PDF document auxiliary reading method and device, equipment and storage medium

Abstract

The invention belongs to the field of computers, and discloses a PDF document auxiliary reading method and device, equipment and a storage medium. The method comprises the steps of obtaining a target question and a target PDF document of a user; performing semantic analysis on the target problem to obtain semantic information of the target problem; and generating answer information corresponding to the target question based on the semantic information and the target PDF document. The target question and the target PDF document of the user can be obtained, and the answer information corresponding to the target question is automatically generated based on the target PDF document. Compared with an existing mode that the user can only manually check the PDF document and search the answer information of the target question from the PDF document, the mode can automatically generate the target question of the user on the basis of the target PDF document, the document reading efficiency of the user is improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a PDF document auxiliary reading method, device, equipment and storage medium. Background Art

[0002] There are a lot of PDF reading scenarios on browsers. Users usually use browsers to download PDF resources on the Internet and then open them with browsers. Although browsers have the function of reading PDF files and can open PDF files by default, when users open PDF documents through browsers for reading, the browser cannot assist users in reading and improve the efficiency of users' reading of PDF documents. Therefore, how to improve the efficiency of users browsing PDF documents has become a technical problem that needs to be solved urgently.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a PDF document auxiliary reading method, device, equipment and storage medium, aiming to solve the technical problem of low reading efficiency when users open PDF documents through browsers for reading in the prior art.

[0005] To achieve the above object, the present invention provides a PDF document auxiliary reading method, the method comprising the following steps:

[0006] Get the user's target question and target PDF document;

[0007] Performing semantic analysis on the target question to obtain semantic information of the target question;

[0008] Answer information corresponding to the target question is generated based on the semantic information and the target PDF document.

[0009] Optionally, the step of performing semantic analysis on the target question to obtain semantic information of the target question includes:

[0010] Perform word segmentation and part-of-speech tagging on the target question to obtain a part-of-speech tagging result;

[0011] Performing syntactic analysis on the target question according to the part-of-speech tagging result to obtain a syntactic analysis result;

[0012] Performing semantic role labeling on the target question to obtain role labeling information;

[0013] The target question is subjected to sentence semantic analysis based on the syntactic analysis result and the role labeling information to obtain semantic information of the target question.

[0014] Optionally, the step of generating answer information corresponding to the target question based on the semantic information and the target PDF document includes:

[0015] searching for reference information in the target PDF document based on the semantic information;

[0016] Generate answer information corresponding to the target question according to the reference information.

[0017] Optionally, after the step of generating answer information corresponding to the target question based on the semantic information and the target PDF document, the step further includes:

[0018] Determine at least one reference information corresponding to the answer information and location information of the reference information in the target PDF document;

[0019] A reference path corresponding to the reference information is generated based on the location information, and the answer information includes the reference path.

[0020] Optionally, after the step of searching the target PDF document for reference information based on the semantic information, the method further includes:

[0021] When the reference information is not found, displaying optional answer strategies;

[0022] Obtaining a target answer strategy selected by the user according to the answer strategy;

[0023] Answer information corresponding to the target question is generated based on the target answer strategy and the semantic information.

[0024] Optionally, the step of generating answer information corresponding to the target question based on the target answer strategy and the semantic information includes:

[0025] When the target answer strategy is to refer to network information, obtaining preset trusted network information;

[0026] Answer information corresponding to the target question is generated based on the preset trusted network information and the semantic information.

[0027] Optionally, the target PDF document includes at least one PDF document selected by a user or a portion of documents selected from a PDF document.

[0028] Optionally, the step of obtaining the user's target question and target PDF document includes:

[0029] Determine a target PDF document selected by a user based on content in at least one PDF document;

[0030] A target question generated by a user based on the target PDF document is obtained.

[0031] Optionally, the PDF document auxiliary reading method further includes:

[0032] Generate optional guidance questions according to the target PDF document, and monitor user operation information;

[0033] Determine the target guidance question selected by the user according to the operation information;

[0034] Generate answer information corresponding to the target guiding question based on the target PDF document.

[0035] Optionally, the step of generating optional guiding questions according to the target PDF document comprises:

[0036] Extract key information from the target PDF document;

[0037] Obtaining a preset question type, and generating an initial question text according to the preset question type and the key information;

[0038] The initial question text is semantically modified to obtain an optional guiding question.

[0039] Optionally, the user inputs the target question in a text or voice manner, and answers the target question in a text or voice manner.

[0040] Optionally, after the step of generating answer information corresponding to the target question based on the semantic information and the target PDF document, the step further includes:

[0041] Acquire the interactive language used by the user;

[0042] The output language of the answer information is determined according to the interactive language.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also provides a PDF document auxiliary reading device, the device comprising:

[0044] The acquisition module is used to obtain the user's target question and target PDF document;

[0045] A semantic analysis module, used to perform semantic analysis on the target question to obtain semantic information of the target question;

[0046] The answer information generating module is used to generate answer information corresponding to the target question based on the semantic information and the target PDF document.

[0047] In addition, to achieve the above-mentioned purpose, the present invention also proposes a PDF document auxiliary reading device, the device comprising: a memory, a processor, and a PDF document auxiliary reading program stored in the memory and executable on the processor, the PDF document auxiliary reading program being configured to implement the steps of the PDF document auxiliary reading method as described above.

[0048] In addition, to achieve the above object, the present invention also proposes a storage medium, on which a PDF document auxiliary reading program is stored. When the PDF document auxiliary reading program is executed by a processor, the steps of the PDF document auxiliary reading method described above are implemented.

[0049] The present invention obtains the user's target question and target PDF document; performs semantic analysis on the target question to obtain semantic information of the target question; and generates answer information corresponding to the target question based on the semantic information and the target PDF document. Since the present invention can obtain the user's target question and target PDF document, the answer information corresponding to the target question is automatically generated based on the target PDF document. Compared with the existing method in which the user can only manually view the PDF document and search for the answer information of the target question from the PDF document, the above method of the present invention can automatically generate the user's target question based on the target PDF document, thereby improving the user's reading efficiency of the document and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a structural diagram of a PDF document auxiliary reading device in a hardware operating environment involved in an embodiment of the present invention;

[0051] Figure 2 This is a flow chart of a first embodiment of a PDF document auxiliary reading method according to the present invention;

[0052] Figure 3 This is a flow chart of a second embodiment of the PDF document auxiliary reading method of the present invention;

[0053] Figure 4 It is a flowchart of a third embodiment of the PDF document auxiliary reading method of the present invention;

[0054] Figure 5 It is a structural block diagram of the first embodiment of the PDF document auxiliary reading device of the present invention.

[0055] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0057] Reference Figure 1 , Figure 1 The present invention is a schematic diagram of the structure of a PDF document auxiliary reading device in a hardware operating environment according to an embodiment of the present invention.

[0058] like Figure 1 As shown, the PDF document auxiliary reading device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0059] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the PDF document auxiliary reading device, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0060] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a PDF document auxiliary reading program.

[0061] exist Figure 1 In the PDF document assisting reading device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the PDF document assisting reading device of the present invention can be set in the PDF document assisting reading device, and the PDF document assisting reading device calls the PDF document assisting reading program stored in the memory 1005 through the processor 1001, and executes the PDF document assisting reading method provided by the embodiment of the present invention.

[0062] Based on the above-mentioned PDF document auxiliary reading device, an embodiment of the present invention provides a PDF document auxiliary reading method, referring to Figure 2 , Figure 2 FIG. 4 is a flow chart of a first embodiment of a PDF document auxiliary reading method according to the present invention.

[0063] In this embodiment, the PDF document auxiliary reading method includes the following steps:

[0064] Step S10: Obtain the user's target question and target PDF document.

[0065] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a mobile phone, a tablet computer, a personal computer, etc., or an electronic device that can realize the above functions or a browser that can implement the PDF document auxiliary reading method in this embodiment. The following takes a PDF document auxiliary reading browser as an example to illustrate this embodiment and the following embodiments.

[0066] In order to improve information processing capabilities, in some embodiments, an intelligent assistant can be installed on the PDF document auxiliary reading browser. The intelligent assistant can be a program built based on the natural language processing technology of the Generative Pre-trained Transformer (GPT) model. The intelligent assistant can receive the user's input text, parse the input text into a computer-understandable data format, and then use the pre-trained neural network model to generate response text.

[0067] In the specific implementation, the intelligent assistant uses the neural network in deep learning technology and is trained through a large amount of corpus data, so that it can learn the structure, grammatical rules and semantic information of the language. After the user enters the text, the intelligent assistant will first segment and parse the text, convert it into a computer-readable vector form, and then send it to the pre-trained neural network model for inference. During the inference process, the intelligent assistant will predict the most likely next response based on the text entered by the user and the previous context. This prediction process is based on the model's learning of a large amount of corpus data, so it can largely restore the way humans express natural language and generate highly coherent and natural response text. Finally, the intelligent assistant returns the generated response text to the user to complete a dialogue interaction. Throughout the process, the intelligent assistant will continue to learn and optimize to provide more accurate and user-friendly answers.

[0068] It should be noted that the target PDF document can be a PDF document opened by the user in the browser, an uploaded PDF document, or partial information in a PDF document selected based on an uploaded or downloaded PDF document. The target PDF document can be a single PDF format document, or multiple PDF documents, or partial text selected from multiple PDF documents. This embodiment is not limited here. The target question can be a question generated by the user based on the target PDF document, or a question related to the target PDF document input by the user. It can include asking about the main content, concepts, viewpoints, technologies, etc. of the target PDF document. Among them, the user inputs the target question and specifies the target PDF document in a text or voice manner, that is, the user can input the target question and / or specify the target PDF document in a voice manner. When the user's input method is voice, when the answer information corresponding to the target question is fed back, the answer information can also be fed back in a voice broadcast manner.

[0069] Furthermore, in some scenarios, it is necessary to ask questions about the content selected by the user with the mouse. Therefore, in order to meet the diverse needs of users, step S10 may include: determining a target PDF document selected by the user based on the content in at least one PDF document; and obtaining a target question generated by the user based on the target PDF document.

[0070] It should be noted that the target PDF document selected by the user based on the content in at least one PDF document can be part of the content in one or more PDF documents selected by the user. The user can use the mouse to select paragraphs, terms, sentences, words, etc. from one or more PDF documents to ask targeted questions about the part of the content. It is more focused and accurate than just asking questions about the entire PDF document content.

[0071] Step S20: performing semantic analysis on the target question to obtain semantic information of the target question.

[0072] It should be noted that semantic analysis refers to an in-depth understanding and interpretation of a text to identify the semantic structure and meaning in the text. The semantic analysis of the target question may be performed by using natural language processing technology to understand the meaning corresponding to the target question to accurately identify the user's intention.

[0073] In a specific implementation, the target question may be semantically analyzed by an intelligent assistant installed on a PDF document auxiliary reading browser to obtain semantic information of the target question.

[0074] Step S30: Generate answer information corresponding to the target question based on the semantic information and the target PDF document.

[0075] It should be noted that generating the answer information corresponding to the target question based on the semantic information and the target PDF document can be to determine the user's intention based on the semantic information, search the target PDF document for information related to the target question according to the user's intention, and generate the answer information corresponding to the target question based on the searched relevant information.

[0076] Furthermore, in order to guide the user's reading and improve reading efficiency during the process of the user reading the PDF document, this embodiment may also include: generating optional guiding questions according to the target PDF document and monitoring the user's operation information; determining the target guiding question selected by the user according to the operation information; and generating answer information corresponding to the target guiding question based on the target PDF document.

[0077] It should be noted that the generation of optional guiding questions based on the target PDF document can be a guiding question based on the main content of the target PDF document, for example: what does xxx mentioned in the target PDF document mean, what is history, what is the specific concept of a term, etc. The main usage scenario is to help users expand their thinking ideas and scope. The operation information can be a click operation or a voice command initiated by the user based on the optional guiding question. Determining the target guiding question selected by the user based on the operation information can be that if the user's operation information is clicking on the guiding question, the target guiding question clicked by the user is determined according to the user's click operation; if the user's operation information is a voice command that triggers the selection of the target guiding question, the target guiding question selected by the user's voice is determined according to the voice command. The generation of the answer information corresponding to the target guiding question based on the target PDF document can refer to the above-mentioned step of generating the answer information corresponding to the target question, and this embodiment is not limited here.

[0078] Furthermore, in order to make the generated guiding questions more consistent with the main content of the PDF document and improve the user experience, the step of generating optional guiding questions based on the target PDF document includes: extracting key information in the target PDF document; obtaining a preset question type, and generating an initial question text based on the preset question type and the key information; and semantically correcting the initial question text to obtain optional guiding questions.

[0079] It should be noted that the extracting of key information from the target PDF document may be performed by extracting key information from the target PDF document such as main viewpoints, events, characters, places, etc. in the target PDF document using feature extraction. The preset question type may be a type of pre-set generated guiding question, which may be set based on different types of PDF documents, or may be a general question type, or a type of guiding question generated by a user, and the preset question type may include factual questions, cause and effect questions, comparison and contrast questions, inference and interpretation questions, etc. The generating of the initial question text according to the preset question type and the key information may be performed by converting the key information into a question form according to the preset question type, and using appropriate question words (such as who, what, why, how, etc.) to help construct the initial question text. The semantic correction of the initial question text to obtain the optional guiding question may be performed by refining and correcting the initial question text to ensure that the question accurately expresses the content to be asked, and correcting the question that needs to be further refined or clarified to obtain the optional guiding question.

[0080] Furthermore, the language in the target PDF document may be different from the language used by the user when asking questions. In order to improve the user's reading efficiency and experience, after step S30, it also includes: obtaining the interactive language used by the user; and determining the output language of the answer information according to the interactive language.

[0081] It should be noted that the interactive language may be the language used by the user when asking the target question or the output language of the answer information selected by the user. The output language of the answer information determined according to the interactive language may be, when the language corresponding to the answer information is inconsistent with the interactive language, performing language conversion on the answer information and translating the answer information into the interactive language for output. The output method may be text display or output through voice playback, and the specific output method may be the question input method used by the user when asking the question or the output method selected by the user.

[0082] This embodiment obtains the user's target question and target PDF document; performs semantic analysis on the target question to obtain semantic information of the target question; and generates answer information corresponding to the target question based on the semantic information and the target PDF document. Since this embodiment can obtain the user's target question and target PDF document, the answer information corresponding to the target question is automatically generated based on the target PDF document. Compared with the existing method in which the user can only manually view the PDF document and search for the answer information of the target question from the PDF document, the above method of this embodiment can automatically generate the user's target question based on the target PDF document, thereby improving the user's reading efficiency of the document and improving the user experience.

[0083] refer to Figure 3 , Figure 3 FIG. 4 is a flow chart of a second embodiment of a PDF document auxiliary reading method according to the present invention.

[0084] Based on the above first embodiment, in this embodiment, step S20 includes:

[0085] Step S201: performing word segmentation and part-of-speech tagging on the target question to obtain a part-of-speech tagging result.

[0086] It should be noted that the word segmentation and part-of-speech tagging of the target question may be to decompose the text in the target question into words and determine the part of speech of each word, such as noun, verb, adjective, etc.

[0087] Step S202: performing syntactic analysis on the target question according to the part-of-speech tagging result to obtain a syntactic analysis result.

[0088] It should be noted that the syntactic analysis of the target question according to the part-of-speech tagging result can be to identify entities in the target question, such as names of people, places, etc., and tag them, and then analyze the grammatical structure and dependency relationship between words in the sentence, such as subject-predicate relationship, modification relationship, etc., to help understand the structure and meaning of the sentence. The syntactic analysis result including the grammatical structure and dependency relationship is obtained.

[0089] Step S203: performing semantic role labeling on the target question to obtain role labeling information.

[0090] It should be noted that the semantic role labeling of the target question may be to determine the semantic role of each word in the sentence, such as subject, object, time, place, etc.

[0091] Step S204: performing sentence semantic analysis on the target question based on the syntactic analysis result and the role labeling information to obtain semantic information of the target question.

[0092] It should be noted that the sentence semantic analysis of the target question based on the syntactic analysis result and the role labeling information may be to convert the sentence text corresponding to the target question into a computer-understandable representation, such as a logical expression, a semantic graph, etc., according to the syntactic analysis result and the role labeling information, which helps to more deeply understand the semantics of the target question and further obtain the semantic information of the target question.

[0093] This embodiment performs word segmentation and part-of-speech tagging on the target question to obtain a part-of-speech tagging result;

[0094] According to the part-of-speech tagging result, the target question is subjected to syntactic analysis to obtain a syntactic analysis result; semantic role tagging is performed on the target question to obtain role tagging information; based on the syntactic analysis result and the role tagging information, the target question is subjected to sentence semantic analysis to obtain semantic information of the target question. This embodiment accurately identifies the semantic information of the target question by performing word segmentation, part-of-speech tagging, syntactic analysis, and semantic role tagging on the target question, and can accurately understand the user's intention, thereby obtaining answer information that better meets the user's expectations and improving the user's efficiency in reading PDF documents.

[0095] refer to Figure 4 , Figure 4 FIG. 4 is a flow chart of a third embodiment of a PDF document auxiliary reading method according to the present invention.

[0096] Based on the above embodiments, in this embodiment, step S30 includes:

[0097] Step S301: searching for reference information in the target PDF document based on the semantic information.

[0098] It should be noted that the reference information may be information related to the target question in the target PDF document. The searching for reference information in the target PDF document based on the semantic information may be to determine the intention of the target question input by the user based on the semantic information, and determine the information in the target PDF document related to the target question, i.e., the reference information, according to the intention. For example, when the user intention corresponding to the target question is to summarize, the reference information may be the entire target PDF document; when the user intention corresponding to the target question is to summarize the relevant information about feature A in the target PDF document, the reference information may be the information related to feature A involved in the target PDF document. When the user intention corresponding to the target question is to explain a noun, the reference information may be information related to the noun.

[0099] Searching for reference information in the target PDF document based on the semantic information may also include determining keywords corresponding to the answer to the target question based on the semantic information, searching the target PDF document based on the keywords, and retrieving reference information containing the keywords in the target PDF document. For example, when the target PDF document is a team building plan, and the target question is the itinerary for the team building on the day, the keywords may include time, itinerary keywords, etc.

[0100] Furthermore, in order to avoid not finding the answer information corresponding to the target question in the target PDF document, after step S301, it also includes: displaying optional answer strategies when the reference information is not found; obtaining the target answer strategy selected by the user based on the answer strategy; and generating the answer information corresponding to the target question based on the target answer strategy and the semantic information.

[0101] It should be noted that the optional answering strategies may include expanding the search scope and using the generalization capability of the model. Expanding the search scope may be adding documents for answering the target question or using information on the network to answer the target question. The target answering strategy may be an answering strategy selected by the user.

[0102] Furthermore, in order to obtain answer information corresponding to the target question, when the target answer strategy is to refer to network information, preset trusted network information is obtained; and answer information corresponding to the target question is generated based on the preset trusted network information and the semantic information.

[0103] It should be noted that the preset trusted network information may be pre-set network information that can be used to answer the target question. For example, only the content in a pre-set specific website and a website with high credibility can be used as reference information for answering the target question. Generating the answer information corresponding to the target question based on the preset trusted network information and the semantic information may be obtaining the reference information corresponding to the target question from the website corresponding to the preset trusted network information, and then generating the answer information corresponding to the target question based on the reference information.

[0104] Step S302: Generate answer information corresponding to the target question according to the reference information.

[0105] It should be noted that the generation of the answer information corresponding to the target question according to the reference information may be to determine the requirements and type of the question according to the semantic information corresponding to the target question, and the question type may include factual questions, reasoning questions, descriptive questions, etc. Determining the requirements of the question may be to analyze the key requirements and restrictions of the target question and clarify the type and range of the required answer. Then, according to the requirements and type of the target question, key information is extracted from the reference information, and the answer to the target question is generated based on the extracted key information.

[0106] Furthermore, in order to facilitate the user to better understand the answer, after step S302, the method further includes: determining at least one reference information corresponding to the answer information and location information of the reference information in the target PDF document;

[0107] A reference path corresponding to the reference information is generated based on the location information, and the answer information includes the reference path.

[0108] It should be noted that the location information is used to describe the specific location of the reference information in the target PDF document, and may include the page number, line number, and identifier, download path or storage path of the target PDF document. The reference path may be an anchor point, link, or specific location description information set for the reference information. By setting a reference path, such as an anchor point, for the reference information, when the user clicks the anchor point corresponding to the reference information, the user can quickly locate the location of the reference information, making it convenient for the user to read the reference information.

[0109] This embodiment searches for reference information in the target PDF document based on the semantic information; and generates answer information corresponding to the target question based on the reference information. In this embodiment, reference information is first searched in the target PDF document based on the semantic information, and then the answer information corresponding to the target question is generated based on the reference information. The answer information corresponding to the target question can be accurately generated based on the target PDF document, thereby improving the reading efficiency of the user.

[0110] Reference Figure 5 , Figure 5 It is a structural block diagram of the first embodiment of the PDF document auxiliary reading device of the present invention.

[0111] like Figure 5 As shown, the PDF document auxiliary reading device proposed in the embodiment of the present invention includes:

[0112] An acquisition module 10 is used to acquire a user's target question and a target PDF document;

[0113] A semantic analysis module 20, configured to perform semantic analysis on the target question to obtain semantic information of the target question;

[0114] The answer information generating module 30 is used to generate answer information corresponding to the target question based on the semantic information and the target PDF document.

[0115] This embodiment obtains the user's target question and target PDF document; performs semantic analysis on the target question to obtain semantic information of the target question; and generates answer information corresponding to the target question based on the semantic information and the target PDF document. Since this embodiment can obtain the user's target question and target PDF document, the answer information corresponding to the target question is automatically generated based on the target PDF document. Compared with the existing method in which the user can only manually view the PDF document and search for the answer information of the target question from the PDF document, the above method of this embodiment can automatically generate the user's target question based on the target PDF document, thereby improving the user's reading efficiency of the document and improving the user experience.

[0116] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0117] In addition, for technical details not fully described in this embodiment, reference may be made to the PDF document auxiliary reading method provided in any embodiment of the present invention, and will not be repeated here.

[0118] Based on the first embodiment of the PDF document auxiliary reading device of the present invention, a second embodiment of the PDF document auxiliary reading device of the present invention is proposed.

[0119] In this embodiment, the semantic analysis module 20 is further used to perform word segmentation and part-of-speech tagging on the target question to obtain a part-of-speech tagging result;

[0120] Performing syntactic analysis on the target question according to the part-of-speech tagging result to obtain a syntactic analysis result;

[0121] Performing semantic role labeling on the target question to obtain role labeling information;

[0122] The target question is subjected to sentence semantic analysis based on the syntactic analysis result and the role labeling information to obtain semantic information of the target question.

[0123] Furthermore, the answer information generating module 30 is further used to search for reference information in the target PDF document based on the semantic information;

[0124] Generate answer information corresponding to the target question according to the reference information.

[0125] Furthermore, the answer information generating module 30 is further used to determine at least one reference information corresponding to the answer information and location information of the reference information in the target PDF document;

[0126] A reference path corresponding to the reference information is generated based on the location information, and the answer information includes the reference path.

[0127] Furthermore, the answer information generating module 30 is also used to display optional answer strategies when the reference information is not found;

[0128] Obtaining a target answer strategy selected by the user according to the answer strategy;

[0129] Answer information corresponding to the target question is generated based on the target answer strategy and the semantic information.

[0130] Furthermore, the answer information generating module 30 is further configured to obtain preset trusted network information when the target answer strategy is to refer to network information;

[0131] Answer information corresponding to the target question is generated based on the preset trusted network information and the semantic information.

[0132] Furthermore, the target PDF document includes at least one PDF document selected by a user or a portion of a document selected from a PDF document.

[0133] Furthermore, the acquisition module 10 is further used to determine a target PDF document selected by a user based on the content in at least one PDF document;

[0134] A target question generated by a user based on the target PDF document is obtained.

[0135] Furthermore, the PDF document auxiliary reading device is also used to generate optional guiding questions according to the target PDF document and monitor the user's operation information;

[0136] Determine the target guidance question selected by the user according to the operation information;

[0137] Generate answer information corresponding to the target guiding question based on the target PDF document.

[0138] Furthermore, the PDF document auxiliary reading device is also used to extract key information from the target PDF document;

[0139] Obtaining a preset question type, and generating an initial question text according to the preset question type and the key information;

[0140] The initial question text is semantically modified to obtain an optional guiding question.

[0141] Furthermore, the user may input the target question in text or voice, and the user may answer the target question in text or voice.

[0142] Furthermore, the answer information generating module 30 is also used to obtain the interactive language used by the user;

[0143] The output language of the answer information is determined according to the interactive language.

[0144] Other embodiments or specific implementations of the PDF document auxiliary reading device of the present invention may refer to the above-mentioned method embodiments, which will not be described in detail here.

[0145] In addition, an embodiment of the present invention further provides a storage medium, on which a PDF document auxiliary reading program is stored. When the PDF document auxiliary reading program is executed by a processor, the steps of the PDF document auxiliary reading method described above are implemented.

[0146] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0147] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0148] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0149] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0150] The present invention discloses A1, a PDF document auxiliary reading method, the PDF document auxiliary reading method comprising the following steps:

[0151] Get the user's target question and target PDF document;

[0152] Performing semantic analysis on the target question to obtain semantic information of the target question;

[0153] Answer information corresponding to the target question is generated based on the semantic information and the target PDF document.

[0154] A2. In the PDF document auxiliary reading method as described in A1, the step of performing semantic analysis on the target question to obtain semantic information of the target question comprises:

[0155] Perform word segmentation and part-of-speech tagging on the target question to obtain a part-of-speech tagging result;

[0156] Performing syntactic analysis on the target question according to the part-of-speech tagging result to obtain a syntactic analysis result;

[0157] Performing semantic role labeling on the target question to obtain role labeling information;

[0158] The target question is subjected to sentence semantic analysis based on the syntactic analysis result and the role labeling information to obtain semantic information of the target question.

[0159] A3. In the PDF document auxiliary reading method as described in A1, the step of generating answer information corresponding to the target question based on the semantic information and the target PDF document comprises:

[0160] searching for reference information in the target PDF document based on the semantic information;

[0161] Generate answer information corresponding to the target question according to the reference information.

[0162] A4. The PDF document auxiliary reading method as described in A3, after the step of generating the answer information corresponding to the target question based on the semantic information and the target PDF document, further comprising:

[0163] Determine at least one reference information corresponding to the answer information and location information of the reference information in the target PDF document;

[0164] A reference path corresponding to the reference information is generated based on the location information, and the answer information includes the reference path.

[0165] A5. The PDF document auxiliary reading method as described in A3, after the step of searching the reference information in the target PDF document based on the semantic information, further comprising:

[0166] When the reference information is not found, displaying optional answer strategies;

[0167] Obtaining a target answer strategy selected by the user according to the answer strategy;

[0168] Answer information corresponding to the target question is generated based on the target answer strategy and the semantic information.

[0169] A6. In the PDF document assisted reading method as described in A5, the step of generating answer information corresponding to the target question based on the target answer strategy and the semantic information comprises:

[0170] When the target answer strategy is to refer to network information, obtaining preset trusted network information;

[0171] Answer information corresponding to the target question is generated based on the preset trusted network information and the semantic information.

[0172] A7. In the PDF document auxiliary reading method as described in any one of A1 to A6, the target PDF document includes at least one PDF document selected by a user or a partial document selected from a PDF document.

[0173] A8. In the PDF document assisted reading method as described in any one of A1 to A6, the step of obtaining the user's target question and the target PDF document comprises:

[0174] Determine a target PDF document selected by a user based on content in at least one PDF document;

[0175] A target question generated by a user based on the target PDF document is obtained.

[0176] A9. The PDF document assisted reading method as described in any one of A1 to A6, wherein the PDF document assisted reading method further comprises:

[0177] Generate optional guidance questions according to the target PDF document, and monitor user operation information;

[0178] Determine the target guidance question selected by the user according to the operation information;

[0179] Generate answer information corresponding to the target guiding question based on the target PDF document.

[0180] A10. The PDF document assisted reading method as described in A9, wherein the step of generating optional guiding questions according to the target PDF document comprises:

[0181] Extract key information from the target PDF document;

[0182] Obtaining a preset question type, and generating an initial question text according to the preset question type and the key information;

[0183] The initial question text is semantically modified to obtain an optional guiding question.

[0184] A11. In the PDF document auxiliary reading method as described in any one of A1 to A6, the user inputs the target question in text or voice, and answers the target question in text or voice.

[0185] A12. The PDF document auxiliary reading method as described in any one of A1 to A6, after the step of generating the answer information corresponding to the target question based on the semantic information and the target PDF document, further comprising:

[0186] Acquire the interactive language used by the user;

[0187] The output language of the answer information is determined according to the interactive language.

[0188] The present invention discloses B13, a PDF document auxiliary reading device, the PDF document auxiliary reading device comprising:

[0189] The acquisition module is used to obtain the user's target question and target PDF document;

[0190] A semantic analysis module, used to perform semantic analysis on the target question to obtain semantic information of the target question;

[0191] The answer information generating module is used to generate answer information corresponding to the target question based on the semantic information and the target PDF document.

[0192] B14, in the PDF document auxiliary reading device as described in B13, the semantic analysis module is further used to perform word segmentation and part-of-speech tagging on the target question to obtain a part-of-speech tagging result;

[0193] Performing syntactic analysis on the target question according to the part-of-speech tagging result to obtain a syntactic analysis result;

[0194] Performing semantic role labeling on the target question to obtain role labeling information;

[0195] The target question is subjected to sentence semantic analysis based on the syntactic analysis result and the role labeling information to obtain semantic information of the target question.

[0196] B15, the PDF document auxiliary reading device as described in B13, wherein the answer information generating module is further used to search for reference information in the target PDF document based on the semantic information;

[0197] Generate answer information corresponding to the target question according to the reference information.

[0198] B16, the PDF document auxiliary reading device as described in B15, the answer information generation module is further used to determine at least one reference information corresponding to the answer information and the position information of the reference information in the target PDF document;

[0199] A reference path corresponding to the reference information is generated based on the location information, and the answer information includes the reference path.

[0200] B17. The PDF document auxiliary reading device as described in B15, wherein the answer information generating module is further used to display optional answer strategies when the reference information is not found;

[0201] Obtaining a target answer strategy selected by the user according to the answer strategy;

[0202] Answer information corresponding to the target question is generated based on the target answer strategy and the semantic information.

[0203] B18, the PDF document auxiliary reading device as described in B17, the answer information generation module is further used to obtain preset trusted network information when the target answer strategy is to refer to network information;

[0204] Answer information corresponding to the target question is generated based on the preset trusted network information and the semantic information.

[0205] The present invention discloses C19, a PDF document auxiliary reading device, the device comprising: a memory, a processor and a PDF document auxiliary reading program stored in the memory and executable on the processor, the PDF document auxiliary reading program being configured to implement the steps of the PDF document auxiliary reading method described in any one of A1 to A12.

[0206] The present invention discloses D20, a storage medium, on which a PDF document auxiliary reading program is stored. When the PDF document auxiliary reading program is executed by a processor, the steps of the PDF document auxiliary reading method as described in any one of A1 to A12 are implemented.

Claims

1. A PDF document auxiliary reading method, characterized in that: The PDF document auxiliary reading method comprises the following steps: Get the user's target question and target PDF document; Performing semantic analysis on the target question to obtain semantic information of the target question; Answer information corresponding to the target question is generated based on the semantic information and the target PDF document.

2. The PDF document auxiliary reading method according to claim 1, characterized in that: The step of performing semantic analysis on the target question to obtain semantic information of the target question includes: Perform word segmentation and part-of-speech tagging on the target question to obtain a part-of-speech tagging result; Performing syntactic analysis on the target question according to the part-of-speech tagging result to obtain a syntactic analysis result; Performing semantic role labeling on the target question to obtain role labeling information; The target question is subjected to sentence semantic analysis based on the syntactic analysis result and the role labeling information to obtain semantic information of the target question.

3. The PDF document auxiliary reading method according to claim 1, characterized in that: The step of generating answer information corresponding to the target question based on the semantic information and the target PDF document includes: searching for reference information in the target PDF document based on the semantic information; Generate answer information corresponding to the target question according to the reference information.

4. The PDF document auxiliary reading method according to claim 3, characterized in that: After the step of generating answer information corresponding to the target question based on the semantic information and the target PDF document, the method further includes: Determine at least one reference information corresponding to the answer information and location information of the reference information in the target PDF document; A reference path corresponding to the reference information is generated based on the location information, and the answer information includes the reference path.

5. The PDF document auxiliary reading method according to claim 3, characterized in that: After the step of searching the target PDF document for reference information based on the semantic information, the method further includes: When the reference information is not found, displaying optional answer strategies; Obtaining a target answer strategy selected by the user according to the answer strategy; Answer information corresponding to the target question is generated based on the target answer strategy and the semantic information.

6. The PDF document auxiliary reading method according to claim 5, characterized in that: The step of generating answer information corresponding to the target question based on the target answer strategy and the semantic information includes: When the target answer strategy is to refer to network information, obtaining preset trusted network information; Answer information corresponding to the target question is generated based on the preset trusted network information and the semantic information.

7. The PDF document auxiliary reading method according to any one of claims 1 to 6, characterized in that: The target PDF document includes at least one PDF document selected by a user or a partial document selected from a PDF document.

8. A PDF document auxiliary reading device, characterized in that: The PDF document auxiliary reading device comprises: The acquisition module is used to obtain the user's target question and target PDF document; A semantic analysis module, used to perform semantic analysis on the target question to obtain semantic information of the target question; The answer information generating module is used to generate answer information corresponding to the target question based on the semantic information and the target PDF document.

9. A PDF document auxiliary reading device, characterized in that: The device comprises: a memory, a processor, and a PDF document auxiliary reading program stored in the memory and executable on the processor, wherein the PDF document auxiliary reading program is configured to implement the steps of the PDF document auxiliary reading method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a PDF document auxiliary reading program, and when the PDF document auxiliary reading program is executed by the processor, the steps of the PDF document auxiliary reading method according to any one of claims 1 to 7 are implemented.

Images