CN110020014B

CN110020014B - Multi-turn question and answer device

Info

Publication number: CN110020014B
Application number: CN201711346369.8A
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: 2017-12-15
Filing date: 2017-12-15
Publication date: 2021-11-12
Anticipated expiration: 2037-12-15
Also published as: CN110020014A

Abstract

The embodiment of the invention discloses a multi-turn question answering device. The multi-round question answering device comprises: the initial request information searching module is used for acquiring initial request information and matching the initial request information with knowledge points in a knowledge base; the multi-turn question-answering flow module triggering module is used for triggering a multi-turn question-answering flow module corresponding to the target topic knowledge point if the initial request information is determined to be matched with the topic question in the target topic knowledge point; and the question-answer interaction module is used for carrying out question-answer interaction with the interactive users according to the interactive nodes currently circulated in the multi-turn question-answer flow module, the knowledge points corresponding to the interactive nodes and stored in the knowledge base and the user interaction information input by the interactive users aiming at the interactive nodes. The scheme of the embodiment of the invention provides a specific implementation mode for multi-turn question-answer interaction with users based on a multi-turn question-answer system, and greatly meets the multi-turn question-answer requirements of interactive users.

Description

Multi-turn question and answer device

Technical Field

The embodiment of the invention relates to an intelligent question answering technology, in particular to a multi-turn question answering device.

Background

Human-computer interaction is the science of studying the interactive relationships between systems and users. The system may be a variety of machines, and may be a computerized system and software. For example, various artificial intelligence systems (intelligent customer service systems, voice control systems, etc.) can be realized through human-computer interaction. Artificial intelligence semantic recognition is the basis for human-machine interaction, which is capable of recognizing human language for conversion into machine-understandable language.

The intelligent question-answering system is a typical application of human-computer interaction, wherein when a user proposes a question, the intelligent question-answering system gives an answer to the question. A multi-turn question-answering system is a very important intelligent question-answering system, and it often needs to interact with users in multiple turns. And determining feedback information provided for the user in the next round of question answering according to the interactive content input by the user in the process of a certain round of question answering. Correspondingly, a multi-turn question-answering system usually corresponds to a multi-turn question-answering process, and the next trend of the whole multi-turn question-answering process is continuously determined from a root node in the multi-turn question-answering process according to user interaction information received at a plurality of interaction nodes (judgment nodes) until a final node in the expectation is finally reached to finish the whole multi-turn question-answering process.

With the continuous progress of the technology, the demand of people for a multi-turn question-answering system and the question-answering demand of the multi-turn system are continuously improved, and the existing multi-turn question-answering technology cannot meet the increasing personalized and convenient question-answering demand of people.

Disclosure of Invention

The embodiment of the invention provides a multi-turn question and answer device, which is used for optimizing the existing multi-turn question and answer device based on a multi-turn question and answer system and improving the question and answer efficiency and accuracy of multi-turn question and answer.

In a first aspect, an embodiment of the present invention provides a multi-round question answering device, which is applied to a multi-round question answering system, where the multi-round question answering system includes: a plurality of rounds of question-answering flow modules corresponding to a plurality of rounds of question-answering flow charts, wherein the plurality of rounds of question-answering flow charts comprise a plurality of graphic assemblies, and the graphic assemblies comprise: a plurality of interactive nodes;

one or more knowledge points which are stored in a knowledge base and have corresponding relations with each interactive node in the multi-round question-answering flow chart, wherein the knowledge points corresponding to the interactive nodes comprise: the system comprises interactive questions and interactive answers, wherein the interactive questions are used for being matched with received user interactive information, and the interactive answers are used for determining the next trend of the multi-turn question-answering flow module; and

theme knowledge points stored in the knowledge base, wherein the theme knowledge points comprise theme questions and theme answers, the theme questions are used for representing trigger conditions of the multiple rounds of question-answering flow modules matched with a multiple rounds of question-answering system, and the theme answers are used for establishing trigger relations between the theme knowledge points and the multiple rounds of question-answering flow modules;

the multi-turn question answering device comprises: the system comprises an initial request information searching module, a knowledge base and a query module, wherein the initial request information searching module is used for acquiring initial request information input by an interactive user and matching the initial request information with knowledge points in the knowledge base, a plurality of knowledge points are stored in the knowledge base, and each knowledge point comprises a question and an answer;

a multi-turn question-answer flow module triggering module, configured to trigger a root node of a multi-turn question-answer flow module corresponding to a target topic knowledge point according to a topic answer in the target topic knowledge point if it is determined that the initial request information input by the interactive user matches a topic question in the target topic knowledge point, where the multi-turn question-answer flow module includes multiple layers of interactive nodes;

and the question-answer interaction module is used for carrying out question-answer interaction with the interactive user according to the first interactive node currently transferred in the multi-turn question-answer flow module, one or more knowledge points which are stored in the knowledge base and correspond to the first interactive node, and user interaction information which is input by the interactive user aiming at the first interactive node.

The embodiment of the invention provides a multi-turn question-answering device applied to a multi-turn question-answering system, which is used for acquiring initial request information through an initial request information searching module and matching the initial request information with knowledge points in a knowledge base; the multi-turn question-answering flow module triggering module is used for triggering a root node of the multi-turn question-answering flow module corresponding to the target topic knowledge point if the initial request information is determined to be matched with the topic question in the target topic knowledge point; the question-answer interaction module is used for performing question-answer interaction with an interactive user according to a first interaction node currently transferred to in the multi-turn question-answer flow module, one or more knowledge points corresponding to the first interaction node and user interaction information input by the interactive user aiming at the first interaction node, and provides a specific implementation mode for performing multi-turn question-answer interaction with the user based on a multi-turn question-answer system, so that the multi-turn question-answer requirements of the interactive user are greatly met, and the question-answer efficiency and accuracy of the multi-turn question-answer are improved.

Drawings

FIG. 1a is a block diagram of a generating device of a multi-round question answering system to which an embodiment of the present invention is applied;

FIG. 1b is a schematic diagram of a graphical multi-turn question-answering flow chart, to which embodiments of the present invention are applicable;

FIG. 1c is a diagram illustrating a user-defined configuration information of an input interaction node, to which an embodiment of the present invention is applicable;

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

FIG. 1e is a diagram illustrating a user-defined configuration information of an input connector according to an embodiment of the present invention;

fig. 2 is a structural diagram of a multi-round question answering device based on a multi-round question answering system according to a first embodiment of the present invention;

fig. 3 is a structural diagram of a multi-round question answering device based on a multi-round question answering system in the second embodiment of the present invention;

fig. 4 is a structural diagram of a multi-round question answering device based on a multi-round question answering system in a third embodiment of the present invention.

Detailed Description

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

It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. 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 invention, question-answer knowledge points in intelligent question-answers and related concepts of semantic expressions are introduced for simple introduction:

1. question-answering knowledge point

The most primitive and simplest form of question-answer knowledge points in the knowledge base is the frequently used FAQ in normal times, and the general form is a question-answer pair. For example, "the tariff for a coloring ring back tone" is a clear description of the standard. The term "question" should not be construed narrowly as "question" but rather broadly as "input" with corresponding "output". For example, for semantic recognition for a control system, an instruction of a user, for example "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 corresponding control.

When the user inputs the information to the machine, the most ideal situation is to use standard questions, and the intelligent semantic recognition system of the machine can immediately understand the meaning of the user. However, rather than using standard questions, users often use some variant form of standard questions. For example, if the standard form of a station switch for a radio is "change station", then the command that the user may use is "switch station", and the machine also needs to be able to recognize that what the user has expressed is the same meaning.

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

Therefore, the knowledge base comprises a plurality of question-answer knowledge points, each question-answer knowledge point comprises a question and an answer, the question comprises a standard question and a plurality of expanded questions, and the questions in the question-answer knowledge points are generally represented in the form of semantic expressions.

2. Semantic expression

The semantic expression mainly comprises words, parts of speech and their or relations, the core of the semantic expression depends on the parts of speech, the simple understanding of the parts of speech is a group of common words, the words can be similar or dissimilar in semantics, and the words can be marked as important or unimportant. The semantic expression and user question relationship is very different from the traditional template matching, in which the template and user question are just matching and unmatching relationships, and the relationship between the semantic expression and 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. Because the semantic expression and the similar question sentence participate in similarity calculation, the definition of the template grammar is not complex, but enough ability to express the semantic is required.

In addition, in each embodiment of the present invention, a multi-round question answering device for setting a multi-round question answering system is provided, where the multi-round question answering system specifically includes:

a plurality of rounds of question-answering flow modules corresponding to a plurality of rounds of question-answering flow charts, wherein the plurality of rounds of question-answering flow charts comprise a plurality of graphic assemblies, and the graphic assemblies comprise: a plurality of interactive nodes;

the topic knowledge points are stored in the knowledge base and comprise topic questions and topic answers, the topic questions are used for representing trigger conditions of the multiple rounds of question-answering flow modules matched with the multiple rounds of question-answering systems, and the topic answers are used for establishing trigger relations between the topic knowledge points and the multiple rounds of question-answering flow modules.

For ease of understanding, the generation apparatus of the multi-turn question-answering system described above will first be briefly described.

As shown in fig. 1a, the generating device of the multi-turn question-answering system applied in this embodiment specifically includes: a multi-turn question-answering flow chart acquisition module 110, a standardized code frame generation module 120, a custom code adding module 130, a corresponding relation establishment module 140, and a subject knowledge point adding module 150, wherein:

and a multi-turn question-answering flow chart acquiring module 110, configured to acquire one or more graphical multi-turn question-answering flow charts.

The multiple rounds of question answering flow charts can be graphical flow charts obtained by selecting and combining various graphical components provided in a set flow editing interface.

Wherein a graph component may comprise nodes and connectors (typically connecting lines) for connecting different nodes. The nodes comprise interactive nodes, the interactive nodes are specifically nodes which can interact with interactive users in a question-answer mode (either a question-answer mode or a question-answer mode), and the next trend of a multi-turn question-answer flow chart can be determined according to user interaction information input by the users under the interactive nodes.

From the overall structure of the multi-round question-answering flow chart, a multi-round question-answering flow chart can comprise a root node representing the beginning of the flow and one or more termination nodes representing the end of the flow. In addition, multiple layers of interactive nodes can be included in the multi-turn question-answering flow chart, and each layer of interactive nodes comprises one or more interactive nodes. Wherein, one layer of interactive nodes corresponds to one question answering stage.

It is to be understood that the nodes may include broadcast nodes, variable setting nodes, or recording nodes, besides the interactive nodes, and this embodiment does not limit this, and generally, a root node in a multi-turn question-and-answer flowchart is an interactive node, and a termination node is a broadcast node.

For ease of understanding, a graphical multi-round question-answering flow chart is shown in FIG. 1 b. As shown in fig. 1b, the diamond-shaped graphic component in the multi-round question-answering flow chart is an interactive node (for example, an age inquiry node 101), and the square-shaped graphic component is a broadcast node (for example, an age not meeting the loan condition node 102). The nodes are connected through node-to-node connecting lines. Wherein, the flow chart of the multi-turn question answering in fig. 1b includes four layers of interactive nodes. Each layer comprises an interactive node, namely: the first layer includes: an inquiry age node 101 (root node) representing an age inquiry stage, a second layer including an inquiry as to whether there is a car-owned house node 103 representing a car-owned house inquiry stage, a third layer including a node 106 inquiring a loan amount representing a loan amount inquiry stage, and a fourth layer including an inquiry installment node 107 representing an installment amount inquiry stage. And different trends of the multi-turn question-answering flow chart are correspondingly determined in each interactive node according to the input different interactive contents. In addition, the multi-turn question-answering flow chart comprises a plurality of termination nodes, namely: the node 102 for indicating the age does not meet the loan condition, the node 109 for indicating excess amount, the node 108 for indicating the excess amount and the node 10A for reporting the loan staging result.

A standardized code frame generating module 120, configured to generate a standardized code frame matched with each of the multiple rounds of question-answering flowcharts according to each of the graph components included in each of the multiple rounds of question-answering flowcharts, where the graph components include: a plurality of interactive nodes.

Furthermore, a multi-turn question-answer flow module capable of being automatically generated is provided. Accordingly, standard implementation code matching different types of graphic components is provided in advance, such as: and establishing standard implementation codes respectively corresponding to the interactive nodes and the broadcast nodes, packaging the standard implementation codes in different library files, and establishing a corresponding relation between the standard implementation codes and the corresponding graphic assemblies in advance. Typically, a storage address (or a reference address) of a standardized implementation code matched with each graphic component may be written in the flow editing interface in advance, and accordingly, a matched standardized code frame may be automatically generated for each graphic component included in a multi-turn question-answering flow chart drawn based on the flow editing interface.

It should be noted that, the embodiment of the present invention mainly focuses on a generation apparatus of a multi-round question-answering system, and therefore, a multi-round question-answering flow chart may include a plurality of interactive nodes, but the technical solution of the embodiment of the present invention may theoretically implement generation of any type of question-answering system, and as long as a corresponding flow chart is drawn as needed, a corresponding standardized code frame may be obtained, and a corresponding flow module may be obtained.

The custom code adding module 130 is configured to generate, according to the custom configuration information matched with each of the graph components in the multiple rounds of question-answering flow charts, custom codes corresponding to each of the graph components, and add the custom codes to positions, associated with the graph components, in the standardized code frame, so as to generate multiple rounds of question-answering flow charts corresponding to the multiple rounds of question-answering flow charts.

It is understood that the standard implementation code matched to each graphic component includes only general functions that the corresponding graphic component can implement. For example: for an interactive node, the corresponding standard implementation code comprises judgment logic, or for a broadcast node, the corresponding standard implementation code comprises broadcast logic and the like. In order to enable one graphic assembly to realize the functions given to the graphic assembly in the multi-turn question-answering flow chart, corresponding custom configuration parameters need to be input.

As a simple example, for the node 102 whose age does not satisfy the loan condition in fig. 1b, the node 102 whose age does not satisfy the loan condition can broadcast the content "the age does not satisfy the loan condition" after being triggered, and accordingly, the "age does not satisfy the loan condition" is a function assigned to the node 102 whose age does not satisfy the loan condition, and in order to enable the node 102 whose age does not satisfy the loan condition to realize the function, the broadcast content needs to be added to the standardized code frame as custom configuration information.

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

Optionally, custom configuration information (for example, age does not satisfy loan conditions) may be directly added to the standardized code frame as the custom code, and a custom code that matches different pre-written custom configuration information may also be added to the standardized code frame according to the custom configuration information (for example, turning on a rejection preference or turning on a knowledge preference), which is not limited in this embodiment.

Correspondingly, if the user-defined setting is completed for all the graphic components included in one multi-turn question-answering flow chart, an implementation code capable of implementing the functions of the multi-turn question-answering flow chart can be generated, namely: a multi-round question-answering flow module according to the embodiment of the invention is generated.

A corresponding relationship establishing module 140, configured to establish a corresponding relationship between each interactive node and one or more knowledge points in a knowledge base, where the knowledge points corresponding to the interactive nodes include: the system comprises interactive questions and interactive answers, wherein the interactive questions are used for being matched with received user interactive information, and the interactive answers are used for determining the next trend of the multi-turn question-answering flow module.

And the interactive nodes need to determine the next trend of the established multi-turn question-answering flow module according to the user interaction information. Namely: the interactive nodes comprise at least two branches, and different branches correspond to different trends of the multi-turn question-answering flow modules. Therefore, different branch conditions need to be set for different branches in the multi-round question-answering flow module, such as: as shown in fig. 1B, if the query age node 101 determines that the user interaction information is "20 years old full", the multi-turn question and answer flow module goes along the branch a to the node 103 querying whether there is a car room, and if the user interaction information is determined to be "20 years old short", the multi-turn question and answer flow module goes along the branch B to the node 102 not meeting the loan condition.

In fact, the expression form of the user interaction information input by the interactive user (i.e. the user who performs question-answering interaction with the multi-turn question-answering system) under one interactive node may not be unique, or a plurality of different user interaction information may all correspond to the same branch condition. As in the previous example, for example, when the user interaction information is "20 years old full", "grown up", or "meeting the age condition", the multiple rounds of question-answering flow modules all circulate along branch a, and besides setting the dynamic trigger condition of branch a (link) to "20 years old full", it is also necessary to establish an interaction knowledge point matching the interaction node in the knowledge base: (full 20 years old ), (adult, full 20 years old) and (meeting the age criteria, full 20 years old). And respectively establishing the corresponding relation between the interactive knowledge point and the inquiry age node 101. Similarly, for the branch "less than 20 years old", it is also necessary to establish an interaction knowledge point matching the interaction node in the knowledge base: (less than 20 years old ), (immature, less than 20 years old) and (not satisfying the age condition, less than 20 years old). Therefore, the query age node 101 needs to establish correspondence with six interactive knowledge points. It is to be understood that knowledge points corresponding to the interactive nodes are distinguished from question-and-answer knowledge points in the prior art, and therefore, for convenience of distinction, knowledge points corresponding to the interactive nodes will be hereinafter referred to as interactive knowledge points.

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

Through the above operations, when the multi-round question-answering flow module flows to the query age node 101, no matter the interactive user inputs "20 years old" or "grown up", the interactive answer "20 years old" is matched in the knowledge base, after the interactive answer "20 years old" is obtained, the multi-round question-answering system can determine that the interactive answer is matched with the dynamic trigger condition set by branch a, and then the multi-round question-answering flow module continues to flow downwards through 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, as described above, the so-called question-answer knowledge points generally include questions and corresponding answers (also referred to as "question-answer" pairs), where the question-answer knowledge points are mainly used in a scene of asking and answering with the interaction user, the questions in the question-answer knowledge points are used for matching with the user interaction information of the interaction user, and if matching is successful, the answers in the question-answer knowledge points are fed back to the interaction user, or a control program matching with the answer content is invoked.

Namely: the question-answering knowledge points can directly determine the interaction processing result (for example, answer feedback content or execution setting control program calling) corresponding to the user interaction information, and the interaction knowledge points are used for determining the branch conditions of the multi-turn question-answering system and have different purposes. In order to distinguish 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 distinguished from the question-answering knowledge points are 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, "20 years old" or "grown up" as described in the previous example, but in order to ensure the simplicity of a multi-turn question-answering system, only a single condition content is generally used when setting a branch condition of the interaction node, for example: "has been 20 years old", and therefore, the concept of interactive knowledge points was introduced. By setting a plurality of interactive knowledge points in the knowledge base for the same branch condition of the same interactive node, namely: and corresponding a plurality of different interactive questions pointing to the same branch to the same interactive answer, namely enabling a plurality of similar expression contents to correspond to the same branch condition.

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

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

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

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

The main knowledge point adding module 150 is configured to add a topic knowledge point corresponding to each multi-turn question-and-answer flow module in a knowledge base, where the topic knowledge point includes a topic question and a topic answer, the topic question is used to represent a trigger condition of the multi-turn question-and-answer flow module, and the topic answer is used to establish a trigger relationship between the topic knowledge point and the multi-turn question-and-answer flow module.

After a plurality of rounds of question-answering flow modules (codes for realizing a plurality of rounds of question-answering flow charts) are generated and the corresponding relation between an interactive node and one or more knowledge points is established in a knowledge base, in order to realize normal use of the plurality of rounds of question-answering flow modules, theme knowledge points corresponding to each of the plurality of rounds of question-answering flow modules need to be further added in the knowledge base.

It should be noted that the above description provides an implementation manner that first generates multiple rounds of question and answer flow modules and then establishes topic knowledge points, and those skilled in the art can understand that the establishment process of topic knowledge points may not be limited to be performed after generating multiple rounds of question and answer flow modules, and is not limited herein. For example, topic knowledge points may be established first, followed by establishing corresponding rounds of question-answering flow modules, and so on.

In fact, the topic knowledge points are different from the question-answer knowledge points in the knowledge base in that: when the user interaction information input by the interactive user is matched with the questions in the question-answer knowledge points, the answers of the question-answer knowledge points are directly output, or the calling of a control program matched with the answer content is executed, and when the user interaction information input by the interactive user (hereinafter referred to as initial request information) is matched with the subject questions of one subject knowledge point, the multi-turn question-answer flow module is correspondingly triggered (for example, the root nodes of the multi-turn question-answer flow module are directly triggered).

Typically, the topic answers in a topic knowledge point may be storage addresses or calling addresses of multiple rounds of question and answer flow modules corresponding to the topic knowledge point, and the like, which can accurately locate information of the multiple rounds of question and answer flow modules.

The device for generating the multi-turn question-answering system can be realized in a what you see is what you get mode, the realization mode of the existing multi-turn question-answering system is optimized, the multi-turn question-answering system is quickly constructed and updated, developers are prevented from being introduced into the multi-turn question-answering system generation process, the workload of the developers is greatly reduced, the cost is reduced, and the accuracy and the efficiency are improved.

Specifically, the custom configuration information may further include: and rejecting the preference corresponding to the interactive node.

When the multi-turn question-answering flow module flows to a first interaction node configured with a function of starting rejection priority, if the received user interaction information is determined not to be matched with the interaction problem in at least one knowledge point corresponding to the first interaction node in the knowledge base, a rejection response is provided, and the user interaction information is requested to be input again.

Namely: if an interactive node is configured with a rejection preference, only interactive problems based on the interactive node can be identified in the interactive node. Typically, if the rejection preference is set for an interactive node of the multi-turn question-and-answer flowchart, a pre-written custom code matching the rejection preference function is obtained, and the custom code is added to the position associated with the interactive node in the standardized code frame.

By setting the rejection preference, the multi-turn question-answering system can be executed according to a pre-designed flow sequence, and random skipping or feedback caused by some questions which cannot be identified by the multi-turn question-answering system and input by a user can not be carried out, so that the regularity and the sequence of the whole multi-turn question-answering system are better.

Unlike the rejection preference, the custom configuration information may further include: a knowledge preference corresponding to the interactive node;

when the multi-turn question-answering flow module flows to a second interactive node configured with a knowledge priority starting function, if the fact that the received user interactive information is not matched with the interactive problems in at least one knowledge point corresponding to the second interactive node in the knowledge base is determined, the user interactive information is globally searched in the knowledge base, and corresponding interactive operation is executed according to the global searching result.

Namely: if an interactive node is configured with knowledge priority, an interactive problem based on the interactive node is firstly identified in the interactive node, and if the identification fails, problems in other knowledge points are continuously identified in the knowledge base. Typically, if a knowledge preference is set for an interactive node of the multi-turn question-and-answer flowchart, a pre-written custom code matching the knowledge preference function is obtained and added to the standardized code framework at a position associated with the interactive node.

By setting the knowledge priority option, the execution flexibility of the multi-turn question-answering system is ensured, and the question-answering interaction with the user can be well carried out when the fact that the user interaction information is not matched with the currently circulated nodes is determined, so that the user satisfaction is further improved.

In a specific example, for a multi-round interactive system corresponding to the flowchart in fig. 1b, there are 6 interactive knowledge points for the interactive node inquiring about the age node 101, and the interactive questions of the 6 interactive knowledge points are "20 years old reached", "grown up", "meeting the age condition", "not 20 years old", "not grown up", and "not meeting the age condition", respectively, when the input user interaction information does not match with the 6 interactive questions, for example: "what is the weather today", if the query age node 101 sets the rejection preference, the multi-turn question-answering system does not give corresponding feedback for the user interaction information, and stays on the query age node 101 to continue to wait for the user to input new interaction information again; if the query age node 101 sets the knowledge priority, the multi-turn question-answering system searches the knowledge base for the question-answering knowledge point corresponding to the question of the query weather, and feeds back the answer of the question-answering knowledge point.

Specifically, the customized configuration information may further include: backtracking function options corresponding to the interactive nodes;

when the multi-turn question-answer flow module flows to a third interactive node configured with a backtracking starting function, if the received user interaction information is determined to be matched with the interaction problem of the upper node corresponding to the third interactive node in the knowledge base, the multi-turn question-answer flow module flows to the upper node corresponding to the third interactive node.

By setting the backtracking function, the universality of the multi-turn question-answering system is stronger, the trend of the whole multi-turn 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 multi-turn question-answering system and the user, particularly, the multi-turn question-answering system can be returned to an executed interaction node for re-execution, and the next trend based on the interaction node is re-determined, so that the actual multi-turn question-answering requirement of the user can be better met.

In a specific example, for the multi-round interactive system corresponding to the flowchart of fig. 1B, the user inputs the user interaction information "less than 20 years old" for the query age node 101, and accordingly, the multi-round interactive system flows to the node 102 whose age does not satisfy the loan condition through the branch B and plays the corresponding broadcast content to the user. At this time, if the user re-inputs the user interaction information of "20 years old is full", the multi-turn question-answering system re-flows (backtracks) to the query age node 101, and according to the above content input by the user, the multi-turn question-answering system re-flows to the query whether there is a room in the car node 103 through the branch a to continue the question-answering interaction with the user.

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

and if the multi-turn question and answer flow module flows to a fourth node configured with broadcast contents, correspondingly broadcasting the broadcast contents corresponding to the fourth node.

In a specific example, as shown in fig. 1b, when the multi-turn question and answer system flows to the interactive node 103 inquiring whether there is a car with a room, the interactive node will broadcast a preset broadcast content, for example, "ask you whether there is a car with a room", and then will determine the next trend of the multi-turn question and answer system based on the subsequently received user interaction information; when the multi-turn question-answering system flows to the broadcast node meeting the 20-million loan conditions, the broadcast node can directly broadcast preset broadcast contents, for example: "you satisfy the 20 ten thousand loan conditions".

Through setting the broadcast content, the method can effectively perform question and answer interaction with the user, and can effectively prompt the interactive content which needs to be input by the user in the next step.

Specifically, the customized configuration information may further include: an interrupt function option corresponding to the node;

when the multi-turn question-answering flow module flows to a fifth node with an interruption function, if user interaction information is received before broadcasting of the broadcast content corresponding to the fifth node is finished, continuous broadcasting of the broadcast content is stopped.

The benefits of setting the interrupt function option are: if a user is familiar with the interaction process of the whole multi-turn question-answering system, the user can quickly input information required to interact without waiting for a node in the multi-turn question-answering system to finish broadcasting, and the efficiency of man-machine interaction is further improved.

In a specific example, as shown in fig. 1b, when the multi-turn question and answer system flows to the interactive node 103 inquiring whether there is a car with a house, in the process that the interactive node reports "ask for whether there is a car with a house", if the interactive node receives "there is a car without a house" input by the user, the broadcast content is not continuously reported, but the interactive node quickly flows to the node 104 meeting the 20 ten thousand loan condition to interact with the user, so that the whole question and answer interaction time is saved.

The multi-turn question-answering system comprises a plurality of sets of realization codes, wherein the realization codes are written and packaged correspondingly according to various function requirements which can be used by the multi-turn question-answering system, so that a flow designer can conveniently select or input the required user-defined configuration requirements according to the actual design requirements, and the universality and the use satisfaction of a generating device of the multi-turn question-answering system are further improved.

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

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

A schematic diagram of custom configuration information for one input connector is shown in fig. 1 e. As shown in fig. 1d, a schematic diagram of the custom configuration information for the connector corresponding to branch a in fig. 1b is given, wherein in the input box corresponding to "condition", the condition that the branch is selected to execute can be input.

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

Example one

Fig. 2 is a flowchart of a multi-turn question-answering device based on a multi-turn question-answering system in an embodiment of the present invention, where the multi-turn question-answering device described in this embodiment is based on the multi-turn question-answering system generated by the generating device of the multi-turn question-answering system, this embodiment is applicable to a situation of performing multi-turn question-answering interaction with an interactive user, and this device may be implemented by the multi-turn question-answering device based on the multi-turn question-answering system, and this device may be implemented by software and/or hardware, and may be generally integrated in a dedicated interactive device with an interactive function (e.g., an intelligent robot) or a general terminal device (e.g., a mobile phone or a tablet computer, etc.) installed with interactive software (e.g., an assistant voice), and this device specifically includes: the system comprises an initial request information searching module 210, a multi-round question-answering flow module triggering module 220 and a question-answering interaction module 230, wherein:

the initial request information searching module 210 is configured to obtain initial request information input by an interactive user, and match the initial request information with knowledge points in a knowledge base, where the knowledge base stores a plurality of knowledge points, and each knowledge point includes a question and an answer.

In this embodiment, the knowledge points stored in the knowledge base include: question-answer knowledge points, topic knowledge points, and knowledge points corresponding to interactive nodes (i.e., interactive knowledge points). The related concepts of the knowledge points are described in detail above, and are not described herein again.

A multi-turn question-answer flow module triggering module 220, configured to trigger a root node of a multi-turn question-answer flow module corresponding to a target topic knowledge point according to a topic answer in the target topic knowledge point if it is determined that the initial request information input by the interactive user matches a topic question in the target topic knowledge point, where the multi-turn question-answer flow module includes multiple layers of interactive nodes.

In this embodiment, the topic answers in the topic knowledge points store information that can accurately locate corresponding multiple rounds of question-answering flow modules, and after it is determined that the initial request information input by the interactive user matches the topic question of one topic knowledge point, the matched multiple rounds of question-answering flow modules can be accurately located, and the root nodes of the multiple rounds of question-answering flow modules are correspondingly triggered, that is: the multi-turn question-answering flow module is activated to carry out question-answering interaction with the interactive users.

The question-answer interaction module 230 is configured to perform question-answer interaction with the interaction user according to the first interaction node currently transferred in the multi-turn question-answer flow module, one or more knowledge points stored in the knowledge base and corresponding to the first interaction node, and user interaction information input by the interaction user for the first interaction node.

As previously described, a multi-turn question-answering flow module includes a plurality of layers of interactive nodes, each layer of interactive nodes includes one or more interactive nodes, and the root node is a first layer of nodes. When the multi-turn question-answer flow module flows to an interactive node, matching user interaction information input by an interactive user based on the interactive node with one or more knowledge points corresponding to the node in a knowledge base, and determining the next trend of the multi-turn question-answer flow module according to a corresponding matching result.

The embodiment of the invention provides a multi-turn question answering device applied to a multi-turn question answering system, which is characterized in that initial request information is obtained and is matched with knowledge points in a knowledge base by using the initial request information; if the initial request information is determined to be matched with the topic question in the target topic knowledge point, triggering a root node of a multi-turn question-answer flow module corresponding to the target topic knowledge point; according to a first interactive node currently transferred to in the multi-turn question-answer flow module, one or more knowledge points corresponding to the first interactive node and stored in a knowledge base, and a technical means for interaction between an interactive user and the interactive user aiming at user interaction information input by the first interactive node, a specific implementation mode for performing multi-turn question-answer interaction with the user based on a multi-turn question-answer system is provided, the multi-turn question-answer requirements of the interactive user are greatly met, and the question-answer efficiency and accuracy of the multi-turn question-answer are improved.

Example two

Fig. 3 is a structural diagram of a multi-turn question-answering device based on a multi-turn question-answering system according to a second embodiment of the present invention, which is optimized based on the above-mentioned embodiment, in which the question-answering interaction module is further embodied, and accordingly, the device according to the second embodiment of the present invention includes:

an initial request information search module 310, a multi-round question-answering flow module trigger module 320 and a question-answering interaction module 330, wherein:

the question-answer interaction module 330 specifically includes:

a user interaction information obtaining unit 3301, configured to obtain user interaction information input by a user for the first interaction node;

a user interaction information matching unit 3302, configured to match the user interaction information with interaction problems in one or more knowledge points corresponding to the first interaction node;

the matching success processing unit 3303 is configured to, if matching is successful, return an interactive answer corresponding to the successfully matched knowledge point to the multi-round question-answer flow module, so that the multi-round question-answer flow module determines a next trend;

in this embodiment, if the user interaction information input by the interactive user matches with one knowledge point corresponding to the currently circulated interactive node, the multi-turn question-answering flow module may determine the next trend of the whole multi-turn question-answering flow module according to the configured dynamic trigger condition and the connection piece matching the interactive answer after acquiring the interactive answer returned by the knowledge base.

And the first repeated execution unit 3304 is configured to continuously repeat the above processes of matching and determining the next trend until the multi-round question-answering flow module exits or the interaction is ended.

In this embodiment, the first repeatedly executing unit 3304 first determines whether to exit the multi-round question-answering flow module or end the interaction: if yes, finishing the interaction; and if not, continuing to perform question-answer interaction with the interactive user according to the node corresponding to the next walking direction.

In this embodiment, for convenience of description, the process of determining whether to exit the multi-round question-answering flow module or end the interaction is placed after the matching success processing unit 3303. In fact, the interactive user may exit the multiple rounds of question and answer flow modules when the multiple rounds of question and answer flow modules are transferred to any node, so that the above determination process may be executed independently and concurrently with each module in the embodiment of the present invention, and the embodiment does not limit the implementation time of the above determination process.

In this embodiment, if the node corresponding to the next trend is an interactive node, the execution of the question-answer interactive module 330 is repeatedly triggered; if the node corresponding to the next trend is a broadcast node and the broadcast node is not a termination node, the corresponding broadcast content is correspondingly broadcast and is transferred to the next node determined by the broadcast node to perform question and answer interaction with the interactive user according to the next trend uniquely determined by the broadcast node (for example, in fig. 1b, the node 104 meeting 20 ten thousand loan conditions and the node 105 meeting 30 ten thousand loan conditions are both uniquely pointed to a node 106 inquiring loan amount); if the node corresponding to the next trend is a broadcast node and the broadcast node is a termination node, the interaction with the interactive user is finished after the corresponding broadcast content is correspondingly broadcast.

In this embodiment, when it is determined that the user interaction information does not match one or more knowledge points corresponding to the first interaction node, different flow processing manners may be adopted for processing according to different types of pre-configured custom configuration parameters corresponding to the first interaction node.

Further, the question-answer interaction module 330 may further include:

a first matching failure processing unit 3305, configured to provide a rejection response to the interaction user and request the interaction user to re-input user interaction information for the first interaction node if the user interaction information is not matched with one or more knowledge points corresponding to the first interaction node and the first interaction node is configured to start a rejection priority function;

in this embodiment, if the first interactive node is configured to start the rejection priority function, matching is performed only on the basis of the interaction problem in the pre-configured knowledge point corresponding to the first interactive node with the user interaction information, and if the matching fails, the identification is rejected, and the interactive user is requested to re-input the user interaction information and re-match the user interaction information.

A second repeated execution unit 3306, configured to trigger the user interaction information matching unit to execute again when new user interaction information is acquired.

Further, the question-answer interaction module 330 may further include:

a second matching failure processing unit 3307, configured to perform global search on the received user interaction information in the knowledge base if the user interaction information is not matched with one or more knowledge points corresponding to the first interaction node and the first interaction node is configured to start a knowledge priority function;

in this embodiment, if the first interaction node is configured to start the knowledge priority function, when the interaction problem in the knowledge point corresponding to the first interaction node fails to match with the user interaction information, other knowledge points included in the knowledge base are used to match with the user interaction information, and a corresponding matching result is fed back.

A knowledge point matching success processing unit 3308, configured to provide an answer corresponding to the found knowledge point to the interactive user if it is determined that the knowledge base includes a knowledge point matching the question and the user interaction information;

the searched knowledge points may be general question-answer knowledge points, and after the answer corresponding to the question-answer knowledge point is provided to the interactive user, the trigger state of the current interactive node (first interactive node) of the multi-turn question-answer system may be continuously maintained, and the user interaction information input by the interactive user for the first interactive node may be continuously obtained for matching.

Further, the knowledge point matching success processing unit 3308 specifically includes:

the multi-turn question-answering flow module ending triggering subunit is used for ending the triggering state of the current multi-turn question-answering flow module if the found knowledge point is determined to be another subject knowledge point;

and the other multi-turn question-answer flow module triggering subunit is used for triggering the multi-turn question-answer flow module corresponding to the other topic knowledge point according to the topic answer in the other topic knowledge point.

A knowledge point matching failure processing unit 3309, configured to provide a matching failure response to the interaction user if it is determined that the problem in each knowledge point in the knowledge base does not match the user interaction information, request the interaction user to re-input the user interaction information for the first interaction node, and trigger the user interaction information matching unit to re-execute when new user interaction information is acquired.

The technical scheme of the embodiment of the invention provides the multi-turn question and answer device aiming at the interaction nodes with the reject priority or the knowledge priority, so that the applicable scenes of the multi-turn question and answer device are further enriched, and the use experience of an interaction user is greatly met.

EXAMPLE III

Fig. 4 is a flowchart of a multi-round question-answering device based on a multi-round question-answering system according to a third embodiment of the present invention, which is optimized based on the third embodiment, in which the question-answering interaction module is further refined, and accordingly, the device according to the third embodiment of the present invention includes:

an initial request information search module 410, a multi-round question-answering flow module trigger module 420 and a question-answering interaction module 430, wherein:

the question-answer interaction module 430 specifically includes:

an upper knowledge point obtaining unit 4301, configured to obtain one or more knowledge points respectively corresponding to the first interaction node and an upper node of the first interaction node stored in the knowledge base if it is determined that the first interaction node is configured to start a backtracking function;

and the upper knowledge point matching success processing unit 4302 is configured to, if it is determined that the received user interaction information matches an interaction question of an upper node corresponding to the first interaction node in the knowledge base, transfer the multi-turn question-answering flow module to the matched upper node, and return an interaction answer corresponding to the successfully matched knowledge point to the multi-turn question-answering flow module, so that the multi-turn question-answering flow module determines a next trend.

In this embodiment, if it is determined that the first interaction node configuration starts the backtracking function, when the multi-turn question and answer flow module flows to the first interaction node, other interaction nodes located above the first interaction node in the multi-turn question and answer flow module can be backtracked according to the actual requirements of the interaction users; if the first interactive node is determined not to be configured with the backtracking starting function, when the multi-turn question and answer flow module is transferred to the first interactive node, other interactive nodes positioned above the first interactive node in the multi-turn question and answer flow module cannot be backtracked.

For example: as shown in fig. 1b, if the multi-round question answering process module has been circulated to the ask loan amount node 106 and the ask loan amount node 106 is configured to start the backtracking function, when the interactive user inputs "20 years old is full", the multi-round question answering process module will be circulated to the ask age node 101 again to perform question answering interaction with the interactive user.

The technical scheme of the embodiment of the invention provides the multi-turn question answering device aiming at the interaction nodes with the backtracking function, so that the applicable scenes of the multi-turn question answering device are further enriched, and the use experience of an interaction user is greatly met.

The device further comprises:

the broadcasting module is used for broadcasting to the interactive users according to broadcasting contents configured by the second node when the multi-turn question-answering flow module is transferred to the second node;

wherein the second node comprises: interactive nodes or broadcast nodes.

The broadcast module is specifically used for: and if the second node is configured to start an interruption function and receives user interaction information before the broadcast content corresponding to the second node is completely broadcast, stopping continuously broadcasting the broadcast content.

Namely: in the process that the broadcast node or the interactive node in the multi-turn question-answering flow module broadcasts the corresponding broadcast content to the interactive user (the broadcast content is not broadcast and is not finished), if the interactive user interrupts the broadcast content, the continuous broadcast of the broadcast content can be stopped.

The benefits of this arrangement are: the multi-turn question answering device with the interrupt function and the interactive nodes or the broadcast nodes is provided, scenes which can be suitable for the multi-turn question answering device are further enriched, and the use experience of interactive users is greatly met.

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. 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, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A multi-turn question answering device is applied to a multi-turn question answering system and is characterized by comprising:

the system comprises an initial request information searching module, a knowledge base and a query module, wherein the initial request information searching module is used for acquiring initial request information input by an interactive user and matching the initial request information with knowledge points in the knowledge base, a plurality of knowledge points are stored in the knowledge base, and each knowledge point comprises a question and an answer;

the multi-round question-answering system comprises: a plurality of rounds of question-answering flow modules corresponding to a plurality of rounds of question-answering flow charts, wherein the plurality of rounds of question-answering flow charts comprise a plurality of graphic assemblies, and the graphic assemblies comprise: a plurality of interactive nodes; one or more knowledge points which are stored in a knowledge base and have corresponding relations with each interactive node in the multi-round question-answering flow chart, wherein the knowledge points corresponding to the interactive nodes comprise: the system comprises interactive questions and interactive answers, wherein the interactive questions are used for being matched with received user interactive information, and the interactive answers are used for determining the next trend of the multi-turn question-answering flow module; the topic knowledge points are stored in the knowledge base and comprise topic questions and topic answers, the topic questions are used for representing trigger conditions of the multi-round question-answering flow modules matched with a multi-round question-answering system, and the topic answers are used for establishing trigger relations between the topic knowledge points and the multi-round question-answering flow modules;

the topic answers in a topic knowledge point are information capable of accurately positioning the multi-turn question-answer process modules, and the information comprises the following steps: the memory address or the calling address of the multi-turn question-answering flow module corresponding to the topic knowledge point;

a standardized code frame generating module, configured to generate a standardized code frame matched with each of the multiple rounds of question-answering flowcharts according to each of the graph components included in each of the multiple rounds of question-answering flowcharts, where the graph components include: a plurality of interactive nodes;

the question-answer interaction module is used for carrying out question-answer interaction with the interactive user according to the first interactive node currently transferred in the multi-turn question-answer flow module, one or more knowledge points which are stored in the knowledge base and correspond to the first interactive node and user interaction information which is input by the interactive user aiming at the first interactive node;

and the first interactive node is configured with an opening rejection priority function or a knowledge priority function.

2. The apparatus of claim 1, wherein the multi-round question-answering flow module corresponding to the multi-round question-answering flow chart comprises:

generating a standardized code frame matched with the multi-round question-answering flow chart according to each graphic component included in the multi-round question-answering flow chart; and

and generating custom codes which respectively correspond to the graphic components and are added to the positions, associated with the graphic components, in the standardized code frame according to the custom configuration information matched with the graphic components in the multi-turn question-answering flow chart.

3. The apparatus of claim 1, wherein the question-answer interaction module comprises:

the user interaction information acquisition unit is used for acquiring user interaction information input by a user aiming at the first interaction node;

the user interaction information matching unit is used for matching the user interaction information with interaction problems in one or more knowledge points corresponding to the first interaction node;

the matching success processing unit is used for returning the interactive answers corresponding to the successfully matched knowledge points to the multi-turn question-answering flow module if the matching is successful so as to enable the multi-turn question-answering flow module to determine the next trend;

and the first repeated execution unit is used for continuously repeating the processes of matching and determining the next trend until the multi-turn question-answering flow module is quitted or the interaction is finished.

4. The apparatus of claim 3, wherein the question-answer interaction module further comprises:

a first matching failure processing unit, configured to provide a rejection response to the interaction user and request the interaction user to re-input user interaction information for the first interaction node if the user interaction information is not matched with one or more knowledge points corresponding to the first interaction node and the first interaction node is configured to start a rejection priority function;

and the second repeated execution unit is used for triggering the user interaction information matching unit to execute again when new user interaction information is acquired.

5. The apparatus of claim 3, wherein the question-answer interaction module further comprises:

a second matching failure processing unit, configured to perform global search on the received user interaction information in the knowledge base if the user interaction information is not matched with one or more knowledge points corresponding to the first interaction node and the first interaction node is configured to start a knowledge priority function;

a knowledge point matching success processing unit, configured to provide an answer corresponding to the found knowledge point to the interactive user if it is determined that the knowledge base includes a knowledge point matching the problem with the user interaction information;

and the knowledge point matching failure processing unit is used for providing a matching failure response to the interactive user if the problem in each knowledge point in the knowledge base is determined not to be matched with the user interaction information, requesting the interactive user to input the user interaction information aiming at the first interaction node again, and triggering the user interaction information matching unit to execute again when new user interaction information is acquired.

6. The apparatus according to claim 5, wherein the knowledge point matching success processing unit specifically includes:

7. The apparatus of claim 1, wherein the question-answer interaction module comprises:

an upper knowledge point acquisition unit, configured to, if it is determined that the first interaction node is configured to start a backtracking function, acquire one or more knowledge points respectively corresponding to the first interaction node and an upper node of the first interaction node stored in the knowledge base;

and the upper-layer knowledge point matching success processing unit is used for circulating the multi-turn question-answering flow module to the matched upper-layer node and returning the interactive answer corresponding to the successfully matched knowledge point to the multi-turn question-answering flow module to enable the multi-turn question-answering flow module to determine the next trend if the received user interaction information is determined to be matched with the interactive question of the upper-layer node corresponding to the first interactive node in the knowledge base.

8. The apparatus of claim 1, further comprising:

wherein the second node comprises: interactive nodes or broadcast nodes.

9. The device of claim 8, wherein the broadcast module is specifically configured to:

and if the second node is configured to start an interruption function and receives user interaction information before the broadcast content corresponding to the second node is completely broadcast, stopping continuously broadcasting the broadcast content.