. When the content of other chapters other than the first chapter is generated, the content of the first preset number of chapters before the current chapter can be used as context information for reference by the content intelligence module. The content intelligence module also refers to the context information to generate the content of the current chapter, so that the context content of the generated research report is more coherent. The first preset number can be set according to actual needs or experience, for example, it can be 1, 2 or more, which is not limited here.

[0066] Steps S204-S207 can be considered as the above Figure 1 An implementation of step S103 of the illustrated embodiment.

[0067] The outline agent module and the content agent module of this embodiment are both implemented by a neural network model, specifically, a generative large model. The generative large model here can also be called a generative language model (General Language Model; GLM), or a generative large language model.

[0068] S208, using a content intelligence module to generate key points of each chapter according to the content of each chapter;

[0069] S209, using an information indexing agent module to search based on the key points of each chapter and the context information of the key points of each chapter to obtain in-depth knowledge related to each chapter;

[0070] For each chapter, the context information of the key points of the chapter may include the key points of a preset number of chapters before and after the current chapter. The search channel for further search may also include at least one of the three channels mentioned in the above embodiment. Preferably, the search results are obtained from the three channels at the same time to obtain richer in-depth knowledge.

[0071] S210, using a content agent module to update the content of each chapter according to the key points of each chapter, the context information of the key points of each chapter, and the in-depth knowledge related to each chapter;

[0072] Optionally, in this embodiment, steps S208-S210 may be executed only once to update the content of a chapter, or may be executed multiple times in a loop to update the content of each chapter, so that the content of each chapter is richer and the context is more coherent. In actual application scenarios, the number of update rounds for the content of each chapter can be specifically set according to needs. The more update rounds, the richer and more accurate the content of each chapter is, that is, the higher the quality of the research report is.

[0073] S211, using a content intelligence module to generate at least one of a summary, a statement, an appendix, and a reference of the research report based on the target content of each chapter;

[0074] S212. Use a content intelligence module to generate a research report based on the report summary, statement, appendix and at least one of the references in the research report, as well as the title of the research report, the outline of the research report, and the contents of each chapter in the research report.

[0075] Specifically, the order of each part of information when integrating and generating a research report can refer to the order of each part of information in a manually written research report, or the order of each part can be limited according to needs, which is not limited here.

[0076] The method for generating a research report in this embodiment can generate a research report intelligently, efficiently and quickly by adopting a data processing intelligent agent module, an outline intelligent agent module, an information indexing intelligent agent module and a content intelligent agent module.

[0077] In this embodiment, the information indexing agent module can search from multiple channels, which can effectively ensure that the relevant knowledge content obtained is rich enough to provide effective data support for the generation of research reports.

[0078] Moreover, the outline intelligent agent module in this embodiment can analyze text information and valid text information to generate an outline of the research report, effectively ensuring the accuracy of the generated outline. The content intelligent agent module can accurately, reasonably and efficiently generate the content of each chapter of the research report based on the outline and relevant knowledge of the research report, and can ensure the richness and comprehensiveness of the content of each chapter generated.

[0079] Furthermore, in this embodiment, a content intelligent body module, an information index intelligent body module and a content intelligent body module can also be used to update the content of each chapter to make the content of each chapter richer. In addition, during the updating process, contextual information is also referred to to make the context of the updated content of each chapter more coherent.

[0080] In summary, by adopting the above solution, this embodiment can generate professional research reports in related fields quickly, efficiently and with high quality.

[0081] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure; Figure 3 As shown, this embodiment provides a device 300 for generating a research report, including:

[0082] The information acquisition module 301 is used to acquire text information and other types of information input by the user when generating a research report; the other types of information include at least one of pictures, charts, formulas and documents in a specified format;

[0083] An information capture module 302 is used to capture valid information in the other types of information using a data processing agent module to obtain valid text information;

[0084] The report generation module 303 is used to generate a research report based on the text information and the effective text information by using an outline intelligent agent module, an information index intelligent agent module and a content intelligent agent module.

[0085] The research report generation device 300 of this embodiment realizes the realization principle and technical effect of the generation of the research report by adopting the above-mentioned modules, which is the same as that of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0086] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure; Figure 4 As shown, the research report generation device 400 of this embodiment includes Figure 3 The research report generation device 300 has modules with the same names and functions: an information acquisition module 401 , an information capture module 402 , and a report generation module 403 .

[0087] like Figure 4 As shown, in the device 400 for generating a research report of this embodiment, the report generating module 403 includes:

[0088] A mining unit 4031, configured to mine the title of the research report based on the text information and the valid text information;

[0089] An outline generating unit 4032 is used to analyze the text information and the valid text information using the outline agent module to generate an outline of the research report;

[0090] A search unit 4033 is used to use the information indexing agent module to search at least one of a preset professional knowledge base, a search engine system on the public network, and a third-party database according to the text information and the valid text information to obtain relevant knowledge;

[0091] The content generation unit 4034 is used to use the content intelligence module to generate the content of each chapter in the research report according to the outline of the research report and the relevant knowledge.

[0092] Further optionally, if Figure 4 As shown, in the device 400 for generating a research report of this embodiment, the report generating module 403 further includes:

[0093] A key point generating unit 4035 is used to generate the key points of each chapter according to the content of each chapter by using the content agent module;

[0094] The search unit 4033 is further used to use the information indexing agent module to perform a search based on the key points of each chapter and the context information of the key points of each chapter to obtain the in-depth knowledge related to each chapter;

[0095] The content generation unit 4034 is also used to adopt the content intelligence module to update the content of each chapter according to the key points of each chapter, the contextual information of the key points of each chapter, and the in-depth knowledge related to each chapter.

[0096] Further optionally, if Figure 4As shown, in the research report generation device 400 of this embodiment, the report generation module 403 further includes an integration unit 4036;

[0097] The content generation unit 4034 is further configured to generate at least one of a summary, a statement, an appendix, and a reference of the research report based on the target content of each chapter by using the content intelligence module;

[0098] Integration unit 4036 is used to adopt the content intelligence module to integrate and generate a research report based on at least one of the report summary, statement, appendix and reference of the research report, as well as the title of the research report, the outline of the research report, and the contents of each chapter in the research report.

[0099] Further optionally, the document in the specified format is a document in word format, a document in excel format or a document in pdf format.

[0100] Further optionally, the information capture module 402 is used to:

[0101] Using the data processing agent module, extracting text content from the other types of information;

[0102] The data processing intelligent agent module is used to extract valid information from the text content in the other types of information to obtain the valid text information.

[0103] Further optionally, the data processing agent module, the outline agent module and the content agent module are all implemented using a neural network model.

[0104] The research report generation device 400 of this embodiment, by adopting the above-mentioned modules, realizes the realization principle and technical effect of the generation of the research report, which is the same as that of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0105] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0106] 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.

[0107] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, 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.

[0108] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0109] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0110] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 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 running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the above-mentioned methods of the present disclosure. For example, in some embodiments, the above-mentioned methods of the present disclosure may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the above-mentioned methods of the present disclosure described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the above-mentioned methods of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0111] Various implementations of the systems and techniques described above 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 implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including 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.

[0112] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0113] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may 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 may 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.

[0114] 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).

[0115] The systems and techniques described herein may 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 with 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 may 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.

[0116] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0117] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0118] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a research report, comprising: Obtain text information and other types of information entered by the user when generating a research report; The other types of information include at least one of pictures, charts, formulas, and documents in a specified format; Using a data processing agent module to capture valid information from the other types of information to obtain valid text information; Based on the text information and the effective text information, an outline intelligent agent module, an information index intelligent agent module and a content intelligent agent module are used to generate a research report.

2. The method according to claim 1, wherein: Based on the text information and the effective text information, an outline intelligent agent module, an information index intelligent agent module and a content intelligent agent module are used to generate a research report, including: Mining the title of the research report based on the text information and the valid text information; Using the outline intelligent agent module, the text information and the valid text information are analyzed to generate an outline of the research report; Using the information indexing agent module, according to the text information and the valid text information, searching from at least one of a preset professional knowledge base, a search engine system on the public network, and a third-party database to obtain relevant knowledge; The content intelligence module is used to generate the contents of each chapter in the research report according to the outline of the research report and the relevant knowledge.

3. The method according to claim 2, wherein: After the content agent module is used to generate the contents of each chapter in the research report according to the outline of the research report and the relevant knowledge, the method includes: Using the content intelligent agent module, the key points of each chapter are generated according to the content of each chapter; Adopting the information indexing agent module, based on the key points of each chapter and the context information of the key points of each chapter, searching again to obtain the deep knowledge related to each chapter; The content intelligence module is used to update the content of each chapter based on the key points of each chapter, the contextual information of the key points of each chapter, and the in-depth knowledge related to each chapter.

4. The method according to any one of claims 2-3, wherein: After generating a research report based on the text information and the effective text information by using an outline agent module, an information index agent module and a content agent module, the method further comprises: Using the content intelligence module, based on the target content of each chapter, generate at least one of the summary, statement, appendix and reference of the research report; The content intelligence module is used to integrate and generate a research report based on the report summary, statement, appendix and at least one of the references of the research report, as well as the title of the research report, the outline of the research report, and the contents of each chapter in the research report.

5. The method according to any one of claims 1 to 3, wherein: The document in the specified format is a document in word format, a document in excel format or a document in pdf format.

6. The method according to any one of claims 1 to 3, wherein: The data processing agent module is used to capture valid information in the other types of information to obtain valid text information, including: Using the data processing agent module, extracting text content from the other types of information; The data processing intelligent agent module is used to extract valid information from the text content in the other types of information to obtain the valid text information.

7. The method according to any one of claims 1 to 3, wherein: The data processing intelligent agent module, the outline intelligent agent module and the content intelligent agent module are all implemented using a neural network model.

8. A device for generating a research report, comprising: The information acquisition module is used to obtain text information and other types of information input by the user when generating a research report; The other types of information include at least one of pictures, charts, formulas, and documents in a specified format; An information capture module, used to capture valid information from the other types of information using a data processing agent module to obtain valid text information; A report generation module is used to generate a research report based on the text information and the effective text information, using an outline intelligent agent module, an information index intelligent agent module and a content intelligent agent module.

9. The device according to claim 8, wherein: The report generation module comprises: A mining unit, configured to mine the title of the research report based on the text information and the valid text information; An outline generating unit, configured to analyze the text information and the valid text information using the outline intelligent agent module to generate an outline of the research report; A search unit, configured to use the information indexing agent module to search at least one of a preset professional knowledge base, a search engine system on a public network, and a third-party database according to the text information and the valid text information to obtain relevant knowledge; The content generation unit is used to use the content intelligence module to generate the content of each chapter in the research report according to the outline of the research report and the relevant knowledge.

10. The device according to claim 9, wherein: The report generation module further includes: A key point generating unit, used to generate the key points of each chapter according to the content of each chapter by using the content intelligent agent module; The search unit is further used to use the information indexing agent module to perform a search based on the key points of each chapter and the context information of the key points of each chapter to obtain the in-depth knowledge related to each chapter; The content generation unit is also used to adopt the content intelligence module to update the content of each chapter according to the key points of each chapter, the contextual information of the key points of each chapter, and the in-depth knowledge related to each chapter.

11. The device according to any one of claims 9 to 10, wherein: The report generation module further includes an integration unit; The content generation unit is further configured to generate at least one of a summary, a statement, an appendix, and a reference of the research report based on the target content of each chapter by using the content intelligence module; The integration unit is used to adopt the content intelligence module to integrate and generate a research report based on at least one of the report summary, statement, appendix and reference of the research report, as well as the title of the research report, the outline of the research report, and the contents of each chapter in the research report.

12. The device according to any one of claims 8 to 10, wherein: The document in the specified format is a document in word format, a document in excel format or a document in pdf format.

13. The device according to any one of claims 8 to 10, wherein: The information capture module is used to: Using the data processing agent module, extracting text content from the other types of information; The data processing intelligent agent module is used to extract valid information from the text content in the other types of information to obtain the valid text information.

14. The device according to any one of claims 8 to 10, wherein: The data processing intelligent agent module, the outline intelligent agent module and the content intelligent agent module are all implemented using a neural network model.

15. 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 7.

16. 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 1-7.

17. 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 7.

Images