An intelligent writing assistant based on meta-analysis system

Abstract

The present invention is applicable to the technical field of intelligent writing, and provides an intelligent writing assistant based on a meta-analysis system, comprising a shell; a controller is arranged inside the shell; a display screen and an operation keyboard electrically connected to the controller are installed outside the shell, and a data acquisition module, a META analysis module, a screening module, a data processing module, a writing plan generation module and a plan processing module are arranged inside the controller; the device performs Meta-analysis based on artificial intelligence, and can complete the retrieval of all databases within a very short time, thereby improving the efficiency of document retrieval, and increasing the number of document samples in each Meta-analysis, thereby ensuring the accuracy and authority of the analysis; a text generation method based on AI-Chain realizes personalized writing services through the mutual coordination and cooperation of various AIs and humanized human-computer interaction, thereby solving the problems of lack of writing ideas and output results not meeting the requirements in the process of writing using a large model.

Description

Technical Field

[0001] The present invention relates to the field of intelligent writing technology, and more specifically, to an intelligent writing assistant based on a meta analysis system. Background Art

[0002] Writing is a skill that is often needed in today's society, but not everyone has good writing skills. Sometimes, there are often situations where there is an article title or title keywords, but there are no sentences or article content to start writing. The previous article assistance system is that when the user is editing a document through a document editing program, it extracts example sentences starting with the input word based on the user's current input word, and then displays them for the user to choose.

[0003] Meta-analysis, also known as "Meta-analysis", Meta means something that appeared later and is more comprehensive, and is usually used to name a new related discipline that comments on the original discipline. It includes not only data combination, but also epidemiological exploration and evaluation of results. It replaces individuals as analysis entities with the findings of original research, and through quantitative synthesis of multiple independent studies, it improves statistical power and draws more reliable and general conclusions.

[0004] Although this method can prompt selectable examples while the user is editing the file when the user already knows how to write an article, for users who only know the article title or a few scattered keywords, the user still has no idea how to start writing the article. At the same time, existing intelligent assistants for writing lack writing ideas when using large models, and the output results do not meet the requirements. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an intelligent writing assistant based on a meta-analysis system. Meta-analysis is performed based on artificial intelligence, and the retrieval of all databases can be completed in a very short time, thereby improving the efficiency of document retrieval and increasing the number of document samples in each Meta-analysis, thereby ensuring the accuracy and authority of the analysis. The text generation method based on AI-Chain realizes personalized writing services through the mutual coordination and cooperation of various AIs and humanized human-computer interaction, thereby solving the problems of lack of writing ideas and output results that do not meet the requirements in the writing process using large models.

[0006] To achieve the above object, the present invention provides the following technical solutions: An intelligent writing assistant based on a meta-analysis system comprises a shell; the characteristic is that a controller is arranged inside the shell; a display screen and an operation keyboard electrically connected to the controller are sequentially installed outside the shell.

[0007] The controller is internally provided with: The data acquisition module extracts keywords of the writing topic based on artificial intelligence and supplements the keywords.

[0008] The META analysis module performs Meta analysis based on the supplemented keywords to obtain an initial document set, and performs topic evaluation and self-checking based on all the documents therein to obtain a final document set.

[0009] A screening module is used to screen all the documents in the final document set to obtain a reference document set.

[0010] A data processing module is used to extract, index and query data from the obtained reference set.

[0011] A writing plan generation module, the writing generation module is used to process the information fragments processed by the data processing module to generate a writing plan and display it to the user; and The solution processing module is based on the text generation method of AI-Chain, and realizes personalized writing services through the mutual cooperation and collaboration of various AIs and humanized human-computer interaction.

[0012] The present invention is further configured as follows: a networking module is also provided inside the controller; the networking module is connected to the external Internet via communication and is used for network retrieval by the client.

[0013] The present invention is further configured as follows: the data processing module includes a data extraction unit, an index establishment unit and a data query unit.

[0014] The data extraction unit is used to integrate the reference set screened by the screening module to extract information fragments that meet the specified content value standards.

[0015] The index building unit is used to build an index of keywords and the information segments that meet the specified content value standard.

[0016] The data query unit is used to obtain information fragments associated with the input keywords and the information fragments that meet the specified content value standards.

[0017] The present invention is further configured as follows: the solution processing module includes a large model writing unit, a large model polishing unit and a human-computer interaction unit.

[0018] The large model writing unit is used to save various information that users think need to be left, and then this module is handed over to the large language model for writing.

[0019] The large model polishing unit is used to repeatedly polish and modify the writing content completed by the large model writing unit, so as to achieve the effect desired by the user.

[0020] The human-computer interaction unit is used for the user to put forward desired polishing requirements during the polishing and modification process and issue instructions to the large model polishing unit to modify and polish the writing content completed by the large model writing unit in real time.

[0021] The present invention is further configured as follows: the solution processing unit also includes a storage unit and an output unit; when the user presses the start writing button on the operating keyboard, the large model is allowed to write through the large model writing unit according to the various information given previously, and the written article is saved through the storage unit and output to the user through the output unit.

[0022] The present invention is further configured as follows: the data acquisition module includes a collection unit, a construction unit, a semantic analysis unit, a processing unit, and a retrieval unit.

[0023] The collection unit is used to collect relevant words in the Internet target database.

[0024] The construction module is used to construct a semantic word library using the words acquired by the acquisition unit from the Internet target database.

[0025] The semantic analysis module classifies the words in the constructed semantic vocabulary through semantic analysis.

[0026] The processing module is used to determine the keywords in the sentence to be processed and determine the data source within a certain range.

[0027] The search module obtains and outputs target documents corresponding to the search terms based on the data source determined by the screening terms.

[0028] The present invention is further configured as follows: the acquisition unit is used to acquire relevant words in the Internet target database and obtain documents containing relevant words from the Internet target data source library as the target data source, and at the same time obtain the target words and extended words of the target words from the target data source.

[0029] The present invention is further configured as follows: the data acquisition module also includes a neural network model construction unit, a target language model generation unit, a target sentence block generation unit, a key information generation unit, a keyword determination unit and a data source determination unit.

[0030] The construction unit of the neural network model is constructed by extracting data from a semantic vocabulary.

[0031] The target language model generation unit trains and adjusts the neural network model based on the keywords in the semantic vocabulary.

[0032] The labeled sentence block generating unit constructs a target sentence block based on the target language model.

[0033] The key information generating unit generates key information based on the multiple groups of target sentence blocks.

[0034] The keyword determination unit receives the sentence to be processed and obtains a related keyword dictionary in the semantic vocabulary to determine the keywords in the sentence to be processed.

[0035] The advantages of the present invention are: The present invention performs Meta-analysis based on artificial intelligence and can complete the retrieval of all databases in a very short time, thereby improving the efficiency of literature retrieval and increasing the number of literature samples in each Meta-analysis, thus ensuring the accuracy and authority of the analysis.

[0036] The present invention uses a pre-trained language model as a feature extraction tool for sentences to be processed, and adds rich underlying information such as part-of-speech features and dictionary features to expand the differentiation of words, making the difference between keywords and non-keywords in the sentences to be processed clearer, thereby more accurately obtaining the keywords in the sentences to be processed.

[0037] The present invention is based on the text generation method of AI-Chain, which realizes personalized writing services through the mutual coordination and cooperation of various AIs and humanized human-computer interaction, and solves the problems of lack of writing ideas and output results not meeting the requirements in the writing process using large models. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The invention discloses an intelligent writing assistant based on a meta-analysis system.

[0039] Figure 2 This is a diagram showing the internal components of the controller of the present invention.

[0040] Figure 3 This is a composition diagram of the data acquisition module of the present invention.

[0041] Figure 4 This is a diagram of the data processing module composition of the present invention.

[0042] Figure 5 This is a diagram showing the composition of the solution processing module of the present invention. DETAILED DESCRIPTION

[0043] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] It should be noted that, unless otherwise specified, all technical and scientific terms used in this application have the same meanings as commonly understood by ordinary technicians in the technical field to which this application belongs.

[0045] In the present invention, unless otherwise specified, the directions used, such as "up" and "down", usually refer to the directions shown in the drawings, or to the vertical, perpendicular or gravity directions; similarly, for ease of understanding and description, "left" and "right" usually refer to the left and right shown in the drawings; "inside" and "outside" refer to the inside and outside relative to the outline of each component itself, but the above-mentioned directions are not used to limit the present invention.

[0046] For example, see Figure 1-5 , the present invention provides the following technical solutions: The invention discloses an intelligent writing assistant based on a meta-analysis system, specifically, comprising a shell; characterized in that: a controller is arranged inside the shell; a display screen and an operation keyboard electrically connected to the controller are sequentially installed outside the shell; the controller is provided with: a data acquisition module, which is based on artificial intelligence to extract keywords of a writing topic and supplement the keywords; a meta-analysis module, which performs meta-analysis according to the supplemented keywords, obtains an initial document set, and performs topic selection evaluation and self-checking according to all the documents therein to obtain a final document set; a screening module, which screens all the documents in the final document set according to the screening module to obtain a reference document set; a data processing module, which is used to extract data, index and query the obtained reference document set; a writing plan generation module, which is used to process the information fragments processed by the data processing module to generate a writing plan and display it to a user; and a plan processing module, which is based on the text generation method of AI-Chain, and realizes personalized writing services through the mutual cooperation and collaboration of various AIs and humanized human-computer interaction.

[0047] Working principle of the first embodiment: Meta-analysis based on artificial intelligence can complete the retrieval of all databases in a very short time, improve the efficiency of literature retrieval, and increase the number of literature samples in each meta-analysis, ensuring the accuracy and authority of the analysis.

[0048] The text generation method based on AI-Chain realizes personalized writing services through the mutual coordination and cooperation of various AIs and humanized human-computer interaction, solving the problems of lack of writing ideas and output results that do not meet the requirements when using large models for writing.

[0049] For example 2, please refer to Figure 1-5 The second embodiment makes the following improvements on the basis of the first embodiment. Specifically, a networking module is further provided inside the controller; the networking module is connected to the external Internet through communication and is used for network retrieval of the client.

[0050] The data processing module includes a data extraction unit, an index establishment unit and a data query unit; the data extraction unit is used to integrate the reference set obtained by the screening module to extract information fragments that meet the specified content value standards; the index establishment unit is used to establish an index of keywords and information fragments that meet the specified content value standards; the data query unit is used to obtain the information fragments associated with the input keywords and the information fragments that meet the specified content value standards.

[0051] The solution processing module includes a large model writing unit, a large model polishing unit and a human-computer interaction unit; the large model writing unit is used to save various information that users think need to be left, and then this module is all handed over to the large language model for writing; the large model polishing unit is used to repeatedly polish and modify the writing content completed by the large model writing unit, so as to achieve the effect desired by the user; the human-computer interaction unit is used for users to put forward their desired polishing requirements during the polishing and modification process and issue instructions to the large model polishing unit, so as to modify and polish the writing content completed by the large model writing unit in real time.

[0052] The solution processing unit also includes a storage unit and an output unit; when the user presses the start writing button on the operating keyboard, the large model will write through the large model writing unit according to the various information given before, and the written article will be saved through the storage unit and output to the user through the output unit.

[0053] Working principle of the second embodiment: Based on the AI-Chain text generation method, the writing and polishing process uses various information generated during the writing preparation process and uses a large language model to write. The large model writing unit uses a large language model to write according to the various information that users think need to be left in the writing preparation process, and outputs the completed article to the user; in the large model polishing unit, the user needs to input the part that he thinks needs to be rewritten and polished again, and then input the direction of polishing that the user wants, and input these contents into the large language model. After the large language model polishes, the corresponding text is output to the user. Because the text written by the large model may not fully meet the requirements, or lack logic and coherence, the polishing module can be used to repeatedly polish and modify this part of the content to achieve the desired effect.

[0054] The screening module can actively screen the evidence collected from the database according to the user's requirements, avoiding the adverse effects of human errors on document screening. For a small number of articles that are difficult to screen, they can be left to the user for manual screening, realizing active retrieval and extraction of keywords in the literature, reducing the user's workload.

[0055] For example 3, please refer to Figure 1-5 , this third embodiment makes the following improvements on the basis of the second embodiment. Specifically, the data acquisition module includes a collection unit, a construction unit, a semantic analysis unit, a processing unit, and a retrieval unit; the collection unit is used to collect relevant words from the Internet target database; the construction module is used to construct a semantic vocabulary with the words obtained by the collection unit from the Internet target database; the semantic analysis module classifies the words in the constructed semantic vocabulary through semantic analysis; the processing module is used to determine the keywords in the sentence to be processed and determine the data source within a certain range; the retrieval module obtains the target document corresponding to the search term based on the data source determined by the screening term and outputs it.

[0056] The collection unit is used to collect related words in the Internet target database and obtain documents containing related words from the Internet target data source library as target data sources, and at the same time obtain target words and extended words of the target words from the target data source.

[0057] The data acquisition module also includes a neural network model construction unit, a target language model generation unit, a target sentence block generation unit, a key information generation unit, a keyword determination unit and a data source determination unit; the neural network model construction unit extracts data from the semantic vocabulary for construction; the target language model generation unit trains and adjusts the neural network model based on the keywords in the semantic vocabulary; the markup sentence block generation unit constructs the target sentence block based on the target language model; the key information generation unit generates key information based on multiple groups of target sentence blocks; the keyword determination unit receives the sentence to be processed and obtains the relevant keyword dictionary in the semantic vocabulary to determine the keywords in the sentence to be processed.

[0058] Working principle of the third embodiment: By using the pre-trained language model as a feature extraction tool for the sentences to be processed and adding rich underlying information such as part-of-speech features and dictionary features to expand the differentiation of words, the difference between keywords and non-keywords in the sentences to be processed is made clearer, so that the keywords in the sentences to be processed can be obtained more accurately.

[0059] When searching for a search term, it is equivalent to searching only in documents containing related terms, which improves the accuracy of the search results; at the same time, since the words in each category in the data acquisition module are words with the same semantics or association relationship, when searching based on the search term stored in the processing module, the search term is actually expanded. It is not simply searching with the search term, but searching with the search term and words with the same semantics or association relationship as the search term, that is, the search scope is expanded and the recall rate is improved; the improvement of the recall rate and precision rate means that the user does not need to search repeatedly, which greatly saves the user's search time.

[0060] Obviously, the above-described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0061] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0062] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0063] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0064] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent writing assistant based on a meta-analysis system, comprising a shell; characterized in that: A controller is arranged inside the housing; a display screen and an operation keyboard electrically connected to the controller are sequentially installed outside the housing; The controller is internally provided with: A data acquisition module, which extracts keywords of writing topics based on artificial intelligence and supplements the keywords; A META analysis module, wherein the META analysis module performs a Meta analysis based on the supplemented keywords to obtain an initial document set, and performs a topic evaluation and self-checking for duplicates based on all the documents therein to obtain a final document set; A screening module, wherein the screening module screens all the documents in the final document set to obtain a reference document set; A data processing module, which is used to extract, index and query data from the obtained reference set; A writing plan generation module, the writing generation module is used to process the information fragments processed by the data processing module to generate a writing plan and display it to the user; and The solution processing module is based on the text generation method of AI-Chain, and realizes personalized writing services through the mutual cooperation and collaboration of various AIs and humanized human-computer interaction.

2. The intelligent writing assistant based on the meta-analysis system according to claim 1, characterized in that: The controller is also provided with a networking module inside; the networking module is connected to the external Internet through communication and is used for network retrieval by the client.

3. The intelligent writing assistant based on the meta-analysis system according to claim 2, characterized in that: The data processing module includes a data extraction unit, an index establishment unit and a data query unit; The data extraction unit is used to integrate the reference set screened by the screening module to extract information fragments that meet the specified content value standards; The index building unit is used to build an index of keywords and the information segments that meet the specified content value standard; The data query unit is used to obtain information fragments associated with the input keywords and the information fragments that meet the specified content value standards.

4. The intelligent writing assistant based on the meta-analysis system according to claim 3, characterized in that: The solution processing module includes a large model writing unit, a large model polishing unit and a human-computer interaction unit; The large model writing unit is used to save various information that users think need to be left, and then all this module is handed over to the large language model for writing; The large model polishing unit is used to repeatedly polish and modify the writing content completed by the large model writing unit, so as to achieve the effect desired by the user; The human-computer interaction unit is used for the user to put forward desired polishing requirements during the polishing and modification process and issue instructions to the large model polishing unit to modify and polish the writing content completed by the large model writing unit in real time.

5. The intelligent writing assistant based on the meta-analysis system according to claim 4, characterized in that: The solution processing unit also includes a storage unit and an output unit; when the user presses the start writing button on the operating keyboard, the large model will write through the large model writing unit according to the various information given previously, and the written article will be saved through the storage unit and output to the user through the output unit.

6. The intelligent writing assistant based on the meta-analysis system according to claim 5, characterized in that: The data acquisition module includes a collection unit, a construction unit, a semantic analysis unit, a processing unit, and a retrieval unit; The acquisition unit is used to acquire relevant words in an Internet target database; The construction module is used to construct a semantic word library with the words acquired by the acquisition unit from the Internet target database; The semantic analysis module is to classify the words in the constructed semantic vocabulary through semantic analysis; The processing module is used to determine the keywords in the sentence to be processed and determine the data source within a certain range; The search module obtains and outputs target documents corresponding to the search terms based on the data source determined by the screening terms.

7. The intelligent writing assistant based on the meta-analysis system according to claim 6, characterized in that: The acquisition unit is used to acquire relevant words from the Internet target database and obtain documents containing relevant words from the Internet target data source library as target data sources, and simultaneously obtain target words and extended words of the target words from the target data source.

8. The intelligent writing assistant based on the meta-analysis system according to claim 7, characterized in that: The data acquisition module also includes a neural network model construction unit, a target language model generation unit, a target sentence block generation unit, a key information generation unit, a keyword determination unit, and a data source determination unit; The construction unit of the neural network model is constructed by extracting data from a semantic vocabulary; The target language model generation unit trains and adjusts the neural network model based on the keywords in the semantic vocabulary; The marked sentence chunk generating unit constructs a target sentence chunk based on the target language model; The key information generating unit generates key information based on the multiple groups of target sentence blocks; The keyword determination unit receives the sentence to be processed and obtains a related keyword dictionary in the semantic vocabulary to determine the keywords in the sentence to be processed.

Images