Auxiliary document automatic generation method, device, storage medium, and program product

Abstract

The disclosed embodiment discloses a method, device, storage medium, and program product for automatically generating auxiliary manuscripts. The method includes: collecting reference materials based on historical manuscripts and reference words; extracting a first word and phrase based on the reference materials; obtaining a first keyword in the reference materials based on the first word and phrase; obtaining manuscript keywords and manuscript materials based on the input second keyword and the first keyword; and generating an auxiliary manuscript based on the manuscript keywords and the manuscript materials. The method can avoid users from manually querying reference materials, saving user time, and intelligently generating auxiliary manuscripts with rich and comprehensive content by autonomously querying reference materials, obtaining manuscript keywords and manuscript materials.

Description

Technical Field

[0001] The present disclosure relates to the technical field of natural language processing, and in particular to a method, device, storage medium, and program product for automatically generating auxiliary documents. Background Art

[0002] When users write, they often need to refer to the content of historical documents or related materials. However, it is difficult for users to quickly find accurate information in the massive amount of information and historical documents. To solve this problem, document embedding methods are often used to write related content in the form of dialogue. This method can meet the writing needs of users to a certain extent, but it cannot quickly provide users with reference materials. Users need to find reference materials themselves and upload them to the conversation. It is difficult for users to comprehensively collect the required reference materials in this process, which makes the content generated by AI relatively one-sided. Summary of the invention

[0003] In view of this, the embodiments of the present disclosure provide a method, device, storage medium, and program product for automatically generating auxiliary documents, which can avoid users from manually querying reference materials, saving user time, and intelligently generate auxiliary documents with rich and comprehensive content by independently querying reference materials, obtaining document keywords and document materials.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for automatically generating an auxiliary document, which adopts the following technical solution:

[0005] Collect references based on historical manuscripts and reference words;

[0006] Extracting a first phrase according to the reference material;

[0007] Obtaining a first keyword in the reference material based on the first phrase;

[0008] Based on the input second keyword and the first keyword, obtaining manuscript keywords and manuscript materials;

[0009] An auxiliary document is generated based on the document keywords and the document material.

[0010] Optionally, extracting the first word or phrase according to the reference material includes:

[0011] Preprocessing the reference material to obtain a word sequence;

[0012] Perform bi-gram splitting on the word sequence to obtain a first word sentence.

[0013] Optionally, obtaining a first keyword in the reference material based on the first word or phrase includes:

[0014] Extracting a second word or sentence from the reference material based on the first word or sentence;

[0015] Determine a first weight of the second word in the reference material based on the TF-IDF algorithm;

[0016] A second word or phrase whose first weight is greater than a first threshold is selected as a first keyword of the reference material.

[0017] Optionally, obtaining a document keyword based on the input second keyword and the first keyword includes:

[0018] Obtaining a first correlation between the first keyword and the second keyword;

[0019] The document keyword is obtained based on the first relevance.

[0020] Optionally, obtaining the document keyword based on the first relevance includes:

[0021] If the first relevance is greater than a third threshold, taking the first keyword as the third keyword;

[0022] The second keyword and / or the randomly selected third keyword are used as the manuscript keyword.

[0023] Optionally, obtaining a manuscript material based on the input second keyword and the first keyword includes:

[0024] Determining a second weight of the manuscript keyword in the reference material and a third weight of the first keyword in the reference material;

[0025] Obtaining a second relevance of the reference material based on the second weight and the third weight;

[0026] The reference material whose second relevance is greater than a fourth threshold is selected as the manuscript material.

[0027] Optionally, generating an auxiliary manuscript based on the manuscript keywords and the manuscript material includes:

[0028] The manuscript keywords and the manuscript materials are input into the LLM model to obtain the auxiliary manuscript output by the LLM model.

[0029] In a second aspect, the embodiment of the present disclosure further provides an auxiliary document automatic generation system, which adopts the following technical solution:

[0030] A data collection module is used to collect reference materials based on historical manuscripts and reference words;

[0031] A word and sentence extraction module, used for extracting a first word and sentence according to the reference material;

[0032] A keyword acquisition module, used for acquiring a first keyword in the reference material based on the first word or phrase;

[0033] A material acquisition module, used for acquiring manuscript keywords and manuscript materials based on the input second keywords and the first keywords;

[0034] A document generation module is used to generate an auxiliary document based on the document keywords and the document materials.

[0035] In a third aspect, the embodiments of the present disclosure further provide a computer device, which adopts the following technical solution:

[0036] The computer device comprises:

[0037] at least one processor; and,

[0038] a memory communicatively connected to the at least one processor; wherein,

[0039] 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 so that the at least one processor can execute any of the above-mentioned auxiliary document automatic generation methods.

[0040] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute any of the above-mentioned auxiliary document automatic generation methods.

[0041] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, including a computer program / instruction, which implements the steps of any of the above methods when executed by a processor.

[0042] The auxiliary manuscript automatic generation method provided by the embodiment of the present disclosure can reflect the user's preferences and needs through the historical manuscripts of the user terminal and the input reference words, so as to collect relevant reference materials for the user independently, without the need for the user to query by himself, saving the user's precious time, and compared with the manual query method, the autonomous query method can collect more comprehensive reference materials, so that the content of the auxiliary manuscript finally generated is more comprehensive. In addition, the first keyword of the reference material can be quickly and accurately located through the first phrase, and the first keyword reflects the key information and core concepts of the reference material. Then, the first keyword and the second keyword input by the user are combined to obtain manuscript keywords and manuscript materials that can reflect the user's writing habits and writing needs, and then an auxiliary manuscript that fits the user's writing theme and purpose is generated to achieve personalized content customization.

[0043] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following preferred embodiments are specifically cited and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A flowchart of a method for automatically generating auxiliary documents provided by an embodiment of the present disclosure;

[0046] Figure 2 A schematic diagram of a process of constructing a dictionary provided in an embodiment of the present disclosure;

[0047] Figure 3 A schematic diagram of a process for obtaining manuscript keywords provided in an embodiment of the present disclosure;

[0048] Figure 4 A principle block diagram of the auxiliary document automatic generation system provided by an embodiment of the present disclosure;

[0049] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0050] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0051] It should be clear that the following embodiments of the present disclosure are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0052] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0053] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0054] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0055] Reference Figure 1 The present invention provides a method for automatically generating an auxiliary document, comprising the following steps:

[0056] S1: Collect reference materials based on historical manuscripts and reference words.

[0057] S2: Extracting a first word or phrase according to the reference material.

[0058] S3: Obtain a first keyword in the reference material based on the first sentence.

[0059] S4: Based on the input second keyword and first keyword, obtain document keywords and document materials.

[0060] S5: Generate auxiliary manuscripts based on manuscript keywords and manuscript materials.

[0061] The manuscript keywords and manuscript materials are input into the LLM model (Large Language Models) to obtain the auxiliary manuscript output by the LLM model. Among them, the LLM model is a deep learning model trained based on massive text data.

[0062] The auxiliary manuscript automatic generation method disclosed in the present invention can reflect the user's preferences and needs through the user's historical manuscripts and the reference words input by the user, and then provide the user with relevant reference materials. By extracting the first word and mapping the first keyword in the reference material, the key information of the reference material can be quickly located, and the core concept of the reference material can be captured more accurately. Then, through the first keyword and the second keyword input by the user, the manuscript keywords and manuscript materials are obtained, and then the auxiliary manuscript is generated. The key to using the second keyword is to determine that the generated manuscript keywords and manuscript materials are highly relevant to the user's required content, so that the auxiliary manuscript generated based on the manuscript keywords and manuscript materials can better fit the user's writing theme and purpose, realize personalized content customization, and improve the quality and usability of the manuscript.

[0063] Compared with the existing method that requires users to search for reference materials by themselves, this method only requires users to provide historical manuscripts and input reference words and second keywords according to their own needs, and then auxiliary manuscripts can be generated independently. Users can directly use the auxiliary manuscripts or modify them based on the auxiliary manuscripts, thereby helping users to quickly complete the writing of manuscripts, so as to avoid users getting lost and wasting time in the massive amount of information when searching for a large amount of information. Moreover, as time goes by, the number of historical manuscripts of users will increase, the number of reference words will also increase, and accordingly, the number of reference materials collected will also increase. Since a large amount of reference materials is more diverse and rich, the quality of the generated auxiliary manuscripts will be better, and the content will be more accurate, comprehensive and rich, meeting the personalized needs of users.

[0064] In summary, this method of automatically generating auxiliary manuscripts can provide users with more targeted writing services, reduce the time users spend searching and organizing information on their own, and thus improve writing efficiency and effectiveness.

[0065] In S1, a crawler method is used to crawl the Internet to capture documents, messages, webpage contents, etc. that are highly relevant to historical manuscripts and reference words as reference materials. There are multiple reference materials, which meet the needs of users in specific fields and satisfy the personal preferences of users. The collected reference materials are stored in the second database to form a database dedicated to the user's personal use. This construction method is simple and easy to operate, and has low maintenance costs. It only needs to continuously store new reference materials in the database. With the maintenance of the database, the content of the database will become richer and more comprehensive.

[0066] Reference Figure 2 The flowchart of constructing a dictionary is shown, in S2, extracting a first word or phrase according to the stored reference material, including the following steps:

[0067] S21: preprocess the reference material to obtain a word sequence;

[0068] S22: Perform bi-gram splitting on the word sequence to obtain the first word sentence.

[0069] In S21, special characters, punctuation marks, numbers, etc. in the reference material are removed to retain the actual word content in the text, and the reference material is segmented using a word segmentation tool or library to generate multiple initial word sequences. For example, spaces can be used to separate words in English.

[0070] Set a stop word list, which stores multiple stop words. Remove the stop words from the initial word sequence to get the final word sequence. Stop words are words that appear frequently but do not carry much semantic information, such as "the", "and", "is", etc.

[0071] In S22, the word sequence is segmented into two consecutive words to obtain word pairs. For example, for the word sequence ["natural", "language", "processing"], two word pairs "natural language" and "languageprocessing" can be generated.

[0072] The first occurrence frequency of word pairs in the reference materials is counted, and word pairs whose first occurrence frequency is greater than the first preset frequency threshold are selected for combination to obtain the second phrase. For example, the first occurrence frequencies of the two word pairs "China" and "People" are both greater than the first preset frequency threshold, and the second phrase obtained by combining the two is "China People". If there is no word pair whose first occurrence frequency is greater than the first preset frequency threshold, or the number of word pairs greater than the first preset frequency threshold is less than the preset number, the top k1 (referring to the first k1 word pairs with the highest first occurrence frequency) word pairs are selected for combination to obtain the second phrase.

[0073] The second occurrence frequency of the second word in the reference material is counted, and the second word whose second occurrence frequency is greater than the second preset frequency threshold is selected as the first word. Usually, the number of first words exceeds 1 million. However, in order to avoid special circumstances, if there is no second occurrence frequency of the second word greater than the second preset frequency threshold, the second words of the top k2 (referring to the second highest occurrence frequency of the first k2 words) are selected as the first word.

[0074] Furthermore, the first words and sentences can be stored in the first database to form a dictionary, and the setting of the dictionary is convenient for managing these first words and sentences. As the database is continuously updated, the dictionary is periodically updated. In addition, the dictionary also supports manual entry and adjustment.

[0075] Provide an implementation method to achieve obtaining the first keyword in the reference material based on the first phrase in S3:

[0076] In the reference material, extract the second phrase that is the same as the first phrase, use the TF-IDF algorithm to determine the first weight of the second phrase in the reference material, select the second phrase whose first weight is greater than the first threshold as the first keyword of the reference material, and mark the first keyword in the corresponding reference material for direct use in the subsequent S4; if the first weights of all second phrases in a reference material are not greater than the first threshold, temporarily delete the reference material, that is, abandon the reference material in this auxiliary manuscript generation link, and the reference material does not participate in the statistics and calculations of the subsequent S4. The first weight is represented by a number between 0 and 1.

[0077] Another possible implementation is provided to achieve obtaining the first keyword in the reference material based on the first phrase in S3:

[0078] In the reference material, extract the second phrase that is the same as the first phrase, use the TF-IDF algorithm to determine the first weight of the second phrase in the reference material, sort the first weights in descending order, select the second phrases corresponding to the first K first weights as the first keyword of the reference material, and mark the first keyword in the corresponding reference material.

[0079] Reference Figure 3 The flowchart of obtaining manuscript keywords is shown. In S4, the method for obtaining manuscript keywords includes the following steps:

[0080] S31: Obtaining a first correlation between the first keyword and the second keyword;

[0081] S32: Obtain document keywords based on the first relevance.

[0082] In S31, the number of reference materials containing both the first keyword and the second keyword is obtained, recorded as the first number; the number of reference materials containing only one of the first keyword and the second keyword is obtained, recorded as the second number; the ratio of the first number divided by the second number is used as the first correlation between the first keyword and the second keyword. For example, the first keyword includes A and B, the second keyword includes C and D, and there are 300 reference materials containing A, B, C, and D at the same time, that is, the first number is 200; there are 700 reference materials containing only A, 500 reference materials containing only B, 1000 reference materials containing only C, and 800 reference materials containing only D. 700, 500, 1000, and 800 are added together, and the result of the addition is 3000, which is the second number, and the first correlation is the ratio of 300 to 3000, that is, 0.1.

[0083] In S32, the first keyword whose first relevance is greater than the third threshold is used as the third keyword. If no first relevance is greater than the third threshold, the first keyword of top k3 (referring to the first k3 first relevance highest values) is selected as the third keyword. All the second keywords and the randomly selected third keywords can be used as manuscript keywords, or only the second keywords can be used as manuscript keywords, or only the randomly selected third keywords can be used as manuscript keywords.

[0084] In S4, the method for obtaining manuscript materials is as follows:

[0085] Based on word frequency statistics or TF-IDF algorithm, determine the second weight of the manuscript keyword in the reference material and the third weight of the first keyword in the reference material; obtain the second relevance of the reference material based on the second weight and the third weight; select the reference material with a second relevance greater than a fourth threshold as the manuscript material. The calculation formula of the second relevance is:

[0086] R z =r zi +r zj ;

[0087] In the formula, R z is the second relevance of the reference numbered z, where z is the reference number; r zi is the second weight of the manuscript keyword numbered i in the reference material numbered z, where i is the manuscript keyword number; r zj It is the third weight of the first keyword numbered j in the reference material numbered z, where j is the number of the first keyword.

[0088] Through the above method, we can accurately retrieve the manuscript keywords and manuscript materials that are highly relevant to user needs, and then use the LLM model to create the manuscript, and produce auxiliary manuscripts that conform to the user's writing habits more quickly.

[0089] Reference Figure 4 The present disclosure provides an auxiliary document automatic generation system, comprising:

[0090] The data collection module 101 is used to collect reference data based on historical manuscripts and reference words;

[0091] A word and sentence extraction module 102, used to extract a first word and sentence according to the reference material;

[0092] A keyword obtaining module 103, used to obtain a first keyword in the reference material based on the first word or phrase;

[0093] The material acquisition module 104 is used to obtain manuscript keywords and manuscript materials based on the input second keywords and first keywords;

[0094] The manuscript generation module 105 is used to generate auxiliary manuscripts based on manuscript keywords and manuscript materials.

[0095] The various variations and specific examples of the auxiliary document automatic generation method provided above are also applicable to the auxiliary document automatic generation system provided in the present disclosure. Through the above detailed description of the auxiliary document automatic generation method, those skilled in the art can clearly know the implementation method of the auxiliary document automatic generation system. For the sake of brevity of the specification, it will not be described in detail here.

[0096] The computer device according to the embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.

[0097] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the computer device to perform desired functions. In one embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory, so that the computer device performs all or part of the steps of the auxiliary document automatic generation method of each embodiment of the present disclosure.

[0098] Those skilled in the art should be able to understand that in order to solve the technical problem of how to obtain a good user experience, the present embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the protection scope of the present disclosure.

[0099] like Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure is shown, which is a schematic diagram of the structure of a computer device suitable for implementing the embodiment of the present disclosure. Figure 5 The computer device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0100] like Figure 5As shown, the computer device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the computer device are also stored. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0101] Typically, the following devices can be connected to the I / O interface: input devices such as sensors or visual information acquisition devices; output devices such as display screens; storage devices such as tapes, hard disks, etc.; and communication devices. The communication device can allow the computer device to communicate with other devices (such as edge computing devices) wirelessly or by wire to exchange data. Figure 5 A computer device having various devices is shown, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0102] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processor, all or part of the steps of the auxiliary document automatic generation method of the embodiment of the present disclosure are executed.

[0103] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0104] According to the computer-readable storage medium of the embodiment of the present disclosure, non-transitory computer-readable instructions are stored thereon. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the auxiliary document automatic generation method of each embodiment of the present disclosure are executed.

[0105] The above-mentioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (e.g., memory card) and media with built-in ROM (e.g., ROM box).

[0106] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0107] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0108] In the present disclosure, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0109] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0110] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0111] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0112] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0113] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for automatically generating auxiliary manuscripts, characterized in that: include: Collect references based on historical manuscripts and reference words; Extracting a first phrase according to the reference material; Obtaining a first keyword in the reference material based on the first phrase; Based on the input second keyword and the first keyword, obtaining manuscript keywords and manuscript materials; Generate an auxiliary manuscript based on the manuscript keywords and the manuscript material; Wherein, obtaining the manuscript keyword based on the input second keyword and the first keyword includes: Obtaining a first correlation between the first keyword and the second keyword; Obtaining the manuscript keyword based on the first relevance; Wherein, obtaining a first correlation between the first keyword and the second keyword includes: Obtain the number of reference materials containing both the first keyword and the second keyword, recorded as the first number; obtain the number of reference materials containing only one of the first keyword and the second keyword, recorded as the second number; and use the ratio of the first number divided by the second number as the first correlation between the first keyword and the second keyword; Wherein, obtaining the manuscript material based on the input second keyword and the first keyword includes: Determining a second weight of the manuscript keyword in the reference material and a third weight of the first keyword in the reference material; Obtaining a second relevance of the reference material based on the second weight and the third weight; The reference material whose second relevance is greater than a fourth threshold is selected as the manuscript material.

2. The method for automatically generating auxiliary manuscripts according to claim 1, characterized in that: The extracting the first phrase according to the reference material comprises: Preprocessing the reference material to obtain a word sequence; The word sequence is split into bi-grams to obtain a first word sentence.

3. The method for automatically generating auxiliary manuscripts according to claim 1, characterized in that: The obtaining of a first keyword in the reference material based on the first word or phrase includes: Extracting a second word or sentence from the reference material based on the first word or sentence; Determine a first weight of the second word in the reference material based on the TF-IDF algorithm; A second word or phrase whose first weight is greater than a first threshold is selected as a first keyword of the reference material.

4. The method for automatically generating auxiliary manuscripts according to claim 1, characterized in that: The obtaining the manuscript keyword based on the first relevance includes: If the first relevance is greater than a third threshold, taking the first keyword as the third keyword; The second keyword and / or the randomly selected third keyword are used as the manuscript keyword.

5. The method for automatically generating auxiliary manuscripts according to claim 1, characterized in that: The generating of the auxiliary manuscript based on the manuscript keywords and the manuscript material comprises: The manuscript keywords and the manuscript materials are input into the LLM model to obtain the auxiliary manuscript output by the LLM model.

6. A computer device, characterized in that: The computer device comprises: at least one processor; and, 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 so that the at least one processor can execute the auxiliary document automatic generation method described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the auxiliary document automatic generation method described in any one of claims 1-5.

8. A computer program product comprising computer instructions, characterized in that: When the computer instruction is executed by a processor, the steps of the method described in any one of claims 1 to 5 are implemented.

Images