Intelligent question-answering processing method, device, equipment and storage medium

Abstract

The present application provides a method, device, equipment and storage medium for processing intelligent questions and answers, which relate to the field of intelligent service technology. The method includes: obtaining the question information input by the user, and determining a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer result associated with the question information; the answer result set includes multiple answer results; according to the preliminary answer result set and the decision rule table, determining the minimum range of answer result set; wherein the number of answer results in the minimum range of answer result set is less than the number of answer results in the preliminary answer result set; according to the minimum range of answer result set and conditional attributes, determining and displaying the optimal answer result; wherein the conditional attributes represent the characteristics of the question information. By adopting this technical solution, the corresponding answer can be determined quickly and accurately according to the question raised by the user.

Description

Technical Field

[0001] The present application relates to the field of intelligent service technology, and in particular to an intelligent question and answer processing method, device, equipment and storage medium. Background Art

[0002] With the rapid development of the Internet and artificial intelligence technology, robots play a very important role in intelligent consulting, navigation and transaction processing. However, there are still some defects in key technologies of intelligent question and answer.

[0003] For example, there are two common methods for question matching: one is to use deep learning algorithms, and the other is to use template matching. For deep learning algorithms, the current intelligent question-answering scenario-level question library is not sufficient to support the training of deep learning models, so it is impossible for deep learning models to output relatively accurate results; for template matching methods, operation and maintenance personnel are required to manually write a large number of extended questions and answers, which is a huge workload and requires a lot of human resources.

[0004] Therefore, there is an urgent need for an answer result matching method that can quickly and accurately determine the corresponding answer based on the question raised by the user. Summary of the invention

[0005] The present application provides a method, apparatus, device and storage medium for processing intelligent questions and answers, which can quickly and accurately determine the corresponding answers based on the questions raised by the user.

[0006] In a first aspect, the present application provides a method for processing intelligent question and answer, the method comprising:

[0007] Obtaining question information input by a user, and determining a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer result associated with the question information; and the answer result set includes multiple answer results;

[0008] Determine a minimum range of answer result set according to the preliminary answer result set and the decision rule table; wherein the number of answer results in the minimum range of answer result set is less than the number of answer results in the preliminary answer result set;

[0009] According to the minimum range of answer result set and condition attributes, the optimal answer result is determined and displayed; wherein the condition attributes represent the characteristics of the question information.

[0010] In one example, obtaining question information input by a user and determining a preliminary answer result set according to a preset semantic association matrix include:

[0011] According to the question information input by the user, determining the answer result associated with the question information and the correlation value corresponding to the answer result in the preset semantic association matrix;

[0012] Compare the correlation value with a threshold value to determine a recall answer result;

[0013] The recalled answer results are sorted according to the natural order of the relevance values ​​to determine the preliminary answer result set.

[0014] In one example, according to the question information input by the user, determining the answer result associated with the question information and the correlation value corresponding to the answer result in the preset semantic association matrix includes:

[0015] Acquire a keyword of the question information input by a user, and determine at least one standard question information matching the keyword in the preset semantic association matrix;

[0016] According to each of the standard question information, the answer result associated with the question information and the correlation value corresponding to the answer result are determined in the preset semantic association matrix.

[0017] In one example, before obtaining the question information input by the user and determining a preliminary answer result set according to a preset semantic association matrix, the method further includes:

[0018] Determine, according to the standard question information and the preset dimension in the preprocessed question information library, a first semantic value of the standard question information and the preset answer;

[0019] Determining, according to the preset answer and the preset dimension, a second semantic value of the preset answer and the standard question information;

[0020] A preset semantic association matrix is ​​determined according to the first semantic value and the second semantic value.

[0021] In one example, determining a minimum range of answer result sets based on the preliminary answer result set and the decision rule table includes:

[0022] Determining an equivalent set of answer results in the decision rule table according to the preliminary answer result set;

[0023] According to the equivalent set of the answer results and the rough set algorithm, a minimum range of answer result set is determined.

[0024] In a second aspect, the present application provides a processing device for intelligent question and answer, the device comprising:

[0025] An acquisition unit is used to acquire question information input by a user and determine a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer result associated with the question information; and the answer result set includes multiple answer results;

[0026] A first determining unit is used to determine a minimum range of answer result set according to the preliminary answer result set and the decision rule table; wherein the number of answer results in the minimum range of answer result set is less than the number of answer results in the preliminary answer result set;

[0027] The second determination unit is used to determine and display the optimal answer result according to the minimum range of answer result set and condition attributes; wherein the condition attributes represent the characteristics of the question information.

[0028] In one example, the acquisition unit includes:

[0029] A correlation value determination module is used to determine, according to the question information input by the user, the answer result associated with the question information and the correlation value corresponding to the answer result in the preset semantic correlation matrix;

[0030] An answer result determination module is used to compare the correlation value with a threshold value to determine a recall answer result;

[0031] The preliminary answer result set determination module is used to sort the recalled answer results according to the natural order of the correlation degree values ​​to determine the preliminary answer result set.

[0032] In one example, the association degree value determination module includes:

[0033] Acquire a keyword of the question information input by a user, and determine at least one standard question information matching the keyword in the preset semantic association matrix;

[0034] According to each of the standard question information, the answer result associated with the question information and the correlation value corresponding to the answer result are determined in the preset semantic association matrix.

[0035] In one example, the device further includes:

[0036] A third determining unit, configured to determine a first semantic value of the standard question information and a preset answer according to the standard question information and the preset dimension in the preprocessed question information library;

[0037] a fourth determining unit, configured to determine, according to the preset answer and the preset dimension, a second semantic value of the preset answer and the standard question information;

[0038] A fifth determining unit is configured to determine a preset semantic association matrix according to the first semantic value and the second semantic value.

[0039] In one example, the first determining unit includes:

[0040] Determining an equivalent set of answer results in the decision rule table according to the preliminary answer result set;

[0041] According to the equivalent set of the answer results and the rough set algorithm, a minimum range of answer result set is determined.

[0042] The present application provides a method, device, equipment and storage medium for intelligent question and answer processing, which obtains the question information input by the user and determines a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer result associated with the question information; the answer result set includes multiple answer results; according to the preliminary answer result set and the decision rule table, the minimum range answer result set is determined; wherein the number of answer results in the minimum range answer result set is less than the number of answer results in the preliminary answer result set; according to the minimum range answer result set and conditional attributes, the optimal answer result is determined and displayed; wherein the conditional attributes represent the characteristics of the question information. By adopting this technical solution, the corresponding answer can be determined quickly and accurately according to the question raised by the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] Figure 1 This is a schematic diagram of a scenario of intelligent question answering provided according to the first embodiment of the present application;

[0045] Figure 2 It is a flowchart of a method for processing intelligent question and answer provided in Embodiment 2 of the present application;

[0046] Figure 3 It is a flowchart of a method for processing intelligent question and answer provided in Embodiment 3 of the present application;

[0047] Figure 4 It is a flowchart of a method for processing intelligent question and answer provided in Embodiment 4 of the present application;

[0048] Figure 5 is a schematic diagram of an intelligent question-answering processing device provided according to Embodiment 5 of the present application;

[0049] Figure 6 is a schematic diagram of an intelligent question-answering processing device provided according to Embodiment 6 of the present application;

[0050] Figure 7 The present invention is a block diagram of a terminal device according to an exemplary embodiment.

[0051] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0052] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0053] The present application provides an intelligent question-answering processing method, which aims to solve the above technical problems in the prior art.

[0054] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0055] Figure 1 is a schematic diagram of a scenario of intelligent question answering provided according to the first embodiment of the present application, from Figure 1 It can be seen that the input method selected to the intelligent client in the application can be text input questions or calling a designated phone number to consult related questions. Among them, the input method of the intelligent client in various applications can be image, text and voice. The intelligent client converts the image and voice into text, processes the converted text information, and displays the processed results. After the user calls the designated phone number, the voice information is converted into text information, and the key information in the text information is queried in the question library and fed back to the user.

[0056] Figure 2 This is a flow chart of a method for processing intelligent questions and answers provided in Example 2 of the present application. Example 2 includes the following steps:

[0057] S201. Obtain question information input by the user, and determine a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer results associated with the question information; the answer result set includes multiple answer results.

[0058] Exemplarily, the question input by the user can be input in text. The semantic association matrix in this embodiment is stored in the question bank. The question bank stores at least one question information and the answer result associated with the question information, wherein the semantic association matrix is ​​obtained by associating at least one question information and the answer result associated with the question information. The higher the correlation between the question information and the answer result associated with the question information in the semantic association matrix, the higher the value in the semantic association matrix.

[0059] For example, the question information entered by the user could be:

[0060] I want to report a lost credit card? The question information in the question bank is in the form of:

[0061] Standard question|answer|answer business type|answer description type; the question information in the question library can be:

[0062] {What is a savings card? | A savings card is a financial transaction card that banks provide to depositors... | Business concept | Graphics};

[0063] {What is the process of opening a savings card? | The steps of opening a savings card are... | Business consultation | Pictures and text};

[0064] {How to open a savings card? | Savings card opening page | Business navigation | Page};

[0065] {What is the process for renewing a savings card? | The steps for renewing a savings card are... | Business consultation | Graphics};

[0066] {How to apply for a replacement savings card? | Savings card replacement page | Business navigation | Page};

[0067] {What is the process for cancelling a savings card? | The steps for cancelling a savings card are... | Business consultation | Graphics};

[0068] {How to cancel a savings card? | Savings card cancellation page | Business navigation | Page};

[0069] {What is the process of reporting a lost savings card? | The steps of reporting a lost savings card are... | Business consultation | Pictures and text};

[0070] {How to report a lost savings card? | Report a lost savings card page | Business navigation | Page};

[0071] {How to calculate savings card rates? | Savings card rates... | Business concept | Graphics};

[0072] {What is a credit card? | A credit card is also called a debit card… | Business concept | Graphics};

[0073] {What is the credit card cancellation process? | The steps to cancel a credit card are... | Business consultation | Pictures and text};

[0074] {How to cancel a credit card? | Credit card cancellation page | Business navigation | Page};

[0075] {What is the process of reporting a credit card loss? | The steps of reporting a credit card loss are... | Business consultation | Pictures and text};

[0076] {How to report a lost credit card? | Credit card loss report page | Business navigation | Page};

[0077] {How to calculate credit card rates? | Credit card rates... | Business concept | Graphics};

[0078] {What is the process of opening a credit card? | The steps of opening a credit card are... | Business consultation | Pictures and text};

[0079] {How to apply for a credit card? | Credit card application page | Business navigation | Page};

[0080] {What is the process for renewing a credit card? | The steps for renewing a credit card are... | Business consultation | Pictures and text};

[0081] {How to apply for a credit card replacement? | Credit card issuance and replacement page | Business navigation | Page}.

[0082] The preliminary answer result set is at least two answer results initially determined in the question library, and the preliminary answer result set is subdivided and determined. For example, the preliminary answer result set may be as follows:

[0083] {What is the process of reporting a credit card loss? | The steps of reporting a credit card loss are... | Business consultation | Pictures and text};

[0084] {How to report a lost credit card? | Credit card loss report page | Business navigation | Page}.

[0085] Furthermore, a result set of answers related to the question input by the user is determined in the question library. For example, if the question input by the user is "I want to report a lost credit card?", the result set of answers related to the question input by the user may be:

[0086] {What is a credit card? | A credit card is also called a debit card, ... | Business concept | Graphics};

[0087] {What is the credit card cancellation process? | The steps to cancel a credit card are... | Business consultation | Pictures and text};

[0088] {How to cancel a credit card? | Credit card cancellation page url | Business navigation | Page};

[0089] {What is the process of reporting a credit card loss? | The steps of reporting a credit card loss are... | Business consultation | Pictures and text};

[0090] {How to report a lost credit card? | Credit card loss report page | Business navigation | Page};

[0091] {How to calculate credit card rates? | Credit card rates, ... | Business concept | Graphics};

[0092] {What is the process of opening a credit card? | The steps of opening a credit card are... | Business consultation | Pictures and text};

[0093] {How to apply for a credit card? | Credit card application page | Business navigation | Page};

[0094] {What is the process for renewing a credit card? | The steps for renewing a credit card are... | Business consultation | Pictures and text};

[0095] {How to apply for a credit card replacement? | Credit card issuance and replacement page | Business navigation | Page};

[0096] {What is the process of reporting a lost savings card? | The steps of reporting a lost savings card are... | Business consultation | Pictures and text};

[0097] {How to report a lost savings card? | Report a lost savings card page | Business navigation | Page}.

[0098] S202. Determine a minimum range of answer result set based on a preliminary answer result set and a decision rule table; wherein the number of answer results in the minimum range of answer result set is less than the number of answer results in the preliminary answer result set.

[0099] In this embodiment, the decision rule table is a decision rule table constructed based on rough sets. Specifically, the decision table Q = (U, R) is a question library system, U represents the domain of the question library, which includes questions, answers and other auxiliary contents, and C, There are two attribute subsets, called conditional attributes and decision attributes, and C∪D=R, Then the question base system is called a decision rule table, denoted as T = (U, R, C, D) or CD decision table for short. The equivalent classes of relation IND(C) and relation IND(D) are called condition class and decision class respectively. After adding the question information input by the user to U, a classification decision engine with decision is formed.

[0100] Answer result hit decision engine: It means analyzing the first 10 search results and obtaining a set equivalent to the question information entered by the user. This set is non-empty. If it is empty, it means that the question database does not contain the answer result.

[0101] Minimum range of answer result set decision engine: Based on the idea of ​​rough set approximation, determine the set that is in the same equivalence relationship as the question information input by the user.

[0102] Specifically, if the question the user enters is:

[0103] I want to report a lost credit card?

[0104] The minimum range of answer result set can be:

[0105] {How to cancel a credit card? | Credit card cancellation page | Business navigation | Page};

[0106] {What is the process of reporting a credit card loss? | Steps for reporting a credit card loss | Business consultation | Pictures and text};

[0107] {How to report a lost credit card? | Credit card loss report page | Business navigation | Page};

[0108] {How to apply for a credit card? | Credit card application page | Business navigation | Page};

[0109] {How to apply for a credit card replacement? | Credit card issuance and replacement page | Business navigation | Page}.

[0110] S203. Determine and display the optimal answer result based on the minimum range of answer result set and condition attributes; wherein the condition attributes represent the characteristics of the question information.

[0111] In this embodiment, the minimum range of answer result set is the set of the most accurate answers to the question. The condition attributes are the purpose of the question, the core information of the question, the question type, the relationship with the semantics of the answer result, the auxiliary information of the question, etc. The optimal answer result is the answer result displayed last.

[0112] In this embodiment, for example, the optimal answer result may be:

[0113] {What is the process for reporting a lost credit card? | The steps for reporting a lost credit card are... | Business consultation | Pictures and text}.

[0114] Furthermore, relevant answer results may be recommended to the user based on the best answer result. For example, the relevant answer results may be:

[0115] {What is the process of reporting a credit card loss? | The steps of reporting a credit card loss are... | Business consultation | Pictures and text},

[0116] {How to cancel a credit card? | Credit card cancellation page | Business navigation | Page},

[0117] {How to apply for a credit card replacement? | Credit card issuance and replacement page | Business navigation | Page},

[0118] {How to open a credit card? | Credit card opening page | Business navigation | Page}.

[0119] The present application provides a method, device, equipment and storage medium for intelligent question and answer processing, which obtains the question information input by the user and determines a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer result associated with the question information; the answer result set includes multiple answer results; according to the preliminary answer result set and the decision rule table, the minimum range answer result set is determined; wherein the number of answer results in the minimum range answer result set is less than the number of answer results in the preliminary answer result set; according to the minimum range answer result set and conditional attributes, the optimal answer result is determined and displayed; wherein the conditional attributes represent the characteristics of the question information. By adopting this technical solution, the corresponding answer can be determined quickly and accurately according to the question raised by the user.

[0120] Figure 3 This is a flowchart of a method for processing intelligent questions and answers provided in Example 3 of the present application. Example 3 includes the following steps:

[0121] S301. According to the question information input by the user, determine the answer result associated with the question information and the correlation value corresponding to the answer result in a preset semantic association matrix.

[0122] In this embodiment, the specific semantic association matrix can be found in Table 1 below, where the correlation value between question 1 and answer 1 is 10, and 10 indicates a relatively high degree of correlation. Table 1 lists 4 answers and 4 questions, and the correlation value between each answer and each question can be obtained from Table 1. The more 10 points on the diagonal, the higher the correlation between the question in the question library and the answer result, and the more other 10 points, the higher the ambiguity between the question in the question library and the answer result, the poorer the quality, and needs to be improved. The more 1-9 points and the closer to the high score, the problem is a problem focusing on a certain business field, and the direct correlation of the problem is high. The correlation needs to be discretized as much as possible to make it easier to divide the boundaries between the questions. The more 0 points, the stronger the independence between the questions and the clearer the boundaries, which is conducive to the use of rough sets for classification; relational reasoning calculations can be performed between questions, forming effective data support for the calculation of the associated answer set.

[0123] Table 1 Semantic association matrix

[0124] Question / Answer Answer 1 Answer 2 Answer 3 Answer 4 Question 1 10 9 8 0 20 Question 2 6 10 0 0 Question 3 1 10 10 0 Question 4 5 9 8 10

[0125] In one example, according to the question information input by the user, determining the answer result associated with the question information and the correlation value corresponding to the answer result in a preset semantic correlation matrix includes:

[0126] A keyword of the question information input by the user is obtained, and at least one standard question information matching the keyword is determined in a preset semantic association matrix.

[0127] In this embodiment, the standard question information is question information in a preset semantic association matrix, and at least one standard question information matching the keyword is found in the preset semantic association matrix.

[0128] According to each standard question information, the answer result associated with the question information and the correlation value corresponding to the answer result are determined in a preset semantic association matrix.

[0129] In this embodiment, the answer results associated with the standard question information are listed, and the correlation degree values ​​corresponding to the answer results are obtained at the same time.

[0130] S302: Compare the correlation value with the threshold value to determine the recalled answer result.

[0131] In this embodiment, the threshold value can be set by the user, and can be 8. Then, in the preset semantic association matrix, the answer results with an association value greater than 8 are returned.

[0132] S303: Sort the recalled answer results according to the natural order of the relevance values ​​to determine a preliminary answer result set.

[0133] In this embodiment, the answer results in the recall results are sorted to obtain a final preliminary answer result set.

[0134] S304. Determine a minimum range of answer result set based on the preliminary answer result set and the decision rule table; wherein the number of answer results in the minimum range of answer result set is less than the number of answer results in the preliminary answer result set.

[0135] Exemplarily, this step may refer to the above-mentioned step S202 and will not be described in detail.

[0136] S305. Determine and display the optimal answer result based on the minimum range of answer result set and condition attributes; wherein the condition attributes represent the characteristics of the question information.

[0137] Exemplarily, this step may refer to the above-mentioned step S203 and will not be described in detail.

[0138] In one example, before obtaining the question information input by the user and determining a preliminary answer result set according to a preset semantic association matrix, the method further includes:

[0139] According to the standard question information and preset dimensions in the preprocessed question information library, the first semantic value of the standard question information and the preset answer is determined; according to the preset answer and the preset dimension, the second semantic value of the preset answer and the standard question information is determined; according to the first semantic value and the second semantic value, a preset semantic association matrix is ​​determined.

[0140] In this embodiment, the semantic association between the question and the answer is mainly calculated, and the question is divided into several dimensions: question type, question purpose, and question core information. Among them, question type: interrogative question, rhetorical question, affirmative question, negative question, etc.; question purpose: reason, place, time, person, function navigation, rule, process, compound, etc.; question core information: core vocabulary, phrases, business keywords, dynamic information, etc.; question auxiliary information: answer type, answer expression form, etc.

[0141] For example, "How to apply for a credit card?" can be structured as: question, process, credit card, application. The calculation process of the second semantic value of the preset answer and the standard question information is: if the original question is hit, it is an inclusion relationship, and the corresponding correlation value in the semantic association matrix is ​​10; if the core information is hit or the purpose information of the question is hit, it is an inclusion relationship, and the corresponding correlation value in the semantic association matrix is ​​10; if part of the core information is hit, it is a semi-inclusion relationship, and the corresponding correlation value in the semantic association matrix is ​​1-9; if no information is hit, it is a non-inclusion relationship, and the corresponding correlation value in the semantic association matrix is ​​0.

[0142] The semantic relationship calculation process from question to answer result is to identify the intention of the question and the answer result through the intention recognition model, where the intention recognition model is built by a neural network model.

[0143] Traverse all questions in the question bank and calculate the semantic relationship between the questions and the answer results respectively; if there are more than two answer results that contain a question sentence at the same time, it means that the question sentence and the answer result are ambiguous, and the answer result or the question should be merged; if there is no semantic relationship between the question sentence and the answer result, it means that this semantic relationship is hidden and does not need to be processed; if a question sentence has more than two answer results, it means that these answer results are related.

[0144] In this embodiment, when calculating the semantic relationship between the answer result and the question, the answer result is firstly subjected to sentence recognition according to a preset model, and the answer result is firstly split into paragraphs, sentences and keywords, and the split results are used for question matching. The preset model may be a deep learning model.

[0145] In one example, a minimum range of answer result set is determined based on a preliminary answer result set and a decision rule table, including: determining an equivalent set of answer results in the decision rule table based on the preliminary answer result set; and determining the minimum range of answer result set based on the equivalent set of answer results and a rough set algorithm.

[0146] In this embodiment, the rough set algorithm is an effective tool for processing various incomplete information such as imprecise, inconsistent, and incomplete information. On the one hand, it benefits from its mature mathematical foundation and does not require prior knowledge; on the other hand, it is easy to use. Since the purpose of creating and starting from the research of rough set theory is to directly analyze and reason data, discover implicit knowledge and reveal potential laws, it is a natural data mining or knowledge discovery method. Compared with other theoretical methods for processing uncertainty problems such as data mining methods based on probability theory, data mining methods based on fuzzy theory, and data mining methods based on evidence theory, the most significant difference is that it does not require any prior knowledge other than the data set required to process the problem, and it has strong complementarity with theories for processing other uncertainty problems.

[0147] The present application provides a method, device, equipment and storage medium for processing intelligent questions and answers, which determines the answer results associated with the question information and the correlation value corresponding to the answer results in a preset semantic correlation matrix according to the question information input by the user, compares the correlation value with the threshold, determines the recalled answer results, sorts the recalled answer results according to the natural order of the correlation value, determines a preliminary answer result set, and determines the minimum range answer result set according to the preliminary answer result set and the decision rule table; wherein the number of answer results in the minimum range answer result set is less than the number of answer results in the preliminary answer result set, and determines and displays the optimal answer result according to the minimum range answer result set and conditional attributes; wherein the conditional attributes characterize the characteristics of the question information. By adopting this technical solution, the corresponding answer can be determined quickly and accurately according to the question raised by the user.

[0148] Figure 4 This is a flowchart of a method for processing intelligent questions and answers provided in Example 4 of the present application. Example 4 includes the following steps:

[0149] S401. Obtain question information input by the user, and determine a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer results associated with the question information; the answer result set includes multiple answer results.

[0150] Exemplarily, the question input by the user can be input in the form of voice information. If the question input by the user is voice information, the voice information is first converted into text information, wherein the conversion algorithm can be to convert the voice information into text information through a voice recognition algorithm, then obtain the question information in the text information, search for the question information in a preset semantic association matrix, and determine the final answer result in the semantic association matrix, and determine the set of the above answer results as a preliminary answer result set.

[0151] S402: Determine an equivalent set of answer results in the decision rule table according to the preliminary answer result set.

[0152] Exemplarily, the preliminary answer result set and the question information input by the user are used as the input of the decision rule table. If the content output by the decision rule table is empty, the equivalent set of answer results is empty, indicating that no answer result matches the question information input by the user. If the content output by the decision rule table is not empty, the output result is used as the equivalent set of answer results.

[0153] S403: Determine the minimum range of answer result set based on the equivalent set of answer results and the rough set algorithm.

[0154] In this embodiment, the answer result set with the minimum range is determined according to the equivalent set of answer results and the upper approximation strategy in the rough set algorithm.

[0155] S404. Determine and display the optimal answer result based on the minimum range of answer result set and condition attributes; wherein the condition attributes represent the characteristics of the question information.

[0156] Exemplarily, this step may refer to the above-mentioned step S203 and will not be described in detail.

[0157] The present application provides a method, device, equipment and storage medium for processing intelligent questions and answers, which obtains the voice question information input by the user, converts the voice question information into text information, determines a preliminary answer result set based on the preset semantic association matrix, and determines an equivalent set of answer results in the decision rule table based on the preliminary answer result set, and determines and displays the optimal answer result based on the minimum range of answer result set and conditional attributes; wherein the conditional attributes characterize the characteristics of the question information. The use of this technical solution can make the way users input questions not limited to text form, and can realize the input of various questions, thereby improving the user experience.

[0158] Figure 5 Schematic diagram of a processing device for intelligent question answering provided in Embodiment 5 of the present application. The device 50 in Embodiment 5 includes:

[0159] The acquisition unit 501 is used to obtain the question information input by the user and determine a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer results associated with the question information; the answer result set includes multiple answer results.

[0160] The first determination unit 502 is used to determine a minimum range answer result set according to a preliminary answer result set and a decision rule table; wherein the number of answer results in the minimum range answer result set is less than the number of answer results in the preliminary answer result set.

[0161] The second determination unit 503 is used to determine and display the optimal answer result according to the minimum range of the answer result set and the condition attribute; wherein the condition attribute represents the characteristics of the question information.

[0162] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0163] Figure 6 Schematic diagram of an intelligent question-answering processing device provided according to Embodiment 6 of the present application. The device 60 in Embodiment 6 includes:

[0164] The acquisition unit 601 is used to obtain the question information input by the user and determine a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer results associated with the question information; the answer result set includes multiple answer results.

[0165] The first determination unit 602 is used to determine a minimum range answer result set according to a preliminary answer result set and a decision rule table; wherein the number of answer results in the minimum range answer result set is less than the number of answer results in the preliminary answer result set.

[0166] The second determination unit 603 is used to determine and display the optimal answer result according to the minimum range of the answer result set and the condition attribute; wherein the condition attribute represents the characteristics of the question information.

[0167] In one example, the acquisition unit 601 includes:

[0168] The association value determination module 6011 is used to determine the answer result associated with the question information and the association value corresponding to the answer result in a preset semantic association matrix according to the question information input by the user.

[0169] The answer result determination module 6012 is used to compare the correlation value with the threshold value to determine the recalled answer result.

[0170] The preliminary answer result set determination module 6013 is used to sort the recalled answer results according to the natural order of the relevance values ​​to determine the preliminary answer result set.

[0171] In one example, the association degree value determination module 6011 includes:

[0172] Obtain keywords of the question information input by the user, and determine at least one standard question information matching the keywords in a preset semantic association matrix; based on each standard question information, determine the answer result associated with the question information and the correlation value corresponding to the answer result in the preset semantic association matrix.

[0173] In one example, the apparatus further includes:

[0174] The third determining unit 604 is used to determine the first semantic value of the standard question information and the preset answer according to the standard question information and the preset dimension in the pre-processed question information library.

[0175] The fourth determining unit 605 is used to determine the second semantic value of the preset answer and the standard question information according to the preset answer and the preset dimension.

[0176] The fifth determining unit 606 is configured to determine a preset semantic association matrix according to the first semantic value and the second semantic value.

[0177] In one example, the first determining unit 602 includes:

[0178] According to the preliminary answer result set, an equivalent set of answer results is determined in the decision rule table; according to the equivalent set of answer results and the rough set algorithm, a minimum range of answer result set is determined.

[0179] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0180] Figure 7 It is a block diagram of a terminal device according to an exemplary embodiment. The device may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0181] Device 700 may include one or more of the following components: a processing component 702 , a memory 704 , a power component 706 , a multimedia component 708 , an audio component 710 , an input / output (I / O) interface 712 , a sensor component 714 , and a communication component 716 .

[0182] The processing component 702 generally controls the overall operation of the device 700, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 702 may include one or more modules to facilitate the interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate the interaction between the multimedia component 708 and the processing component 702.

[0183] The memory 704 is configured to store various types of data to support operations on the device 700. Examples of such data include instructions for any application or method operating on the device 700, contact data, phone book data, messages, pictures, videos, etc. The memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0184] The power supply component 706 provides power to the various components of the device 700. The power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 700.

[0185] The multimedia component 708 includes a screen that provides an output interface between the device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front camera and / or a rear camera. When the device 700 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0186] The audio component 710 is configured to output and / or input audio signals. For example, the audio component 710 includes a microphone (MIC), and when the device 700 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 704 or sent via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting audio signals.

[0187] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0188] The sensor assembly 714 includes one or more sensors for providing various aspects of status assessment for the device 700. For example, the sensor assembly 714 can detect the open / closed state of the device 700, the relative positioning of components, such as the display and keypad of the device 700, the sensor assembly 714 can also detect the position change of the device 700 or a component of the device 700, the presence or absence of user contact with the device 700, the orientation or acceleration / deceleration of the device 700, and the temperature change of the device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 714 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0189] The communication component 716 is configured to facilitate wired or wireless communication between the device 700 and other devices. The device 700 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 716 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0190] In an exemplary embodiment, the apparatus 700 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above methods.

[0191] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, and the instructions can be executed by the processor 720 of the device 700 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0192] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a terminal device, enables the terminal device to execute the above-mentioned intelligent question and answer processing method of the terminal device.

[0193] The present application also discloses a computer program product, including a computer program, which implements the method described in this embodiment when executed by a processor.

[0194] Various embodiments of the systems and techniques described above in the present application can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor, which can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0195] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or electronic device.

[0196] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0197] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0198] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data electronic device), or a computing system that includes middleware components (e.g., an application electronic device), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0199] The computer system may include a client and an electronic device. The client and the electronic device are generally far away from each other and usually interact through a communication network. The relationship between the client and the electronic device is generated by computer programs running on corresponding computers and having a client-electronic device relationship with each other. The electronic device may be a cloud electronic device, also known as a cloud computing electronic device or a cloud host, which is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The electronic device may also be an electronic device of a distributed system, or an electronic device combined with a blockchain. It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0200] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0201] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for processing intelligent question and answer, It is characterized in that The method comprises: Obtaining question information input by a user, and determining a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer result associated with the question information; and the answer result set includes multiple answer results; Determine a minimum range of answer result set according to the preliminary answer result set and the decision rule table; wherein the number of answer results in the minimum range of answer result set is less than the number of answer results in the preliminary answer result set; Determine and display the optimal answer result according to the minimum range of answer result set and condition attributes; wherein the condition attributes represent the characteristics of the question information; According to the preliminary answer result set and the decision rule table, a minimum range of answer result set is determined, including: Determining an equivalent set of answer results in the decision rule table according to the preliminary answer result set; According to the equivalent set of the answer results and the rough set algorithm, a minimum range of answer result set is determined.

2. The method according to claim 1, It is characterized in that Obtain the question information entered by the user and determine a preliminary answer result set based on the preset semantic association matrix, including: According to the question information input by the user, determining the answer result associated with the question information and the correlation value corresponding to the answer result in the preset semantic association matrix; Compare the correlation value with a threshold value to determine a recall answer result; The recalled answer results are sorted according to the natural order of the relevance values ​​to determine the preliminary answer result set.

3. The method according to claim 2, It is characterized in that According to the question information input by the user, determining the answer result associated with the question information and the correlation value corresponding to the answer result in the preset semantic association matrix includes: Acquire a keyword of the question information input by a user, and determine at least one standard question information matching the keyword in the preset semantic association matrix; According to each of the standard question information, the answer result associated with the question information and the correlation value corresponding to the answer result are determined in the preset semantic association matrix.

4. The method according to any one of claims 1 to 3, It is characterized in that Before obtaining the question information input by the user and determining a preliminary answer result set according to a preset semantic association matrix, the following is also included: Determine, according to the standard question information and the preset dimension in the preprocessed question information library, a first semantic value of the standard question information and the preset answer; Determining, according to the preset answer and the preset dimension, a second semantic value of the preset answer and the standard question information; A preset semantic association matrix is ​​determined according to the first semantic value and the second semantic value.

5. A processing device for intelligent question and answer, It is characterized in that The device comprises: An acquisition unit is used to acquire question information input by a user and determine a preliminary answer result set according to a preset semantic association matrix; wherein the semantic association matrix represents the relationship between the question information and the answer result associated with the question information; and the answer result set includes multiple answer results; A first determining unit is used to determine a minimum range of answer result set according to the preliminary answer result set and the decision rule table; wherein the number of answer results in the minimum range of answer result set is less than the number of answer results in the preliminary answer result set; A second determination unit is used to determine and display the optimal answer result according to the minimum range of answer result set and condition attributes; wherein the condition attributes represent the characteristics of the question information; The first determining unit is specifically configured to: Determining an equivalent set of answer results in the decision rule table according to the preliminary answer result set; According to the equivalent set of the answer results and the rough set algorithm, a minimum range of answer result set is determined.

6. The device according to claim 5, It is characterized in that The acquisition unit comprises: A correlation value determination module is used to determine, according to the question information input by the user, the answer result associated with the question information and the correlation value corresponding to the answer result in the preset semantic correlation matrix; An answer result determination module is used to compare the correlation value with a threshold value to determine a recall answer result; The preliminary answer result set determination module is used to sort the recalled answer results according to the natural order of the correlation degree values ​​to determine the preliminary answer result set.

7. An electronic device, It is characterized in that include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 4.

8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 4 when executed by a processor.

9. A computer program product, It is characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 4 when being executed by a processor.

Images