Problem expansion method and device, electronic equipment and computer readable storage medium

Abstract

The application relates to an artificial intelligence technology and discloses a question expansion method and device, equipment and a storage medium. The method comprises the following steps: extracting an inquiry mode word and an entity noun in a to-be-expanded question; extracting a standard question containing the inquiry mode word and a synonymous question with the same meaning as the standard question in a question and answer library, and marking the inquiry mode word and the inquiry mode word contained in the synonymous question as a keyword; performing word segmentation and part-of-speech tagging on the standard question and the synonymous question to obtain a sentence structure; extracting a front adjacent substantive word and a rear adjacent substantive word of the keyword in the standard question and the synonymous question according to the sentence structure; extracting the inquiry mode word in the keyword, and extracting the front adjacent substantive word and the rear adjacent substantive word; and according to the keyword, the front adjacent substantive word, the rear adjacent substantive word and the proper noun, composing a preset number of expansion questions in a preset grammar format. The application can automatically generate expansion questions according to an input question.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a problem extension method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] Intelligent customer service has been widely adopted across various industries to answer user questions. When answering user questions, intelligent customer service relies on a knowledge base; therefore, the quality of the knowledge base directly determines the quality of the service. A knowledge base typically consists of standard questions, extended questions, and answers. When a user asks a question, the intelligent customer service performs similarity matching on each extended question, then deduces the standard question to obtain the answer and provides it to the user. However, different users with the same intent can ask questions flexibly, which can easily lead to situations where extended questions are not matched, especially with newly added questions to the knowledge base. These types of questions may have no extended questions or very few extended questions.

[0003] Currently, users primarily construct extended questions manually based on their own cognitive level. However, these constructed extended questions are generally of low quality, characterized by overly short sentences and significant semantic deviations. This leads to semantic discrepancies between the extended questions and the standard questions, thereby affecting the accuracy of the answers output by the intelligent customer service. Summary of the Invention

[0004] This invention provides a question expansion method, apparatus, and computer-readable storage medium, the main purpose of which is to automatically generate expanded questions to improve the question-and-answer database, saving time and effort.

[0005] To achieve the above objectives, the present invention provides a problem extension method, comprising:

[0006] Obtain the question to be expanded, and extract the query mode words and entity nouns from the question to be expanded;

[0007] Extract questions containing the aforementioned question-and-answer term from a pre-defined question-and-answer database and record them as standard questions. Record questions with the same meaning as the standard questions as synonym questions. Collect the aforementioned question-and-answer term and other question-and-answer term contained in the synonym questions and record them as keywords.

[0008] The standard questions and synonym questions are segmented and tagged with parts of speech to obtain the sentence structure;

[0009] Based on the sentence structure, extract the preceding and following content words of the keywords in the standard question and synonym question, and form a binary tuple with the preceding and following content words;

[0010] A preset number of query word terms are randomly selected from the keywords, and a preset number of preceding and following content words are selected from the tuples. Based on the keywords, preceding and following content words, and the proper nouns, a preset number of extended questions are formed according to a preset grammatical format.

[0011] Optionally, the word segmentation of the standard question and the synonym question includes:

[0012] According to the preset word segmentation strategy, the strings in the standard question and the synonym question are matched with words in a pre-built word segmentation dictionary to obtain an initial word segmentation set;

[0013] Based on the initial word segmentation set, the word segments of the standard question and the synonym question are calculated using a pre-built probabilistic word segmentation model.

[0014] Optionally, the step of calculating the word segments of the standard question and the synonym question using a pre-built probabilistic word segmentation model based on the initial word segmentation set includes:

[0015] The probability of each word in the initial word segmentation set is calculated using the following probabilistic word segmentation model P(S):

[0016]

[0017] Among them, W1, W2, ..., W m Let m be the initial word segmentation set, and p(W) be the number of words in the initial word segmentation set. i |W i-1 ) indicates in the participle W i-1 When the word W appears i The probability of occurrence;

[0018] Select word segments W with a probability greater than a preset threshold. i-1 As the segmentation of the standard question and the synonym question.

[0019] Optionally, the step of extracting the preceding and following content words of the keywords in the standard question and synonym question based on the sentence structure includes:

[0020] Determine the index position m of the keyword in the standard question and synonym question;

[0021] Extract the content words indexed before m from the sentence structure, and denot them as the preceding adjacent content word s1;

[0022] Extract the content words indexed after m from the sentence structure, and denot them as the next adjacent content word s2;

[0023] The two pairs (s1, s2) are formed by s1 and s2.

[0024] Optionally, extracting the question mode words from the question to be expanded includes:

[0025] The question to be expanded is matched with a preset extended vocabulary, and the words in the question to be expanded that successfully match the extended vocabulary are used as the query mode words in the expanded question.

[0026] Optionally, the step of extracting questions containing the questioning style words from a preset question-and-answer database and labeling them as standard questions, and questions with the same meaning as the standard questions and labeling them as synonymous questions, includes:

[0027] Retrieve the query method words from the preset question-and-answer database and mark the question sentences containing the query method words;

[0028] The marked questions are extracted into a preset text document and recorded as standard questions;

[0029] The questions that have a mapping relationship with the standard questions are extracted into the text document and denoted as synonym questions.

[0030] Optionally, obtaining the question to be expanded includes:

[0031] Accepts user input for expanded questions;

[0032] Determine the text format of the question to be expanded;

[0033] When the question to be expanded is in text format, the question to be expanded is obtained directly;

[0034] When the question to be expanded is in text format or speech format, a preset text conversion tool is used to convert the speech format question to be expanded into a text format question.

[0035] To address the above problems, the present invention also provides a problem expansion device, the device comprising:

[0036] The question parsing module is used to obtain the question to be expanded and extract the query mode words and entity nouns from the question to be expanded;

[0037] The keyword extraction module is used to extract questions containing the query method words from a preset question and answer database and record them as standard questions and questions with the same meaning as the standard questions as synonym questions, and record the query method words and other query method words contained in the synonym questions as keywords.

[0038] The sentence structure generation module is used to perform word segmentation and part-of-speech tagging on the standard questions and synonym questions to obtain the sentence structure.

[0039] The binary extraction module is used to extract the preceding and following content words of the keyword in the standard question and synonym question according to the sentence structure, and to form a binary tuple from the preceding and following content words.

[0040] The extended question generation module is used to randomly extract a preset number of query word terms from the keywords, extract a preset number of preceding and following content words from the tuples, and form a preset number of extended questions according to the keywords, preceding and following content words, and proper nouns in a preset grammatical format.

[0041] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0042] At least one processor; and,

[0043] A memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the problem extension method described above.

[0045] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the aforementioned problem extension method.

[0046] This invention can automatically generate expanded questions based on the input question, eliminating the need for manual construction by the user. Furthermore, the generated expanded questions are simply transformations of the input question, maintaining the semantics of the original question. Therefore, the question expansion method, apparatus, electronic device, and computer-readable storage medium proposed in this invention can enrich the knowledge base and improve the accuracy of answers output by intelligent customer service. Attached Figure Description

[0047] Figure 1 A flowchart illustrating a problem expansion method provided in an embodiment of the present invention;

[0048] Figure 2 A functional block diagram of a problem extension device provided in an embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the problem extension method according to an embodiment of the present invention.

[0050] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0052] This application provides a problem expansion method. The execution subject of the problem expansion method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the problem expansion method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0053] Reference Figure 1 The diagram shown is a flowchart illustrating a problem expansion method provided in an embodiment of the present invention.

[0054] The embodiments of this invention can be applied to intelligent voice customer service systems. The automatic generation of extended questions in intelligent voice customer service systems can enrich the question-and-answer knowledge base and improve the question-and-answer performance of intelligent voice customer service and chatbots.

[0055] In this embodiment, the problem expansion method includes:

[0056] S1. Obtain the question to be expanded, and extract the query mode words and entity nouns from the question to be expanded.

[0057] Specifically, obtaining the question to be expanded includes:

[0058] Accepts user input for expanded questions;

[0059] Determine the text format of the question to be expanded;

[0060] When the question to be expanded is in text format, the question to be expanded is obtained directly;

[0061] When the question to be expanded is in text format or speech format, a preset text conversion tool is used to convert the speech format question to be expanded into a text format question.

[0062] Specifically, the query word can be an interrogative word in the question to be expanded, such as "what," "who," "where," etc. Further, in this embodiment of the invention, the question to be expanded is matched with a preset expanded vocabulary, and the words in the question to be expanded that successfully match the expanded vocabulary are used as query words in the expanded question.

[0063] Furthermore, the entity nouns refer to words that have actual meaning and are of the type of physical objects. This invention can use existing natural language processing methods to identify the entity nouns in the question to be expanded.

[0064] For example, in one embodiment of the present invention, if the question to be expanded is "Where is your new delivery address?", then the extracted query word is "where", and the extracted proper noun is "new delivery address".

[0065] S2. Extract questions containing the aforementioned question-and-answer term from a pre-defined question-and-answer database and record them as standard questions, and record questions with the same meaning as the standard questions as synonym questions. Then, record the aforementioned question-and-answer term and other question-and-answer term contained in the synonym questions as keywords.

[0066] Specifically, the preset question-and-answer database can be a publicly available question-and-answer knowledge base or a self-service question-and-answer database for enterprises and institutions. The preset question-and-answer database includes a large number of question texts, and questions with the same meaning within these texts have a preset mapping relationship.

[0067] Specifically, the step of extracting questions containing the aforementioned question-asking terms from a preset question-and-answer database and labeling them as standard questions, and questions with the same meaning as the standard questions and labeling them as synonymous questions, includes:

[0068] Retrieve the query style terms from the question-and-answer database and mark the question containing the query style terms;

[0069] The marked questions are extracted into a preset text document and recorded as standard questions;

[0070] The questions that have a mapping relationship with the standard questions are extracted into the text document and denoted as synonym questions.

[0071] In this embodiment of the invention, the other question words included in the synonym question are interrogative words with the same meaning as the question word. For example, if the question word is "where", then the other question words included in the synonym question can be interrogative words such as "what place" or "where".

[0072] S3. Perform word segmentation and part-of-speech tagging on the standard questions and synonym questions to obtain the sentence structure;

[0073] In a preferred embodiment of the present invention, the step of segmenting the standard question and the synonym question includes:

[0074] According to the preset word segmentation strategy, the strings in the standard question and the synonym question are matched with words in a pre-built word segmentation dictionary to obtain an initial word segmentation set;

[0075] Based on the initial word segmentation set, the word segments of the standard question and the synonym question are calculated using the pre-constructed probabilistic word segmentation model P(S).

[0076] In this embodiment of the invention, the probabilistic word segmentation model P(S) is:

[0077]

[0078] Among them, W1, W2, ..., W m Let m be the initial word segmentation set, and p(W) be the number of words in the initial word segmentation set. i |W i-1 ) indicates in the participle W i-1 When the word W appears i The probability of occurrence.

[0079] In this embodiment of the invention, word segmentation W with a probability greater than a preset threshold is selected. i-1 As the segmentation of the standard question and the synonym question.

[0080] In this embodiment of the invention, the preset word segmentation strategy can be forward maximum matching and / or reverse maximum matching, etc.

[0081] The forward maximum matching method matches words in the word segmentation dictionary according to the forward order of the sentence (from left to right). For example, "developing countries" is segmented into "development / China / country". The reverse maximum matching method matches words in the word segmentation dictionary according to the reverse order of the sentence (from right to left). For example, "developing countries" is segmented into "development / China / country".

[0082] Furthermore, the part-of-speech tagging can be implemented using machine learning algorithms, including generalized Markov model members such as Hidden Markov Models (HMMs), Maximum Entropy Markov Models (MEMMs), and Conditional Random Fields (CRFs), as well as deep learning algorithms represented by Recurrent Neural Networks (RNNs). In addition, some conventional machine learning classifiers, such as Support Vector Machines (SVMs), can also be used for part-of-speech tagging after improvements. This will not be described in detail here.

[0083] Specifically, the part-of-speech tagging result is the part-of-speech information carried by each element of the text to be processed. For example, if the text to be tagged is: "Where is your new delivery address?", then the part-of-speech tagging result can be: "you pron, of aux.v, new delivery address n, is v, where int";

[0084] Among them, pron can represent a pronoun, aux.v can represent an auxiliary word, n can represent a noun, v can represent a verb, and int can represent an interrogative word.

[0085] The final sentence structure can be: pron+aux.v+n+v+int.

[0086] S4. Based on the sentence structure, extract the preceding and following content words of the keyword in the standard question and synonym question, and form a binary tuple from the preceding and following content words.

[0087] In this embodiment of the invention, the step of extracting the preceding and following content words of the keywords in the standard question and synonym question based on the sentence structure includes:

[0088] Determine the index position m of the keyword in the standard question and synonym question;

[0089] Extract the content words indexed before m from the sentence structure, and denot them as the preceding adjacent content word s1;

[0090] Extract the content words indexed after m from the sentence structure, and denot them as the next adjacent content word s2;

[0091] The two pairs (s1, s2) are formed by s1 and s2.

[0092] The content words are words with explicit lexical meanings, including nouns, verbs, adjectives, etc. Furthermore, if the keyword is at the beginning of the sentence or there is no content word preceding the keyword, then s1 is 0; if the keyword is at the end of the sentence or there is no content word following the keyword, then s2 is 0.

[0093] In one embodiment of the present invention, one of the standard questions is: "Where is your new delivery address?" Then, according to the sentence structure: pron+aux.v+n+v+int, the extracted s1 is "yes" and the extracted s2 is "0".

[0094] S5. Randomly select a preset number of query word terms from the keywords, and select a preset number of preceding and following content words from the tuples. Based on the keywords, preceding and following content words, and the proper nouns, form a preset number of extended questions according to a preset grammatical format.

[0095] Specifically, the step of extracting a preset number of preceding and following content words from the binary tuple includes:

[0096] The set q1 is obtained by removing duplicates from the preceding adjacent content words, and the set q2 is obtained by removing duplicates from the following adjacent content words. A preset number of preceding adjacent content words and a preset number of following adjacent content words are extracted from the sets q1 and q2 respectively using permutation and combination formulas.

[0097] Furthermore, the preset grammatical format can be the structure that makes up a complete sentence. For example, the grammatical structure in Chinese can be subject (noun or pronoun) + predicate (verb) + object (noun or pronoun), etc.

[0098] This invention can automatically generate extended questions based on the input question, without requiring the user to manually construct them. The generated extended questions are transformed from the input question and will not deviate from the semantics of the original question, thereby enriching the knowledge base and improving the accuracy of the answers output by the intelligent customer service.

[0099] like Figure 2 The diagram shown is a functional block diagram of a problem extension device provided in an embodiment of the present invention.

[0100] The question expansion device 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the question expansion device 100 may include a question parsing module 101, a keyword extraction module 102, a sentence structure generation module 103, a binary tuple extraction module 104, and an expanded question generation module 105. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0101] In this embodiment, the functions of each module / unit are as follows:

[0102] The question parsing module 101 is used to obtain the question to be expanded and extract the question mode words and entity nouns in the question to be expanded.

[0103] The keyword extraction module 102 is used to extract questions containing the inquiry method words from a preset question and answer database and record them as standard questions and questions with the same meaning as the standard questions as synonym questions, and to record the inquiry method words and other inquiry method words contained in the synonym questions as keywords.

[0104] The sentence structure generation module 103 is used to perform word segmentation and part-of-speech tagging on the standard questions and synonym questions to obtain the sentence structure.

[0105] The binary extraction module 104 is used to extract the preceding and following content words of the keyword in the standard question and synonym question according to the sentence structure, and to form a binary tuple from the preceding and following content words.

[0106] The extended question generation module 105 is used to randomly extract a preset number of query word terms from the keywords, extract a preset number of preceding and following content words from the tuples, and form a preset number of extended questions according to the keywords, preceding and following content words, and the proper nouns in a preset grammatical format.

[0107] In detail, the modules in the problem expansion device 100 described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The problem extension method uses the same technical means and can produce the same technical effect, so it will not be elaborated here.

[0108] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements the problem extension method according to an embodiment of the present invention.

[0109] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program, such as a problem extension program, stored in the memory 11 and capable of running on the processor 10.

[0110] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing problem extension programs) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0111] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as code for problem extension programs, but also to temporarily store data that has been output or will be output.

[0112] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0113] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0114] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0115] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0116] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0117] The problem extension program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions that, when run in the processor 10, can achieve the following:

[0118] Obtain the question to be expanded, and extract the query mode words and entity nouns from the question to be expanded;

[0119] Extract questions containing the aforementioned question-and-answer term from a pre-defined question-and-answer database and record them as standard questions. Record questions with the same meaning as the standard questions as synonym questions. Collect the aforementioned question-and-answer term and other question-and-answer term contained in the synonym questions and record them as keywords.

[0120] The standard questions and synonym questions are segmented and tagged with parts of speech to obtain the sentence structure;

[0121] Based on the sentence structure, extract the preceding and following content words of the keywords in the standard question and synonym question, and form a binary tuple with the preceding and following content words;

[0122] A preset number of query word terms are randomly selected from the keywords, and a preset number of preceding and following content words are selected from the tuples. Based on the keywords, preceding and following content words, and the proper nouns, a preset number of extended questions are formed according to a preset grammatical format.

[0123] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0124] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0125] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0126] Obtain the question to be expanded, and extract the query mode words and entity nouns from the question to be expanded;

[0127] Extract questions containing the aforementioned question-and-answer term from a pre-defined question-and-answer database and record them as standard questions. Record questions with the same meaning as the standard questions as synonym questions. Collect the aforementioned question-and-answer term and other question-and-answer term contained in the synonym questions and record them as keywords.

[0128] The standard questions and synonym questions are segmented and tagged with parts of speech to obtain the sentence structure;

[0129] Based on the sentence structure, extract the preceding and following content words of the keywords in the standard question and synonym question, and form a binary tuple with the preceding and following content words;

[0130] A preset number of query word terms are randomly selected from the keywords, and a preset number of preceding and following content words are selected from the tuples. Based on the keywords, preceding and following content words, and the proper nouns, a preset number of extended questions are formed according to a preset grammatical format.

[0131] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0132] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0133] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0134] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0135] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0136] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0137] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0138] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for extending a problem, characterized in that, The method includes: Obtain the question to be expanded, and extract the query mode words and entity nouns from the question to be expanded; Extract questions containing the aforementioned question-and-answer term from a pre-defined question-and-answer database and record them as standard questions. Record questions with the same meaning as the standard questions as synonym questions. Collect the aforementioned question-and-answer term and other question-and-answer term contained in the synonym questions and record them as keywords. The standard questions and synonym questions are segmented and tagged with parts of speech to obtain the sentence structure; Based on the sentence structure, extract the preceding and following content words of the keywords in the standard question and synonym question, and form a binary tuple with the preceding and following content words; A preset number of query word terms are randomly selected from the keywords, and a preset number of preceding and following content words are selected from the tuples. Based on the keywords, preceding and following content words, and proper nouns, a preset number of extended questions are formed according to a preset grammatical format. The step of extracting the preceding and following content words of the keyword in the standard question and synonym question based on the sentence structure includes: determining the index position m of the keyword in the standard question and synonym question; extracting the content word before the index m from the sentence structure, denoted as the preceding adjacent content word s1; extracting the content word after the index m from the sentence structure, denoted as the following adjacent content word s2; and forming a tuple (s1, s2) from s1 and s2.

2. The problem expansion method as described in claim 1, characterized in that, The word segmentation of the standard question and the synonym question includes: According to the preset word segmentation strategy, the strings in the standard question and the synonym question are matched with words in a pre-built word segmentation dictionary to obtain an initial word segmentation set; Based on the initial word segmentation set, a pre-built probabilistic word segmentation model is used. The word segmentation of the standard question and the synonym question is calculated. in, For the initial word segmentation set, The number of words in the initial word segmentation set. Indicates in participle When the word appears The probability of occurrence is selected by choosing word segments whose probability is greater than a preset threshold. As the segmentation of the standard question and the synonym question.

3. The problem expansion method as described in claim 1, characterized in that, The extraction of query mode words from the question to be expanded includes: The question to be expanded is matched with a preset extended vocabulary, and the words in the question to be expanded that successfully match the extended vocabulary are used as the query mode words in the expanded question.

4. The problem expansion method as described in claim 1, characterized in that, The step of extracting questions containing the aforementioned question-asking terms from a pre-defined question-and-answer database and labeling them as standard questions, and questions with the same meaning as the standard questions and labeling them as synonymous questions, includes: Retrieve the query method words from the preset question-and-answer database and mark the question sentences containing the query method words; The marked questions are extracted into a preset text document and recorded as standard questions; The questions that have a mapping relationship with the standard questions are extracted into the text document and denoted as synonym questions.

5. The problem expansion method as described in claim 1, characterized in that, The process of obtaining the question to be expanded includes: Accepts user input for expanded questions; Determine the text format of the question to be expanded; When the question to be expanded is in text format, the question to be expanded is obtained directly; When the question to be expanded is in text format or speech format, a preset text conversion tool is used to convert the speech format question to be expanded into a text format question.

6. A problem expansion device, characterized in that, The device includes: The question parsing module is used to obtain the question to be expanded and extract the query mode words and entity nouns from the question to be expanded; The keyword extraction module is used to extract questions containing the query method words from a preset question and answer database and record them as standard questions and questions with the same meaning as the standard questions as synonym questions, and record the query method words and other query method words contained in the synonym questions as keywords. The sentence structure generation module is used to perform word segmentation and part-of-speech tagging on the standard questions and synonym questions to obtain the sentence structure. The binary extraction module is used to extract the preceding and following content words of the keyword in the standard question and synonym question according to the sentence structure, and to form a binary tuple from the preceding and following content words. The extended question generation module is used to randomly extract a preset number of query word terms from the keywords, extract a preset number of preceding and following content words from the tuples, and form a preset number of extended questions according to the keywords, preceding and following content words, and proper nouns in a preset grammatical format. The step of extracting the preceding and following content words of the keyword in the standard question and synonym question based on the sentence structure includes: determining the index position m of the keyword in the standard question and synonym question; extracting the content word before the index m from the sentence structure, denoted as the preceding adjacent content word s1; extracting the content word after the index m from the sentence structure, denoted as the following adjacent content word s2; and forming a tuple (s1, s2) from s1 and s2.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the problem extension method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the problem extension method as described in any one of claims 1 to 5.

Images