Content management method and device based on prompt word question and answer interaction, equipment and medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses a content management method based on prompt word question and answer interaction, which comprises the following steps: obtaining an input question of an interaction interface, extracting a prompt word of the input question to obtain an input prompt word of the input question; and sequentially performing key word verification, template expectation verification, individualization verification and emotion abnormality judgment on the input prompt word, so that a feedback answer, an expected template, an individualized answer or a question answer of the input prompt word can be selectively generated through the verification. In addition, the application also relates to the blockchain technology, and data lists can be stored in nodes of the blockchain. The application also discloses a content management device, equipment and medium based on prompt word question and answer interaction. The application can be applied to the field of digital medicine, and the content management based on prompt word question and answer interaction can improve the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a content management method and device based on prompt word question and answer interaction, equipment and medium. BACKGROUND

[0002] A medical health management platform is a software system that helps hospitals manage digital content and publish digital content to the network. Users of the medical health management platform can use the platform to create, edit, organize, and publish content. As a platform for storing digital content, the medical health management platform has evolved into various operation methods and interaction processes to meet different user demands and facilitate collaborative management of digital content.

[0003] Traditional medical health management platforms use manual forms and drag-and-drop configurations, which not only require a certain amount of manpower to maintain, but also result in poor user experience for patients. Moreover, for different patients, supporting medical staff often repeat the same answers to the same questions, which wastes a portion of operating and research and development costs and affects the speed of responding to patients. Therefore, how to improve the experience of users when asking questions and answering questions has become a problem that needs to be solved. SUMMARY

[0004] The present application provides a content management method and device based on prompt word question and answer interaction, which mainly aims to solve the problem of low experience of users when asking questions and answering questions.

[0005] To achieve the above-mentioned purpose, the present application provides a content management method based on prompt word question and answer interaction, comprising:

[0006] Obtaining an input question of an interaction interface, extracting a prompt word from the input question to obtain an input prompt word of the input question;

[0007] Obtaining an interaction database of the interaction interface, and determining whether the input prompt word passes a keyword verification using the interaction database;

[0008] When the input prompt word passes the keyword verification, generating a feedback answer of the input prompt word using the interaction database;

[0009] When the input prompt word does not pass the keyword verification, determining whether the input prompt word passes a template expectation verification;

[0010] When the input prompt word passes the template expectation verification, generating an expected template of the input question according to the input prompt word;

[0011] determining whether the input prompt word passes personalized verification when the input prompt word does not pass the template expectation verification;

[0012] generating a personalized answer to the input question according to the input prompt word when the input prompt word passes the personalized verification;

[0013] when the input prompt word does not pass the personalized verification, performing emotional abnormality judgment on the input prompt word, generating a communication type of the input question according to the emotional abnormality judgment result, and generating a question answer of the input question according to the communication type.

[0014] Optionally, the prompt word extraction on the input question comprises:

[0015] performing word segmentation processing on the input question to obtain question word segmentation of the input question;

[0016] generating word segmentation frequency of the question word segmentation one by one, performing common word extraction on the question word segmentation according to the word segmentation frequency, and obtaining common words of the question word segmentation;

[0017] performing stop word filtering on the common words to obtain standard word segmentation of the question word segmentation;

[0018] generating the input prompt word of the input question according to the standard word segmentation.

[0019] Optionally, the determination of whether the input prompt word passes keyword verification by using the interaction database comprises:

[0020] obtaining an interaction keyword of the interaction database, performing vector conversion on the interaction keyword to obtain an interaction vector of the interaction keyword;

[0021] performing vector conversion on the input prompt word to obtain an input vector of the input prompt word;

[0022] calculating a vector distance between the interaction vector and the input vector, and determining a word similarity between the input prompt word and the interaction keyword according to the vector distance;

[0023] performing keyword verification on the input prompt word by using the word similarity and a preset similarity threshold.

[0024] Optionally, the generation of the feedback answer of the input prompt word by using the interaction database comprises:

[0025] obtaining a similar keyword of the input prompt word, and determining a link index of the similar keyword in the interaction database;

[0026] generate the feedback answer of the input prompt word according to the link data of the similar keywords.

[0027] Optionally, the generating the expected template of the input question according to the input prompt word comprises:

[0028] performing function word screening on the input prompt word to obtain an input function word of the input prompt word;

[0029] obtaining a historical template of a historical user, performing primary filtering on the historical template according to the input function word to obtain a primary template of the historical template;

[0030] performing module configuration on the primary template according to the input function word to obtain a configuration template of the primary template, and determining that the configuration template is the expected template of the input question.

[0031] Optionally, the generating the personalized answer of the input question according to the input prompt word comprises:

[0032] determining an input user of the input question according to an interaction interface of the input question, and obtaining a historical habit value of the input user;

[0033] generating a word weight of the input prompt word according to the historical habit value;

[0034] generating an input weighted value of the input question according to the word weight and the input prompt word, and generating the personalized answer of the input question according to the input weighted value.

[0035] Optionally, the performing emotion abnormality judgment on the input prompt word and generating the communication type of the input question according to the emotion abnormality judgment result comprises:

[0036] obtaining a question context of the input question, performing emotion analysis on the input prompt word according to the question context to obtain an input emotion value of the input prompt word;

[0037] performing emotion abnormality judgment on the input prompt word by using the input emotion value and a preset emotion threshold value, and determining that the communication type of the input question is intelligent reply when the input emotion value is greater than the preset emotion threshold value;

[0038] determining that the communication type of the input question is manual reply when the input emotion value is less than or equal to the preset emotion threshold value.

[0039] To solve the above problems, the application further provides a content management device based on prompt word question and answer interaction, the device comprising:

[0040] The prompt word extraction module is configured to obtain an input question of an interactive interface, perform prompt word extraction on the input question, and obtain an input prompt word of the input question.

[0041] The keyword verification is configured to obtain an interactive database of the interactive interface, and determine whether the input prompt word passes the keyword verification by using the interactive database.

[0042] The feedback answer generation module is configured to generate a feedback answer of the input prompt word by using the interactive database when the input prompt word passes the keyword verification.

[0043] The template expectation verification module is configured to determine whether the input prompt word passes template expectation verification when the input prompt word does not pass the keyword verification.

[0044] The expectation template generation module is configured to generate an expectation template of the input question according to the input prompt word when the input prompt word passes the template expectation verification.

[0045] The individualization verification module is configured to determine whether the input prompt word passes individualization verification when the input prompt word does not pass the template expectation verification.

[0046] The individualized answer generation module is configured to generate an individualized answer of the input question according to the input prompt word when the input prompt word passes the individualization verification.

[0047] The emotion abnormality judgment module is configured to perform emotion abnormality judgment on the input prompt word when the input prompt word does not pass the individualization verification, generate a communication type of the input question according to a result of the emotion abnormality judgment, and generate a question answer of the input question according to the communication type.

[0048] To solve the above problems, the present application further provides a device, which comprises:

[0049] at least one processor; and

[0050] a memory connected to the at least one processor in communication; wherein

[0051] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the content management method based on prompt word question and answer interaction.

[0052] To solve the above problems, the application further provides a medium, wherein at least one computer program is stored in the medium, and the at least one computer program is executed by a processor in a device to implement the content management method based on the prompt word question and answer interaction.

[0053] The embodiment of the application obtains an input question of an interactive interface, extracts a prompt word of the input question, and obtains an input prompt word of the input question, so as to identify a user input appeal based on the input prompt word, and sequentially perform keyword verification, template expectation verification, individualization verification, and emotion abnormality judgment on the input prompt word, so that the user quickly selects the most suitable module for data display and function configuration, greatly improves the configuration and release efficiency of the operation personnel for digital content management, and simultaneously, the emotion abnormality judgment quickly gives an answer while taking care of the emotion of the user, provides support for the corresponding maintenance personnel when necessary, records the current user behavior habit and preference, quickly responds to similar prompt words and performs individualized recommendation, continuously optimizes the digital content management efficiency, and improves the user experience, and therefore, the content management method, device, equipment, and medium based on the prompt word question and answer interaction can solve the problem that the experience is low when the user asks questions and answers. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 A flowchart of the content management method based on the prompt word question and answer interaction provided by an embodiment of the application is shown in the figure.

[0055] Figure 2 A flowchart of the prompt word extraction of a question provided by an embodiment of the application is shown in the figure.

[0056] Figure 3 A flowchart of the keyword verification of a prompt word provided by an embodiment of the application is shown in the figure.

[0057] Figure 4 A function module diagram of the content management device based on the prompt word question and answer interaction provided by an embodiment of the application is shown in the figure.

[0058] Figure 5 A structure diagram of an electronic device for implementing the content management method based on the prompt word question and answer interaction provided by an embodiment of the application is shown in the figure.

[0059] The implementation, functional features, and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are merely intended to explain the application, and are not intended to limit the application.

[0061] The embodiment of the present application provides a content management method based on prompt word question and answer interaction. The execution subject of the content management method based on prompt word question and answer interaction includes but is not limited to at least one of devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the present application. In other words, the content management method based on prompt word question and answer interaction can be executed by software or hardware installed in 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 and the like. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0062] Referring to Figure 1 Fig. 1 shows a flowchart of the content management method based on prompt word question and answer interaction provided by an embodiment of the present application. In the embodiment, the content management method based on prompt word question and answer interaction includes the following steps.

[0063] S1, an input question of an interaction interface is acquired, prompt word extraction is performed on the input question, and an input prompt word of the input question is obtained.

[0064] In the embodiment of the present application, in a medical health platform, the input question of the interaction interface can be a question according to a symptom expression of a user relative, can be acquisition of a medical history of a patient, can be a description of the medical history of the patient, and can be physical data of the patient and the like.

[0065] In detail, the interaction interface refers to an interface that ensures that doctors and patients or users and the platform can effectively communicate on the medical health platform, so that the patients or users can effectively acquire medical information,

[0066] In the embodiment of the present application, referring to Figure 2 Fig. 2 shows that the prompt word extraction is performed on the input question, and the input prompt word of the input question is obtained, and includes the following steps.

[0067] S21, word segmentation processing is performed on the input question, and question word segmentation of the input question is obtained;

[0068] S22, a word segmentation frequency of the question word segmentation is generated one by one, common word extraction is performed on the question word segmentation according to the word segmentation frequency, and common words of the question word segmentation are obtained;

[0069] S23, stop word filtering is performed on the common words, and standard word segmentation of the question word segmentation is obtained;

[0070] S24, generating the input prompt word of the input question according to the standard segmentation.

[0071] In detail, the input prompt word can be patient medical history, such as main medical history, past medical history, family history, and allergy history, etc.; the input prompt word can be patient symptoms, such as pain, fever, vomiting, dizziness, etc.; the input prompt word can be physical data, such as age, height, weight, blood pressure, heart rate, etc.

[0072] In detail, the segmentation processing of the input question can better understand and analyze the input question, and provide clearer basis for subsequent data storage and processing, and at the same time, in the actual interactive interface design, more appropriate input controls and prompt information can be selected according to the segmentation, further optimizing the user experience.

[0073] In detail, the frequency of each segmentation in the question can be counted according to the segmentation of the question. The frequency calculation of the segmentation can help extract important words from the text, weaken stop words, and reduce the number of words. These processes help better understand and analyze the text content, and provide more useful features and data for subsequent natural language processing and machine learning.

[0074] In detail, the stop words can include some common conjunctions, prepositions, and articles, etc. These stop words are not helpful for the processing of the question and the subsequent natural language processing and machine learning, so they need to be filtered.

[0075] Further, the stop word filtering method includes using known stop word list, calculating word frequency, TF-IDF, inverse document frequency, or using part-of-speech tagging in language model for dynamic text processing, wherein some commonly used stop word list can be downloaded and used on the Internet, or special stop word list can be customized according to specific application scenarios.

[0076] In detail, the input prompt word generated according to the standard segmentation of the input question can help the user quickly locate the information to be filled in, and the input is accurate and fast, and at the same time, it can also reduce the error input and repeated filling, improve the input efficiency and experience.

[0077] S2, obtaining the interactive database of the interactive interface, and determining whether the input prompt word passes the keyword verification by using the interactive database.

[0078] In the embodiments of the present application, the interaction database is generally created, maintained and updated during the system development process. Generally, developers can use a database management system (DBMS) or other related tools to create, configure and manage the database. In a medical health system, the interaction database of the interaction interface often needs to be obtained and integrated from multiple channels, such as extracting doctor and patient information from a hospital information system, obtaining price and inventory information from drug and consumable suppliers, and obtaining treatment information from acupuncture and physiotherapy department systems; at the same time, some ready-made open data sources can also be used as the source of the interaction database of the interaction interface, such as government open data and Internet medical health platforms. These data sources need to go through data mining and data cleaning processes to improve the quality and availability of the data.

[0079] In the embodiments of the present application, the interaction database is generally created, maintained and updated during the system development process. Generally, developers can use a database management system (DBMS) or other related tools to create, configure and manage the database. In a medical health system, the interaction database of the interaction interface often needs to be obtained and integrated from multiple channels, such as extracting doctor and patient information from a hospital information system, obtaining price and inventory information from drug and consumable suppliers, and obtaining treatment information from acupuncture and physiotherapy department systems; at the same time, some ready-made open data sources can also be used as the source of the interaction database of the interaction interface, such as government open data and Internet medical health platforms. These data sources need to go through data mining and data cleaning processes to improve the quality and availability of the data. Figure 3 As shown in the method, the step of determining whether the input prompt word passes the keyword verification by using the interaction database comprises:

[0080] S31, obtaining an interaction keyword of the interaction database, and performing vector conversion on the interaction keyword to obtain an interaction vector of the interaction keyword;

[0081] S32, performing vector conversion on the input prompt word to obtain an input vector of the input prompt word;

[0082] S33, calculating a vector distance between the interaction vector and the input vector, and determining a word similarity between the input prompt word and the interaction keyword according to the vector distance;

[0083] S34, performing keyword verification on the input prompt word by using the word similarity and a preset similarity threshold.

[0084] In detail, the interaction keyword refers to a database index of the interaction database.

[0085] In detail, the step of determining whether the input prompt word passes the keyword verification by using the interaction database refers to verifying the keyword of the input prompt word by using the interaction database to check whether it is legal or already exists, for example: for a patient's medical history, it can be verified whether the patient has the disease history, for a symptom, it can be verified whether it conforms to the corresponding disease characteristics, and for body data, it can be verified whether it conforms to the conventional measurement standard.

[0086] In detail, the step of calculating the vector distance between the interaction vector and the input vector can be a Euclidean distance algorithm, and the step of determining the word similarity between the input prompt word and the interaction keyword according to the vector distance refers to representing the word similarity between the input prompt word and the interaction keyword by using the inverse of the vector distance.

[0087] In detail, the keyword verification on the input prompt word refers to comparing the word similarity with the preset similarity threshold, and performing keyword verification on the input prompt word according to the comparison.

[0088] Further, when the word similarity is greater than the preset similarity threshold, the input prompt word passes the keyword verification; and when the word similarity is less than or equal to the preset similarity threshold, the input prompt word fails the keyword verification.

[0089] S3, when the input prompt word passes the keyword verification, generating a feedback answer of the input prompt word by using the interaction database.

[0090] In the embodiment of the present application, the generating of the feedback answer of the input prompt word by using the interaction database refers to querying corresponding information in the interaction database according to the input prompt word, and collecting related data and knowledge. The query operation can be performed by using an ORM framework or a native SQL command. Based on the query result and a strategy, the feedback answer of the input prompt word is generated, which includes but is not limited to a recommended treatment scheme, a disease diagnosis suggestion, a lifestyle guidance, etc. The generation of the feedback answer can adopt a knowledge graph, a rule engine, machine learning, etc.

[0091] Further, the generated feedback answer is returned to an interaction interface to prompt a user to perform corresponding operations and processing. A front-end framework or a back-end API can be used to perform corresponding interactions.

[0092] In the embodiment of the present application, the generating of the feedback answer of the input prompt word by using the interaction database includes:

[0093] Obtaining a similar keyword of the input prompt word, and determining a link index of the similar keyword in the interaction database;

[0094] Generating link data of the similar keyword according to the interaction database and the link index, and generating the feedback answer of the input prompt word according to the link data.

[0095] In detail, in the interaction database, the similar keyword and its associated data are linked and indexed to establish corresponding relationships and dependencies, so that the link index of the similar keyword in the interaction database can be determined.

[0096] In detail, the generating the feedback answer of the input prompt word according to the link data of the similar keywords refers to generating the corresponding answer according to the query result and the link data, which can include recommending a treatment plan, providing a disease diagnosis suggestion, and providing lifestyle guidance.

[0097] S4, when the input prompt word fails the keyword verification, determining whether the input prompt word passes the template expectation verification.

[0098] In the embodiments of the present application, the determining whether the input prompt word passes the template expectation verification refers to determining the requirement of the user for the expected template according to the input prompt word; and the template expectation verification refers to verifying the input prompt word by using text analysis, voice recognition, or manual input, and checking whether it meets the template expectation. For example, if the input prompt word is for a disease symptom, it can be verified whether it meets the description requirement of the disease symptom, considering the degree, frequency, and duration of the symptom; and if the input prompt word is for a medical record, it can be verified whether it meets the format requirement of the medical record, including medical history, diagnosis, and treatment plan.

[0099] In detail, the expectation verification can be performed according to the matching degree of the prompt word.

[0100] S5, when the input prompt word passes the template expectation verification, generating an expected template of the input question according to the input prompt word.

[0101] In the embodiments of the present application, the generating an expected template of the input question according to the input prompt word refers to analyzing the data and functions that the user needs to display, and determining the corresponding module types and elements according to the requirement description and expectation of the user, which include but are not limited to module types, display formats, interface designs, data sources, and interaction modes.

[0102] Further, based on the user data and expected requirements, as well as the best practices and resource library, a suitable module is automatically generated, and an interface for user selection and customization is provided, and the automatic generation of the module can adopt a code generator, template-oriented programming, algorithm optimization, and the like.

[0103] In the embodiments of the present application, the generating an expected template of the input question according to the input prompt word includes:

[0104] performing function word screening on the input prompt word to obtain an input function word of the input prompt word;

[0105] obtaining a historical template of a historical user, and performing primary filtering on the historical template according to the input function word to obtain a primary template of the historical template;

[0106] According to the input function word, the primary template is configured to obtain a configuration template of the primary template, and it is determined that the configuration template is the expected template of the input question.

[0107] In detail, the function word screening of the input prompt word refers to screening some functions of the input prompt word about the expected template, and using the function words to configure the template of the expected template.

[0108] In detail, the historical template is obtained by integrating and analyzing user information of historical users, and can include access pages, click links, selected services, read contents, and the like, and can also include user preferences, habits, and demands.

[0109] In detail, the primary filtering of the historical template according to the input function word refers to matching all historical templates according to the input function word, and performing primary filtering on the historical templates according to the matching result; the module configuration of the primary template according to the input function word refers to determining related information, attributes, and parameters of the primary template, and further configuring the primary template by using the input function word, and the template configuration includes data source configuration, UI design, interaction logic, and the like, wherein the template configuration can be performed in a visual interface or in code to meet different user needs and requirements.

[0110] S6, when the input prompt word does not pass the template expectation verification, it is determined whether the input prompt word passes the individualization verification.

[0111] In the embodiment of the application, the determination of whether the input prompt word passes the individualization verification refers to the determination of whether the user needs individualization recommendation, and the individualization recommendation is determined according to the configuration habits and preference of the user.

[0112] S7, when the input prompt word passes the individualization verification, generating an individualization answer of the input question according to the input prompt word.

[0113] In the embodiment of the application, the generating of the individualization answer of the input question according to the input prompt word includes:

[0114] According to the interaction interface of the input question, the input user of the input question is determined, and the historical habit value of the input user is obtained.

[0115] According to the historical habit value, the word weight of the input prompt word is generated.

[0116] generate an input weighting value of the input question according to the word weight and the input prompt word, and generate a personalized answer of the input question according to the input weighting value.

[0117] In detail, the input user of the input question is determined according to the interactive interface, and information related to the input question can be obtained from the interface attributes of the interactive interface, including interactive mode, content input form, data type, data length, data specification, etc. Through the interface input information and the interactive mode, the user attributes related to the input question are identified, including user ID, gender, age, historical information, disease history, habit preference, etc.

[0118] In detail, the historical habit value of the input user is a habit vector of the historical habit of the input user, and a machine learning algorithm or a deep learning algorithm is used to learn the historical habit value of the habit vector. The historical habit value is generated according to the learned model; the historical habit value represents the historical habit of the input user, that is, the input frequency of the input user for a certain input prompt word can be represented by the historical habit value.

[0119] In detail, the input weighting value of the input question can be generated according to the corresponding weight of the input prompt word determined by the word weight, the corresponding weight of the input prompt word is assigned to the corresponding input prompt word, and the weight values of each input prompt word in the input question are added to obtain the input weighting value of the input question.

[0120] S8, when the input prompt word does not pass the personalized verification, the emotion abnormality of the input prompt word is judged, the communication type of the input question is generated according to the emotion abnormality judgment result, and the question answer of the input question is generated according to the communication type.

[0121] In the embodiment of the application, the emotion abnormality of the input prompt word is judged, and the communication type of the input question is generated according to the emotion abnormality judgment result, including:

[0122] The question context of the input question is obtained, the input emotion value of the input prompt word is obtained by performing emotion analysis on the input prompt word according to the question context;

[0123] The input emotion value and the preset emotion threshold value are used to judge the emotion abnormality of the input prompt word, and when the input emotion value is greater than the preset emotion threshold value, the communication type of the input question is determined as intelligent reply;

[0124] When the input emotion value is less than or equal to the preset emotion threshold value, it is determined that the communication type of the input question is artificial reply.

[0125] In detail, the emotion abnormality judgment on the input prompt word refers to emotion analysis on the input prompt word to judge the emotion tendency, including positive, neutral and negative, and emotion analysis algorithm can be used, such as dictionary-based emotion analysis and neural network-based emotion analysis, to perform emotion analysis on the input prompt word; according to the emotion analysis result, the abnormality of the input prompt word is judged, and if the emotion tendency of the prompt word is negative or the input frequency is high, the emotion of the user may be abnormal.

[0126] In detail, when the input emotion value is less than the preset emotion threshold value, the emotion tendency is negative; when the input emotion value is equal to the preset emotion threshold value, the emotion tendency is neutral; and when the input emotion value is greater than the preset emotion threshold value, the emotion tendency is positive.

[0127] Further, when the emotion tendency is positive, the input question can be answered by the intelligent system, which reduces the pressure between doctors and patients and reduces the work burden, so that the patient and the doctor are in a more relaxed state, thereby achieving better doctor-patient communication effect; when the emotion tendency is negative and neutral, artificial intervention is needed to answer the input question of the user to avoid invalid communication between the user and the intelligent answering system.

[0128] In detail, the emotion abnormality judgment on the input prompt word is because each user may have different emotions, and the current emotion state of the user is judged through the input prompt word, so as to provide targeted emotional value in the reply, and in this process, some related polishing is performed without affecting the accuracy of the reply information, so as to improve the satisfaction of the user.

[0129] In the embodiment of the application, the input question of the interactive interface is acquired, the input prompt word of the input question is extracted, the input prompt word of the input question is obtained, the input prompt word is identified based on the input prompt word, the input prompt word is sequentially verified, the template expectation is verified, the individuality is verified, and the emotion abnormality is judged, so that the user can quickly select the most suitable module for data display and function configuration, greatly improving the configuration and release efficiency of the digital content management of the operation personnel, and the emotion abnormality judgment gives a quick answer while taking care of the emotion of the user, provides support for the corresponding maintenance personnel when necessary, records the current user behavior habit and preference, quickly responds to similar prompt words and performs personalized recommendation, continuously optimizes the digital content management efficiency, and improves the user experience, so that the content management method based on prompt word question and answer interaction can solve the problem that the experience is low when the user asks questions and answers.

[0130] As Figure 4 shown in FIG. 1, it is a functional module diagram of the content management device based on the prompt word question and answer interaction provided by an embodiment of the present application.

[0131] The content management device 100 based on the prompt word question and answer interaction can be installed in a device. According to the functions to be implemented, the content management device 100 based on the prompt word question and answer interaction can include a prompt word extraction module 101, a keyword verification module 102, a feedback answer generation module 103, a template expectation verification module 104, an expectation template generation module 105, a personalization verification module 106, a personalized answer generation module 107, and an emotion abnormality judgment module 108. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by a device processor and can complete a fixed function, which are stored in the memory of the device.

[0132] In the present embodiment, the functions of each module / unit are as follows:

[0133] The prompt word extraction module 101 is configured to obtain an input question of an interactive interface, perform prompt word extraction on the input question, and obtain an input prompt word of the input question.

[0134] The keyword verification module 102 is configured to obtain an interactive database of the interactive interface, and determine whether the input prompt word passes keyword verification by using the interactive database.

[0135] The feedback answer generation module 103 is configured to generate a feedback answer of the input prompt word by using the interactive database when the input prompt word passes the keyword verification.

[0136] The template expectation verification module 104 is configured to determine whether the input prompt word passes template expectation verification when the input prompt word does not pass the keyword verification.

[0137] The expectation template generation module 105 is configured to generate an expectation template of the input question according to the input prompt word when the input prompt word passes the template expectation verification.

[0138] The personalization verification module 106 is configured to determine whether the input prompt word passes personalization verification when the input prompt word does not pass the template expectation verification.

[0139] The personalized answer generation module 107 is configured to generate a personalized answer of the input question according to the input prompt word when the input prompt word passes the personalization verification.

[0140] The emotion abnormality judgment module 108 is configured to, when the input prompt word fails to pass the individualized verification, judge emotion abnormality of the input prompt word, generate a communication type of the input question according to a result of the emotion abnormality judgment, and generate a question answer of the input question according to the communication type.

[0141] As shown in Figure 5 FIG. 1 is a structural schematic diagram of an electronic device for implementing a content management method based on prompt word question and answer interaction according to an embodiment of the present application.

[0142] The electronic device can include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as a content management program based on prompt word question and answer interaction.

[0143] In some embodiments, the processor 10 can be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions. The processor 10 can include one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, combinations thereof, and the like. The processor 10 is the control unit of the device, which connects various components of the device through various interfaces and lines, executes programs or modules stored in the memory 11 (such as the content management program based on prompt word question and answer interaction), and calls data stored in the memory 11 to perform various functions of the device and process data.

[0144] The memory 11 includes at least one type of medium, such as flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory), magnetic memory, disk, optical disk, and the like. In some embodiments, the memory 11 can be an internal storage unit of the device, such as a mobile hard disk of the device. In other embodiments, the memory 11 can also be an external storage device of the device, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. Further, the memory 11 can include both an internal storage unit and an external storage device. The memory 11 can be used to store application software and various data installed on the device, such as the code of the content management program based on prompt word question and answer interaction, and can also be used to temporarily store data that has been output or will be output.

[0145] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize the connection and communication between the memory 11 and the at least one processor 10, etc.

[0146] The communication interface 13 is used for communication between the above-mentioned device and other devices, including a network interface and a user interface. Optionally, the network interface can include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the device and other devices. The user interface can be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface can also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch, etc. Among them, the display can also be appropriately called a display screen or a display unit, which is used to display the information processed in the device and to display the visualized user interface.

[0147] Only the device with components is shown in the figure, and those skilled in the art can understand that the structure shown in the figure does not constitute a limitation on the device, and can include fewer or more components than the figure, or combine certain components, or different component arrangements.

[0148] For example, although not shown, the device can also include a power supply (such as a battery) for powering each component. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so as to realize functions such as charge management, discharge management, and power consumption management through the power management device. The power supply can also include one or more direct current or alternating current power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. Any components. The device can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0149] It should be understood that the embodiments are only for illustration and are not limited in the scope of the patent application by this structure.

[0150] The content management program based on the prompt word question and answer interaction stored in the memory 11 in the device is a combination of a plurality of instructions, which, when running in the processor 10, can realize:

[0151] obtaining an input question of an interactive interface, performing prompt word extraction on the input question to obtain an input prompt word of the input question;

[0152] obtaining an interactive database of the interactive interface, and determining whether the input prompt word passes a keyword verification by using the interactive database;

[0153] when the input prompt word passes the keyword verification, generating a feedback answer of the input prompt word by using the interactive database;

[0154] when the input prompt word does not pass the keyword verification, determining whether the input prompt word passes a template expectation verification;

[0155] when the input prompt word passes the template expectation verification, generating an expected template of the input question according to the input prompt word;

[0156] when the input prompt word does not pass the template expectation verification, determining whether the input prompt word passes a personalization verification;

[0157] when the input prompt word passes the personalization verification, generating a personalized answer of the input question according to the input prompt word;

[0158] when the input prompt word does not pass the personalization verification, performing emotion abnormality judgment on the input prompt word, generating a communication type of the input question according to the emotion abnormality judgment result, and generating a question answer of the input question according to the communication type.

[0159] Specifically, the specific implementation method of the processor 10 on the above instructions can refer to the description of the related steps in the corresponding embodiment of the accompanying drawings, which will not be described here.

[0160] Further, the modules / units integrated in the device, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a medium. The medium can be volatile or non-volatile. For example, the medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM).

[0161] The application also provides a medium storing a computer program, which, when executed by a processor of a device, can realize:

[0162] obtaining an input question of an interactive interface, performing prompt word extraction on the input question to obtain an input prompt word of the input question;

[0163] obtaining an interaction database of the interaction interface, determining whether the input prompt word passes keyword verification by using the interaction database;

[0164] generating a feedback answer of the input prompt word by using the interaction database when the input prompt word passes the keyword verification;

[0165] determining whether the input prompt word passes template expectation verification when the input prompt word does not pass the keyword verification;

[0166] generating an expected template of the input question according to the input prompt word when the input prompt word passes the template expectation verification;

[0167] determining whether the input prompt word passes individualization verification when the input prompt word does not pass the template expectation verification;

[0168] generating an individualized answer of the input question according to the input prompt word when the input prompt word passes the individualization verification;

[0169] generating a communication type of the input question according to a result of emotion abnormality judgment of the input prompt word, and generating a question answer of the input question according to the communication type when the input prompt word does not pass the individualization verification.

[0170] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other manners. For example, the above described apparatus embodiments are merely schematic, and the division of the modules is merely a logical function division, and there can be another division manner in actual implementation.

[0171] The modules illustrated as separated components can or can not be physically separated, and the components illustrated as modules can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the embodiments.

[0172] In addition, each function module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of hardware plus software function module.

[0173] It will be obvious to a person skilled in the art that the application is not limited to the details of the above-described exemplary embodiments but can be implemented in other embodiments without departing from the scope of the application.

[0174] The embodiments should therefore be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the description given above, which is intended to be illustrative only and not restrictive; therefore all changes coming within the meaning and equivalency range of the claims are intended to be embraced therein. Any reference signs in the claims should not be construed as limiting the scope of the claims.

[0175] The blockchain referred to in the present application is a new application mode of distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm and other computer technologies. Blockchain, in essence, is a decentralized database, a series of data blocks associated using cryptographic methods, each data block containing a batch of network transaction information, used to verify the validity of the information (anti-fake) and generate the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer, etc.

[0176] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Artificial intelligence (AI) is the use of digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0177] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The plurality of units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names and not to indicate any particular order.

[0178] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application.

Claims

1. A content management method based on prompt-word question-and-answer interaction, characterized in that, The method includes: Obtain the input question from the interactive interface, extract prompt words from the input question, and obtain the input prompt words for the input question; Obtain the interaction database of the interactive interface, and use the interaction database to determine whether the input prompt word passes keyword verification; When the input prompt word passes the keyword verification, the interactive database is used to generate a feedback answer for the input prompt word; When the input prompt fails the keyword verification, determine whether the input prompt passes the template expectation verification; When the input prompt word passes the template expectation verification, an expected template for the input question is generated based on the input prompt word. When the input prompt fails the template expectation verification, determine whether the input prompt has passed the personalized verification. When the input prompt passes the personalized verification, a personalized answer to the input question is generated based on the input prompt. When the input prompt fails the personalized verification, the input prompt is judged to be emotionally abnormal. Based on the result of the emotional abnormality judgment, the communication type of the input question is generated, and based on the communication type, the answer to the input question is generated.

2. The content management method based on prompt-word question-and-answer interaction as described in claim 1, characterized in that, The step of extracting prompt words from the input question to obtain the input prompt words for the input question includes: The input question is segmented into words to obtain the question segments of the input question; The word frequency of each question word is generated, and common words are extracted from the question words based on the word frequency to obtain the common words of the question words; Stop word filtering is performed on the commonly used words to obtain the standard word segmentation for the problem; The input prompt words for the input question are generated based on the standard word segmentation.

3. The content management method based on prompt-word question-and-answer interaction as described in claim 1, characterized in that, The step of determining whether the input prompt word passes keyword verification using the interactive database includes: Obtain the interaction keywords from the interaction database, perform vector transformation on the interaction keywords, and obtain the interaction vector of the interaction keywords; The input prompt word is transformed into a vector to obtain the input vector of the input prompt word; Calculate the vector distance between the interaction vector and the input vector, and determine the word similarity between the input prompt word and the interaction keyword based on the vector distance; The input prompt words are validated using the word similarity and a preset similarity threshold.

4. The content management method based on prompt-word question-and-answer interaction as described in claim 1, characterized in that, The step of generating feedback answers using the interactive database for the input prompt words includes: Obtain similar keywords to the input prompt and determine the link index of the similar keywords in the interactive database; Based on the interactive database and the link index, link data for the similar keywords is generated, and based on the link data, feedback answers for the input prompt words are generated.

5. The content management method based on prompt-word question-and-answer interaction as described in claim 1, characterized in that, The step of generating the expected template for the input question based on the input prompt words includes: The input prompt words are filtered for functional words to obtain the input functional words of the input prompt words; Obtain historical templates of historical users, and perform primary filtering on the historical templates based on the input function words to obtain the primary templates of the historical templates; The primary template is configured according to the input function words to obtain the configuration template of the primary template, and the configuration template is determined to be the expected template of the input question.

6. The content management method based on prompt-word question-and-answer interaction as described in claim 1, characterized in that, The step of generating a personalized answer to the input question based on the input prompts includes: The user who inputs the input question is determined based on the interactive interface of the input question, and the historical habit values ​​of the input user are obtained. The word weights of the input prompt words are generated based on the historical habit values; The input weight value of the input question is generated based on the word weights and the input prompt words, and a personalized answer to the input question is generated based on the input weight value.

7. The content management method based on prompt-word question-and-answer interaction as described in any one of claims 1 to 6, characterized in that, The step of determining the emotional abnormality of the input prompt and generating the communication type of the input question based on the emotional abnormality determination result includes: Obtain the question context of the input question, perform sentiment analysis on the input prompt words based on the question context, and obtain the input sentiment value of the input prompt words; The input sentiment value and a preset sentiment threshold are used to determine the emotional abnormality of the input prompt words. When the input sentiment value is greater than the preset sentiment threshold, the communication type of the input question is determined to be intelligent reply. When the input sentiment value is less than or equal to the preset sentiment threshold, the communication type of the input question is determined to be a manual response.

8. A content management device based on prompt-word question-and-answer interaction, characterized in that, The device includes: The prompt word extraction module is used to obtain the input question of the interactive interface, extract prompt words from the input question, and obtain the input prompt words of the input question; The keyword verification module is used to obtain the interaction database of the interactive interface and use the interaction database to determine whether the input prompt word passes the keyword verification. The feedback answer generation module is used to generate a feedback answer for the input prompt word using the interactive database when the input prompt word passes the keyword verification. The template expectation verification module is used to determine whether the input prompt word passes the template expectation verification when the input prompt word fails the keyword verification. The expectation template generation module is used to generate an expectation template for the input question based on the input prompt when the input prompt passes the template expectation verification. A personalized verification module is used to determine whether the input prompt word passes personalized verification when the input prompt word fails the template expectation verification. A personalized answer generation module is used to generate a personalized answer to the input question based on the input prompt when the input prompt passes the personalized verification. The emotion abnormality judgment module is used to judge the emotion abnormality of the input prompt word when the input prompt word fails the personalized verification, generate the communication type of the input question based on the emotion abnormality judgment result, and generate the question answer of the input question based on the communication type.

9. 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, the computer program being executed by the at least one processor to enable the at least one processor to perform the content management method based on prompt-word question-and-answer interaction as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the content management method based on prompt-word question-and-answer interaction as described in any one of claims 1 to 7.

Images