CN109960489B

CN109960489B - Method, device, equipment, medium and question-answering system for generating intelligent question-answering system

Info

Publication number: CN109960489B
Application number: CN201711419805.XA
Authority: CN
Inventors: 李波; 姜中秋; 曾永梅; 朱频频
Original assignee: Shanghai Xiaoi Robot Technology Co Ltd
Current assignee: Shanghai Xiaoi Robot Technology Co Ltd
Priority date: 2017-12-25
Filing date: 2017-12-25
Publication date: 2024-01-02
Anticipated expiration: 2037-12-25
Also published as: CN109960489A

Abstract

The embodiment of the invention discloses a method, a device, equipment, a storage medium and an intelligent question-answering system for generating the intelligent question-answering system. The generating method comprises the following steps: acquiring a graphical question-answer flow chart; generating a processing framework matched with the question-answering flow chart according to each graphic component included in the question-answering flow chart; generating a question-answering flow module corresponding to the question-answering flow chart according to the user-defined configuration information matched with each graphic component in the question-answering flow chart; establishing a corresponding relation between each interaction node and one or more knowledge points in a knowledge base; and adding topic knowledge points corresponding to each question and answer flow module in a knowledge base. The scheme of the embodiment of the invention optimizes the implementation mode of the existing intelligent question-answering system, realizes the rapid construction and update of the intelligent question-answering system, improves the efficiency of generating the intelligent question-answering system, and greatly reduces the workload of developers.

Description

Method, device, equipment, medium and question-answering system for generating intelligent question-answering system

Technical Field

The embodiment of the invention relates to an intelligent question-answering technology, in particular to a method, a device, terminal equipment, a storage medium and an intelligent question-answering system for generating the intelligent question-answering system.

Background

Human-machine interaction is the science of studying the interaction relationship between a system and a user. The system may be a variety of machines, as well as computerized systems and software. For example, various artificial intelligence systems (intelligent customer service systems, voice control systems, etc.) can be implemented through human-computer interaction. Artificial intelligence semantic recognition is the basis for human-machine interaction that is capable of recognizing human language to convert to a language that can be understood by a machine.

An intelligent question-answering system is a typical application of man-machine interaction, wherein after a user presents a question, the intelligent question-answering system presents an answer to the question. An intelligent question-answering system is one of the most important, which often requires question-answering interactions with users. And determining feedback information provided for the user in the next round of question answering according to the interaction content input by the user in a certain round of question answering process. Correspondingly, an intelligent question-answering system corresponds to a question-answering flow, and from a root node in the question-answering flow, the next trend of the whole question-answering flow is continuously determined according to user interaction information received by a plurality of interaction nodes (judgment nodes) until a final node in a preset arrival period is reached to complete the whole question-answering flow.

When the intelligent question-answering system is realized in the prior art, a question-answering flow chart drawn by a flow designer is often realized in a code form by a developer. The code comprises semantic understanding, flow trend, docking of a business data system, broadcasting of a conversation to a user and the like. That is, after the flow designer of the intelligent question-answering system puts forward the demand, the developer realizes the writing of the corresponding codes. That is, the code for implementing the process is a black box for the process designer of the intelligent question-answering system, if any change is needed to the intelligent question-answering system, even if only the answer operation is modified, a developer is introduced to modify the process code, the corresponding process service is regenerated and updated to the server, and in addition, if the process service does not follow the established process in the interaction process, the problem in the breakpoint search code is also needed to be set through the intervention of the developer.

Disclosure of Invention

The embodiment of the invention provides a method, a device, terminal equipment, a storage medium and an intelligent question-answering system for generating the intelligent question-answering system, so as to optimize the implementation mode of the existing intelligent question-answering system and improve the efficiency of generating the intelligent question-answering system.

In a first aspect, an embodiment of the present invention provides a method for generating an intelligent question-answering system, including:

acquiring one or more graphical question-answering flowcharts;

generating a processing framework matched with each question-answer flow chart according to each graph component included in each question-answer flow chart, wherein the graph components comprise: the system comprises a plurality of interaction nodes, broadcasting nodes and connecting pieces for connecting different nodes;

generating custom codes respectively corresponding to the graphic components according to custom configuration information matched with the graphic components in the question-answering flow chart, and adding the custom codes to positions associated with the graphic components in the processing framework to generate a question-answering flow chart module corresponding to the question-answering flow chart;

the custom configuration information includes: broadcast content corresponding to a node, the node comprising: interaction nodes and broadcasting nodes;

if the question-answering flow module flows to a first node configured with broadcast content, the broadcast content corresponding to the first node is correspondingly broadcast;

establishing a corresponding relation between each interaction node and one or more knowledge points in a knowledge base, wherein the knowledge points corresponding to the interaction nodes comprise: the interactive questions are used for matching with the received user interaction information, and the interactive answers are used for determining the next trend of the question-answering flow module;

Adding a topic knowledge point corresponding to each question-answer flow module in a knowledge base, wherein the topic knowledge points comprise topic questions and topic answers, the topic questions are used for representing triggering conditions of the question-answer flow modules, and the topic answers are used for establishing triggering relations between the topic knowledge points and the question-answer flow modules.

In a second aspect, an embodiment of the present invention further provides a terminal device, where the terminal device includes:

one or more processors;

storage means for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a method of generating an intelligent question-answering system according to any embodiment of the present invention.

In a third aspect, embodiments of the present invention further provide a computer storage medium having stored thereon a computer program which, when executed by a processor, implements a method of generating an intelligent question-answering system according to any of the embodiments of the present invention.

In a fourth aspect, the embodiment of the present invention further provides an intelligent question-answering system, where the intelligent question-answering system is generated by a method for generating an intelligent question-answering system according to any one of the embodiments of the present invention.

In a fifth aspect, an embodiment of the present invention further provides an apparatus for generating an intelligent question-answering system, including:

the question-answering flow chart acquisition module is used for acquiring one or more graphical question-answering flow charts;

the processing framework generating module is used for generating a processing framework matched with each question-answer flow chart according to each graph component included in each question-answer flow chart, wherein the graph components comprise: the system comprises a plurality of interaction nodes, broadcasting nodes and connecting pieces for connecting different nodes;

the custom code adding module is used for generating custom codes respectively corresponding to the graphic components according to custom configuration information matched with the graphic components in the question-answering flow chart and adding the custom codes to the positions, associated with the graphic components, in the processing frame so as to generate the question-answering flow module corresponding to the question-answering flow chart;

The corresponding relation establishing module is used for establishing a corresponding relation between each interaction node and one or more knowledge points in the knowledge base, and the knowledge points corresponding to the interaction nodes comprise: the interactive questions are used for matching with the received user interaction information, and the interactive answers are used for determining the next trend of the question-answering flow module;

the system comprises a question and answer flow module, a topic knowledge point adding module, a question and answer flow module and a question and answer processing module, wherein the question and answer flow module is used for processing a question and answer, the question and answer processing module is used for processing a question and answer flow module, and the question and answer processing module is used for processing a question and answer flow module.

The embodiment of the invention provides a method, a device, equipment, a storage medium and an intelligent question-answering system, which can automatically generate a question-answering flow module for realizing the function of a question-answering flow chart through a graphical question-answering flow chart and user-defined configuration information set for each graphic component in the question-answering flow chart, and then can flexibly realize the use of the intelligent question-answering system generated based on the question-answering flow module by establishing the correspondence between a plurality of interaction nodes and one or more knowledge points in the question-answering flow chart in a knowledge base and adding the topic knowledge points corresponding to each question-answering flow module in the knowledge base. The technical scheme of the embodiment of the invention provides a method for generating the intelligent question-answering system, which can be realized in a what-you-see-is-what-you-get mode, optimizes the realization mode of the existing intelligent question-answering system, realizes the rapid construction and updating of the intelligent question-answering system, avoids introducing developers in the generation process of the intelligent question-answering system, greatly reduces the workload of the developers, reduces the cost and improves the accuracy and the efficiency.

Drawings

FIG. 1a is a flow chart of a method of generating an intelligent question-answering system according to one embodiment of the present invention;

FIG. 1b is a schematic diagram of a graphical question-answering flow chart according to a first embodiment of the present invention;

FIG. 1c is a schematic diagram illustrating a method for inputting custom configuration information of an interaction node according to a first embodiment of the present invention;

fig. 1d is a schematic diagram of inputting custom configuration information of a broadcast node according to a first embodiment of the present invention;

FIG. 1e is a schematic diagram of custom configuration information of an input connector according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method of generating an intelligent question-answering system in accordance with a second embodiment of the present invention;

FIG. 3 is a schematic diagram of a computer device according to a fourth embodiment of the present invention;

fig. 4 is a block diagram of an apparatus for generating an intelligent question-answering system according to a sixth embodiment of the present invention.

Detailed Description

The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.

It should be further noted that, for convenience of description, only some, but not all of the matters related to the present invention are shown in the accompanying drawings. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently, or at the same time. Furthermore, the order of the operations may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.

In order to facilitate understanding of the content of the embodiment of the present invention, first, a description is given of knowledge points of questions and answers in intelligent questions and answers, and related concepts of semantic expressions for simple description:

1. question-answering knowledge point

The most primitive and simplest form of question-answer knowledge points in the knowledge base is the FAQ commonly used in normal times, and the general form is a "question-answer" pair. For example, "tariffs for color ring" is a clear-expressed standard question description. "question" here should not be interpreted narrowly as "query" but rather broadly as an "input" with a corresponding "output". For example, for semantic recognition of a control system, an instruction by the user, such as "turn on radio", should also be understood as a "question", in which case the corresponding "answer" may be a call to a control program for executing the respective control.

When a user inputs to the machine, the most ideal case is that the user uses a standard question, and the intelligent semantic recognition system of the machine can immediately understand the meaning of the user. However, users often do not use a question of standards, but rather are some variant of a question of standards. For example, if the standard format of station switching for radio is "change station", then the user may use the command "switch station" and the machine needs to be able to recognize that the user is expressing the same meaning.

For intelligent semantic recognition, an extended question of a standard question is required in the knowledge base, and the extended question is slightly different from the expression form of the standard question, but has the same meaning.

Thus, the knowledge base includes a plurality of question-answer knowledge points, each of which includes questions and answers, the questions including standard questions and a plurality of extended questions, the questions in the question-answer knowledge points typically being presented in the form of semantic expressions.

2. Semantic expressions

Semantic expressions are mainly composed of words, parts of speech and their "or" relationships, the core of which depends on the "part of speech", and the simple understanding of parts of speech is a group of words with commonality, which may or may not be semantically similar, and which may or may not be labeled as important. The relation between the semantic expression and the user question is greatly different from the traditional template matching, in which the template and the user question are only matched and unmatched, and the relation between the semantic expression and the user question is represented by a quantized value (similarity), and the quantized value and the similarity between the similar question and the user question can be compared with each other. Since the semantic expression is to participate in similarity calculation together with a similar question, the definition of the template grammar is not necessarily complex, but there is enough capability to express the semantics.

Example 1

Fig. 1a is a flowchart of a method for generating an intelligent question-answering system according to an embodiment of the present invention, where the embodiment is applicable to a case of generating an intelligent question-answering system according to a question-answering flowchart, and the intelligent question-answering system specifically refers to a system capable of performing question-answering interaction with an interactive user, where the method may be performed by an apparatus for generating an intelligent question-answering system according to an embodiment of the present invention, where the apparatus may be implemented in a software and/or hardware manner, and may be generally integrated in a terminal device or a server for generating an intelligent question-answering system, where the terminal device or the server is directly or indirectly connected to a knowledge base. As shown in fig. 1a, the method in this embodiment specifically includes:

s110, one or more graphical question and answer flowcharts are obtained.

In this embodiment, the question-answering flow chart may specifically be a graphical flow chart obtained by selecting and combining each graphic component provided in the setup flow editing interface by the flow designer.

Alternatively, the question-answering flow chart may be a multi-round question-answering flow chart, and correspondingly, the generated intelligent question-answering system is a multi-round intelligent question-answering system.

Wherein the graphic assembly may comprise nodes and connectors (typically, connecting lines) for connecting the different nodes. The nodes comprise interaction nodes, and the interaction nodes specifically refer to nodes which can interact with an interaction user in question and answer (can be used for asking and answering one by one or asking and answering more) and can determine the next trend of a question and answer flow chart according to user interaction information input by the user under the interaction nodes.

From the perspective of the overall structure of the question-and-answer flow chart, a question-and-answer flow chart may include a root node representing the beginning of the flow and one or more end nodes representing the end of the flow. In addition, the question-answering flow chart can also comprise multiple layers of interaction nodes, and each layer of interaction nodes comprises one or more interaction nodes. Wherein, a layer of interaction nodes corresponds to a question-answering stage.

Of course, it may be understood that the nodes may include, in addition to the interaction node, a broadcast node, a variable setting node, or a recording node, which is not limited in this embodiment, and generally, a root node in a question-answering flowchart is an interaction node, and a termination node is a broadcast node.

For ease of understanding, a graphical question-answering flow chart is shown in fig. 1 b. As shown in FIG. 1b, the diamond-shaped graphic components in the question-answering flow chart are interactive nodes (e.g., query age node 101), and the square-shaped graphic components are broadcasting nodes (e.g., age does not satisfy loan condition node 102). The nodes are connected through node-to-node connecting wires. The question-answering flow chart in fig. 1b includes four layers of interaction nodes. Each layer includes an interaction node, namely: the first layer comprises: inquiring the age node 101 (root node), inquiring the age, inquiring the number of the vehicle, inquiring whether the vehicle has a house, node 103, inquiring the house, inquiring the loan amount, node 106, inquiring the loan amount, and node 107. And each interactive node correspondingly determines different trends of the question-answer flow chart according to different input interactive contents. In addition, the question-answering flow chart includes a plurality of termination nodes, namely: an age not meeting loan condition node 102, a reminder excess node 109, a reminder excess stage number node 108, and a report loan stage result node 10A.

S120, generating a processing frame matched with each question-answer flow chart according to each graph component included in each question-answer flow chart, wherein the graph components comprise: a plurality of interaction nodes.

In this embodiment, a question-answer flow module that can be automatically generated is provided. Accordingly, standard implementation codes matched with different types of graphic components are provided in advance, for example: and establishing standard implementation codes respectively corresponding to the interaction node and the broadcasting node, packaging the standard implementation codes in different library files, and pre-establishing a corresponding relation between the standard implementation codes and the corresponding graphic components. Typically, a storage address (or a reference address) of a standardized implementation code matched with each graphic component may be written in advance in the flow editing interface, and correspondingly, a matched processing frame may be automatically generated for each graphic component included in the question-answer flow chart drawn based on the flow editing interface.

It should be noted that, the embodiment of the present invention mainly focuses on a method for generating an intelligent question-answering system, so that a question-answering flow chart may include a plurality of interaction nodes, however, the technical solution of the embodiment of the present invention may theoretically implement any type of generation of an intelligent question-answering system, and a corresponding processing frame may be obtained only by drawing a corresponding flow chart according to needs, and further a corresponding flow module may be obtained.

S130, generating custom codes respectively corresponding to the graphic components according to the custom configuration information matched with the graphic components in the question-answering flow chart, and adding the custom codes to positions associated with the graphic components in the processing frame to generate a question-answering flow module corresponding to the question-answering flow chart.

It will be appreciated that only the general functions that the corresponding graphic component is capable of implementing are included in the standard implementation code that matches each graphic component. For example: for an interaction node, the corresponding standard implementation code includes judgment logic, or for a broadcasting node, the corresponding standard implementation code includes broadcasting logic, etc. In order for a graphic component to be able to implement the functionality assigned to it in the question-answer flow chart, it is necessary to input corresponding custom configuration parameters.

For a simple example, for the node 102 with the age not meeting the loan condition in fig. 1b, the node 102 with the age not meeting the loan condition needs to be triggered to report the content "the age not meeting the loan condition", and correspondingly, the "the age not meeting the loan condition" is a function given to the node 102 with the age not meeting the loan condition, so that the node 102 with the age not meeting the loan condition can realize the function, the report content needs to be added into the processing framework as the custom configuration information.

Typically, blank code segments may be reserved at set positions in standard implementation codes matched with each graphic component, and when a custom configuration parameter input for one graphic component in the question-answering flowchart is obtained (for example, a parameter configuration interface input provided through a flow editing interface), the custom code matched with the custom configuration parameter is added into the corresponding blank code segment, so as to implement the function of the custom graphic component.

Alternatively, the custom configuration information (for example, the age does not satisfy the loan condition) may be directly added as the custom code in the processing framework, and the custom code matched with different custom configuration information and pre-written in a matching manner may be added in the processing framework according to the custom configuration information (for example, opening the rejection preference or opening the knowledge preference), which is not limited in this embodiment.

Accordingly, if the custom setting is completed for all graphic components included in one question-answering flow chart, an implementation code capable of implementing the function of the question-answering flow chart may be generated, that is: the question-answering flow module of the embodiment of the invention is generated.

S140, establishing a corresponding relation between each interaction node and one or more knowledge points in a knowledge base, wherein the knowledge points corresponding to the interaction nodes comprise: the interactive question is used for matching with the received user interaction information, and the interactive answer is used for determining the next trend of the question-answering flow module.

In this embodiment, the interaction node needs to determine the next trend of the set question-answer flow module according to the user interaction information. Namely: the interactive node comprises at least two branches, and different branches correspond to different trends of the question-answering flow module. Therefore, different branching conditions need to be set for different branches in the question-answering flow module, for example: as shown in fig. 1B, at the query age node 101, if it is determined that the user interaction information is "20 years old", the question-answering flow module flows along branch a to query whether there is a room node 103, and if it is determined that the user interaction information is "20 years old", the question-answering flow module flows along branch B to query that the age does not satisfy the loan condition node 102.

In practice, the expression form of the user interaction information input by the interaction user (i.e. the user performing the question-answering interaction with the intelligent question-answering system) under one interaction node may not be unique, or a plurality of different user interaction information may correspond to the same branching condition. For example, when the user interaction information is "full 20 years", "adult", or "meeting the age condition", the question-answering flow module will flow along the branch a, and in addition to setting the dynamic trigger condition of the branch a (the connector) to "full 20 years", it is also necessary to establish an interaction knowledge point matched with the interaction node in the knowledge base: (full 20 years old ), (adult, full 20 years old) and (meeting age conditions, full 20 years old). And establishes the correspondence between the interaction knowledge points and the query age node 101, respectively. Similarly, for the "less than 20 years old" branch, it is also necessary to establish interaction knowledge points in the knowledge base that match the interaction nodes: (less than 20 years old ), (less than 20 years old) and (less than 20 years old without meeting the age condition). Thus, query age node 101 needs to establish correspondence with six points of interaction knowledge in total. It is to be understood that knowledge points corresponding to the interaction nodes are distinguished from question-answer knowledge points in the prior art, and therefore, for convenience of distinction, knowledge points corresponding to the interaction nodes will be hereinafter collectively referred to as interaction knowledge points.

The first half part of each bracket represents an interaction question of the interaction knowledge point and is used for matching with the received user interaction information, and the second half part of each bracket represents an interaction answer of the interaction knowledge point and is used for determining the next trend of the question-answer flow module.

Through the above operation, when the question-answering flow module flows to the query age node 101, no matter whether the interactive user inputs "full 20 years old" or "adult", the interactive answer of "full 20 years old" can be matched in the knowledge base, after the interactive answer of "full 20 years old" is obtained, the intelligent question-answering system can determine that the interactive answer matches with the dynamic trigger condition set by the branch a, and then the question-answering flow module continues to flow downwards through the branch a.

It should be emphasized again that, the interaction knowledge points corresponding to the interaction nodes stored in the knowledge base are different from the question-answer knowledge points stored in the knowledge base, and as mentioned above, the question-answer knowledge points generally include questions and corresponding answers (may also be referred to as "question-answer" pairs), where the question-answer knowledge points are mainly applicable to a scenario of performing question-answer with an interaction user, where the questions in the question-answer knowledge points are used to match with user interaction information of the interaction user, and if the matching is successful, the answers in the question-answer knowledge points are fed back to the interaction user, or a call of a control program matched with the answer content is executed.

Namely: the question-answering knowledge point can directly determine the interactive processing result (e.g., feedback answer content or execution of a call to set a control program) corresponding to the user interactive information, and the interactive knowledge point is used to determine the branching condition of the intelligent question-answering system, and the two uses are different. In order to facilitate distinguishing the two types of knowledge points in different application scenes, the interactive knowledge points and the question-answering knowledge points can be stored in different storage positions in the knowledge base, or knowledge point labels and the like which are different from the question-answering knowledge points can be added in the interactive knowledge points.

In fact, the main purpose of setting the interaction knowledge point is to consider that the content of the received user interaction information may be various for the same interaction node, for example, "full 20 years old" or "adult" as described in the foregoing, but in order to ensure the design simplicity of an intelligent question-answering system, in general, when setting a branching condition of the interaction node, only a single condition content is used, for example: "20 years old" and therefore, the concept of interactive knowledge points was introduced. By setting a plurality of interaction knowledge points in the knowledge base for the same branching condition of the same interaction node, namely: and a plurality of different interaction questions pointing to the same branch correspond to the same interaction answer, so that a plurality of approximate expression contents can correspond to the previous branch condition.

In other embodiments of the present invention, when the question-answer knowledge points are different from the interaction knowledge points, they may not be distinguished, which is within the scope of the present invention.

As in the previous example, a question-answering flow module may include multiple connectors to connect different nodes, so that the determination of the next trend of the question-answering flow module may be implemented by configuring custom configuration information of a target connector for connecting an upper interactive node and a lower node.

Accordingly, the custom configuration information may include: dynamic condition configuration information matched with the target connection; the target connection piece is used for connecting an associated upper node and an associated lower node, and the associated upper node is an interaction node;

the dynamic condition configuration information is a condition that the question-answer flow module flows from the associated upper node to the associated lower node, and the dynamic condition configuration information is matched with an interaction answer in a knowledge point corresponding to the associated upper node in the knowledge base.

And S150, adding a topic knowledge point corresponding to each question-answer flow module in a knowledge base, wherein the topic knowledge points comprise topic questions and topic answers, the topic questions are used for representing the triggering conditions of the question-answer flow modules, and the topic answers are used for establishing the triggering relation between the topic knowledge points and the question-answer flow modules.

In this embodiment, after the question-answering flow module (code for implementing the question-answering flow chart) is generated and the correspondence between the interaction node and one or more knowledge points is established in the knowledge base, in order to implement normal use of the question-answering flow module, a subject knowledge point corresponding to each question-answering flow module needs to be further added in the knowledge base.

It should be noted that, in this embodiment, an implementation manner is provided in which the question-answer flow module is first generated and then the topic knowledge points are established, and those skilled in the art will understand that the process of establishing the topic knowledge points may not be limited to being performed after the question-answer flow module is generated, but is not limited thereto. For example, topic knowledge points may be established first, followed by a corresponding question-answer flow module or the like.

In practice, the topic knowledge points are different from question-answer knowledge points in the knowledge base in that: when the user interaction information input by the interaction user matches with the questions in the question-answering knowledge points, the answers of the question-answering knowledge points are directly output, or the control program matched with the answer content is called, and when the user interaction information input by the interaction user (hereinafter, collectively called as initial request information) matches with the subject questions of one subject knowledge point, the question-answering flow module is correspondingly triggered (for example, the root node of the question-answering flow module is directly triggered).

Typically, the topic answers in a topic knowledge point can be the storage address or the call address of the question-answer flow module corresponding to the topic knowledge point, and the like, which can accurately locate the information of the question-answer flow module.

The embodiment of the invention provides a method for generating an intelligent question-answering system, which can automatically generate a question-answering flow module for realizing the function of the question-answering flow chart through a graphical question-answering flow chart and user-defined configuration information set for each graphical component in the question-answering flow chart, and can flexibly realize the use of the intelligent question-answering system generated based on the question-answering flow module by establishing the corresponding relation between a plurality of interaction nodes in the question-answering flow chart and one or more knowledge points in a knowledge base and adding the topic knowledge points corresponding to each question-answering flow module in the knowledge base. The technical scheme of the embodiment of the invention provides a method for generating the intelligent question-answering system, which can be realized in a what-you-see-is-what-you-get mode, optimizes the realization mode of the existing intelligent question-answering system, realizes the rapid construction and updating of the intelligent question-answering system, avoids introducing developers in the generation process of the intelligent question-answering system, greatly reduces the workload of the developers, reduces the cost and improves the accuracy and the efficiency.

In the foregoing embodiments, the custom configuration information may further include: and rejecting the preferential options corresponding to the interactive nodes.

When the question-answering flow module flows to a first interactive node configured to start the refusal to identify the priority function, if the received user interaction information is not matched with the interaction problems in at least one knowledge point corresponding to the first interactive node in the knowledge base, an refusal response is provided, and the user interaction information is requested to be input again.

Namely: if an interaction node is configured with rejection preference, only interaction problems based on the interaction node can be identified in the interaction node. Typically, if a rejection preference is set for an interaction node of the question-answer flow chart, a pre-written custom code matching the rejection preference function is obtained and added to the processing framework at a location associated with the interaction node.

By setting the refusing priority option, the intelligent question-answering system can be executed according to a pre-designed flow sequence, and any jump or feedback can not be carried out due to the fact that some intelligent question-answering systems cannot recognize the questions input by a user, so that the regularity and the sequence of the whole intelligent question-answering system are better.

Unlike the rejection preference, the custom configuration information may further include: knowledge preference options corresponding to the interaction nodes;

when the question-answering flow module flows to a second interaction node configured to start a knowledge priority function, if it is determined that the received user interaction information is not matched with interaction problems in at least one knowledge point corresponding to the second interaction node in a knowledge base, performing global searching on the user interaction information in the knowledge base, and executing corresponding interaction operation according to a global searching result.

Namely: if one interaction node is configured with knowledge preferences, the interaction problem based on the interaction node is first identified in the interaction node, and if the identification fails, the problem in other knowledge points is continuously identified in the knowledge base. Typically, if a knowledge preference is set for an interaction node of the question-answer flow chart, a pre-written custom code matching the knowledge preference function is obtained and added to the processing framework at a location associated with the interaction node.

By setting the knowledge preference, the execution flexibility of the intelligent question-answering system is ensured, and the question-answering interaction with the user can be well performed when the fact that the user interaction information is not matched with the currently circulated node is determined, so that the user satisfaction degree is further improved.

In a specific example, for the interaction system corresponding to the flowchart of fig. 1b, there are 6 interaction knowledge points corresponding to the interaction node, i.e. the query age node 101, and the interaction questions of the 6 interaction knowledge points are "20 years old", "adult", "meeting age condition", "20 years old", "underage", and "underage condition", respectively, when the input user interaction information does not match the 6 interaction questions, for example: "how weather today" if the query age node 101 sets a rejection preference, the intelligent question-answering system will not give corresponding feedback for the user interaction information, and stay on the query age node 101 to continue waiting for the user to reenter new interaction information; if the query age node 101 sets a knowledge preference, the intelligent question-answering system searches a knowledge base for a question-answer knowledge point corresponding to the question of the query weather, and feeds back an answer to the question-answer knowledge point, for example, "weather today is sunny, temperature 25 ℃.

On the basis of the foregoing embodiments, the custom configuration information may further include: backtracking function options corresponding to the interactive nodes;

When the question-answering flow module flows to a third interactive node configured to start a backtracking function, if the received user interaction information is determined to be matched with the interaction problem of an upper node corresponding to the third interactive node in the knowledge base, the question-answering flow module flows to the upper node corresponding to the third interactive node.

By setting the backtracking function, the universality of the intelligent question-answering system is stronger, the trend of the whole intelligent question-answering system can be readjusted at any time according to the content input by the user in the question-answering interaction process of the intelligent question-answering system and the user, and particularly, the intelligent question-answering system can be readmitted to an executed interaction node for re-execution, and the next trend based on the interaction node can be redetermined, so that the actual question-answering requirement of the user can be better met.

In a specific example, for the interaction system corresponding to the flowchart of fig. 1B, for querying the age node 101, the user inputs the user interaction information of "less than 20 years old", and accordingly, the intelligent question-answering system flows to the node 102 with the age not meeting the loan condition through the branch B, and broadcasts the corresponding broadcast content to the user. At this time, if the user re-inputs the user interaction information of "20 years old", the intelligent question-answering system will re-flow (backtrack) to the inquiring age node 101, and according to the above content input by the user, the intelligent question-answering system re-flows to inquire whether there is a car house node 103 to continue the question-answering interaction with the user through the branch a.

Specifically, the graphic assembly may further include: and broadcasting the node. Accordingly, the custom configuration information may include: broadcast content corresponding to a node, the node comprising: interaction nodes and broadcasting nodes;

and if the question-answering flow module flows to a fourth node configured with broadcasting content, broadcasting the broadcasting content corresponding to the fourth node correspondingly.

In a specific example, as shown in fig. 1b, when the intelligent question-answering system flows to the interactive node that inquires whether there is a room node 103 of a car, the interactive node firstly broadcasts a preset broadcast content, for example, "please ask you if there is a room of a car", and then determines the next trend of the intelligent question-answering system based on the subsequently received user interaction information; when the intelligent question-answering system flows to the broadcasting node meeting the 20 ten thousand loan condition, the broadcasting node can directly broadcast preset broadcasting contents, for example: "you meet 20 ten thousand loan conditions".

Through setting the broadcasting content, effective question-answer interaction can be carried out with the user, and effective prompt can be carried out on the interaction content which needs to be input next by the user.

On the basis of the foregoing embodiments, the custom configuration information may further include: breaking function options corresponding to the nodes;

When the question-answering flow module flows to a fifth node for starting the interrupt function, if user interaction information is received before broadcasting of the broadcasting content corresponding to the fifth node is finished, continuing broadcasting of the broadcasting content is stopped.

The advantages of setting the interrupt function option are: if a user is familiar with the interaction process of the whole intelligent question-answering system, the user can quickly input information required to be interacted without waiting for one node in the intelligent question-answering system to finish broadcasting, and the efficiency of human-computer interaction is further improved.

In a specific example, as shown in fig. 1b, when the intelligent question-answering system flows to the interactive node of inquiring whether there is a room with a car 103, in the process that the interactive node broadcasts "ask you if you have a room with a car", if the "there is no room with a car" input by the user is received, the broadcast content is not broadcast continuously, but flows to the node 104 meeting 20 ten thousand loan conditions to interact with the user rapidly, so that the whole question-answering interaction time is saved.

According to the technical scheme of the embodiment of the invention, corresponding implementation codes are correspondingly written and packaged according to various functional requirements possibly used by the intelligent question-answering system, so that a flow designer can conveniently select or input the required custom configuration requirements according to actual design requirements, and the universality and the use satisfaction of the method for generating the intelligent question-answering system are further improved.

For ease of understanding, a schematic diagram of inputting custom configuration information of an interaction node is shown in fig. 1 c. As shown in fig. 1c, a schematic diagram of custom configuration information for the query age node 101 in fig. 1b is given. In the input box corresponding to "knowledge", all the interaction questions corresponding to the query age node 101 may be input.

A schematic diagram of inputting custom configuration information of a broadcast node is shown in fig. 1 d. As shown in fig. 1d, a schematic diagram of custom configuration information for the alert excess node 109 in fig. 1b is given. In the answer box, the broadcast content corresponding to the alert excess node 109 may be input.

A schematic diagram of custom configuration information of an input connector is shown in fig. 1 e. As shown in fig. 1d, a schematic diagram of custom configuration information for the connection corresponding to branch a in fig. 1b is given, wherein in the input box corresponding to "condition", the condition under which the branch is selected to be executed may be input.

Typically, when a user double clicks or single clicks one graphic component in the question-answer flow chart, the input template of the user-defined configuration information is correspondingly popped up, and the flow designer can input different user-defined configuration information to different graphic components through simple selection and input operation.

Example two

Fig. 2 is a flowchart of a method for generating an intelligent question-answering system according to a second embodiment of the present invention, where the method is optimized based on the foregoing embodiments, and in this embodiment, the operations of generating a processing framework matching with each question-answering flowchart and establishing a correspondence between each interaction node and one or more knowledge points in a knowledge base according to each graphic component included in each question-answering flowchart are specified. Correspondingly, the method of the embodiment of the invention comprises the following steps:

s210, one or more graphical question and answer flowcharts are obtained.

S220, acquiring a root node in the question-answer flow chart, generating a reference standardized code corresponding to the root node according to the type of the root node, and adding the reference standardized code into an original code frame.

S230, starting from the next layer of the root node, sequentially acquiring one node in the question-answering flow chart as a current traversal node.

Typically, if the next level of the root node includes a plurality of nodes, the nodes of the level continue to traverse the next level of nodes after all the nodes of the level are traversed according to a certain traversal order, e.g., left to right or right to left.

S240, according to the type of the current traversal node, obtaining an additional standardized code corresponding to the current traversal node.

S250, adding the additional standardized codes into the original code frame correspondingly according to the positions of the standardized codes of the upper layer of nodes connected with the current traversal node through the connecting piece in the original code frame.

S260, judging whether the processing of all nodes in the question-answering flow chart is finished or not: if yes, executing S270; otherwise, execution returns to S230.

S270, taking the original code frame obtained after the processing is completed as a processing frame matched with the question-answer flow chart.

It should be noted that, the embodiment of the present invention provides a method for generating a processing frame according to a drawn question-answer flow chart, actually, the processing frame may be updated and generated in real time in the drawing process of the question-answer flow chart, and the embodiment does not limit the generation timing of the processing frame.

S280, generating custom codes respectively corresponding to the graphic components according to the custom configuration information matched with the graphic components in the question-answering flow chart, and adding the custom codes to the positions, associated with the graphic components, in the processing frame so as to generate a question-answering flow module corresponding to the question-answering flow chart.

S290, one or more knowledge points input for each interaction node in each intelligent question-answering system are obtained.

S2100, judging whether the knowledge base comprises the input knowledge points or not: if yes, executing S2110; otherwise, S2120 is performed.

In this embodiment, considering such an application scenario, a plurality of question-answering flow modules may each correspond to a knowledge point in the knowledge base, for example, the intelligent question-answering system for the staged loan consultation in fig. 1b needs to use the interactive node of the query age, and the intelligent question-answering system for the credit card to handle the consultation also needs to use the interactive node of the query age. Thus, it is not necessary to set multiple duplicate knowledge points in the knowledge base for the same interaction node.

Correspondingly, when one or more knowledge points input by a flow designer aiming at one interaction node of the question-answer flow chart are acquired, different operations are executed according to the storage condition of the knowledge points in the knowledge base: if the knowledge points are stored in the knowledge base, directly establishing the corresponding relation between the knowledge points and the interactive nodes; if the knowledge point is not stored in the knowledge base, the corresponding relation between the knowledge point and the interactive node is continuously built after the knowledge point is built in the knowledge base. The advantages of this arrangement are: on the basis of ensuring normal information inquiry, the total amount of information stored in the knowledge base is greatly reduced.

S2110, directly establishing a corresponding relation between the existing knowledge points and the interaction nodes in the corresponding intelligent question-answering system in the knowledge base, and executing S2130.

S2120, newly establishing the knowledge points in the knowledge base, establishing corresponding relations between the newly established knowledge points and interaction nodes in the corresponding intelligent question-answering system in the knowledge base, and executing S2130.

S2130, adding a topic knowledge point corresponding to each question-answer flow module in a knowledge base, wherein the topic knowledge points comprise topic questions and topic answers, the topic questions are used for representing triggering conditions of the question-answer flow modules, and the topic answers are used for establishing triggering relations between the topic knowledge points and the question-answer flow modules.

The technical scheme of the embodiment of the invention avoids the defect that the processing frame is correspondingly updated when the processing frame is generated in the process of drawing the flow chart based on the drawn question-answer flow chart, improves the generation efficiency of the question-answer flow module, and can greatly reduce the total information in the knowledge base without repeatedly storing the information in the knowledge points corresponding to the interaction nodes.

Example III

The embodiment of the invention provides an intelligent question-answering system, which is generated by the method for generating the intelligent question-answering system according to any embodiment of the invention.

The intelligent question-answering system comprises: the question-answering flow module corresponds to a question-answering flow chart, wherein the question-answering flow chart comprises a plurality of graphic components, and the graphic components comprise: a plurality of interaction nodes;

one or more knowledge points stored in a knowledge base and having a corresponding relation with each interaction node in the question-answering flow chart, wherein the knowledge points corresponding to the interaction nodes comprise: the interactive questions are used for matching with the received user interaction information, and the interactive answers are used for determining the next trend of the question-answering flow module; and

the topic knowledge points are stored in the knowledge base and comprise topic questions and topic answers, the topic questions are used for representing triggering conditions of the question-answering flow module matched with the intelligent question-answering system, and the topic answers are used for establishing triggering relations between the topic knowledge points and the question-answering flow module.

Further, the question-answering flow module corresponding to the question-answering flow chart specifically includes:

According to each graphic component included in the question-answering flow chart, a generated processing framework matched with the question-answering flow chart; and

and adding the generated custom codes corresponding to the graphic components respectively to positions associated with the graphic components in the processing framework according to the custom configuration information matched with the graphic components in the question-answering flow chart.

The technical scheme of the embodiment of the invention provides an intelligent question-answering system generated based on a method for generating the intelligent question-answering system. Through the intelligent question-answering system, a required question-answering flow module can be conveniently and effectively triggered according to question-answering requirements, and knowledge point types stored in a knowledge base are greatly enriched.

Example IV

Fig. 3 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 3 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in fig. 3 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.

As shown in FIG. 3, computer device 12 is in the form of a general purpose computing device. Components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Computer device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 3, commonly referred to as a "hard disk drive"). Although not shown in fig. 3, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.

The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and/or any devices (e.g., network card, modem, etc.) that enable the computer device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be appreciated that although not shown in fig. 3, other hardware and/or software modules may be used in connection with computer device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

Processing unit 16 executes various functional applications and data processing, such as implementing the method of generating an intelligent question-answering system provided by embodiments of the present invention, by running programs stored in system memory 28.

Namely: the processing unit implements when executing the program: acquiring one or more graphical question-answering flowcharts;

Example five

A fifth embodiment of the present invention provides a computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements a method for generating an intelligent question-answering system as provided by all the inventive embodiments of the present application:

namely: the program when executed by the processor implements: acquiring one or more graphical question-answering flowcharts;

Any combination of one or more computer readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

Example six

Fig. 4 is a structural diagram of an apparatus for generating an intelligent question-answering system according to a sixth embodiment of the present invention, as shown in fig. 4, the apparatus includes: the system comprises a question and answer flow diagram acquisition module 410, a processing framework generation module 420, a custom code addition module 430, a correspondence establishment module 440 and a topic knowledge point addition module 450. Wherein:

a question-answer flow chart acquisition module 410 for acquiring one or more graphical question-answer flow charts;

a processing frame generating module 420, configured to generate a processing frame matched with each question-answer flowchart according to each graphic component included in each question-answer flowchart, where the graphic components include: the system comprises a plurality of interaction nodes, broadcasting nodes and connecting pieces for connecting different nodes;

a custom code adding module 430, configured to generate custom codes corresponding to the graphic components respectively according to custom configuration information matched with the graphic components in the question-answering flow chart, and add the custom codes to positions associated with the graphic components in the processing frame, so as to generate a question-answering flow module corresponding to the question-answering flow chart;

the correspondence establishing module 440 is configured to establish a correspondence between each of the interaction nodes and one or more knowledge points in the knowledge base, where the knowledge points corresponding to the interaction nodes include: the interactive questions are used for matching with the received user interaction information, and the interactive answers are used for determining the next trend of the question-answering flow module;

the topic knowledge point adding module 450 is configured to add topic knowledge points corresponding to each question and answer flow module in a knowledge base, where the topic knowledge points include topic questions and topic answers, the topic questions are used to represent triggering conditions of the question and answer flow modules, and the topic answers are used to establish triggering relationships between the topic knowledge points and the question and answer flow modules.

On the basis of the above embodiments, the custom configuration information includes: rejecting the preferential selection item corresponding to the interactive node;

On the basis of the above embodiments, the custom configuration information includes: knowledge preference options corresponding to the interaction nodes;

On the basis of the above embodiments, the custom configuration information includes: backtracking function options corresponding to the interactive nodes;

On the basis of the above embodiments, the custom configuration information includes: breaking function options corresponding to the nodes;

On the basis of the above embodiments, the custom configuration information includes: dynamic condition configuration information matched with the target connection;

the target connection piece is used for connecting an associated upper node and an associated lower node, and the associated upper node is an interaction node;

the dynamic condition configuration information is a condition that the multi-round question-answering flow module flows from the associated upper node to the associated lower node, and the dynamic condition configuration information is matched with an interaction answer in a knowledge point corresponding to the associated upper node in the knowledge base.

On the basis of the above embodiments, the processing frame generating module includes:

a root node obtaining unit, configured to obtain a root node in the question-answer flow chart, generate a reference standardized code corresponding to the root node according to a type of the root node, and add the reference standardized code to an original code frame;

A current traversal node obtaining unit, configured to sequentially obtain, from a next layer of the root node, one node in the question-answering flowchart as a current traversal node;

an additional standardized code obtaining unit, configured to obtain an additional standardized code corresponding to the current traversal node according to the type of the current traversal node;

an additional standardized code adding unit, configured to add the additional standardized code to the original code frame according to a position of a standardized code of a previous layer node connected to the current traversal node through a connector in the original code frame;

the repeated execution unit is used for triggering the execution of the current traversal node acquisition unit until the processing of all nodes in the question-answering flow chart is completed;

and the processing frame acquisition unit is used for taking the original code frame obtained after the processing is completed as a processing frame matched with the question-answer flow chart.

On the basis of the above embodiments, the correspondence establishing module includes:

the knowledge point acquisition module is used for acquiring one or more knowledge points input for each interaction node in each intelligent question-answering system;

The first corresponding relation establishing unit is used for establishing a new knowledge point in the knowledge base and establishing a corresponding relation between the newly established knowledge point and an interaction node in a corresponding intelligent question-answering system in the knowledge base if the knowledge base does not comprise the input knowledge point;

and the second corresponding relation establishing unit is used for directly establishing the corresponding relation between the existing knowledge points and the interactive nodes in the corresponding intelligent question-answering system in the knowledge base if the knowledge base is determined to comprise the input knowledge points.

Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims

1. A method of generating an intelligent question-answering system, comprising:

acquiring one or more graphical question-answering flowcharts;

2. The method of claim 1, wherein the custom configuration information comprises: rejecting the preferential selection item corresponding to the interactive node;

3. The method according to claim 1 or 2, wherein the custom configuration information comprises: knowledge preference options corresponding to the interaction nodes;

4. The method of claim 1, wherein the custom configuration information comprises: backtracking function options corresponding to the interactive nodes;

5. The method of claim 1, wherein the custom configuration information comprises: breaking function options corresponding to the nodes;

6. The method of claim 1, wherein the custom configuration information comprises: dynamic condition configuration information matched with the target connection;

7. The method of claim 1, wherein generating a processing framework that matches each question-answer flow graph from the graphical components included in the question-answer flow graph comprises:

acquiring a root node in the question-answering flow chart, generating a reference standardized code corresponding to the root node according to the type of the root node, and adding the reference standardized code into an original code frame;

sequentially acquiring one node in the question-answering flow chart from the next layer of the root node as a current traversal node;

acquiring an additional standardized code corresponding to the current traversal node according to the type of the current traversal node;

according to the position of the standardized code of the upper layer node connected with the current traversal node through a connecting piece in the original code frame, correspondingly adding the additional standardized code into the original code frame;

Returning to execute the operation of sequentially acquiring one node in the question-answer flow chart from the next layer of the root node as the current traversal node until the processing of all nodes in the question-answer flow chart is completed;

and taking the original code frame obtained after the processing is completed as a processing frame matched with the question-answering flow chart.

8. The method according to any one of claims 1-7, wherein establishing correspondence between each of the interaction nodes and one or more knowledge points in a knowledge base comprises:

acquiring one or more knowledge points input for each interaction node in each intelligent question-answering system;

if the knowledge base does not comprise the input knowledge points, the knowledge points are newly built in the knowledge base, and the corresponding relation between the newly built knowledge points and the interactive nodes in the corresponding intelligent question-answering system is built in the knowledge base;

if the knowledge base is determined to comprise the input knowledge points, the corresponding relation between the existing knowledge points and the interactive nodes in the corresponding intelligent question-answering system is directly established in the knowledge base.

9. An apparatus for generating an intelligent question-answering system, comprising:

10. The apparatus of claim 9, wherein the custom configuration information comprises: rejecting the preferential selection item corresponding to the interactive node;

11. The apparatus according to claim 9 or 10, wherein the custom configuration information comprises: knowledge preference options corresponding to the interaction nodes;

12. The apparatus of claim 9, wherein the custom configuration information comprises: backtracking function options corresponding to the interactive nodes;

13. The apparatus of claim 9, wherein the custom configuration information comprises: breaking function options corresponding to the nodes;

14. The apparatus of claim 9, wherein the custom configuration information comprises: dynamic condition configuration information matched with the target connection;

15. The apparatus of claim 9, wherein the processing framework generation module comprises:

16. The apparatus according to any one of claims 9-15, wherein the correspondence establishing module includes:

17. A terminal device, characterized in that the terminal device comprises:

One or more processors;

storage means for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of generating an intelligent question-answering system as set forth in any one of claims 1-8.

18. A computer storage medium having stored thereon a computer program which when executed by a processor implements a method of generating an intelligent question-answering system according to any one of claims 1 to 8.

19. A smart question-answering system, characterized in that it is generated by a method of generating a smart question-answering system according to any one of claims 1-8.