Method, device and equipment for dialogue text analysis using DSL, and storage medium

Abstract

The present application relates to text processing technology, and discloses a dialogue text analysis method using DSL, including: obtaining a policy text, and extracting keywords in the policy text to obtain policy keywords; using the policy keywords to segment the policy text to obtain a segmented policy text set; converting the segmented policy text set into a text vector set, and inputting the text vector into a preset large language model to perform text reorganization to obtain a reorganized text block; using a preset text-to-specific description language algorithm to convert the reorganized text block into a policy structured description sentence set, and converting the policy structured description sentence set into a literal format content to obtain a text analysis result of the policy text. The present application also provides a dialogue text analysis device using DSL, equipment and a storage medium. The present application can improve the efficiency of dialogue text analysis using DSL.

Description

Technical Field

[0001] This invention relates to the field of text processing technology, and in particular to a method, apparatus, device, and storage medium for implementing conversational text analysis using DSL. Background Technology

[0002] Policy documents are typically numerous and lengthy, often leading to information fragmentation and redundancy, making it difficult to quickly locate key information. In lengthy policy documents, relevant clauses, measures, or implementation details may be buried under a vast amount of text. Furthermore, lengthy policy documents may contain numerous technical terms, conceptual explanations, and logical deductions, which may be unfamiliar and obscure to the general public. This results in the public or implementers struggling to quickly find the information they need, leading to problems such as policies being "unavailable," "incomprehensible," and "unusable." To better enable the public to understand policy trends and clarify their needs, effective methods are needed for structured policy analysis. This allows for the rapid extraction of relevant information from numerous policy documents, enabling quick identification of target policies, mastery of policy content, and understanding of policy dynamics. Summary of the Invention

[0003] This invention provides a method, apparatus, device, and storage medium for implementing conversational text analysis using DSL, which can improve the efficiency of implementing conversational text analysis using DSL.

[0004] To achieve the above objectives, this invention provides a dialogic text analysis method using a DSL, comprising:

[0005] Obtain the policy text and extract the keywords from it to obtain the policy keywords;

[0006] The policy text is segmented using the policy keywords to obtain a set of policy text blocks;

[0007] The segmented policy text set is converted into a text vector set, and the text vectors are input into a preset large language model for text recombination to obtain recombined text blocks;

[0008] The recombined text block is transformed into a set of policy structured description statements using a preset text-to-specific description language algorithm, and then the set of policy structured description statements is transformed into text format content to obtain the text analysis results of the policy text.

[0009] Optionally, the extraction of keywords from the policy text includes:

[0010] Identify stop words in the policy text and remove them to obtain a simplified policy text;

[0011] Perform word segmentation on the simplified policy text to obtain a policy text terminology set;

[0012] Perform keyword extraction on the policy text terminology set to obtain the policy text keyword set.

[0013] Optionally, the step of performing word segmentation on the simplified policy text to obtain a policy text terminology set includes:

[0014] Based on preset grammatical requirements, a word segmentation dictionary is constructed using a large amount of policy text;

[0015] The simplified policy text is segmented using the word segmentation dictionary to obtain the policy text word set.

[0016] Optionally, segmenting the policy text using the policy keywords includes:

[0017] The keyword density of each sentence in the policy text is identified, and the policy text is segmented according to the text input constraints of the preset natural language processing model to obtain a block policy text set.

[0018] Optionally, the step of converting the reconstructed text block into a set of policy structured description statements using a preset text-to-specific description language algorithm includes:

[0019] Extract the entity elements, relation elements, and event elements of each block of policy text in the reconstructed text block;

[0020] The entity elements, relation elements, and event elements are combined using a preset text-to-specific description language algorithm to obtain the structured description statement of the policy;

[0021] The policy structure description statements corresponding to each policy block are summarized to obtain the policy structure description statement set.

[0022] Optionally, inputting the text vector into a preset large language model for text reconstruction includes:

[0023] The text vector is input into a preset large language model, and the preset large language model is used to generate a statement hidden state based on the entity elements, relation elements and event elements in the text vector.

[0024] The hidden state of the statement is used as an auxiliary input. The auxiliary input is combined with the next text vector and then input into a preset large language model to obtain the associated text.

[0025] By integrating the associated texts corresponding to all text vectors, a reconstructed text block is obtained.

[0026] Optionally, converting the segmented policy text set into a text vector set includes:

[0027] Construct a vocabulary for the segmented policy text set, and use the vocabulary as the bag-of-words for a preset text vector transformation model;

[0028] The words in the segmented policy text set are converted into text vectors using the bag-of-words and the preset text vector conversion model. The text vector set is obtained by summing the text vectors of each word in the segmented policy text set.

[0029] To address the aforementioned problems, the present invention also provides a device for implementing conversational text analysis using a DSL, the device comprising:

[0030] The text processing module is used to acquire policy text, extract keywords from the policy text to obtain policy keywords, and segment the policy text using the policy keywords to obtain a set of segmented policy texts.

[0031] The structured description statement conversion module is used to convert the block policy text set into a text vector set, and input the text vectors into a preset large language model for text recombination to obtain recombined text blocks;

[0032] The text analysis module is used to convert the recombined text block into a set of policy structured description statements using a preset text-to-specific description language algorithm, and to convert the set of policy structured description statements into text format content to obtain the text analysis results of the policy text.

[0033] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0034] At least one processor; and,

[0035] A memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the above-described dialogic text analysis method using DSL.

[0037] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the aforementioned dialogic text analysis method using DSL.

[0038] This invention achieves the extraction of key information from policy texts through word segmentation and keyword extraction. By using a pre-defined large language model to reconstruct the text vector sets corresponding to the segmented policy text sets, the effective information in the policy texts can be accurately processed. Furthermore, by utilizing a pre-defined text-to-specific description language algorithm to transform the reconstructed text blocks into a set of structured policy description statements, the contextual relationships of the extracted policy text keywords can be realized, accurately reflecting the intent and improving the efficiency of policy text analysis. Attached Figure Description

[0039] Figure 1 This is a flowchart illustrating a dialog-based text analysis method using DSL, as provided in an embodiment of the present invention.

[0040] Figure 2 A functional block diagram of a dialog-based text analysis device using DSL is provided in an embodiment of the present invention.

[0041] Figure 3 This is a schematic diagram of the structure of an electronic device that implements a dialog-based text analysis method using DSL, according to an embodiment of the present invention.

[0042] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0043] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0044] This application provides a method for implementing conversational text analysis using DSL. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for implementing conversational text analysis using DSL can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0045] Reference Figure 1As shown in the figure, it is a schematic flowchart of a method for implementing conversational text analysis using DSL provided by an embodiment of the present invention. In this embodiment, the method for implementing conversational text analysis using DSL includes:

[0046] S1. Obtain a policy text, and extract keywords from the policy text to obtain policy keywords.

[0047] In an embodiment of the present invention, the policy text refers to a formal document used to describe, stipulate or explain policies, regulations, guiding principles or legislations. These texts are usually formulated by government agencies, legislative bodies or other official organizations, aiming to guide the formulation and implementation of public policies, ensure compliance with laws and regulations, and provide detailed explanations for specific policy areas. Policy texts usually have characteristics such as a large quantity and a long length. The length of the text often leads to scattered and redundant information, making it difficult to quickly locate key information. Relevant clauses, measures or implementation details may be submerged in a large amount of text. Moreover, long policy texts may contain a large number of professional terms, concept explanations and logical derivations, which may be relatively unfamiliar and obscure to the general public.

[0048] As an embodiment of the present invention, the extraction of keywords from the policy text includes:

[0049] Identify stop words in the policy text, and remove the stop words in the policy text to obtain a refined policy text;

[0050] Perform a word segmentation operation on the refined policy text to obtain a set of policy text words;

[0051] Perform a keyword extraction operation on the set of policy text words to obtain a set of policy text keyword words.

[0052] In an embodiment of the present invention, stop words refer to words that are usually ignored in text processing because stop words may not provide useful information during queries and are very common in the language, such as Chinese auxiliary words like "的", "是", "在", etc., and English words like "the", "is", "at", etc. In natural language processing (NLP) tasks, stop words are usually removed from the data to reduce noise and improve processing efficiency. For example, in "The history of XX City", removing stop words results in "XX City history".

[0053] Furthermore, the performing a word segmentation operation on the refined policy text to obtain a set of policy text words includes:

[0054] Construct a word segmentation dictionary using a large number of policy texts according to preset grammar requirements;

[0055] Segment the streamlined policy text according to the word segmentation dictionary to obtain the policy text word set.

[0056] In an embodiment of the present invention, the word segmentation dictionary refers to a word set constructed by using independent and non-repeating words in a large number of policy texts according to strict grammatical requirements.

[0057] In an embodiment of the present invention, the word segmentation operation (Word Segmentation) is a basic task in natural language processing (NLP), which is particularly important for Chinese language without space separation. Word segmentation refers to splitting a continuous text string into meaningful units, usually words or phrases. In Chinese, word segmentation is the process of identifying the boundaries of each word in a sentence and separating them. For example, the Chinese sentence "I love XX City" can be segmented into "I / love / XX City" after the word segmentation operation.

[0058] S2. Segment the policy text by using the policy keywords to obtain a set of segmented policy texts.

[0059] As an embodiment of the present invention, the segmenting the policy text by using the policy keywords includes:

[0060] Identify the keyword density of each sentence in the policy text, and segment the policy text according to the keyword density and the text input limit of a preset natural language processing model to obtain a set of segmented policy texts.

[0061] In an embodiment of the present invention, the keyword density refers to the proportion of the number of occurrences of the extracted keywords in the overall word segmentation.

[0062] S3. Convert the set of segmented policy texts into a set of text vectors, and input the text vectors into a preset large language model for text recombination to obtain recombined text blocks.

[0063] In an embodiment of the present invention, the text vector refers to the process of converting text data into a numerical vector, which enables a computer to process and analyze text.

[0064] As an embodiment of the present invention, the converting the set of segmented policy texts into a set of text vectors includes:

[0065] Construct a vocabulary for the set of segmented policy texts, and use the vocabulary as the bag of words of a preset text vector conversion model;

[0066] Use the bag of words and the preset text vector conversion model to convert the words in the set of segmented policy texts into text vectors, and summarize the text vectors of each word in the set of segmented policy texts to obtain the set of text vectors.

[0067] In this embodiment of the invention, the text vector conversion model is a word vector conversion tool that converts words into word vectors. It can adopt the Word2vec model, which consists of an input layer, a projection layer, and an output layer.

[0068] In this embodiment of the invention, the bag-of-words refers to a text representation method used for natural language processing and information retrieval. The text in the bag-of-words (such as sentences or documents) is represented as the number of times words appear in the vocabulary, without considering grammar or word order.

[0069] In this embodiment of the invention, the preset large language model refers to a large machine learning model used to process word language processing tasks, wherein the preset large language model may adopt an LLM (Large Language Models) model.

[0070] As an embodiment of the present invention, the step of inputting the text vector into a preset large language model for text reconstruction includes:

[0071] The text vector is input into a preset large language model, and the preset large language model is used to generate a statement hidden state based on the entity elements, relation elements and event elements in the text vector.

[0072] The hidden state of the statement is used as an auxiliary input. The auxiliary input is combined with the next text vector and then input into a preset large language model to obtain the associated text.

[0073] By integrating the associated texts corresponding to all text vectors, a reconstructed text block is obtained.

[0074] In this embodiment of the invention, the statement hidden state refers to a step variable in the neural network that captures information prior to the sequence. The statement hidden state enables the network to take into account contextual information, thereby making more accurate predictions and generating data.

[0075] S4. Using a preset text-to-specific description language algorithm, the recombined text block is converted into a set of policy structured description statements, and the set of policy structured description statements is converted into text format content to obtain the text analysis results of the policy text.

[0076] In this embodiment of the invention, the preset text-to-specific description language algorithm refers to the Text-to-DSL algorithm. DSL stands for Domain-Specific Language, which is a computer programming language specifically designed to solve problems in a specific domain.

[0077] As an embodiment of the present invention, the step of converting the recombined text block into a set of policy structured description statements using a preset text-to-specific description language algorithm includes:

[0078] Extract the entity elements, relation elements, and event elements of each block of policy text in the reconstructed text block;

[0079] The entity elements, relation elements, and event elements are combined using a preset text-to-specific description language algorithm to obtain the structured description statement of the policy;

[0080] The policy structure description statements corresponding to each policy block are summarized to obtain the policy structure description statement set.

[0081] In this embodiment of the invention, the entity element refers to a clearly identifiable noun or noun phrase, representing an object, person, place, organization, or concept. The relation element refers to the semantic connection or interaction between entity elements. The event element refers to an action or situation that occurs. For example, in the sentence "Company XX released Product XX in 2021," "release" is an event involving the entities "Company XX" and "Product XX," and is associated with the time "2021."

[0082] In this embodiment of the invention, the text format refers to a plain text format without any text embellishment.

[0083] This invention, through word segmentation and keyword extraction of policy texts, enables the acquisition of key information within the policy texts. By using a pre-defined large language model to reconstruct the text vector sets corresponding to the segmented policy text sets, the effective information in the policy texts can be accurately processed. Furthermore, by utilizing a pre-defined text-to-specific description language algorithm to transform the reconstructed text blocks into a set of structured policy description statements, the contextual relationships of the extracted policy text keywords can be realized, accurately reflecting the intent and improving the efficiency of policy text analysis.

[0084] like Figure 2 The diagram shown is a functional block diagram of a dialog-based text analysis device using DSL provided in an embodiment of the present invention.

[0085] The dialogic text analysis device 100 using DSL described in this invention can be installed in an electronic device. Depending on the functions implemented, the dialogic text analysis device 100 using DSL may include a text processing module 101, a structured description statement conversion module 102, and a text analysis module 103.

[0086] The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0087] In this embodiment, the functions of each module / unit are as follows:

[0088] The text processing module 101 is configured to obtain a policy text, extract keywords from the policy text to obtain policy keywords, and use the policy keywords to segment the policy text to obtain a segmented policy text set.

[0089] In the embodiment of the present invention, the policy text refers to a formal document used to describe, stipulate or explain policies, regulations, guiding principles or legislations. These texts are usually formulated by government agencies, legislative bodies or other official organizations for the purpose of guiding the formulation and implementation of public policies, ensuring compliance with laws and regulations, and providing detailed explanations for specific policy areas. Policy texts usually have the characteristics of a large number and a long length. The length of the text often leads to the dispersion and redundancy of information, making it difficult to quickly locate key information. Relevant clauses, measures or implementation details may be submerged in a large amount of text. Moreover, long policy texts may contain a large number of professional terms, concept explanations and logical derivations, which may be relatively unfamiliar and obscure to the general public.

[0090] As an embodiment of the present invention, the extraction of keywords from the policy text includes:

[0091] Identify stop words in the policy text, remove the stop words in the policy text to obtain a refined policy text;

[0092] Perform word segmentation on the refined policy text to obtain a set of policy text words;

[0093] Perform keyword extraction on the set of policy text words to obtain a set of policy text keyword words.

[0094] In the embodiment of the present invention, the stop words refer to words that are usually ignored in text processing because they may not provide useful information in queries and are very common in the language, such as Chinese auxiliary words like "de", "shi", "zai", etc., and English words like "the", "is", "at", etc. In natural language processing (NLP) tasks, stop words are usually removed from the data to reduce noise and improve processing efficiency. For example, in "The history of XX City", removing stop words gives "XX City history".

[0095] Further, the performing word segmentation on the refined policy text to obtain a set of policy text words includes:

[0096] Construct a word segmentation dictionary using a large number of policy texts according to preset grammar requirements;

[0097] Segment the streamlined policy text according to the word segmentation dictionary to obtain the set of policy text words.

[0098] In an embodiment of the present invention, the word segmentation dictionary refers to a word set constructed using independent and non-repeating words in a large number of policy texts according to strict grammatical requirements.

[0099] In an embodiment of the present invention, the word segmentation operation (Word Segmentation) is a basic task in natural language processing (NLP), which is particularly important for Chinese languages without space separation. Word segmentation refers to the process of splitting a continuous text string into meaningful units, usually words or phrases. In Chinese, word segmentation is the process of identifying the boundaries of each word in a sentence and separating them. For example, the Chinese sentence "I love XX City" can be segmented into "I / love / XX City" after the word segmentation operation.

[0100] As an embodiment of the present invention, the segmentation of the policy text using the policy keywords includes:

[0101] Identify the keyword density of each sentence in the policy text, and segment the policy text according to the keyword density and text input limitations of a preset natural language processing model to obtain a set of segmented policy texts.

[0102] In an embodiment of the present invention, the keyword density refers to the proportion of the number of occurrences of the extracted keywords in the overall word segmentation.

[0103] The structured description statement conversion module 102 is used to convert the set of segmented policy texts into a set of text vectors, and input the text vectors into a preset large language model for text recombination to obtain recombined text blocks.

[0104] In an embodiment of the present invention, the text vector refers to the process of converting text data into a numerical vector, which enables a computer to process and analyze text.

[0105] As an embodiment of the present invention, the conversion of the set of segmented policy texts into a set of text vectors includes:

[0106] Construct a vocabulary for the set of segmented policy texts, and use the vocabulary as the bag of words of a preset text vector conversion model;

[0107] Use the bag of words and the preset text vector conversion model to convert the words in the set of segmented policy texts into text vectors, and summarize the text vectors of each word in the set of segmented policy texts to obtain the set of text vectors.

[0108] In this embodiment of the invention, the text vector conversion model is a word vector conversion tool that converts words into word vectors. It can adopt the Word2vec model, which consists of an input layer, a projection layer, and an output layer.

[0109] In this embodiment of the invention, the bag-of-words refers to a text representation method used for natural language processing and information retrieval. The text in the bag-of-words (such as sentences or documents) is represented as the number of times words appear in the vocabulary, without considering grammar or word order.

[0110] In this embodiment of the invention, the preset large language model refers to a large machine learning model used to process word language processing tasks, wherein the preset large language model may adopt an LLM (Large Language Models) model.

[0111] As an embodiment of the present invention, the step of inputting the text vector into a preset large language model for text reconstruction includes:

[0112] The text vector is input into a preset large language model, and the preset large language model is used to generate a statement hidden state based on the entity elements, relation elements and event elements in the text vector.

[0113] The hidden state of the statement is used as an auxiliary input. The auxiliary input is combined with the next text vector and then input into a preset large language model to obtain the associated text.

[0114] By integrating the associated texts corresponding to all text vectors, a reconstructed text block is obtained.

[0115] In this embodiment of the invention, the statement hidden state refers to a step variable in the neural network that captures information prior to the sequence. The statement hidden state enables the network to take into account contextual information, thereby making more accurate predictions and generating data.

[0116] The text analysis module 103 is used to convert the recombined text block into a set of policy structured description statements using a preset text-to-specific description language algorithm, and to convert the set of policy structured description statements into text format content to obtain the text analysis results of the policy text.

[0117] In this embodiment of the invention, the preset text-to-specific description language algorithm refers to the Text-to-DSL algorithm. DSL stands for Domain-Specific Language, which is a computer programming language specifically designed to solve problems in a specific domain.

[0118] As an embodiment of the present invention, the step of converting the recombined text block into a set of policy structured description statements using a preset text-to-specific description language algorithm includes:

[0119] Extract the entity elements, relation elements, and event elements of each block of policy text in the reconstructed text block;

[0120] The entity elements, relation elements, and event elements are combined using a preset text-to-specific description language algorithm to obtain the structured description statement of the policy;

[0121] The policy structure description statements corresponding to each policy block are summarized to obtain the policy structure description statement set.

[0122] In this embodiment of the invention, the entity element refers to a clearly identifiable noun or noun phrase, representing an object, person, place, organization, or concept. The relation element refers to the semantic connection or interaction between entity elements. The event element refers to an action or situation that occurs. For example, in the sentence "Company XX released Product XX in 2021," "release" is an event involving the entities "Company XX" and "Product XX," and is associated with the time "2021."

[0123] In this embodiment of the invention, the text format refers to a plain text format without any text embellishment.

[0124] Reference Figure 3 The diagram shown is a structural schematic of an electronic device that implements a dialog-based text analysis method using DSL, according to an embodiment of the present invention.

[0125] The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13. It may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a program for implementing a conversational text analysis method using DSL.

[0126] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a program for implementing a conversational text analysis method using DSL), and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0127] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as code for a program implementing a conversational text analysis method using DSL, but also to temporarily store data that has been output or will be output.

[0128] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0129] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0130] Figure 3 Only electronic devices with components are shown; those skilled in the art will understand that... Figure 3 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0131] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0132] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0133] The memory 11 in the electronic device stores a program for implementing a conversational text analysis method using DSL, which is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0134] Obtain the policy text and extract the keywords from it to obtain the policy keywords;

[0135] The policy text is segmented using the policy keywords to obtain a set of policy text blocks;

[0136] The segmented policy text set is converted into a text vector set, and the text vectors are input into a preset large language model for text recombination to obtain recombined text blocks;

[0137] The recombined text block is transformed into a set of policy structured description statements using a preset text-to-specific description language algorithm, and then the set of policy structured description statements is transformed into text format content to obtain the text analysis results of the policy text.

[0138] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0139] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0140] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0141] Obtain the policy text and extract the keywords from it to obtain the policy keywords;

[0142] The policy text is segmented using the policy keywords to obtain a set of policy text blocks;

[0143] The segmented policy text set is converted into a text vector set, and the text vectors are input into a preset large language model for text recombination to obtain recombined text blocks;

[0144] The recombined text block is transformed into a set of policy structured description statements using a preset text-to-specific description language algorithm, and then the set of policy structured description statements is transformed into text format content to obtain the text analysis results of the policy text.

[0145] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0146] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0148] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0149] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0150] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0151] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0152] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for conversational text analysis using DSL, characterized by, The method includes: Obtain the policy text and extract the keywords from it to obtain the policy keywords; The policy text is segmented using the policy keywords to obtain a set of policy text blocks; The segmented policy text set is converted into a text vector set, and the text vectors in the text vector set are input into a preset large language model for text recombination to obtain recombined text blocks. The step of inputting the text vectors in the text vector set into the preset large language model for text recombination includes: inputting the text vectors in the text vector set into the preset large language model, and using the preset large language model to generate implicit statement states based on entity elements, relation elements, and event elements in the text vectors; using the implicit statement states as auxiliary input, combining the auxiliary input with the next text vector and inputting it into the preset large language model to obtain associated text; and integrating the associated texts corresponding to all text vectors to obtain recombined text blocks. The recombined text block is transformed into a set of policy structured description statements using a preset text-to-specific description language algorithm, and then the set of policy structured description statements is transformed into text format content to obtain the text analysis results of the policy text.

2. The dialogic text analysis method using DSL as described in claim 1, characterized in that, The extraction of keywords from the policy text includes: Identify stop words in the policy text and remove them to obtain a simplified policy text; Perform word segmentation on the simplified policy text to obtain a policy text terminology set; Perform keyword extraction on the policy text terminology set to obtain the policy text keyword set.

3. The method for conversational text analysis using DSL according to claim 2, wherein, The process of performing word segmentation on the simplified policy text yields a policy text terminology set, including: Based on preset grammatical requirements, a word segmentation dictionary is constructed using a large amount of policy text; The simplified policy text is segmented using the word segmentation dictionary to obtain the policy text word set.

4. The method for conversational text analysis using DSL according to claim 1, wherein, The segmentation of the policy text using the policy keywords includes: The keyword density of each sentence in the policy text is identified, and the policy text is segmented according to the text input constraints of the preset natural language processing model to obtain a block policy text set.

5. The method for conversational text analysis using DSL according to claim 1, wherein, The step of using a preset text-to-specific description language algorithm to convert the reconstructed text block into a set of policy structured description statements includes: Extract the entity elements, relation elements, and event elements of each block of policy text in the reconstructed text block; The entity elements, relation elements, and event elements are combined using a preset text-to-specific description language algorithm to obtain the structured description statement of the policy; The policy structure description statements corresponding to each policy block are summarized to obtain the policy structure description statement set.

6. The method for conversational text analysis using DSL according to claim 1, wherein, The step of converting the segmented policy text set into a text vector set includes: Construct a vocabulary for the segmented policy text set, and use the vocabulary as the bag-of-words for a preset text vector transformation model; The words in the segmented policy text set are converted into text vectors using the bag-of-words and the preset text vector conversion model. The text vector set is obtained by summing the text vectors of each word in the segmented policy text set.

7. An apparatus for conversational text analysis using DSL, characterized by, The apparatus can implement the dialogic text analysis method using DSL as described in any one of claims 1 to 6, and the apparatus includes: The text processing module is used to acquire policy text, extract keywords from the policy text to obtain policy keywords, and segment the policy text using the policy keywords to obtain a set of segmented policy texts. The structured description statement conversion module is used to convert the block policy text set into a text vector set, and input the text vectors in the text vector set into a preset large language model for text recombination to obtain recombined text blocks. The step of inputting the text vectors in the text vector set into the preset large language model for text recombination includes: inputting the text vectors in the text vector set into the preset large language model, and using the preset large language model to generate a statement implicit state based on entity elements, relation elements, and event elements in the text vectors; using the statement implicit state as auxiliary input, combining the auxiliary input with the next text vector and inputting it into the preset large language model to obtain associated text; and integrating the associated texts corresponding to all text vectors to obtain recombined text blocks. The text analysis module is used to convert the recombined text block into a set of policy structured description statements using a preset text-to-specific description language algorithm, and to convert the set of policy structured description statements into text format content to obtain the text analysis results of the policy text.

8. An electronic device, comprising: The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the dialogic text analysis method using DSL as described in any one of claims 1 to 6.

9. A computer readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the dialogic text analysis method using DSL as described in any one of claims 1 to 6.

Images