Text auxiliary reading method and device, equipment, medium and program product

Abstract

The embodiment of the invention discloses a text auxiliary reading method and device, equipment, a medium and a program product. The method comprises the following steps: acquiring a reference text, and analyzing the reference text to obtain a text analysis result; marking text identification information of the text analysis result according to the identification information of the text analysis result in the reference text; according to a preset text segmentation granularity, segmenting the text analysis result to obtain a first text segmentation result; grouping the first text segmentation results according to the text identification information corresponding to the first text segmentation results to obtain second text segmentation results; and obtaining a user question of the user in the text-assisted reading, and determining a text-assisted reading result according to the user question, the first text segmentation result and the second text segmentation result. According to the method, auxiliary text reading is carried out through various segmentation results, reply of various kinds of questions can be achieved, and the applicability, comprehensiveness and accuracy of text reading are improved.

Description

Technical Field

[0001] The present invention relates to the field of natural language processing technology, and in particular to a text-assisted reading method, device, equipment, medium and program product. Background Art

[0002] With the rapid development of artificial intelligence technology, text-assisted reading has proven its practicality and value in many fields. Text-assisted reading can efficiently collect, analyze and interpret a large amount of literature, allowing users to browse and understand documents more quickly, thereby greatly improving work and learning efficiency and achieving the dual goals of cost savings and effect improvement.

[0003] Text-assisted reading is usually based on Retrieval-Augmented Generation (RAG) technology, which combines retrieval and generation to solve the hallucination problem of the large language model itself to a great extent in the form of prompt words, thereby improving the accuracy of the model's responses in text-assisted reading.

[0004] However, RAG technology only recalls part of the documents during retrieval, resulting in incomplete responses to summary questions in text-assisted reading; and insufficient accuracy in responses to multiple types of complex questions, resulting in poor adaptability of text-assisted reading. Summary of the invention

[0005] The present invention provides a text-assisted reading method, device, equipment, medium and program product to improve the applicability, comprehensiveness and accuracy of text reading.

[0006] According to one aspect of the present invention, a text-assisted reading method is provided, the method comprising:

[0007] Acquire a reference text, and parse the reference text to obtain a text parsing result;

[0008] According to the identification information of the text analysis result in the reference text, marking the text identification information of the text analysis result;

[0009] Segmenting the text parsing result according to a preset text segmentation granularity to obtain a first text segmentation result;

[0010] According to the text identification information corresponding to each of the first text segmentation results, each of the first text segmentation results is grouped to obtain a second text segmentation result;

[0011] A user question of a user in text-assisted reading is obtained, and a text-assisted reading result is determined according to the user question, the first text segmentation result, and the second text segmentation result.

[0012] According to another aspect of the present invention, there is provided a text auxiliary reading device, the device comprising:

[0013] A text parsing module, used to obtain a reference text and parse the reference text to obtain a text parsing result;

[0014] An identification information marking module, used for marking text identification information of the text analysis result according to the identification information of the text analysis result in the reference text;

[0015] A text segmentation module, used to segment the text parsing result according to a preset text segmentation granularity to obtain a first text segmentation result;

[0016] A text grouping module, used for grouping each of the first text segmentation results according to the text identification information corresponding to each of the first text segmentation results to obtain a second text segmentation result;

[0017] The text-assisted reading module is used to obtain user questions of the user in the text-assisted reading, and determine the text-assisted reading results according to the user questions, the first text segmentation results and the second text segmentation results.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the text-assisted reading method described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the text-assisted reading method described in any embodiment of the present invention when executed.

[0023] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the text-assisted reading method according to any embodiment of the present invention is implemented.

[0024] The technical solution of the embodiment of the present invention obtains a reference text and parses the reference text to obtain a text parsing result; annotates the text identification information of the text parsing result according to the identification information of the text parsing result in the reference text; segments the text parsing result according to a preset text segmentation granularity to obtain a first text segmentation result; groups each first text segmentation result according to the text identification information corresponding to each first text segmentation result to obtain a second text segmentation result; obtains the user's question in text-assisted reading, and determines the text-assisted reading result according to the user question, the first text segmentation result and the second text segmentation result, thereby solving the problem that text-assisted reading cannot be applied to multiple types of question responses, has poor applicability, poor comprehensiveness of question responses, and poor accuracy. By performing text-assisted reading with multiple segmentation results, multiple types of question responses can be achieved, thereby improving the applicability, comprehensiveness and accuracy of text reading.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a flow chart of a text-assisted reading method provided according to Embodiment 1 of the present invention;

[0028] Figure 2 This is a specific application diagram of a text-assisted reading method provided according to Embodiment 1 of the present invention;

[0029] Figure 3 is a structural schematic diagram of a text auxiliary reading device provided according to Embodiment 2 of the present invention;

[0030] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the text auxiliary reading method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] Figure 1 1 is a flowchart of a text-assisted reading method provided according to the first embodiment of the present invention. This embodiment is applicable to the case where a large language model is used to analyze a document and answer a user's question. The method can be executed by a text-assisted reading device. The text-assisted reading device can be implemented in the form of hardware and / or software. The text-assisted reading device can be configured in an electronic device such as a computer. Figure 1 As shown, the method includes:

[0035] Step 110: Obtain a reference text, and parse the reference text to obtain a text parsing result.

[0036] The reference text may be a file of one or more document types. Document types include, but are not limited to, comma separated values ​​(CSV), portable document format (PDF), Word document (DOC), spreadsheet (Excel), image (Image), and presentation (PPT) formats. The reference text may be a file uploaded by the user, or the reference text may be a file related to the user's question obtained by searching the public information of the large language model.

[0037] The analysis of the reference text can be to retain the content of the document itself as comprehensively as possible to ensure the comprehensiveness and accuracy of the content information in the subsequent processing stage. The analysis of the text can be performed by using an optical character recognition (OCR) tool to analyze the document content. However, due to the diversity of document formats and the fact that the document may contain structured and unstructured data, the reliability of text analysis using OCR is insufficient. Therefore, when analyzing the reference text, targeted text analysis under specific types can be performed according to the document type of the reference text to improve the reliability of the text analysis results.

[0038] In an optional implementation of the embodiment of the present invention, parsing the reference text to obtain a text parsing result includes: identifying the document type of the reference text; calling a parser of a corresponding type according to the document type, parsing the reference text through the parser, and obtaining a text parsing result.

[0039] The document type of the reference text may be identified by a text icon, or by a text attribute, or by a text suffix.

[0040] Figure 2 FIG. 1 is a schematic diagram of a specific application of a text-assisted reading method provided according to Embodiment 1 of the present invention. Figure 2 As shown, in an embodiment of the present invention, the parsing end of text-assisted reading can be set with a parser aggregate. In the parser aggregate, a CSV parser, a PDF parser, a DOC parser, an Excel parser, an Image parser, and a PPT parser can be pre-set. For texts of different document types, parsers of corresponding types can be used for targeted parsing. For example, for a PDF document, different model modules in the PDF parser are used to parse the text content, image content, and table content therein respectively. Among them, the PDF parser can call efficient optical character recognition (Rapid OCR) based on deep learning technology. When parsing, data preprocessing operations such as data cleaning and data filtering can be performed on the data.

[0041] Step 120: annotate the text identification information of the text analysis result according to the identification information of the text analysis result in the reference text.

[0042] The identification information of the text analysis result in the reference text includes but is not limited to the text chapter, page number, subject content, content format, and content serial number. The annotation of the text analysis result can be the page number of the text analysis result in the text and the serial number of the type of the text analysis result. For example, the text analysis result is which table in the PDF, whether it is the title content, etc.

[0043] In an optional implementation of an embodiment of the present invention, text identification information of the text parsing result is annotated according to the identification information of the text parsing result in the reference text, including: identifying the page number, chapter, and subject content of the text parsing result in the reference text; generating text identification information of the text parsing result according to the page number, chapter, and subject content, and annotating the text identification information.

[0044] By annotating text identification information, the content attribution of each text analysis result can be identified, making it easier to segment the text analysis results into different categories.

[0045] Step 130: segment the text analysis result according to a preset text segmentation granularity to obtain a first text segmentation result.

[0046] In an embodiment of the present invention, the preset text segmentation granularity includes but is not limited to the minimum unit of text processing (token), sentence (sentence), and the minimum unit of text composition (character). For example, when the preset text segmentation granularity adopted is token, the sentence "Hello world" will be divided into two tokens "Hello" and "world". When the preset text segmentation granularity adopted is sentence, "The weather is so nice today, let's go to the park to play!" will be used as a segmentation result. When the preset text segmentation granularity adopted is character, "Hello" will be divided into five characters "H", "e", "l", "l", and "o".

[0047] "Token", "Sentence" and "Character" play different roles in text processing. Token, as the basic unit of text processing, enables the model to understand and analyze text more accurately. Sentence is the basic unit of information transmission and expression, used to express a complete idea or meaning. Character is the smallest unit of text and is of great significance for text encoding and storage. In practical applications, these three segmentation granularities can be interconnected and interact with each other to form the basic framework of text processing.

[0048] The first text segmentation result may be a result obtained by segmenting the text parsing result according to a preset text segmentation granularity. In practical applications, since a single minimum unit is difficult to express meaning, the segmentation result may be intercepted by a preset length to obtain the first text segmentation result. That is, the text parsing result is segmented according to the preset text segmentation granularity, and the segmentation result is divided by a preset length to obtain the first text segmentation result.

[0049] Step 140: group the first text segmentation results according to the text identification information corresponding to the first text segmentation results to obtain second text segmentation results.

[0050] When parsing the reference text, the text parsing result is annotated with text identification information. The text identification information of the first text segmentation result may be the same as the text identification information of the corresponding text parsing result. When the text identification information corresponding to the plurality of first text segmentation results is the same or similar, the plurality of first text segmentation results may be grouped together to obtain a second text segmentation result.

[0051] For example, when the first text segmentation result 1 and the first text segmentation result 2 both belong to the same sub-segment under the same subject content, chapter, or page number, the first text segmentation result 1 and the first text segmentation result 2 can be grouped together to obtain the second text segmentation result.

[0052] Specifically, in an optional implementation of an embodiment of the present invention, each first text segmentation result is grouped according to the text identification information corresponding to each first text segmentation result to obtain a second text segmentation result, including: when the text identification information corresponding to multiple first text segmentation results meets a preset identification similarity condition, the multiple first text segmentation results are divided into a group to obtain a second text segmentation result.

[0053] Exemplarily, similarity calculation can be performed on the text identification information corresponding to the multiple first text segmentation results to obtain a similarity value. For example, the similarity of the text identification information corresponding to the multiple first text segmentation results is determined by a cosine similarity algorithm. When the calculated similarity is greater than a preset similarity threshold, the multiple first text segmentation results can be divided into a group to obtain a second text segmentation result. For example, the similarity threshold can be a value greater than or equal to 85%.

[0054] In the embodiment of the present invention, the first text segmentation result can be understood as a local segmentation, and the second text segmentation result can be understood as a global segmentation. Figure 2 As shown in the figure, local blocks and global blocks are obtained based on the text parsing results at the retrieval end. Local blocks focus on the aggregation of local information, such as using paragraph length as the segmentation standard; global blocks focus on the control of global information to ensure that global information is efficiently retained. Furthermore, based on local blocks and global blocks, high-quality responses to various types of questions can be provided.

[0055] Step 150: Obtain a user question in text-assisted reading, and determine a text-assisted reading result according to the user question, the first text segmentation result, and the second text segmentation result.

[0056] Among them, the user question, the first text segmentation result and the second text segmentation result can all be input into the large language model for analysis to obtain the text assisted reading result. Replying to questions based on the first text segmentation result and the second text segmentation result can improve the quality of responses to different questions.

[0057] In an optional implementation of an embodiment of the present invention, a text-assisted reading result is determined based on a user question, a first text segmentation result, and a second text segmentation result, including: determining index information of text segments based on the first text segmentation result and the second text segmentation result; determining prompt words based on similarity matching between the index information and the user question; and inputting the prompt words and the user question into a large language model to obtain a text-assisted reading result.

[0058] The index information of the text segmentation can be information generated by the search end by vectorizing and indexing the first text segmentation result and the second text segmentation result. The index information is matched with the user question by similarity, and reordered according to the similarity to obtain prompt words. The prompt words can be index information that is highly similar to the user question. Figure 2 As shown, at the generation end, the user question can be analyzed by the agent in the large language model, and the text-assisted reading result can be obtained based on the prompt words based on the first text segmentation result and the second text segmentation result.

[0059] In an embodiment of the present invention, in order to achieve accurate responses to different types of questions, multiple agents can be set to respond to different categories of questions to improve the overall response effect. Specifically, in an optional implementation of an embodiment of the present invention, a text-assisted reading result is determined based on the user question, the first text segmentation result, and the second text segmentation result, including: analyzing the user question to determine the question category of the user question; when the question category is a detail question, determining the text-assisted reading result based on the first text segmentation result by the basic agent; when the question category is a summary question, determining the text-assisted reading result based on the first text segmentation result and the second text segmentation result by the summary agent; when the question category is a data analysis question, determining the text-assisted reading result based on the first text segmentation result by the data analysis agent.

[0060] In this embodiment, the question type can be a detail question, a summary question, or a data analysis question. The detail question can be a question about extracting the basic content and information in the document. Figure 2 The large language model shown can use the basic agent to use only the first text segmentation result to compare and rearrange information similarity and determine the text auxiliary reading result. By using only the first text segmentation result, the corresponding answer to the detailed user question can be obtained accurately and quickly.

[0061] When answering summary questions, in order to improve the comprehensiveness of the response, such as Figure 2 As shown, a summary agent can be used to determine the text auxiliary reading result according to the first text segmentation result and the second text segmentation result. Replying to summary-type user questions based on the first text segmentation result and the second text segmentation result can improve the comprehensiveness and quality of the reply.

[0062] When asking data analysis questions, such as Figure 2 As shown, the code module can be called by the data analysis agent through the constructed analysis->code->code parsing->return result tool call flow to solve practical problems of data analysis.

[0063] The technical solution of this embodiment obtains a reference text and parses the reference text to obtain a text parsing result; annotates the text identification information of the text parsing result according to the identification information of the text parsing result in the reference text; segments the text parsing result according to a preset text segmentation granularity to obtain a first text segmentation result; groups each first text segmentation result according to the text identification information corresponding to each first text segmentation result to obtain a second text segmentation result; obtains the user's question in text-assisted reading, and determines the text-assisted reading result according to the user question, the first text segmentation result and the second text segmentation result, thereby solving the problem that text-assisted reading cannot be applied to multiple types of question responses, has poor applicability, poor comprehensiveness of question responses, and poor accuracy. By performing text-assisted reading with multiple segmentation results, multiple types of question responses can be achieved, thereby improving the applicability, comprehensiveness and accuracy of text reading.

[0064] like Figure 2 As shown, an application process of the text-assisted reading method provided by an embodiment of the present invention may be: multiple types of parsers are set at the parsing end, and documents of corresponding types are parsed in a targeted manner through different parsers to ensure data integrity. At the retrieval end, different types of data are cleaned and formatted, and the first text segmentation results of local blocks and the second text segmentation results of global blocks are obtained through an improved segmentation algorithm to assist the agent in paying attention to global information. At the generation end, different types of user questions are responded to through basic agents, summary agents, and data analysis agents to improve the overall response effect.

[0065] Embodiment 2

[0066] Figure 3 is a schematic diagram of the structure of a text auxiliary reading device provided according to the second embodiment of the present invention. Figure 3As shown, the device includes: a text parsing module 310, a logo information marking module 320, a text segmentation module 330, a text grouping module 340 and a text auxiliary reading module 350. Among them:

[0067] The text parsing module 310 is used to obtain a reference text and parse the reference text to obtain a text parsing result;

[0068] The identification information marking module 320 is used to mark the text identification information of the text analysis result according to the identification information of the text analysis result in the reference text;

[0069] The text segmentation module 330 is used to segment the text parsing result according to a preset text segmentation granularity to obtain a first text segmentation result;

[0070] A text grouping module 340, configured to group each first text segmentation result according to text identification information corresponding to each first text segmentation result to obtain a second text segmentation result;

[0071] The text-assisted reading module 350 is used to obtain a user question in the text-assisted reading, and determine a text-assisted reading result according to the user question, the first text segmentation result, and the second text segmentation result.

[0072] Optionally, the text grouping module 340 includes:

[0073] The text grouping unit is used to group the multiple first text segmentation results into one group to obtain the second text segmentation results when the text identification information corresponding to the multiple first text segmentation results meets the preset identification similarity condition.

[0074] Optionally, the text auxiliary reading module 350 includes:

[0075] A problem category determination unit, used to analyze user problems and determine the problem category of the user problems;

[0076] A first text-assisted reading result determining unit, configured to determine a text-assisted reading result according to the first text segmentation result through a basic intelligent agent when the question category is a detail-related question;

[0077] A second text-assisted reading result determination unit, configured to determine a text-assisted reading result by using a summary agent according to the first text segmentation result and the second text segmentation result when the question category is a summary question;

[0078] The third text-assisted reading result determination unit is used to determine the text-assisted reading result according to the first text segmentation result through the data analysis agent when the question category is a data analysis question.

[0079] Optionally, the text auxiliary reading module 350 includes:

[0080] An index information determination unit, used to determine index information of text segmentation according to the first text segmentation result and the second text segmentation result;

[0081] A prompt word determination unit, used to perform similarity matching between the index information and the user question to determine the prompt word;

[0082] The text-assisted reading unit is used to input prompt words and user questions into the large language model to obtain text-assisted reading results.

[0083] Optionally, the text parsing module 310 includes:

[0084] A document type identification unit, used to identify the document type of the reference text;

[0085] The text parsing unit is used to call a parser of a corresponding type according to the document type, and parse the reference text through the parser to obtain a text parsing result.

[0086] Optionally, the identification information marking module 320 includes:

[0087] An identification information recognition unit, used to identify the page number, chapter, and subject content of the text analysis result in the reference text;

[0088] The identification information marking unit is used to generate text identification information of the text parsing result according to the page number, chapter, and subject content, and to mark the text identification information.

[0089] The text-assisted reading device provided in the embodiment of the present invention can execute the text-assisted reading method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0090] Embodiment 3

[0091] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0092] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0093] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0094] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a text-assisted reading method.

[0095] In some embodiments, the text-assisted reading method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the text-assisted reading method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the text-assisted reading method in any other appropriate manner (e.g., by means of firmware).

[0096] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0098] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0100] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0101] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0102] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0103] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A text-assisted reading method, characterized in that: include: Acquire a reference text, and parse the reference text to obtain a text parsing result; According to the identification information of the text analysis result in the reference text, marking the text identification information of the text analysis result; Segmenting the text parsing result according to a preset text segmentation granularity to obtain a first text segmentation result; According to the text identification information corresponding to each of the first text segmentation results, each of the first text segmentation results is grouped to obtain a second text segmentation result; A user question of a user in text-assisted reading is obtained, and a text-assisted reading result is determined according to the user question, the first text segmentation result, and the second text segmentation result.

2. The method according to claim 1, characterized in that According to the text identification information corresponding to each of the first text segmentation results, each of the first text segmentation results is grouped to obtain a second text segmentation result, including: When the text identification information corresponding to the plurality of first text segmentation results meets a preset identification similarity condition, the plurality of first text segmentation results are grouped into one group to obtain a second text segmentation result.

3. The method according to claim 1, characterized in that Determining a text auxiliary reading result according to the user question, the first text segmentation result, and the second text segmentation result includes: Analyze the user problem and determine the problem category of the user problem; When the question category is a detail question, determining a text auxiliary reading result according to the first text segmentation result by the basic intelligent agent; When the question category is a summary question, the summary agent determines the text auxiliary reading result according to the first text segmentation result and the second text segmentation result; When the question category is a data analysis question, the text-assisted reading result is determined by the data analysis agent according to the first text segmentation result.

4. The method according to claim 1, characterized in that: Determining a text auxiliary reading result according to the user question, the first text segmentation result, and the second text segmentation result includes: Determining index information of text segments according to the first text segmentation result and the second text segmentation result; Perform similarity matching between the index information and the user question to determine a prompt word; The prompt words and the user questions are input into a large language model to obtain a text-assisted reading result.

5. The method according to claim 1, characterized in that Parsing the reference text to obtain a text parsing result includes: Identifying the document type of the reference text; A parser of a corresponding type is called according to the document type, and the reference text is parsed by the parser to obtain a text parsing result.

6. The method according to claim 1, characterized in that According to the identification information of the text analysis result in the reference text, marking the text identification information of the text analysis result includes: Identify the page number, chapter, and subject content of the text analysis result in the reference text; The text identification information of the text analysis result is generated according to the page number, chapter, and subject content, and the text identification information is annotated.

7. A text-assisted reading device, characterized in that: include: A text parsing module, used to obtain a reference text and parse the reference text to obtain a text parsing result; An identification information marking module, used for marking text identification information of the text analysis result according to the identification information of the text analysis result in the reference text; A text segmentation module, used to segment the text parsing result according to a preset text segmentation granularity to obtain a first text segmentation result; A text grouping module, used for grouping each of the first text segmentation results according to the text identification information corresponding to each of the first text segmentation results to obtain a second text segmentation result; The text-assisted reading module is used to obtain user questions of the user in the text-assisted reading, and determine the text-assisted reading results according to the user questions, the first text segmentation results and the second text segmentation results.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the text-assisted reading method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the text-assisted reading method according to any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the text-assisted reading method according to any one of claims 1 to 6.

Images