Question and answer result display method, device, equipment and storage medium

Abstract

The embodiment of the present application provides a method, device, equipment and storage medium for displaying question and answer results, the method comprising: receiving a target question asked by a user, generating an answer corresponding to the target question; performing word segmentation and keyword extraction on the answer, and if the keyword hits the target, performing text analysis on the answer to generate structured data; generating visual display information based on the structured data to display the question and answer result image corresponding to the target question. The present application can solve the problem that the prior art cannot provide intuitive and effective question and answer results, and thus cannot meet the user's needs for more intuitive and efficient display of the required information.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of intelligent question and answer, and in particular, to a method, device, equipment and storage medium for displaying question and answer results. Background Art

[0002] With the development of artificial intelligence, the research and development of intelligent question-answering technology is very hot, and related technologies have been widely used in various smart devices. At present, smart devices such as smart TVs and smart screens generally support voice question-answering systems. The main functions are voice and text interaction. In the most commonly used chat and search-based question-answering, the content returned to users is basically text, voice answers, or retrieved text content, such as news, encyclopedia introductions, etc.

[0003] In today's information society, the quality of information depends largely on how it is expressed. In addition, current research is basically focused on improving the accuracy of answers, and the answers returned are mostly sentences or other text content. Therefore, simply returning data to users in the form of text or voice, especially returning long texts, makes it difficult for users to concentrate and read for a long time, and they cannot quickly grasp the key points of the required information, and cannot meet users' needs for more intuitive and efficient presentation of the required information.

[0004] Therefore, the existing technology cannot provide intuitive and effective question-and-answer results, and thus cannot meet the user's demand for a more intuitive and efficient presentation of the required information. Summary of the invention

[0005] The embodiments of the present application provide a question-and-answer result display method, apparatus, device, and storage medium to solve the problem that the prior art cannot provide intuitive and effective question-and-answer results, and thus cannot meet the user's needs for more intuitive and efficient presentation of the required information.

[0006] In a first aspect, an embodiment of the present application provides a method for displaying question and answer results, including:

[0007] Receive a target question asked by a user, and generate an answer corresponding to the target question;

[0008] Perform word segmentation and keyword extraction on the answer. If the keyword hits the target, perform text analysis on the answer to generate structured data;

[0009] Based on the structured data, visual display information is generated to display the question and answer result image corresponding to the target question.

[0010] In a possible design, the text analysis is performed on the answer to generate structured data, including:

[0011] If the answer carries additional text information associated with the answer, word frequency statistics, entity and relationship extraction, and event extraction are performed on the answer and the additional text information respectively to generate the structured data.

[0012] In a possible design, the answer and the additional text information are respectively subjected to word frequency statistics, entity and relationship extraction, and event extraction to generate the structured data, including:

[0013] Performing word frequency statistics on the answer and the additional text information to obtain a word frequency statistical result;

[0014] Jointly decoding the main entity and the object entity in the answer and the additional text information to obtain an entity pair, and determining the relationship between the main entity and the object entity by learning the mapping between the main entity and the object entity; wherein the entity pair includes the main entity and the object entity;

[0015] Performing event extraction on the answer and the additional text information to obtain event identification information and / or argument role classification information;

[0016] Generate structured data based on word frequency statistics, entity pairs, relationships between subject entities and object entities, and event identification information and / or argument role classification information.

[0017] In one possible design, the method further includes:

[0018] Information retrieval is performed in the data for at least one of the answer, the additional text information and the structured data. If a result is retrieved, the retrieval result is added to the structured data as additional information to generate new structured data.

[0019] In a possible design, generating visual display information according to the structured data includes:

[0020] Matching the structured data with a picture style to generate visual display information; wherein the picture style at least includes a word cloud diagram, a relationship network diagram, a static / dynamic statistical diagram, a timeline diagram, a trend diagram, a map, and a QR code diagram;

[0021] Display the visual display information.

[0022] In a possible design, the word segmentation and keyword extraction of the answer includes:

[0023] Performing word segmentation processing on the answer and the additional text information to obtain a plurality of word segments;

[0024] Keyword extraction is performed on the multiple participles to obtain multiple keywords, and the multiple participles and the multiple keywords are used to provide word frequency statistics.

[0025] In a second aspect, an embodiment of the present application provides a question and answer result display device, the device comprising:

[0026] The first processing module is used to receive a target question asked by a user and generate an answer corresponding to the target question;

[0027] The second processing module is used to perform word segmentation and keyword extraction on the answer. If the keyword hits the target, the answer is subjected to text analysis to generate structured data;

[0028] The display module is used to generate visual display information based on the structured data to display the question and answer result image corresponding to the target question.

[0029] In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor and a memory;

[0030] The memory stores computer-executable instructions;

[0031] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the question and answer result display method as described in the above-mentioned first aspect and various possible designs of the first aspect.

[0032] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer execution instructions stored thereon. When a processor executes the computer execution instructions, the steps of the question and answer result display method described in the above-mentioned first aspect and various possible designs of the first aspect are implemented.

[0033] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the question and answer result display method as described in the first aspect and various possible designs of the first aspect.

[0034] The question-and-answer result display method, device, equipment, storage medium, and computer program product provided in this embodiment first receive the target question asked by the user and generate the answer corresponding to the target question; then perform word segmentation and keyword extraction on the answer, and if the keyword hits the target, perform text analysis on the answer to generate structured data; then generate visual display information based on the structured data to display the question-and-answer result image corresponding to the target question. Through visualization technology, the content required by the user is processed in graphics and images, and the diverse and complex text information is visualized in graphics and images, so that the user can view the required content more intuitively and efficiently, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0036] Figure 1 A schematic diagram of a scenario of the question-answer result display method provided for this application;

[0037] Figure 2 A flowchart of a method for displaying question and answer results provided in an embodiment of the present application;

[0038] Figure 3 A flowchart of a method for displaying question and answer results provided in yet another embodiment of the present application;

[0039] Figure 4 A schematic diagram of structured data provided in an embodiment of the present application;

[0040] Figures 5A-5F A schematic diagram of a visual display of question and answer results provided in an embodiment of the present application;

[0041] Figure 6 A flowchart of a method for displaying question and answer results provided in another embodiment of the present application;

[0042] Figure 7 A schematic diagram of the structure of a question and answer result display device provided in an embodiment of the present application;

[0043] Figure 8 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0045] Most smart TVs and smart screens already support voice question-and-answer systems. The main functions are currently voice and text interaction. In addition to specific functions, the content returned to users may include visual content (such as weather maps, etc.). In the most commonly used chat and search-based question-and-answer services, text and voice answers are basically returned to users, or retrieved text content, such as news, encyclopedia introductions, etc. In today's information society, the quality of information depends to a large extent on its expression. Simply returning data to users in the form of text or voice, especially returning long texts, makes it difficult for users to concentrate and read for a long time, and they cannot quickly grasp the key points of the required information, and cannot meet the user's needs for a more intuitive and efficient presentation of the required information. In addition, the current intelligent question-and-answer technology is mainly committed to improving the accuracy of answers, and the answers returned are mostly sentences or other text content, lacking specific attention and systematic optimization for the presentation of answers. Therefore, the existing technology cannot provide intuitive and effective question-and-answer results, and thus cannot meet the user's needs for a more intuitive and efficient presentation of the required information.

[0046] Therefore, in order to solve the above problems, the technical concept of this application is to use visualization technology to process the content required by users in the form of graphics and images, and to visualize the diverse and complex text information in the form of graphics and images, so that users can grasp the required content more intuitively and efficiently; in addition, compared with boring text answers, visual interaction can better increase users' interest in using the question-and-answer system, thereby improving the user experience.

[0047] In practical applications, see Figure 1 As shown, Figure 1 A schematic diagram of a scenario of the question-answer result display method provided in the present application. The execution subject of the embodiment of the present application may be a display device, and the display device may be a smart device such as a smart TV or a smart screen. Taking the smart TV 10 as an example, the process of displaying the question-answer result may be:

[0048] First, the user calls the voice assistant in the smart TV 10 installed with the question-and-answer system, for example, calling Xiao X. Xiao X responds to the call (for example: Hello, Xiao X is here) and displays the question-and-answer window 101. After Xiao X responds, the user asks the question he wants to ask (for example: the family of character A), and the smart TV starts searching for the answer corresponding to the question, and extracts keywords from the answer. If the keyword can be extracted, the answer is analyzed for text, structured data is generated, and visual display information is generated based on the structured data, such as a visual picture based on where the European Cup is held, and displayed on the question-and-answer window.

[0049] Specifically, combined Figure 3 As shown in the figure, firstly, the original text (such as the answer and the additional text information carried in the answer) is mined, such as text preprocessing, text feature extraction, and text feature measurement; then the mined text information is visually drawn, such as primitive design and primitive layout, and then the question and answer results are displayed in the form of pictures and fed back to the user to achieve human-computer interaction. Through text analysis and visualization technology, users are provided with intuitive and efficient question and answer results, thereby improving the user experience.

[0050] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0051] Figure 2 The following is a flow chart of the method for displaying question and answer results provided in the embodiment of the present application. Figure 2 As shown, the method may include:

[0052] S201: Receive a target question asked by a user, and generate an answer corresponding to the target question.

[0053] In this embodiment, the user's question is passed through the question-answering system, and an answer can be generated. Sometimes the answer will be accompanied by text information, such as related encyclopedias, news, etc.

[0054] For example, a user asks "Where is the European Cup held?" and the generated answer is "This year's European Cup is held in: Location A, Location B, Location C." The answer may also carry other sports events as additional text information.

[0055] S202: Segment the answer and extract keywords. If the keywords hit the target, perform text analysis on the answer to generate structured data.

[0056] In this embodiment, during the keyword extraction process of the answer, since the answer may be in text form, the answer can be segmented and then the keywords can be extracted from the segmented words. If the keyword hits the target, the visualization display step is entered, otherwise the original answer is directly output (if the question-answering system directly returns the bottom-up result or returns a non-text result, the original answer is directly output).

[0057] In a possible design, this embodiment provides a detailed description of how to extract keywords based on the above embodiment. Segmentation and keyword extraction of the answer can be achieved through the following steps:

[0058] Step a1, performing word segmentation processing on the answer and the additional text information to obtain a plurality of word segments;

[0059] Step a2: extract keywords from the multiple segmented words to obtain multiple keywords. The multiple segmented words and the multiple keywords are used to provide word frequency statistics.

[0060] In this embodiment, the word segmentation based on statistics, the specific steps are: dynamic planning to find the maximum probability path, find the maximum segmentation combination based on word frequency, for unregistered words, use the HMM model based on the ability of Chinese characters to form words, such as identifying unregistered nouns such as names, place names, and institution names. And use the Viterbi algorithm to recalculate the optimal segmentation path for word segmentation processing of the result text. Then, based on the word segmentation results, keyword extraction is performed. See Table 1 below (taking the 2020 European Cup as an example).

[0061] Table 1

[0062]

[0063] S203: Generate visual display information based on the structured data to display the question and answer result image corresponding to the target question.

[0064] In this embodiment, visualization generation is mainly based on Python, and the visualization styles include: wordnet word cloud, relationship network diagram, timeline, trend chart, map, treemap, QR code generation, etc. Based on structured data, a relatively matching picture style is found from the visualization style, and then based on the matched picture style, the structured data is generated into a corresponding question and answer result image.

[0065] The question-and-answer result display method provided in this embodiment first receives the target question asked by the user and generates the answer corresponding to the target question; then performs word segmentation and keyword extraction on the answer, and if the keyword hits the target, performs text analysis on the answer to generate structured data; then generates visual display information based on the structured data to display the question-and-answer result image corresponding to the target question. Through visualization technology, the content required by the user is processed into graphics and images, and the diverse and complex text information is visualized in graphics and images, so that the user can view the required content more intuitively and efficiently, thereby improving the user experience.

[0066] In a possible design, this embodiment provides a detailed description of S202 based on the above embodiment. Text analysis of the answer is performed to generate structured data, which can be achieved by the following steps:

[0067] If the answer carries additional text information associated with the answer, word frequency statistics, entity and relationship extraction, and event extraction are performed on the answer and the additional text information respectively to generate the structured data.

[0068] In this embodiment, text analysis may include but is not limited to modules such as word frequency statistics, entity and relationship extraction, event extraction, and information retrieval (new functional modules may be added later based on actual business needs), which are used to process answers and additional text information and generate structured data.

[0069] Among them, word frequency statistics are used to count keywords in the text, and the method is [target word].count. If the answer is a long text, in addition to the keywords, the overall word frequency statistics are performed after the text is segmented; the entity, relationship, and event extract structured triples or multi-tuple information; the information retrieval module is based on information retrieval technology, using keywords to search in the database (ElasticSearch), and if the results are obtained, they will be added as additional information. The details are shown in Table 2 below:

[0070] Table 2

[0071]

[0072]

[0073] In one possible design, the process of generating structured data is:

[0074] Step b1, performing word frequency statistics on the answer and the additional text information to obtain a word frequency statistical result;

[0075] The main entity and the guest entity in the answer and the additional text information are jointly decoded to obtain an entity pair, and the relationship between the main entity and the guest entity is determined by learning the mapping between the main entity and the guest entity; wherein the entity pair includes the main entity and the guest entity.

[0076] Step b2: extracting events from the answer and the additional text information to obtain event identification information and / or argument role classification information.

[0077] Step b3: Generate structured data based on word frequency statistics, entity pairs, relationships between subject entities and object entities, and event identification information and / or argument role classification information.

[0078] In this embodiment, for word frequency statistics, word frequency statistics are performed based on the keywords extracted in the above embodiment.

[0079] Regarding information extraction (used for entity, relationship and event extraction of question and answer result text), that is, extracting specific events or factual information from natural language text to help us automatically classify, extract and reconstruct massive content. This information usually includes entities, relationships, and events. For example, extracting time, place, key figures, etc. from news. Information extraction mainly includes three subtasks: a) entity extraction and linking: that is, named entity recognition; b) relationship extraction: usually what we call triple extraction, mainly used to extract the relationship between entities; c) event extraction: equivalent to the extraction of a multi-relationship.

[0080] Among them, the joint extraction of entities and relations. Named Entity Recognition (NER), also known as "proper name recognition", refers to the recognition of entities with specific meanings in text, mainly including names of people, places, institutions, proper nouns, etc. NER is the underlying basic signal of Deep Query Understanding (DQU), and is mainly used in search recall, user intent recognition, entity linking and other links.

[0081] In addition, relation extraction usually comes after entity extraction and entity linking. After identifying the key entities in the sentence, it is also necessary to extract the semantic relationship between two or more entities. Semantic relations are usually used to connect two entities and express the main meaning of the text together with the entities. Common relation extraction results can be represented by a triple of SPO structure, namely (Subject, Predication, Object).

[0082] Specifically, the CASREL (cascade binary tagging framework) model with BERT as encoding is used to build a triple relationship extraction algorithm framework. The algorithm extracts entity pairs by jointly decoding the main entity and the guest entity, and determines the relationship between the two by learning the mapping between the main entity and the guest entity. The objective function of the algorithm is as follows:

[0083]

[0084] Where D represents the training data set, sentence X j ∈D,T j ={(s,r,o)} represents X j All possible triples in ; s represents subject (i.e., main entity), r represents relation (i.e., relationship), o represents object (i.e., guest entity); p r Indicates the probability that the model recognizes o for a given s in relation r. If o is not recognized, it is empty and is represented by express.

[0085] For event extraction, events of interest to users can be extracted from unstructured information and presented to users in a structured manner. The event extraction task can be decomposed into four subtasks: trigger word recognition, event type classification, argument recognition, and role classification tasks. Among them, trigger word recognition and event type classification can be combined into the event recognition task. Event recognition determines the event type to which each word in a sentence belongs, which is a word-based multi-classification task. Argument recognition and role classification can be combined into an argument role classification task. The role classification task is a multi-classification task based on word pairs, which determines the role relationship between any pair of trigger words and entities in a sentence.

[0086] Therefore, event extraction tasks can be generally divided into two categories: meta-event extraction and topic event extraction. Meta-events represent the occurrence of an action or a change in state. They are often driven by verbs, but can also be triggered by other parts of speech such as nouns that can represent actions. They include the main components involved in the action (such as time, place, people, etc.). The topic event includes a core event or activity and all events and activities directly related to it, and can be composed of multiple meta-event fragments.

[0087] In this embodiment, the method is mainly based on the meta-event extraction method, and the framework also uses the BERT-encoded triple relationship extraction algorithm framework, but the definition in the data format is different.

[0088] In a possible design, this embodiment provides a detailed description of the question and answer result display method based on the above embodiment. The method can also be implemented by the following steps:

[0089] An information search is performed in a database for at least one of the answer, the additional text information and the structured data. If a result is found, the search result is added to the structured data as additional information to generate new structured data.

[0090] In this embodiment, information retrieval is the main way for users to query and obtain information. According to the classification of data, search is also divided into two types: a) search for structured data: such as search for databases or metadata; b) search for unstructured data: such as search for file content, grep command under Linux, and search engines can search a large amount of content data. In this embodiment, it is mainly based on structured data, and the search is performed in the database. If the search results are found, they are added as additional information (see Table 2).

[0091] In a possible design, how to generate visual display information according to the structured data can be achieved through the following steps:

[0092] Step c1, matching the structured data with a picture style to generate visual display information; wherein the picture style at least includes a word cloud diagram, a relationship network diagram, a static / dynamic statistical diagram, a timeline diagram, a trend diagram, a map, and a QR code diagram;

[0093] Step c2: display the visual display information.

[0094] In this embodiment, the generated structured data (see Figure 4 The schematic diagram of the structured data shown in the figure) matches the output style and determines whether to output the original text answer at the same time. Taking the above-mentioned European Cup as an example, the image style is matched: map() class—world. A visualization map, i.e., visualization display information, is generated, and the visualization result, i.e., visualization display information, is returned to the user.

[0095] For example, the classification example is shown (see Figures 5A-5F Schematic diagram of the visual display of the question and answer results provided):

[0096] a) Wordnet word cloud. Combine the blessing words in Table 3 to generate a blessing word cloud (combined Figure 5A Word cloud diagram shown)

[0097] Table 3

[0098]

[0099] Among them, according to business needs, keyword masks can also be customized. For example, the New Year keyword mask is set to the style of "Good fortune arrives", and a special style word cloud is generated (combined with Figure 5B the word cloud diagram shown).

[0100] b) Relationship network diagram. Based on the person relationships in Table 2, a relationship network diagram is generated (combined with Figure 5C the relationship network diagram shown).

[0101] Table 4

[0102]

[0103] c) Static / dynamic statistical chart. Based on the previous medal information in Table 5, a statistical chart is generated (combined with Figure 5D the statistical chart shown, where M, P, and Q represent the locations of the medal winners).

[0104] Table 5

[0105]

[0106]

[0107] d) Timeline. Based on a certain movie series in Table 6, a timeline diagram is generated (combined with Figure 5E the timeline diagram shown).

[0108] Table 6

[0109]

[0110] e) Treemap. Based on the distribution information of the direct stores of a certain brand of mobile phone in Table 7, a treemap is generated (combined with Fig. 5F the treemap shown).

[0111] Table 7

[0112]

[0113] The display of maps and QR codes is not listed one by one here. The generation process can refer to the process of generating visualization display information based on structured data in the above embodiments, which will not be elaborated here.

[0114] In practical applications, combined with Figure 6The flowchart of the question-answering result display method shown in the figure. First, the user's query passes through the question-answering system, and an answer can be generated (sometimes the answer will be accompanied by text information, such as related encyclopedias, news, etc.). The generated information is segmented and keywords are extracted. If the keyword hits the target, it enters the visualization display step (based on the structured data matching output style, visualization display generation, and then output visualization + text answer). Otherwise, the original answer is directly output (if the question-answering system directly returns a fallback result or returns a non-text result, the original answer is also directly output).

[0115] Corresponding to the question and answer result display method of the above embodiment, Figure 7 This is a schematic diagram of the structure of the question and answer result display device provided in the embodiment of the present application. For the convenience of explanation, only the parts related to the embodiment of the present application are shown. Figure 7 As shown, the question and answer result display device 70 includes: a first processing module 701, a second processing module 702, and a display module 703; the first processing module 701 is used to receive a target question asked by a user and generate an answer corresponding to the target question; the second processing module 702 is used to perform word segmentation and keyword extraction on the answer, and if the keyword hits the target, perform text analysis on the answer to generate structured data; the display module 703 is used to generate visual display information based on the structured data, so as to display the question and answer result image corresponding to the target question.

[0116] The question and answer result display device provided in this embodiment is configured with a first processing module 701, a second processing module 702, and a display module 603, which are used to receive a target question asked by a user and generate an answer corresponding to the target question; then the answer is segmented and keyword extracted, and if the keyword hits the target, the answer is subjected to text analysis to generate structured data; and based on the structured data, visual display information is generated to display the question and answer result image corresponding to the target question. Through visualization technology, the content required by the user is processed in graphics and images, and the diverse and complex text information is visualized in graphics and images, so that the user can view the required content more intuitively and efficiently, thereby improving the user experience.

[0117] The device provided in the embodiment of the present application can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar, and the embodiment of the present application will not be repeated here.

[0118] In one possible design, the second processing module includes a first processing unit; the first processing unit is used to perform word frequency statistics, entity and relationship extraction, and event extraction on the answer and the additional text information, respectively, to generate the structured data when the answer carries additional text information associated with the answer.

[0119] In a possible design, the first processing unit is specifically configured to:

[0120] Performing word frequency statistics on the answer and the additional text information to obtain a word frequency statistical result;

[0121] Jointly decoding the main entity and the object entity in the answer and the additional text information to obtain an entity pair, and determining the relationship between the main entity and the object entity by learning the mapping between the main entity and the object entity; wherein the entity pair includes the main entity and the object entity;

[0122] Performing event extraction on the answer and the additional text information to obtain event identification information and / or argument role classification information;

[0123] Generate structured data based on word frequency statistics, entity pairs, relationships between subject entities and object entities, and event identification information and / or argument role classification information.

[0124] In one possible design, the question and answer result display device may also include a third processing module, which is used to perform information retrieval in a database for at least one of the answer, the additional text information and the structured data. If a result is retrieved, the retrieval result is added to the structured data as additional information to generate new structured data.

[0125] In a possible design, the display processing module is specifically used to:

[0126] Matching the structured data with a picture style to generate visual display information; wherein the picture style at least includes a word cloud diagram, a relationship network diagram, a static / dynamic statistical diagram, a timeline diagram, a trend diagram, a map, and a QR code diagram;

[0127] Display the visual display information.

[0128] In a possible design, the second processing module is further specifically used for:

[0129] Performing word segmentation processing on the answer and the additional text information to obtain a plurality of word segments;

[0130] Keyword extraction is performed on the multiple participles to obtain multiple keywords, and the multiple participles and the multiple keywords are used to provide word frequency statistics.

[0131] Figure 8 The hardware structure diagram of the electronic device provided in the embodiment of the present application is shown in FIG. Figure 8 As shown, the electronic device 80 provided in this embodiment includes: at least one processor 801 and a memory 802. The processor 801 and the memory 802 are connected via a bus 803.

[0132] In a specific implementation process, at least one processor 801 executes the computer-executable instructions stored in the memory 802, so that at least one processor 801 executes the method in the above method embodiment.

[0133] The specific implementation process of the processor 801 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0134] In the above Figure 8 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0135] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0136] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0137] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the question and answer result display method of the above method embodiment is implemented.

[0138] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the question and answer result display method of the above method embodiment.

[0139] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0140] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0141] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for displaying question and answer results, characterized in that: The method comprises: Receive a target question asked by a user, and generate an answer corresponding to the target question; Perform word segmentation and keyword extraction on the answer. If the keyword hits the target, perform text analysis on the answer to generate structured data; Matching the image style to the structured data to generate visual display information for displaying the question-answer result image corresponding to the target question; The text analysis of the answer is performed to generate structured data, including: If the answer carries additional text information associated with the answer, then frequency statistics are performed on the answer and the additional text information to obtain a frequency statistics result; Jointly decoding the main entity and the object entity in the answer and the additional text information to obtain an entity pair, and determining the relationship between the main entity and the object entity by learning the mapping between the main entity and the object entity; wherein the entity pair includes the main entity and the object entity; Performing event extraction on the answer and the additional text information to obtain event identification information and / or argument role classification information; Generate structured data based on word frequency statistics, entity pairs, relationships between subject entities and object entities, and event identification information and / or argument role classification information.

2. The method according to claim 1, characterized in that The method further comprises: An information search is performed in a database for at least one of the answer, the additional text information and the structured data. If a result is found, the search result is added to the structured data as additional information to generate new structured data.

3. The method according to claim 1 or 2, characterized in that: The image styles include at least a word cloud diagram, a relationship network diagram, a static / dynamic statistical diagram, a timeline diagram, a trend diagram, a map, and a QR code diagram; After generating the visual display information, the method further includes: displaying the visual display information.

4. The method according to claim 1, characterized in that: The word segmentation and keyword extraction of the answer includes: Performing word segmentation processing on the answer and the additional text information to obtain a plurality of word segments; Keyword extraction is performed on the multiple participles to obtain multiple keywords, and the multiple participles and the multiple keywords are used to provide word frequency statistics.

5. A display adjustment device, characterized in that: The device comprises: The first processing module is used to receive a target question asked by a user and generate an answer corresponding to the target question; The second processing module is used to perform word segmentation and keyword extraction on the answer. If the keyword hits the target, the answer is subjected to text analysis to generate structured data; A display module, used to match the image style to the structured data, generate visual display information, and display the question and answer result image corresponding to the target question; The second processing module is specifically configured to perform word frequency statistics on the answer and the additional text information to obtain a word frequency statistics result if the answer carries additional text information associated with the answer; Jointly decoding the main entity and the object entity in the answer and the additional text information to obtain an entity pair, and determining the relationship between the main entity and the object entity by learning the mapping between the main entity and the object entity; wherein the entity pair includes the main entity and the object entity; Performing event extraction on the answer and the additional text information to obtain event identification information and / or argument role classification information; Generate structured data based on word frequency statistics, entity pairs, relationships between subject entities and object entities, and event identification information and / or argument role classification information.

6. An electronic device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the question and answer result display method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the question and answer result display method as described in any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the question and answer result display method described in any one of claims 1 to 4 are implemented.

Images