Intelligent question-answering method, device, equipment, and medium based on network system

Abstract

The embodiments of the present application belong to the field of data processing and relate to an intelligent question-and-answer method for use in a network system, including obtaining a user question-and-answer set; dividing the user question-and-answer set into a menu data set, an auxiliary data set, and a supplementary data set; identifying the association relationship between the menu data set, the auxiliary data set, and the supplementary data set; calculating the content weight values ​​of multiple question-and-answer content sets; performing similarity retrieval on query keywords from the user question-and-answer set to obtain similar query keywords; performing similar answer retrieval on similar query keywords to obtain candidate answer data; obtaining click events, and determining the target usage answer for the similar query keywords from the candidate answer data based on the association relationship and the click event. The present application also provides an intelligent question-and-answer device, equipment, and medium for use in a network system. In addition, the present application also relates to blockchain technology, and the user question-and-answer set can be stored in the blockchain. The present application improves the efficiency of network system function use and the accuracy of question and answer.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to an intelligent question-answering method, apparatus, device, and medium for use in a network system. Background Art

[0002] With the development of internet information technology, the use of network systems to manage various information has become mainstream. For example, in the financial sector, insurance product information is also managed through network systems. However, with the deepening of informatization, the number of network systems required to manage information has increased. Users find it difficult to master all the functional procedures of network systems, which leads to frequent errors in user operation and reduces the efficiency of network system functions. Improving the efficiency of system functions has become a pressing issue.

[0003] Traditional question-answering methods receive questions input by users, perform information retrieval based on the questions, and then return the answers to the questions.

[0004] However, the applicant found that the traditional question-and-answer method has certain defects. On the one hand, as the functions of the network system increase, the function menus also increase. When users use the system, they cannot find relevant information about the use of the function menus through the question-and-answer database, which makes the accuracy of questions and answers based on the use of the network system low; on the other hand, when the user takes great pains to find the system function he wants, the traditional question-and-answer method cannot accurately feedback the method of using the function, resulting in low efficiency of users using the network system functions and low accuracy of question and answer. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to propose an intelligent question-answering method, device, equipment and medium based on the use of a network system, the main purpose of which is to improve the efficiency of the use of network system functions and the accuracy of question-answering.

[0006] In order to solve the above technical problems, the embodiment of the present application provides an intelligent question-answering method based on the use of a network system, which adopts the following technical solutions:

[0007] Obtain user Q&A collection based on the use of network systems;

[0008] Dividing the user question and answer set into a menu data set, an auxiliary data set, and a supplementary data set;

[0009] Identifying an association relationship among the menu data set, the auxiliary data set, and the supplementary data set;

[0010] Classifying the user question and answer set to obtain a plurality of question and answer content sets, and calculating content weight values ​​of the plurality of question and answer content sets;

[0011] receiving a query keyword input by a user terminal, and performing a similarity search on the query keyword from the user question and answer set to obtain similar query keywords;

[0012] Perform similar answer retrieval on the similar query keyword according to the content weight value to obtain candidate menu answer data, candidate auxiliary answer data and candidate supplementary answer data;

[0013] Obtain a click event corresponding to the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data sent by the user terminal, and determine the target usage answer for the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data based on the association relationship and the click event.

[0014] Furthermore, the dividing of the user question and answer set into a menu data set, an auxiliary data set, and a supplementary data set includes:

[0015] Performing word segmentation on the user question and answer set to obtain a word segmentation question and answer set;

[0016] Performing category labeling on the word segmentation question and answer set to obtain labeling category information;

[0017] The word segmentation question and answer set is divided into the menu data set, the auxiliary data set and the supplementary data set according to the marked category information.

[0018] Furthermore, performing similarity retrieval on the query keyword from the user question and answer set to obtain similar query keywords includes:

[0019] Calculating the similarity between the query keyword and the question keywords in the user question and answer set;

[0020] The question keyword with the highest similarity is selected as the similar query keyword.

[0021] Furthermore, the similar answer retrieval is performed on the similar query keyword according to the content weight value to obtain candidate menu answer data, candidate auxiliary answer data and candidate supplementary answer data, including:

[0022] Obtaining similar answers corresponding to the similar query keywords, wherein the similar answers include similar menu answers, similar auxiliary answers, and similar supplementary answers;

[0023] Determining whether the content weight value is greater than a preset reliability;

[0024] When the content weight value is greater than a preset confidence level, the similar menu answer corresponding to the content weight value is used as the first candidate menu answer data;

[0025] Using the similar auxiliary answer corresponding to the content weight value as the first candidate auxiliary answer data;

[0026] Using the similar supplementary answer corresponding to the content weight value as first candidate supplementary answer data;

[0027] When the content weight value is not greater than the preset confidence level, the similar menu answer corresponding to the content weight value is used as the second candidate menu answer data;

[0028] Using the similar auxiliary answer corresponding to the content weight value as the second candidate auxiliary answer data;

[0029] Using the similar supplementary answer corresponding to the content weight value as second candidate supplementary answer data;

[0030] Aggregating the first candidate menu answer data and the second candidate menu answer data to obtain the candidate menu answer data;

[0031] Aggregating the first candidate auxiliary answer data and the second candidate auxiliary answer data to obtain the candidate auxiliary answer data;

[0032] The first candidate supplementary answer data and the second candidate supplementary answer data are aggregated to obtain candidate supplementary answer data.

[0033] Furthermore, determining the target usage answer for the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data, or the candidate supplementary answer data based on the association relationship and the click event includes:

[0034] Sorting the candidate menu answer data, the candidate auxiliary answer data, and the candidate supplementary answer data to obtain a sorted answer set;

[0035] identifying a click answer in the sorted answer set according to the click event;

[0036] When the click answer is an answer in the candidate menu answer data, the candidate menu answer data and the corresponding auxiliary answer and supplementary answer are used as target usage answers for the similar query keyword according to the association relationship;

[0037] When the click answer is an answer in the candidate auxiliary answer data, the candidate auxiliary answer data and the corresponding menu answer and supplementary answer are used as target usage answers for the similar query keyword according to the association relationship;

[0038] When the click answer is an answer in the candidate supplementary answer data, the candidate supplementary answer data and the corresponding menu answer and supplementary auxiliary answer are used as target usage answers for the similar query keyword according to the association relationship.

[0039] Furthermore, the calculating of content weight values ​​of the plurality of question-and-answer content sets includes:

[0040] Acquire multiple content factors of multiple question-and-answer content sets, and define initial menu factor weight values, initial auxiliary factor weight values, and initial supplementary factor weight values ​​corresponding to each content factor in the menu dataset, the auxiliary dataset, and the supplementary dataset, respectively;

[0041] Accumulating the weights of each of the initial menu factor weights, each of the initial auxiliary factor weights, and each of the initial supplementary factor weights to obtain a menu weight value, an auxiliary weight value, and a supplementary weight value;

[0042] The menu weight values, the auxiliary weight values, and the supplementary weight values ​​are aggregated to obtain content weight values ​​of multiple question-and-answer content sets.

[0043] Furthermore, the identifying the association relationship among the menu data set, the auxiliary data set, and the supplementary data set includes:

[0044] respectively obtaining data identifiers of the menu data set, the auxiliary data set, and the supplementary data set;

[0045] The association relationship among the menu data set, the auxiliary data set and the supplementary data set is searched according to the data identifier.

[0046] In order to solve the above technical problems, the embodiment of the present application further provides an intelligent question-answering device based on a network system, which adopts the following technical solution:

[0047] An acquisition module is used to obtain a user question and answer set based on the use of the network system;

[0048] A division module, configured to divide the user question and answer set into a menu data set, an auxiliary data set, and a supplementary data set;

[0049] an identification module, configured to identify an association relationship among the menu data set, the auxiliary data set, and the supplementary data set;

[0050] a calculation module, configured to classify the user question and answer set to obtain a plurality of question and answer content sets, and calculate content weight values ​​of the plurality of question and answer content sets;

[0051] A first search module is configured to receive a query keyword input by a user terminal, and perform a similar search on the query keyword from the user question and answer set to obtain similar query keywords;

[0052] A second retrieval module is configured to perform similar answer retrieval on the similar query keyword according to the content weight value, and obtain candidate menu answer data, candidate auxiliary answer data, and candidate supplementary answer data;

[0053] A question-and-answer module is used to obtain a click event corresponding to the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data sent by the user terminal, and determine the target usage answer of the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data based on the association relationship and the click event.

[0054] In order to solve the above technical problems, the embodiment of the present application further provides a device, which adopts the following technical solution:

[0055] a memory storing at least one computer program; and

[0056] The processor executes the computer program stored in the memory to implement the above-mentioned intelligent question-answering method based on the network system.

[0057] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable medium, which adopts the following technical solution:

[0058] The computer-readable medium stores at least one computer program, and the at least one computer program is executed by a processor in an electronic device to implement the above-mentioned intelligent question-answering method based on the use of a network system.

[0059] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0060] In an embodiment of the present invention, first, by dividing the user question and answer set obtained based on the use of the network system into a menu data set, an auxiliary data set and a supplementary data set, a method for using the system function can be provided during the use of the network system, thereby improving the efficiency of the use of the network system function; secondly, by calculating the content weight value of the user question and answer set, it is easy to find the accurate answer corresponding to the user keyword in the subsequent use, thereby improving the accuracy of the subsequent question and answer based on the use of the network system, and by performing a similar search on the query keyword from the user question and answer set, similar query keywords are obtained, thereby improving the accuracy of the question and answer in the question and answer process of the network system; finally, by performing a similar answer search on the similar query keyword, and determining the target use answer of the similar query keyword from the candidate menu answer data, candidate auxiliary answer data or candidate supplementary answer data based on the association relationship and click event, the answer data clicked by the user can be prioritized as the target answer, and different menu answers and the auxiliary answers and supplementary answers corresponding to the menu answers can be used as the final answer, thereby further improving the accuracy of the question and answer and the efficiency of using the network system function. Therefore, the intelligent question and answer method, device, equipment and medium based on the use of the network system proposed in this application can improve the efficiency of the use of the network system function and the accuracy of the question and answer. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0062] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0063] Figure 2 A flowchart of an embodiment of an intelligent question-answering method based on a network system according to the present application;

[0064] Figure 3 yes Figure 2 A flowchart of a specific implementation of step S202;

[0065] Figure 4 This is a schematic structural diagram of an embodiment of an intelligent question-answering device based on a network system according to the present application;

[0066] Figure 5 It is a structural diagram of an embodiment of a device according to the present application. DETAILED DESCRIPTION

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0068] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0069] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0070] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0071] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0072] Terminal devices 101, 102, and 103 can be various electronic devices with display screens and support web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture E-based network system using intelligent question and answer perts Group Audio Layer III, Moving Picture Experts Compression Standard Audio Layer 3), MP4 (Moving Picture E-based network system using intelligent question and answer perts Group Audio Layer IV, Moving Picture Experts Compression Standard Audio Layer 4) players, laptop computers and desktop computers, etc.

[0073] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0074] It should be noted that the intelligent question-answering method based on the network system provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the intelligent question-answering device based on the network system is generally set in the server / terminal device.

[0075] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0076] Continue to refer Figure 2 , shows a flow chart of an embodiment of an intelligent question-answering method based on a network system according to the present application. The intelligent question-answering method based on a network system comprises the following steps:

[0077] S201: Obtain a user question and answer set based on the use of the network system.

[0078] In this embodiment of the present invention, the network system refers to a system for managing network information, such as an insurance product information management system. The user question and answer collection includes questions raised by historical users when using the network system and the corresponding textual responses. For example, in the financial field, the user question and answer collection may be a collection of historical user question and answer data regarding all insurance products on an insurance network system.

[0079] S202: Divide the user question and answer set into a menu data set, an auxiliary data set, and a supplementary data set.

[0080] In an embodiment of the present invention, the menu data set is a set of functional menu data within a network system. The specific menu data is determined based on the actual scenario. For example, in the insurance field, the menu data set may include message push of insurance products, explanations of insurance products, insurance message types, and strategy selection for purchasing insurance.

[0081] The auxiliary data set is a data set that helps explain the use of the function menu in the network system. For example, if a function menu is a strategy selection menu, the auxiliary data set can be a text data set that describes how to use the strategy selection menu.

[0082] The supplementary data set refers to a data set of historical user experiences or usage tips for the network system function menu. For example, in the insurance field, a data set of instructions and precautions for the insurance product consultation function menu.

[0083] In an embodiment of the present invention, by dividing the user question and answer set into a menu data set, an auxiliary data set and a supplementary data set, a method for using system functions can be provided during the use of the network system, thereby improving the efficiency of using the network system functions.

[0084] As an embodiment of the present invention, refer to Figure 3 As shown, dividing the user question and answer set into a menu data set, an auxiliary data set, and a supplementary data set includes the following steps S2021-S2023:

[0085] S2021. Segment the user question and answer set to obtain a segmented question and answer set;

[0086] S2022: perform category labeling on the word segmentation question and answer set to obtain labeling category information;

[0087] S2023. Divide the word segmentation question and answer set into the menu data set, the auxiliary data set, and the supplementary data set according to the marked category information.

[0088] The word segmentation can be achieved by using the Hanlp word segmentation tool to obtain a word segmentation question and answer set that can fully express the meaning of each sentence.

[0089] In one embodiment of the present invention, the category annotation refers to searching a preset dictionary for a corresponding category annotation for the word segmentation question and answer set. When the word segmentation question and answer set has a matching term in the dictionary, the matching term and the term category annotation are used as the annotated category information for the word segmentation question and answer set. The preset dictionary can be a user-defined dictionary. The annotated category information includes menu category annotation information, auxiliary category annotation information, and supplementary category annotation information.

[0090] S203: Identify the association relationship among the menu data set, the auxiliary data set, and the supplementary data set.

[0091] In an embodiment of the present invention, there is a corresponding association relationship between the answer data of the menu data set, the auxiliary data set and the supplementary data set. Specifically, one menu answer data corresponds to one auxiliary answer data and one supplementary answer data, wherein the auxiliary answer data is used to explain how to use the menu function; the supplementary answer data is used to explain the experience of historical users in using the menu function.

[0092] In an embodiment of the present invention, by identifying the association between the menu data set, the auxiliary data set and the supplementary data set, after the user finds the system function he wants, auxiliary instructions for using the function can be provided, and function usage skills of historical users can be further provided, thereby improving the efficiency of users in using network system functions and the accuracy of questions and answers.

[0093] As an embodiment of the present invention, the identifying the association relationship among the menu dataset, the auxiliary dataset, and the supplementary dataset includes:

[0094] respectively obtaining data identifiers of the menu data set, the auxiliary data set, and the supplementary data set;

[0095] The association relationship among the menu data set, the auxiliary data set and the supplementary data set is searched according to the data identifier.

[0096] The data identifier is a category identifier, through which different categories of information can be searched, and the association relationship between different categories of data can be identified based on the same keywords in different categories of information. The association relationship search can be implemented through a MySql query statement.

[0097] S204: performing content classification on the user question and answer set to obtain multiple question and answer content sets, and calculating content weight values ​​of the multiple question and answer content sets.

[0098] In an embodiment of the present invention, the multiple question and answer content sets include multiple content factors, wherein the multiple content factors include but are not limited to word segmentation content factors, affiliation organization content factors, update time content factors, best answer number content factors, answer view number content factors and regional content factors, etc.

[0099] Specifically, in an embodiment of the present invention, the word segmentation content factor description is a factor that describes the specific content of the user's question and answer set, including the word segmentation of the function menu, the title of the auxiliary document, the specific content of the auxiliary document, and the title of other answer types, as well as the word segmentation of the question answer content. The longer the word segmentation length of the keyword matching in the user's question and answer set, the more accurate the corresponding question and answer result; the affiliation content factor refers to the organization information corresponding to the specific content of different categories when the user logs into the network system, including the headquarters, second-level organization, third-level organization and fourth-level organization, which can be dynamically adjusted based on actual business; the update time content factor refers to the user's question The last update time of the answer set. The closer the time is to the current time, the higher the question and answer matching accuracy of the user question and answer set, that is, the greater the possibility of the answer result the user wants; the best answer number content factor refers to the number of times it has been marked as a wanted answer by historical users. The more times it is marked, the more accurate the answer; the view count content factor is the number of times the answer has been viewed by historical users. The more times it has been viewed, the more accurate the answer; the regional content factor refers to the regional information corresponding to the specific content of the user question and answer set. Some content may only be suitable for use in limited cities. For example, the purchase of insurance product A is only open to users in region B, and can be dynamically adjusted based on actual business.

[0100] In the embodiment of the present invention, the content weight value is a value describing the frequency of the content appearing in the user question and answer set.

[0101] In an embodiment of the present invention, by classifying the content of the user question and answer set to obtain multiple question and answer content sets, and calculating the content weight values ​​of the multiple question and answer content sets, it is possible to facilitate users to subsequently find accurate answers corresponding to user keywords, thereby improving the accuracy of subsequent questions and answers used based on the network system.

[0102] As an embodiment of the present invention, calculating the content weight values ​​of the multiple question-and-answer content sets includes:

[0103] Acquire multiple content factors of multiple question-and-answer content sets, and define initial menu factor weight values, initial auxiliary factor weight values, and initial supplementary factor weight values ​​corresponding to each content factor in the menu dataset, the auxiliary dataset, and the supplementary dataset, respectively;

[0104] Accumulating the weights of each of the initial menu factor weights, each of the initial auxiliary factor weights, and each of the initial supplementary factor weights to obtain a menu weight value, an auxiliary weight value, and a supplementary weight value;

[0105] The menu weight values, the auxiliary weight values, and the supplementary weight values ​​are aggregated to obtain content weight values ​​of multiple question-and-answer content sets.

[0106] Among them, the initial menu factor weight value, the initial auxiliary factor weight value and the initial supplementary factor weight value are obtained based on the weight ratio of the content factors corresponding to the menu data set, auxiliary data set and supplementary data set respectively, and the weight ratio of the content factor can be customized based on the actual business scenario.

[0107] Specifically, in the embodiment of the present invention, the weight of the word segmentation content factor is 30% if the user question and answer set matches the factor, and 0% if it does not match; the weight of the affiliated organization content factor is 25% at most if the user question and answer set matches the specified organization factor, 10% if the content in the user question and answer set can match all affiliated organizations, and 0% if it does not match; the weight of the update time content factor is 20% if the user question and answer set matches the update time of the current month, 5% if it matches the update time within half a year, and 0% if it matches the update time after half a year; the weight of the best answer number content factor is If the number of matches is greater than 10, the weight is 15%; if the number is greater than 5, the weight is 10%; if the number is greater than 3, the weight is 5%; if the number is greater than 1, the weight is 3%; if the number is 0%, the weight is 0%; for the weight of the content factor of the number of views, if the user Q&A set is matched more than 15 times, the weight is 5%; if the number is greater than 10, the weight is 3%; if the number is greater than 5, the weight is 2%; if the number is greater than 1, the weight is 1%; if the number is 0%, the weight is 0%; for the regional content factor, if the user Q&A set is matched to a specific region, the weight is 5%; if the content in the user Q&A set can match all regions, the weight is 3%; if there is no match, the weight is 0%.

[0108] In one embodiment of the present invention, the menu weight value is the cumulative value of the initial menu factor weight values ​​matched by the menu data set; the auxiliary weight value refers to the cumulative value of the initial auxiliary factor weight values ​​matched by the auxiliary data set; and the supplementary weight value refers to the cumulative value of the initial supplementary factor weight values ​​matched by the supplementary data set.

[0109] For example, there is a menu data for searching insurance products. The content factors of the menu data match the weight of the word "insurance product" with 30%, the weight of the secondary institution with 25%, the weight of the update time of the month with 20%, and the weight of 18 views with 5%. Then the menu weight value of the menu data is 30% + 25% + 20% + 5% = 80%.

[0110] Furthermore, the menu weight value, the auxiliary weight value and the supplementary weight value are aggregated, that is, the menu weight value, the auxiliary weight value and the supplementary weight value are accumulated to obtain content weight values ​​of multiple question and answer content sets.

[0111] S205: Receive a query keyword input by a user terminal, perform a similarity search on the query keyword from the user question and answer set, and obtain similar query keywords.

[0112] In this embodiment of the present invention, the query keyword refers to the question text entered by the user terminal on the network system. For example, the user terminal may enter a question on the insurance network system asking how to find the insurance product type selection function menu. The similar query keyword refers to a question keyword that is similar to the question text in the user's Q&A collection.

[0113] In an embodiment of the present invention, by receiving a query keyword input by a user terminal, a similar search is performed on the query keyword from the user question and answer set to obtain a similar query keyword. In the question and answer process used in the network system, similar questions corresponding to the query keyword can be found, thereby improving the subsequent question and answer efficiency.

[0114] As an embodiment of the present invention, performing similarity retrieval on the query keyword from the user question and answer set to obtain similar query keywords includes:

[0115] Calculating the similarity between the query keyword and the question keywords in the user question and answer set;

[0116] According to the similarity, the question keyword with the highest similarity is selected as the similar query keyword.

[0117] The similarity can be calculated using a cosine similarity formula.

[0118] In one embodiment of the present invention, the specific calculation process of the similar query keywords is to retrieve k question keywords with the largest cosine similarity to the query keyword from the question-and-answer user set, select k question keywords from the top-k similarity results for constraints based on the K-means clustering algorithm, and use the question keyword with the highest similarity in the top-k similarity results as the similar query keyword of the query keyword.

[0119] S206: Perform similar answer retrieval on the similar query keywords according to the content weight value to obtain candidate menu answer data, candidate auxiliary answer data and candidate supplementary answer data.

[0120] In an embodiment of the present invention, the candidate menu answer data is answer data whose weight value corresponding to the menu data is within a preset range; the candidate auxiliary answer data is answer data whose weight value corresponding to the auxiliary data is within a preset range; the candidate supplementary answer data is answer data whose weight value corresponding to the supplementary data is within a preset range, wherein the preset range is a preset reliability, which can be dynamically adjusted based on actual business.

[0121] In an embodiment of the present invention, by performing similar answer retrieval on the similar query keywords according to the content weight value, candidate menu answer data, candidate auxiliary answer data and candidate supplementary answer data are obtained, which can screen out suitable candidate answers in the question-and-answer process used in the network system, reduce the amount of calculation, and improve the accuracy of subsequent questions and answers.

[0122] As an embodiment of the present invention, the similar answer retrieval for the similar query keyword according to the content weight value to obtain candidate menu answer data, candidate auxiliary answer data and candidate supplementary answer data includes:

[0123] Obtaining similar answers corresponding to the similar query keywords, wherein the similar answers include similar menu answers, similar auxiliary answers, and similar supplementary answers;

[0124] Determining whether the content weight value is greater than a preset reliability;

[0125] When the content weight value is greater than a preset confidence level, the similar menu answer corresponding to the content weight value is used as the first candidate menu answer data;

[0126] Using the similar auxiliary answer corresponding to the content weight value as the first candidate auxiliary answer data;

[0127] Using the similar supplementary answer corresponding to the content weight value as first candidate supplementary answer data;

[0128] When the content weight value is not greater than the preset confidence level, the similar menu answer corresponding to the content weight value is used as the second candidate menu answer data;

[0129] Using the similar auxiliary answer corresponding to the content weight value as the second candidate auxiliary answer data;

[0130] Using the similar supplementary answer corresponding to the content weight value as second candidate supplementary answer data;

[0131] Aggregating the first candidate menu answer data and the second candidate menu answer data to obtain the candidate menu answer data;

[0132] Aggregating the first candidate auxiliary answer data and the second candidate auxiliary answer data to obtain the candidate auxiliary answer data;

[0133] The first candidate supplementary answer data and the second candidate supplementary answer data are aggregated to obtain candidate supplementary answer data.

[0134] Among them, the preset credibility may refer to a content weight value greater than 80%, which is dynamically adjusted based on actual business; when the content weight value is greater than 80%, the top-5 similar menu answers corresponding to the content weight value greater than 80% may be selected as the first candidate menu answer data, the top-5 similar auxiliary answers may be selected as the first candidate auxiliary answer data, and the top-5 similar supplementary answers may be selected as the first candidate supplementary answer data, wherein the first candidate menu answer data, the first candidate auxiliary answer data, and the first candidate supplementary answer data can represent different types of best answers corresponding to similar query keywords.

[0135] In one embodiment of the present invention, when the content weight value is less than 80%, the second candidate menu answer data, the second candidate auxiliary answer data and the second candidate supplementary answer data include different types of most similar answers and similar answers corresponding to similar query keywords. All candidate answers will display the top-5 best answers, most similar answers and similar answers corresponding to different types on the network system to facilitate selection by the user terminal.

[0136] S207. Obtain a click event corresponding to the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data sent by the user terminal, and determine a target usage answer for the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data based on the association relationship and the click event.

[0137] In an embodiment of the present invention, the click event refers to a click instruction sent by a user terminal corresponding to the candidate menu answer data, the candidate auxiliary answer data, or the candidate supplementary answer data. The target use answer is an answer that responds to a similar query keyword and is determined based on the user click instruction.

[0138] For example, if the similar query keyword is how to quickly find insurance product D, the corresponding target uses the search path of the answer product search function menu, and the corresponding auxiliary answer data from the function menu is the product number of insurance product D, and finally the information of insurance product D is obtained.

[0139] In an embodiment of the present invention, by obtaining a click event corresponding to the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data sent by the user terminal, the target usage answer of the similar query keyword is determined from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data according to the association relationship and the click event. The answer data clicked by the user can be given priority as the target answer, and different menu answers and the auxiliary answers and supplementary answers corresponding to the menu answers can be used together as the final answer, which can further improve the accuracy of question and answer and the efficiency of using network system functions.

[0140] As an embodiment of the present invention, determining the target usage answer for the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data, or the candidate supplementary answer data based on the association relationship and the click event includes:

[0141] Sorting the candidate menu answer data, the candidate auxiliary answer data, and the candidate supplementary answer data to obtain a sorted answer set;

[0142] identifying a click answer in the sorted answer set according to the click event;

[0143] When the click answer is an answer in the candidate menu answer data, the candidate menu answer data and the corresponding auxiliary answer and supplementary answer are used as target usage answers for the similar query keyword according to the association relationship;

[0144] When the click answer is an answer in the candidate auxiliary answer data, the candidate auxiliary answer data and the corresponding menu answer and supplementary answer are used as target usage answers for the similar query keyword according to the association relationship;

[0145] When the click answer is an answer in the candidate supplementary answer data, the candidate supplementary answer data and the corresponding menu answer and supplementary auxiliary answer are used as target usage answers for the similar query keyword according to the association relationship.

[0146] Among them, the menu answer data, the candidate auxiliary answer data and the candidate supplementary answer data are sorted in top-5 from high to low according to the content weight value, and a total of 15 sorted answer sets including the best answer, the most similar answer and similar answers are obtained; when the click event is identified as the best answer in the candidate menu answer data, the target usage answer is the best menu answer clicked and all auxiliary answers and all supplementary answers corresponding to the best menu answer.

[0147] Furthermore, in an embodiment of the present invention, when a click event is identified as the most similar answer in the candidate menu answer data, the target usage answer is the most similar menu answer clicked and all auxiliary answers and all supplementary answers corresponding to the most similar menu answer.

[0148] When the click event is identified as a similar answer in the candidate menu answer data, the target use answer is the clicked similar menu answer and all auxiliary answers and all supplementary answers corresponding to the similar menu answer.

[0149] In an optional embodiment of the present invention, if the candidate answers of the above-mentioned 15 ranked answer sets do not meet the needs of the user terminal, other results clicked by the user terminal can be received, and the 15th to 30th answers can be displayed in order from large to small according to the content weight values ​​of the other results until the user terminal reaches the target usage answer corresponding to the expected similar query keyword.

[0150] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0151] In an embodiment of the present invention, first, by dividing the user question and answer set obtained based on the use of the network system into a menu data set, an auxiliary data set and a supplementary data set, a method for using the system function can be provided during the use of the network system, thereby improving the efficiency of the use of the network system function; secondly, by calculating the content weight value of the user question and answer set, it is easy to find the accurate answer corresponding to the user keyword in the subsequent use, thereby improving the accuracy of the subsequent question and answer based on the use of the network system, and by performing a similar search on the query keyword from the user question and answer set, similar query keywords are obtained, thereby improving the accuracy of the question and answer in the question and answer process of the network system; finally, by performing a similar answer search on the similar query keyword, and determining the target use answer of the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data according to the association relationship and the click event, the answer data clicked by the user can be prioritized as the target answer, and different menu answers and the auxiliary answers and supplementary answers corresponding to the menu answers can be used as the final answer, thereby further improving the accuracy of the question and answer and the efficiency of using the network system function. Therefore, the intelligent question and answer method based on the use of the network system proposed in this application can improve the efficiency of the use of the network system function and the accuracy of the question and answer.

[0152] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware via computer-readable instructions. The computer-readable instructions can be stored in a computer-readable medium, and when the program is executed, it can include the processes in the above-described method embodiments. The above-mentioned medium can be a non-volatile medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0153] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0154] Further references Figure 4 , as a response to the above Figure 2 The present application provides an embodiment of an intelligent question-answering device based on a network system. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0155] like Figure 4 As shown, the intelligent question-answering device 400 based on the network system described in this embodiment includes: an acquisition module 401, a division module 402, an identification module 403, a calculation module 404, a first retrieval module 405, a second retrieval module 406, and a question-answering module 407.

[0156] in:

[0157] The acquisition module 401 is used to obtain a user question and answer set based on the use of the network system;

[0158] The division module 402 is used to divide the user question and answer set into a menu data set, an auxiliary data set and a supplementary data set;

[0159] The identification module 403 is used to identify the association relationship between the menu data set, the auxiliary data set and the supplementary data set;

[0160] The calculation module 404 is used to classify the content of the user question and answer set to obtain multiple question and answer content sets, and calculate the content weight values ​​of the multiple question and answer content sets;

[0161] The first search module 405 is configured to receive a query keyword input by a user terminal, and perform a similar search on the query keyword from the user question and answer set to obtain similar query keywords;

[0162] The second retrieval module 406 is configured to perform similar answer retrieval on the similar query keyword according to the content weight value, and obtain candidate menu answer data, candidate auxiliary answer data, and candidate supplementary answer data;

[0163] The question and answer module 407 is used to obtain a click event corresponding to the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data sent by the user terminal, and determine the target usage answer of the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data based on the association relationship and the click event.

[0164] In this embodiment, the functions of each module / unit are as follows:

[0165] In detail, each module in the intelligent question-answering device 400 based on the network system in the embodiment of the present invention adopts the same Figures 1 to 3 The same technical means are used as the intelligent question-answering method based on the network system described in , and can produce the same technical effects, so I will not go into details here.

[0166] In an embodiment of the present invention, firstly, by dividing the user question and answer set obtained based on the use of the network system into a menu data set, an auxiliary data set and a supplementary data set, a method for using the system function can be provided during the use of the network system, thereby improving the efficiency of the use of the network system function; secondly, by calculating the content weight value of the user question and answer set, it is easy to find the accurate answer corresponding to the user keyword in the subsequent use, thereby improving the accuracy of the subsequent question and answer based on the use of the network system, and by performing a similar search on the query keyword from the user question and answer set, similar query keywords are obtained, thereby improving the accuracy of the question and answer in the question and answer process of the network system; finally, by performing a similar answer search on the similar query keyword, and determining the target use answer of the similar query keyword from the candidate menu answer data, candidate auxiliary answer data or candidate supplementary answer data according to the association relationship and the click event, the answer data clicked by the user can be prioritized as the target answer, and different menu answers and the auxiliary answers and supplementary answers corresponding to the menu answers can be used as the final answer, thereby further improving the accuracy of the question and answer and the efficiency of using the network system function. Therefore, the intelligent question and answer device based on the use of the network system proposed in this application can improve the efficiency of the use of the network system function and the accuracy of the question and answer.

[0167] The device 5 includes a memory 51, a processor 52, and a network interface 53 that are interconnected through a system bus. It should be noted that the figure only shows a device 5 having components 51-53, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0168] The device can be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The device can interact with the user through a keyboard, a mouse, a remote control, a touchpad, or a voice control device.

[0169] The memory 51 includes at least one type of readable medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or D based intelligent question-answering memory for network systems), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, magnetic disk, optical disk, etc. In some embodiments, the memory 51 can be an internal storage unit of the device 5, such as the hard disk or memory of the device 5. In other embodiments, the memory 51 can also be an external storage device of the device 5, such as a plug-in hard disk equipped on the device 5, a smart memory card (SMC), a secure digital (SD) card, a flash memory card, etc. Of course, the memory 51 can also include both the internal storage unit of the device 5 and its external storage device. In this embodiment, the memory 51 is generally used to store the operating system and various application software installed on the device 5, such as computer-readable instructions for the intelligent question-answering method used in the network system. In addition, the memory 51 can also be used to temporarily store various types of data that have been output or are to be output.

[0170] In some embodiments, the processor 52 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 52 is generally used to control the overall operation of the device 5. In this embodiment, the processor 52 is used to execute computer-readable instructions stored in the memory 51 or process data, such as computer-readable instructions for executing the intelligent question-answering method used by the network-based system.

[0171] The network interface 53 may include a wireless network interface or a wired network interface. The network interface 53 is generally used to establish a communication connection between the device 5 and other electronic devices.

[0172] In an embodiment of the present invention, first, by dividing the user question and answer set obtained based on the use of the network system into a menu data set, an auxiliary data set and a supplementary data set, a method for using the system function can be provided during the use of the network system, thereby improving the efficiency of the use of the network system function; secondly, by calculating the content weight value of the user question and answer set, it is easy to find the accurate answer corresponding to the user keyword in the subsequent use, thereby improving the accuracy of the subsequent question and answer based on the use of the network system, and by performing a similar search on the query keyword from the user question and answer set, similar query keywords are obtained, thereby improving the accuracy of the question and answer in the question and answer process of the network system; finally, by performing a similar answer search on the similar query keyword, and determining the target use answer of the similar query keyword from the candidate menu answer data, candidate auxiliary answer data or candidate supplementary answer data according to the association relationship and the click event, the answer data clicked by the user can be prioritized as the target answer, and different menu answers and the auxiliary answers and supplementary answers corresponding to the menu answers can be used as the final answer, thereby further improving the accuracy of the question and answer and the efficiency of using the network system function. Therefore, the intelligent question and answer device based on the use of the network system proposed in this application can improve the efficiency of the use of the network system function and the accuracy of the question and answer.

[0173] The present application also provides another embodiment, namely, providing a computer-readable medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the intelligent question-answering method based on the network system as described above.

[0174] In an embodiment of the present invention, first, by dividing the user question and answer set obtained based on the use of the network system into a menu data set, an auxiliary data set and a supplementary data set, a method for using the system function can be provided during the use of the network system, thereby improving the efficiency of the use of the network system function; secondly, by calculating the content weight value of the user question and answer set, it is easy to find the accurate answer corresponding to the user keyword in the subsequent use, thereby improving the accuracy of the subsequent question and answer based on the use of the network system, and by performing a similar search on the query keyword from the user question and answer set, similar query keywords are obtained, thereby improving the accuracy of the question and answer in the question and answer process of the network system; finally, by performing a similar answer search on the similar query keyword, and determining the target use answer of the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data according to the association relationship and the click event, the answer data clicked by the user can be prioritized as the target answer, and different menu answers and the auxiliary answers and supplementary answers corresponding to the menu answers can be used together as the final answer, thereby further improving the accuracy of the question and answer and the efficiency of using the network system function. Therefore, the intelligent question and answer medium based on the use of the network system proposed in this application can improve the efficiency of the use of the network system function and the accuracy of the question and answer.

[0175] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0176] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. An intelligent question-answering method based on a network system, characterized in that: The steps include: Obtain user Q&A collection based on the use of network systems; The user question and answer set is divided into a menu data set, an auxiliary data set, and a supplementary data set, wherein the menu data set is a function menu data set in the network system, the auxiliary data set is a data set of help instructions for using the function menu in the network system, and the supplementary data set is a text data set of historical users' experience or usage skills in using the function menu of the network system; Identifying an association relationship among the menu data set, the auxiliary data set, and the supplementary data set; Classifying the user question and answer set to obtain a plurality of question and answer content sets, and calculating content weight values ​​of the plurality of question and answer content sets; receiving a query keyword input by a user terminal, and performing a similarity search on the query keyword from the user question and answer set to obtain similar query keywords; Perform similar answer retrieval on the similar query keyword according to the content weight value to obtain candidate menu answer data, candidate auxiliary answer data and candidate supplementary answer data; Obtain a click event corresponding to the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data sent by the user terminal, and determine the target usage answer for the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data based on the association relationship and the click event.

2. The intelligent question-answering method based on a network system according to claim 1, characterized in that: The dividing the user question and answer set into a menu data set, an auxiliary data set, and a supplementary data set includes: Performing word segmentation on the user question and answer set to obtain a word segmentation question and answer set; Performing category labeling on the word segmentation question and answer set to obtain labeling category information; The word segmentation question and answer set is divided into the menu data set, the auxiliary data set and the supplementary data set according to the marked category information.

3. The intelligent question-answering method based on a network system according to claim 1, characterized in that: The performing similarity search on the query keyword from the user question and answer set to obtain similar query keywords includes: Calculating the similarity between the query keyword and the question keywords in the user question and answer set; The question keyword with the highest similarity is selected as the similar query keyword.

4. The intelligent question-answering method based on a network system according to claim 1, characterized in that: The similar answer retrieval is performed on the similar query keyword according to the content weight value to obtain candidate menu answer data, candidate auxiliary answer data and candidate supplementary answer data, including: Obtaining similar answers corresponding to the similar query keywords, wherein the similar answers include similar menu answers, similar auxiliary answers, and similar supplementary answers; Determining whether the content weight value is greater than a preset reliability; When the content weight value is greater than a preset confidence level, the similar menu answer corresponding to the content weight value is used as the first candidate menu answer data; Using the similar auxiliary answer corresponding to the content weight value as the first candidate auxiliary answer data; Using the similar supplementary answer corresponding to the content weight value as first candidate supplementary answer data; When the content weight value is not greater than the preset confidence level, the similar menu answer corresponding to the content weight value is used as the second candidate menu answer data; Using the similar auxiliary answer corresponding to the content weight value as the second candidate auxiliary answer data; Using the similar supplementary answer corresponding to the content weight value as second candidate supplementary answer data; Aggregating the first candidate menu answer data and the second candidate menu answer data to obtain the candidate menu answer data; Aggregating the first candidate auxiliary answer data and the second candidate auxiliary answer data to obtain the candidate auxiliary answer data; The first candidate supplementary answer data and the second candidate supplementary answer data are aggregated to obtain candidate supplementary answer data.

5. The intelligent question-answering method based on a network system according to any one of claims 1 to 4, characterized in that: The determining of the target usage answer for the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data, or the candidate supplementary answer data according to the association relationship and the click event includes: Sorting the candidate menu answer data, the candidate auxiliary answer data, and the candidate supplementary answer data to obtain a sorted answer set; identifying a click answer in the sorted answer set according to the click event; When the click answer is an answer in the candidate menu answer data, the candidate menu answer data and the corresponding auxiliary answer and supplementary answer are used as target usage answers for the similar query keyword according to the association relationship; When the click answer is an answer in the candidate auxiliary answer data, the candidate auxiliary answer data and the corresponding menu answer and supplementary answer are used as target usage answers for the similar query keyword according to the association relationship; When the click answer is an answer in the candidate supplementary answer data, the candidate supplementary answer data and the corresponding menu answer and supplementary auxiliary answer are used as target usage answers for the similar query keyword according to the association relationship.

6. The intelligent question-answering method based on a network system according to any one of claims 1 to 4, characterized in that: Calculating the content weight values ​​of the multiple question-and-answer content sets includes: Acquire multiple content factors of multiple question-and-answer content sets, and define initial menu factor weight values, initial auxiliary factor weight values, and initial supplementary factor weight values ​​corresponding to each content factor in the menu dataset, the auxiliary dataset, and the supplementary dataset, respectively; Accumulating the weights of each of the initial menu factor weights, each of the initial auxiliary factor weights, and each of the initial supplementary factor weights to obtain a menu weight value, an auxiliary weight value, and a supplementary weight value; The menu weight values, the auxiliary weight values, and the supplementary weight values ​​are aggregated to obtain content weight values ​​of multiple question-and-answer content sets.

7. The intelligent question-answering method based on a network system according to any one of claims 1 to 4, characterized in that: The identifying the association relationship among the menu data set, the auxiliary data set, and the supplementary data set includes: respectively obtaining data identifiers of the menu data set, the auxiliary data set, and the supplementary data set; The association relationship among the menu data set, the auxiliary data set and the supplementary data set is searched according to the data identifier.

8. An intelligent question-answering device based on a network system, characterized in that: include: An acquisition module is used to obtain a user question and answer set based on the use of the network system; a division module, configured to divide the user question and answer set into a menu data set, an auxiliary data set, and a supplementary data set, wherein the menu data set is a data set of function menus in the network system, the auxiliary data set is a data set of help instructions for using the function menus in the network system, and the supplementary data set is a data set of explanatory texts of historical users' experiences or usage tips for using the function menus of the network system; an identification module, configured to identify an association relationship among the menu data set, the auxiliary data set, and the supplementary data set; a calculation module, configured to classify the user question and answer set to obtain a plurality of question and answer content sets, and calculate content weight values ​​of the plurality of question and answer content sets; A first search module is configured to receive a query keyword input by a user terminal, and perform a similar search on the query keyword from the user question and answer set to obtain similar query keywords; A second retrieval module is configured to perform similar answer retrieval on the similar query keyword according to the content weight value, and obtain candidate menu answer data, candidate auxiliary answer data, and candidate supplementary answer data; A question-and-answer module is used to obtain a click event corresponding to the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data sent by the user terminal, and determine the target usage answer of the similar query keyword from the candidate menu answer data, the candidate auxiliary answer data or the candidate supplementary answer data based on the association relationship and the click event.

9. A device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, it implements the steps of the intelligent question-answering method based on a network system as described in any one of claims 1 to 7.

10. A computer-readable medium, characterized in that The computer-readable medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the intelligent question-answering method based on a network system according to any one of claims 1 to 7.

Images