Historical figure knowledge proofreading method and system, storage medium and electronic device

Abstract

The application provides a historical figure knowledge proofreading method and system, a storage medium and an electronic device, comprising: constructing a historical figure first knowledge database and a historical figure second knowledge database; obtaining a text to be proofread, and performing assertion detection on the text to be proofread to obtain an assertion detection result; obtaining an identification field in the text to be proofread based on the assertion detection result; searching for a corresponding historical figure in the historical figure first knowledge database according to the identification field, and searching for relevant reference information of the historical figure in the historical figure second knowledge database; and obtaining a proofreading result of the historical figure knowledge based on the historical figure, the relevant reference information and the text to be proofread. The application constructs the historical figure knowledge database offline, and in the process of online proofreading, the historical figure is determined through the identification field first, and then the corresponding relevant reference information is searched, effectively solving the problem of irrelevant and redundant search information, and improving the proofreading efficiency and accuracy.

Description

Technical Field

[0001] The present application belongs to the technical field of deep learning, and in particular relates to a method, system, storage medium and electronic device for proofreading knowledge of historical figures. Background Art

[0002] Proofreading knowledge about historical figures is a key link in ensuring the accuracy and credibility of historical information. Its importance is mainly reflected in two aspects: first, through multi-source data comparison (such as official history, archaeological discoveries, and academic papers) and logical verification (timeline conflict detection, character relationship contradiction analysis), it effectively corrects the distortion of historical figure information caused by errors in document copying, subjective interpretation bias, or modern misinterpretation, providing a reliable basis for academic research and cultural communication; second, in the digital age, automated proofreading technology can efficiently process massive amounts of historical data, prevent the spread of erroneous information in the Internet environment, and maintain the objectivity of historical narratives. For example, it can automatically identify and correct common sense errors such as "Zhang Fei was a civil servant in the Three Kingdoms period" to avoid misleading public cognition.

[0003] The application areas of historical figure knowledge proofreading span a wide range of academic, educational, and cultural sectors. In academia, it helps researchers quickly verify key information such as birth and death dates and official positions in digitized ancient texts, improving textual research efficiency. In education, it ensures the accuracy of historical figure descriptions in textbooks and museum commentaries. In cultural communication, it provides fact-checking services for film, television, and historical novels, balancing artistic creativity with historical facts. In digital humanities projects, it serves as a fundamental step in building high-precision historical knowledge graphs. For example, by resolving discrepancies in different texts regarding the number of Zheng He's voyages to the West, reliable standardized data can be generated. These applications collectively promote the scientific inheritance and innovative use of historical knowledge. When proofreading historical figure knowledge, the retrieved content is often inconsistent, containing a large amount of redundant and irrelevant information, and lacks reasoning capabilities. Therefore, how to efficiently and accurately proofread historical figure knowledge is a technical challenge that those skilled in the art are urgently seeking to address. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, storage medium and electronic device for proofreading knowledge of historical figures, which can effectively avoid redundant and irrelevant retrieval information and proofread the knowledge of historical figures efficiently and accurately.

[0005] In a first aspect, the present application provides a method for proofreading knowledge about historical figures, the method comprising:

[0006] Constructing a primary knowledge database of historical figures and a secondary knowledge database of historical figures;

[0007] Acquire a text to be proofread, and perform assertion detection on the text to be proofread to obtain an assertion detection result;

[0008] acquire an identification field in the text to be proofread based on the assertion detection result;

[0009] retrieve a corresponding historical figure in the historical figure first knowledge database and relevant reference information of the historical figure in the historical figure second knowledge database according to the identification field;

[0010] acquire a proofreading result of historical figure knowledge based on the historical figure, the relevant reference information and the text to be proofread.

[0011] In an implementation form of the first aspect, the constructing the historical figure first knowledge database and the historical figure second knowledge database comprises:

[0012] acquiring historical figure article data;

[0013] extracting entities and relationships from the historical figure article data as data fields, and extracting assertion expressions as data expressions;

[0014] storing the historical figure article data and the data fields as the historical figure first knowledge database;

[0015] converting the data expressions into data expression vectors, and storing the data expression vectors and the historical figure article data to which the data expressions belong as the historical figure second knowledge database.

[0016] In an implementation form of the first aspect, the acquiring the identification field in the text to be proofread based on the assertion detection result comprises:

[0017] when the text to be proofread includes an assertion expression, the assertion detection result is passed, and an identification field in the text to be proofread is extracted to proofread the text to be proofread based on historical figure knowledge;

[0018] when the text to be proofread does not include an assertion expression, the assertion detection result is failed, and no identification field in the text to be proofread is extracted.

[0019] In an implementation form of the first aspect, the acquiring the identification field in the text to be proofread comprises:

[0020] extracting entities in the text to be proofread as identification entity fields;

[0021] extracting relationships in the text to be proofread as identification relationship fields;

[0022] extracting assertion expressions in the text to be proofread as identification assertion fields;

[0023] The identification entity field, the identification relationship field, and the identification assertion field are taken as the identification field.

[0024] In an implementation form of the first aspect, the corresponding historical figure is retrieved online in the historical figure first knowledge database according to the identification field.

[0025] The historical figure entity is obtained based on the identification entity field and the identification relationship field.

[0026] Knowledge retrieval is performed in the historical figure first knowledge database based on the historical figure entity to obtain the corresponding historical figure.

[0027] In an implementation form of the first aspect, the related reference information of the historical figure is retrieved online in the historical figure second knowledge database according to the identification field.

[0028] The identification assertion field and the data expression vector are subjected to semantic similarity detection to retrieve an assertion expression related to the historical figure in the historical figure second knowledge database.

[0029] The retrieved assertion expression and the historical figure article data are subjected to semantic consistency detection to take an assertion expression with a high confidence score as the related reference information.

[0030] In an implementation form of the first aspect, the proofreading result of historical figure knowledge is obtained based on the historical figure, the related reference information, and the text to be proofread.

[0031] The identification field, the related reference information, and the text to be proofread are input into a preset proofreading prompt, so that a large language model performs proofreading on the text to be proofread based on the proofreading prompt to obtain the proofreading result of historical figure knowledge.

[0032] In a second aspect, the present application provides a proofreading system of historical figure knowledge, the system comprising:

[0033] A construction module is configured to construct a historical figure first knowledge database and a historical figure second knowledge database.

[0034] An obtaining module is configured to obtain a text to be proofread and perform assertion detection on the text to be proofread to obtain an assertion detection result.

[0035] A second obtaining module is configured to obtain an identification field in the text to be proofread based on the assertion detection result.

[0036] an online retrieval module, configured to retrieve a corresponding historical figure from the historical figure first knowledge database and retrieve relevant reference information of the historical figure from the historical figure second knowledge database according to the identification field;

[0037] a proofreading module, configured to obtain a proofreading result of historical figure knowledge based on the historical figure, the relevant reference information and the text to be proofread.

[0038] In a third aspect, the present application provides an electronic device, comprising a processor and a memory;

[0039] the memory is configured to store a computer program;

[0040] the processor is configured to execute the computer program stored in the memory, so that the electronic device executes the proofreading method of historical figure knowledge.

[0041] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by an electronic device to implement the proofreading method of historical figure knowledge.

[0042] As described above, the proofreading method of historical figure knowledge, system, storage medium and electronic device provided by the present application have the following beneficial effects:

[0043] (1) The present application can utilize the context semantic information of historical figure article data, has semantic understanding and reasoning ability, and effectively improves the accuracy of proofreading.

[0044] (2) The present application does not completely rely on relation extraction model, but realizes accurate proofreading based on multi-element database, and has strong robustness.

[0045] (3) The present application can determine the relevant historical figure and reference information based on the identification field, and proofread based on the key information, effectively excluding the interference of irrelevant content on the proofreading judgment. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 Fig. 1 shows a flowchart of the proofreading method of historical figure knowledge according to an embodiment of the present application.

[0047] Figure 2 Fig. 2 shows a flowchart of constructing a historical figure knowledge database according to an embodiment of the present application.

[0048] Figure 3 Fig. 3 shows a flowchart of retrieving a corresponding historical figure from a historical figure knowledge database according to an identification field according to an embodiment of the present application.

[0049] Figure 4A flowchart showing a process of retrieving relevant reference information of a historical figure from a historical figure knowledge database according to an identification field in an embodiment.

[0050] Figure 5 A structural diagram showing a proofreading system of historical figure knowledge of the present application in an embodiment.

[0051] Figure 6 A structural diagram showing an electronic device of the present application in an embodiment. DETAILED DESCRIPTION

[0052] The implementation manner of the present application is described below through specific examples, and other advantages and effects of the present application can be easily understood by those skilled in the art from the disclosure of the present specification. The present application can also be implemented or applied through other different specific implementation manners, and various modifications or changes can be made to the details in the present specification based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0053] It should be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present application, and only the components related to the present application are shown in the diagrams, not the number, shape and size of the components when actually implemented. The shapes, number and proportions of the components when actually implemented can be arbitrarily changed, and the layout pattern of the components can be more complex.

[0054] The proofreading of historical figure knowledge is a process of ensuring the accuracy and consistency of the information of the life and deeds of a historical figure through multi-source authoritative data comparison and logical verification. The traditional historical figure information proofreading scheme is a logic of extracting triples and matching rules. Specifically, a relationship extraction model is first used to extract the relationship in the text, such as "Li Bai-Character-Tai Bai", and then it is queried whether the relationship is established in the knowledge base. There are two problems with this approach: first, the hard rule proofreading logic is complex, the development and maintenance cost is high, and it cannot utilize the context semantic information, does not have semantic understanding and reasoning ability, and is prone to false positives; second, the effect of the extraction model is highly dependent, and the judgment of the relationship in the text completely depends on the result of the extraction model. Once the extraction is wrong, the final result of the system is definitely wrong, and the robustness is extremely poor. In addition, the recent scheme is a proofreading method based on a large model and a knowledge base, and the retrieval method is mainly based on an embedding model, and the most relevant text knowledge is retrieved according to the semantic similarity of the text. The problem with this retrieval method is that the retrieved content is uneven, and irrelevant content will greatly interfere with the judgment of the large model.

[0055] In order to at least solve the above-mentioned technical problems, the present application provides a proofreading method, system, storage medium and electronic device for historical figure knowledge, which can build a historical figure knowledge database offline, extract and integrate historical figure knowledge, and in the process of online proofreading, first determine the historical figure through the identification field, and then retrieve the relevant reference information corresponding to the historical figure, effectively solving the problem of redundant and irrelevant retrieved information, and improving proofreading efficiency and accuracy.

[0056] The technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings in the embodiments of the present application.

[0057] Figure 1 The flowchart of the proofreading method of the historical figure knowledge provided by the embodiment of the present application is shown. Figure 1 As shown, the method for proofreading knowledge of historical figures includes steps S1 to S5.

[0058] Step S1: Construct a first knowledge database of historical figures and a second knowledge database of historical figures.

[0059] This application organizes the knowledge related to historical figures, performs knowledge cleaning, knowledge extraction and knowledge integration to build a historical figure knowledge database offline. Figure 2 The flowchart of the proofreading method of the historical figure knowledge provided by the embodiment of the present application is shown. Figure 2 As shown, building a historical figure knowledge database includes steps S11 to S14.

[0060] Step S11: Obtain historical figure article data.

[0061] Historical figure article data refers to structured or unstructured textual information centered around historical figures, typically encompassing key elements such as the figure's life story, deeds, historical context, and social relationships. This data can be sourced from a variety of sources, including ancient texts, academic papers, biographies, digital archives, and online encyclopedias. In some embodiments, historical figure article data can be obtained from highly reliable data sources, such as the Cihai (Encyclopedia of Chinese), Dabaike (Encyclopedia of Encyclopedias), or other open-source knowledge bases.

[0062] Step S12: extracting entities and relationships from the historical figure article data as data fields, and extracting assertion expressions as data expressions.

[0063] An entity refers to an objective object or concept in a text that has independent meaning and can be explicitly referred to, usually including specific or abstract elements such as people, places, organizations, times, and numbers. In the historical figure knowledge system, entities are the basic nodes that constitute the information network, such as "Qin Shi Huang" "AD 221" "Qin Dynasty", and their core features include uniqueness (distinguished by unique identifiers), classification (classified according to predefined categories), and attribute association (such as the birth and death years and place of birth of a person entity). In some embodiments, entities can be extracted from historical figure article data by an entity extraction model. For example, the entity extraction model extracts the person entities "Li Bai" and "Du Fu" and the location entity "Chang'an" from "Li Bai and Du Fu met in Chang'an".

[0064] In some embodiments, relationships can be extracted from historical figure article data by a relationship extraction model. Relationships describe the semantic association or interaction between entities, embodied in a "subject-predicate-object" triple structure. In historical figure analysis, relationships can be divided into three categories: static attributes (such as "Ying Zheng is the First Emperor of Qin"), dynamic events (such as "Yue Fei led the Yue Clan Army"), and abstract connections (such as "Confucius influenced Confucianism").

[0065] In some embodiments, assertions can be extracted from historical figure article data by an assertion extraction model. An assertion refers to a statement in a text that explicitly expresses a certain judgment or claim, usually containing strong positive or negative language (such as "must" "never"), used to convey opinions or conclusions that cannot be doubted. Such expressions have three core attributes: high certainty (such as "the imperial examination system began in the Sui Dynasty"), verifiability (can be falsified by historical materials), and structural features (often accompanied by data, references, and other evidence to support).

[0066] Step S13, storing the historical figure article data and the data field as the historical figure first knowledge database.

[0067] In some embodiments, historical figure article data and data fields are converted to json format and stored in an Elasticsearch database as the historical figure first knowledge database. That is, the historical figure first knowledge database includes historical figure article data in json format, and should include entities, relationship triples, and assertions. In addition, the json format of the assertion is actually also stored in the historical figure first knowledge database.

[0068] Step S14, converting the data expression into a data expression vector, and storing the data expression vector and the historical figure article data to which the data expression belongs as the historical figure second knowledge database.

[0069] In some embodiments, the data representation is embedded, thereby converting the data representation into a continuous data representation vector, which enables mathematical calculations and similarity comparisons in a high-dimensional space by capturing the semantic or feature associations between the data. After obtaining the data representation vector, the data representation vector is stored in the Milvs database, which serves as the second knowledge database of the historical figures. At the same time, the json to which the data representation vector belongs, i.e., the historical figure article data, is recorded. Among them, the Milvus library can achieve semantic generalization, and can cope with changes and expansions at the semantic level to a certain extent, ensuring effective knowledge proofreading under different semantic expressions.

[0070] It should be noted that when forming the first knowledge database of historical figures and the second knowledge database of historical figures, the knowledge data finally stored in the database needs to be manually reviewed by experts to ensure the accuracy of the knowledge, and then form the historical figure knowledge database.

[0071] Step S2: Obtain the text to be proofread, and perform assertion detection on the text to be proofread to obtain an assertion detection result.

[0072] Step S3: Obtain an identification field in the text to be proofread based on the assertion detection result.

[0073] In some embodiments, the input sources of the text to be proofread can include various types such as user-generated historical texts, web scraped content, academic document fragments, etc. Such texts often contain errors in historical knowledge, such as misplaced relationships between characters, incorrect birth and death dates, etc.

[0074] In some embodiments, after obtaining the text to be proofread, assertion detection is performed on the text to determine whether to proofread knowledge about historical figures. For example, assertion detection can be performed using the BERT model. The BERT (Bidirectional Encoder Representations from Transformers) model, through a deep bidirectional attention mechanism, effectively captures the contextual dependencies and deterministic characteristics of assertive statements in text, enabling high-precision assertion detection. Specifically, the BERT model converts the input text to be proofread (e.g., "The imperial examination system must have begun in the Sui Dynasty") into context-sensitive word vectors. Using a fine-tuned classification head, it identifies assertive words (e.g., "must have") and their semantic strength. It also combines the semantic logic of the entire sentence to determine the degree of certainty (e.g., classifying it as "absolute assertion" or "speculative statement").

[0075] Further, the obtaining of the identification field in the text to be proofread based on the assertion detection result comprises: when the text to be proofread includes an assertion expression, the assertion detection result is passed, and the identification field in the text to be proofread is extracted to proofread the historical figure knowledge of the text to be proofread; when the text to be proofread does not include an assertion expression, the assertion detection result is failed, and the identification field in the text to be proofread is not extracted.

[0076] Further, when the assertion detection result is passed, the identification field in the text to be proofread is extracted, comprising: extracting an entity in the text to be proofread as an identification entity field; extracting a relationship in the text to be proofread as an identification relationship field; extracting an assertion expression in the text to be proofread as an identification assertion field; and taking the identification entity field, the identification relationship field and the identification assertion field as the identification field.

[0077] Step S4: searching for a corresponding historical figure in the historical figure first knowledge database and searching for relevant reference information of the historical figure in the historical figure second knowledge database according to the identification field.

[0078] In some embodiments, the historical figure first knowledge database is searched according to the identification field, and then relevant knowledge is proofread. Figure 3 A flowchart of a historical figure knowledge proofreading method provided by an embodiment of the present application is shown in FIG. 1. Figure 3 As shown in FIG. 1, searching for a corresponding historical figure in the historical figure knowledge database according to the identification field comprises steps S41 and S42.

[0079] Step S41: obtaining a figure entity based on the identification entity field and the identification relationship field.

[0080] Step S42: performing knowledge search in the historical figure first knowledge database based on the figure entity to obtain a corresponding historical figure.

[0081] In some embodiments, figure entities involved in the identification entity field and the identification relationship field can be extracted, and knowledge search is performed in the historical figure first knowledge database based on the obtained figure entities to exclude irrelevant figures, so as to obtain relevant historical figures. For example, figure entities such as "reporter Li" "Li Bai" "Professor Xu" and "Du Fu" can be extracted from the identification entity field and the identification relationship field, and "Li Bai" and "Du Fu" are obtained as historical figures based on the knowledge search in the historical figure first knowledge database based on the above figure entities.

[0082] In some embodiments, after obtaining the historical figure, the application retrieves relevant reference information of the historical figure in the historical figure second knowledge database online, so as to proofread the text to be proofread. Figure 4 A flowchart of a proofreading method of historical figure knowledge provided by an embodiment of the application is shown. As shown in Figure 4 Retrieving relevant reference information of the historical figure in the historical figure second knowledge database according to the identification field includes steps S43 and S44.

[0083] Step S43, performing semantic similarity detection on the identification assertion field and the data expression vector to retrieve an assertion expression related to the historical figure in the historical figure second knowledge database.

[0084] Semantic similarity detection is to quantify the semantic closeness between two pieces of text by calculating the spatial distance (such as cosine similarity or Euclidean distance) between text vectors, and the core is to break through the surface lexical difference to capture the deep meaning association. In some embodiments, the BERT model can be used to convert the identification assertion field into a query vector, and the cosine similarity between the query vector and the data expression vector stored in the historical figure second knowledge database is calculated, and the assertion expression related to the historical figure is obtained according to the cosine similarity.

[0085] In some embodiments, the assertion expression related to the historical figure can be retrieved by threshold judgment. That is, when the cosine similarity between a data expression vector and the vector representation converted from the identification assertion field exceeds a set threshold, the data expression vector is considered as an assertion expression related to the historical figure.

[0086] Step S44, performing semantic consistency detection on the retrieved assertion expression and the historical figure article data to obtain an assertion expression with a high confidence score as the relevant reference information.

[0087] In some embodiments, the retrieved assertion expression in the historical figure second knowledge database and the historical figure article data can be subjected to time conflict detection, logical contradiction analysis and other detection, such as judging whether the retrieved assertion expression is supported by multiple historical figure article data, i.e. the matching degree with the historical figure article data, so as to calculate the confidence score, and the assertion expression with a high confidence score is taken as the relevant reference information.

[0088] Step S5, obtaining a proofreading result of historical figure knowledge based on the historical figure, the relevant reference information and the text to be proofread.

[0089] After obtaining the historical figures and related reference information in the text to be proofread, the historical figures, the related reference information and the text to be proofread can be input into a preset proofreading prompt, so that a large language model performs proofreading on the text to be proofread based on the proofreading prompt, and obtains a proofreading result of historical figure knowledge.

[0090] A large language model (LLM) refers to a Transformer architecture model containing billions (or more) of parameters. Its large parameter size enables it to learn complex patterns and semantic relationships in massive amounts of text data, thereby having strong semantic understanding and reasoning capabilities. For example, when processing natural language text, it can understand the logical relationships between words and sentences, accurately capture the meaning of the context, and then perform in-depth analysis and processing on the text content. A large language model is essentially a generative model. When given a paragraph as input, it generates a piece of text based on the learned knowledge and patterns. However, without reference information input, the content directly generated by the large language model may not be very accurate. This is because its generation result mainly depends on its own prior knowledge, which may be affected by the limitations or ambiguity of the training data. For example, in some problems involving specific fields or time-sensitive issues, the model's own memory may not be able to provide accurate answers.

[0091] Therefore, in order to reduce the occurrence of knowledge hallucination of the large language model and efficiently and accurately proofread historical figure knowledge, the present application uses retrieval enhancement generation technology to retrieve relevant reference information according to the input text to be proofread, and then inputs the retrieved historical figures, relevant reference information and text to be proofread into the preset proofreading prompt of the large language model, so that the large language model can infer a proofreading result that is more consistent with the context based on the determined historical figures and relevant reference information, effectively improve the accuracy of the answer, and prevent the occurrence of knowledge hallucination. In addition, since the relevant reference information and the historical figures are closely related, even if the text to be proofread has some ambiguity, non-standard language expression or is interfered by a certain degree of noise, as long as the historical figure knowledge mentioned is consistent with the content of the relevant reference information, it can be proofread, thereby improving the robustness and anti-interference ability of the model.

[0092] The protection scope of the historical figure knowledge proofreading method described in the embodiments of the present application is not limited to the execution order of the steps listed in the embodiments. Any scheme realized by adding, replacing or replacing steps of the prior art according to the principles of the present application is included in the protection scope of the present application.

[0093] The historical figure knowledge proofreading system can implement the historical figure knowledge proofreading method provided in the present application, but the implementation device of the historical figure knowledge proofreading system provided in the present application includes but is not limited to the structure of the historical figure knowledge proofreading system enumerated in the present embodiment, and any structure modification and replacement of the prior art made according to the principle of the present application are included in the protection scope of the present application.

[0094] As shown in Figure 5 In an embodiment, the historical figure knowledge proofreading system provided in the present application includes a construction module 41, an acquisition module 42, a second acquisition module 43, an online retrieval module 44 and a proofreading module 45.

[0095] The construction module 41 is configured to construct a historical figure first knowledge database and a historical figure second knowledge database.

[0096] The acquisition module 42 is configured to acquire a text to be proofread, and perform assertion detection on the text to be proofread to obtain an assertion detection result.

[0097] The second acquisition module 43 is configured to acquire an identification field in the text to be proofread based on the assertion detection result.

[0098] The online retrieval module 44 is configured to perform online retrieval of a corresponding historical figure in the historical figure first knowledge database according to the identification field, and perform online retrieval of relevant reference information of the historical figure in the historical figure second knowledge database.

[0099] The proofreading module 45 is configured to acquire a historical figure knowledge proofreading result based on the historical figure, the relevant reference information and the text to be proofread.

[0100] The construction module 41, the acquisition module 42, the second acquisition module 43, the online retrieval module 44 and the proofreading module 45 correspond to the steps of the historical figure knowledge proofreading method in a one-to-one manner, and thus will not be described here.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the modules / units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of modules or units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the modules / units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or modules / units, and can be electrical, mechanical or in other forms.

[0102] The modules / units described as separated components may or may not be physically separated, and the components shown as modules / units may or may not be physical modules, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the modules / units may be selected according to actual needs to achieve the purposes of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated in one processing module, or may be physically separated, or two or more modules / units may be integrated in one module / unit.

[0103] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0104] The embodiments of the present application also provide a computer readable storage medium. Those of ordinary skill in the art can understand that all or part of the steps of the methods described above can be completed by programs instructing a processor, and the programs can be stored in a computer readable storage medium, which is a non-transitory medium, such as a random access memory, a read only memory, a flash memory, a hard disk, a solid state disk, a magnetic tape, a floppy disk, an optical disc and any combination thereof. The storage medium described above can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid state disk (SSD)) etc.

[0105] The embodiments of the present application also provide an electronic device. The electronic device includes a processor and a memory.

[0106] The memory is configured to store a computer program.

[0107] The memory includes: ROM, RAM, disk, U disk, memory card or optical disc and various media that can store program codes.

[0108] The processor is connected with the memory, and is used for executing the computer program stored in the memory, so that the electronic device executes the above-mentioned historical figure knowledge proofreading method.

[0109] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP) and the like; and can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0110] As shown in Figure 6 The electronic device of the present application is in the form of a general-purpose computing device. The components of the electronic device can include, but are not limited to, one or more processors or processing units 51, a memory 52, and a bus 53 connecting different system components, including the memory 52 and the processing unit 51.

[0111] The bus 53 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an industry standard architecture (ISA) bus, a microchannel architecture (MAC) bus, an enhanced ISA bus, a video electronics standards association (VESA) local bus, and a peripheral component interconnect (PCI) bus.

[0112] The electronic device typically includes a variety of computer system readable media. These media can be any available media that is accessible by the electronic device and includes both volatile and non-volatile media, removable and non-removable media.

[0113] The memory 52 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 521 and / or cache memory 522. The electronic device can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 523 can be used for reading from and writing to non-removable, non-volatile magnetic media (e.g., a "hard drive").Figure 6 not shown, is typically referred to as a "hard disk drive"). While Figure 6 not shown, can be provided for reading from or writing to a removable nonvolatile magnetic disk (e.g., a "floppy disk"), and can also be provided for reading from or writing to a removable nonvolatile optical disk such as a CD-ROM or other optical media. Each of these drives can be connected to the bus 53 by one or more drive interfaces. The memory 52 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.

[0114] Program / utility 524 having a set (at least one) of program modules 5241 can be stored in memory 52 by way of example, and not limiting, including an operating system, one or more application programs, other program modules, and program data, each of which

[0115] The electronic device can also communicate with one or more external devices such as a keyboard or a pointing device, a display, etc. through I / O interface 54 and with one or more devices that enable a user to interact with the electronic device and / or one or more devices that enable the electronic device to communicate with one or more other computing devices. Such communication can be through the I / O interface 54. Furthermore, the electronic device can communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or the Internet) through network adapter 55. As Figure 6 illustrated, network adapter 55 communicates with the other components of the electronic device through bus 53. It should be understood that although not shown, other hardware and / or software components could be used in conjunction with the electronic device. These components, which are well known in the art, include, but are not limited to, a microcode, a device driver, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0116] The foregoing embodiments serve merely as illustration of the principles of the application and the efficacy thereof, and are not intended to limit the application in any way. Any modifications or changes which do not depart from the spirit and scope of the application are intended to be included. Accordingly, all equivalent modifications or changes are intended to be included within the scope of the application as defined by the following claims.

Claims

1. A method for proofreading knowledge about historical figures, characterized in that: The method comprises: Build a knowledge database of historical figures; Obtaining a text to be proofread and an identification field in the text to be proofread; online searching the historical figure and related reference information in the historical figure knowledge database according to the identification field; Acquire a proofreading result of the historical figure knowledge based on the historical figure, the relevant reference information and the text to be proofread; and After obtaining the text to be proofread, the method includes: Performing assertion detection on the text to be proofread to determine whether to proofread the historical figure knowledge; When the text to be proofread includes assertions, proofreading the text for historical figures; When the text to be proofread does not include an assertion statement, the text to be proofread is not proofread for knowledge of historical figures; wherein the assertion statement is a statement in the text to be proofread that clearly expresses a deterministic judgment or claim.

2. The method for proofreading knowledge of historical figures according to claim 1, characterized in that: Building a historical figure knowledge database includes: Get data on articles about historical figures; Extracting entities and relationships from the historical figure article data as data fields, and extracting assertion expressions as data expressions; Storing the historical figure article data and the data fields as a first knowledge database; Converting the data representation into a data representation vector, and storing the data representation vector and the historical figure article data to which the data representation belongs as a second knowledge database; The first knowledge database and the second knowledge database are used as the historical figure knowledge database.

3. The method for proofreading knowledge of historical figures according to claim 2, characterized in that: Obtaining the identification field in the text to be proofread includes: Extracting entities from the text to be proofread as identifying entity fields; Extracting the relationship in the text to be proofread as an identification relationship field; Extracting an assertion statement in the text to be proofread as an identification assertion field; The identification entity field, the identification relationship field and the identification assertion field are used as the identification field.

4. The method for proofreading knowledge of historical figures according to claim 3, characterized in that: Retrieving a corresponding historical figure in the historical figure knowledge database according to the identification field includes: Acquire a person entity based on the identification entity field and the identification relationship field; A knowledge search is performed in the first knowledge database based on the character entity to obtain a corresponding historical character.

5. The method for proofreading knowledge of historical figures according to claim 3, characterized in that: Retrieving the relevant reference information of the historical figure in the historical figure knowledge database according to the identification field includes: Performing semantic similarity detection on the identification assertion field and the data expression vector to retrieve assertion expressions related to the historical figure in the second knowledge database; A semantic consistency check is performed on the retrieved assertion expressions and the historical figure article data, so that the assertion expressions with high confidence scores are used as the relevant reference information.

6. The method for proofreading knowledge of historical figures according to claim 1, characterized in that: The proofreading results of the historical figure knowledge obtained based on the historical figure, the relevant reference information and the text to be proofread include: The identification field, the relevant reference information and the text to be proofread are input into a preset proofreading prompt, so that the large language model proofreads the text to be proofread based on the proofreading prompt to obtain a proofreading result of historical figure knowledge.

7. A proofreading system for historical figure knowledge, characterized in that: The system comprises: Construction module, used to build a historical figure knowledge database; An acquisition module, configured to acquire a text to be proofread and an identification field in the text to be proofread; An online search module, configured to search online for corresponding historical figures and related reference information in the historical figure knowledge database according to the identification field; a proofreading module, configured to obtain a proofreading result of the historical figure knowledge based on the historical figure, the relevant reference information, and the text to be proofread; and After obtaining the text to be proofread, performing assertion detection on the text to be proofread to determine whether to proofread the knowledge of historical figures; When the text to be proofread includes assertions, proofreading the text for historical figures; When the text to be proofread does not include an assertion statement, the text to be proofread is not proofread for knowledge of historical figures; wherein the assertion statement is a statement in the text to be proofread that clearly expresses a deterministic judgment or claim.

8. An electronic device, characterized in that: The electronic device includes: a processor and a memory; The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory, so as to enable the electronic device to execute the method for proofreading knowledge of historical figures according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by an electronic device, the method for collating knowledge of historical figures according to any one of claims 1 to 6 is realized.

Images