CN114385816B - Dialogue flow mining method, device, electronic device and computer storage medium - Google Patents
Dialogue flow mining method, device, electronic device and computer storage medium Download PDFInfo
- Publication number
- CN114385816B CN114385816B CN202210032825.6A CN202210032825A CN114385816B CN 114385816 B CN114385816 B CN 114385816B CN 202210032825 A CN202210032825 A CN 202210032825A CN 114385816 B CN114385816 B CN 114385816B
- Authority
- CN
- China
- Prior art keywords
- node
- virtual node
- intention information
- cluster
- initial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/358—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the application provides a conversation flow mining method, a device, electronic equipment and a computer storage medium, wherein a visual interface is provided, a first type of cluster intention with a mapping relation with the node intention of a first virtual node is determined in response to a triggering operation of the first virtual node in the interface, a second conversation file and a second type of cluster intention are obtained by carrying out intention clustering on a corresponding first conversation file, an initial node intention corresponding to the second type of cluster intention and a second initial virtual node corresponding to the initial node intention are added, the second initial virtual node is used as a downstream node of the first virtual node to form virtual node-to-node topological connection, the second initial virtual node is adjusted to be a second updated virtual node in response to an editing operation of the selected second initial virtual node, the node intention of the second updated virtual node and the second type of cluster intention are established, and the node intention of the second updated virtual node is obtained and displayed based on the mapping relation. The efficiency of excavation is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of Internet, in particular to a conversation flow mining method and device, electronic equipment and a computer storage medium.
Background
At present, intelligent conversation robots have been widely used in a variety of scenarios, where the intelligent conversation robots can converse with clients through natural language, thereby completing the specified tasks of the clients. In the actual operation process, the intelligent conversation robot performs actual operation based on a conversation flow which is mined in advance, specifically, firstly, conversation sentences input by clients are obtained, intention recognition is performed on the sentences, then, nodes corresponding to the intention are positioned in the conversation flow which is built in advance, further, the next node (target node) of the node in the whole process is determined, finally, corresponding operation is executed based on the intention corresponding to the target node, and corresponding answer sentences are output.
The dialogue flow mining process is a process of clustering dialogue data intents of multiple rounds. When a specific mining round is triggered, intent clustering is performed on a group of dialogue data, so that a plurality of intent clusters are obtained, and each intent cluster corresponds to a group of sub-dialogue data with the same intent.
In order to improve the mining efficiency, parallel mining is usually triggered independently for multiple groups of dialogue data, but in each mining round, a user may perform manual editing operations such as merging and deleting on the mining result, the operations may affect the mining result, and in order to ensure the accuracy of the mining result, intent clustering needs to be performed again on the dialogue data performing the editing operations, which may cause a drastic reduction in the mining efficiency of the whole dialogue stream.
Disclosure of Invention
In view of the above, an embodiment of the present application provides a method for mining a dialog flow to at least partially solve the above-mentioned problems.
According to a first aspect of an embodiment of the present application, there is provided a method for mining an original dialog file, including:
Providing a visual interface, wherein the visual interface is used for displaying at least one virtual node and node intention information of the at least one virtual node;
Responding to triggering operation of a first virtual node, and determining first type cluster intention information with a mapping relation with node intention information of the first virtual node;
performing intent clustering on the first dialogue files corresponding to the first-class cluster intent information to obtain a plurality of second dialogue files and second-class cluster intent information corresponding to each second dialogue file;
Adding initial node intention information corresponding to each second type of cluster intention information and second initial virtual nodes corresponding to each initial node intention information respectively in a visual interface, and taking the second initial virtual nodes as downstream nodes of the first virtual nodes to form topological connection relations among the virtual nodes;
receiving edit operation input of a user on one or more selected second initial virtual nodes;
Responding to the editing operation of the selected second initial virtual nodes, and adjusting each second initial virtual node into a second updating virtual node so as to update the topological connection relation;
and establishing a mapping relation between the node intention information of each second updated virtual node and the second type cluster intention information, and obtaining and displaying the node intention information of each second updated virtual node based on the mapping relation.
According to a second aspect of the embodiment of the present application, there is provided a dialog flow mining apparatus for mining an original dialog file, including:
The visual interface providing module is used for providing a visual interface, and the visual interface is used for displaying at least one virtual node and node intention information of the at least one virtual node;
the first type cluster intention information determining module is used for responding to the triggering operation of the first virtual node and determining first type cluster intention information with a mapping relation with the node intention information of the first virtual node;
The intention clustering module is used for carrying out intention clustering on the first dialogue files corresponding to the first-class cluster intention information to obtain a plurality of second dialogue files and second-class cluster intention information corresponding to each second dialogue file;
The topology connection relation obtaining module is used for adding initial node intention information corresponding to each second type of cluster intention information in the visual interface, and second initial virtual nodes corresponding to each initial node intention information respectively, and taking the second initial virtual nodes as downstream nodes of the first virtual nodes to form topology connection relation among the virtual nodes;
The receiving module is used for receiving edit operation input of a user on the selected one or more second initial virtual nodes;
the topology connection relation updating module is used for responding to the editing operation of the selected second initial virtual nodes, and adjusting each second initial virtual node into a second updated virtual node so as to update the topology connection relation;
The mapping relation establishing and node intention information display module is used for establishing a mapping relation between the node intention information of each second updated virtual node and the second type cluster intention information, and obtaining and displaying the node intention information of each second updated virtual node based on the mapping relation.
According to a third aspect of the embodiment of the present application, there is provided an electronic device, including a processor, a memory, a communication interface, and a communication bus, where the processor, the memory, and the communication interface complete communication between each other through the communication bus, and the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform an operation corresponding to the conversational flow mining method according to the first aspect.
According to a fourth aspect of embodiments of the present application, there is provided a computer storage medium having stored thereon a computer program for live interaction, which when executed by a processor implements the method of conversational streaming mining of a live room according to the first aspect.
According to a fifth aspect of embodiments of the present application, there is provided a computer program product for live interaction, comprising computer instructions for instructing a computing device to perform operations corresponding to the method for conversational streaming mining of a real-time live room as described in the first aspect.
According to the dialog flow mining method, data involved in a dialog flow mining process are divided into 4 levels, namely a virtual node level, a node intention information level, a cluster intention information level and a dialog file level, wherein the levels sequentially have association relations that virtual nodes in the virtual node level are in one-to-one correspondence with node intention information in the node intention information level, the node intention information in the node intention information level and the cluster intention information in the cluster intention information level have mapping relations, and the cluster intention information in the cluster intention information level is in one-to-one correspondence with dialog files in the dialog file level.
When the first virtual node is triggered, namely when the mining starts, according to the association relation, the first cluster intention information with a mapping relation with the node intention information of the node and the corresponding first dialogue file are sequentially determined, then intention clustering is carried out on the first dialogue file, so that a second dialogue file and the corresponding second cluster intention information are obtained, initial node intention information corresponding to the second cluster intention information and the corresponding second initial virtual node (downstream node of the first virtual node or a child node) are added in the interface to form a preliminary mining result, and when the selected second initial virtual node is triggered to edit, namely when the user corrects the preliminary mining result, only the virtual node in the virtual node level, the node intention information corresponding to the node intention information level, the mapping relation between the corresponding node intention information and the class cluster intention information in the class cluster intention information level are adjusted, and the dialogue file is not required to be clustered again, so that the efficiency of the dialogue file mining is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a schematic diagram of a management structure of visual conversational flow data mining according to a first embodiment of the application;
fig. 2 is a schematic view of a dialog flow mining method according to a first embodiment of the present application;
FIG. 3 is a schematic flow diagram of a mining task trigger for visual dialog flow mining in accordance with a first embodiment of the application;
FIG. 4 is a schematic diagram illustrating editing operations performed on nodes in an interactive labeling process according to a first embodiment of the present application;
FIG. 5 is a schematic diagram of a multi-round mining process for visual dialog mining according to a first embodiment of the present application;
FIG. 6 is a flow chart illustrating steps of a method for mining conversational flows according to a first embodiment of the application;
fig. 7 is a block diagram of a dialog flow mining apparatus according to a second embodiment of the present application;
Fig. 8 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
In order to better understand the technical solutions in the embodiments of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the present application, shall fall within the scope of protection of the embodiments of the present application.
The implementation of the embodiments of the present application will be further described below with reference to the accompanying drawings.
Embodiment 1,
Referring to fig. 1, fig. 1 is a schematic diagram of a management structure of visual dialog data mining according to an embodiment of the present application, and in order to facilitate understanding of a technical solution of the present application, first, a description is given of a management structure of visual dialog data mining according to an embodiment of the present application with reference to fig. 1.
In the embodiment of the application, the dialogue stream data mining is abstracted into four layers, namely a virtual node layer, a node intention information layer, a cluster intention information layer and a dialogue file layer. When a plurality of virtual nodes exist, the virtual node layer also comprises a topological connection relation among the virtual nodes, and the topological connection relation is used for displaying to a user in a visual interface. The node intention information layer comprises node intention information corresponding to each virtual node in the virtual node layer one by one, the node intention information is used for representing the intention of the corresponding virtual node, and the hierarchy is also displayed in the visual interface. The cluster intention information layer comprises cluster intention information, and a one-to-one or one-to-many mapping relation exists between the node intention information and the cluster intention information. Specifically, one node intention information may have a mapping relationship with only one cluster-like intention information (in this case, the node intention information may be the same as the cluster-like intention information), or one node intention information may have a mapping relationship with a plurality of cluster-like intention information at the same time (in this case, the node intention information may be intention information obtained by aggregating the cluster-like intention information). The dialogue file layer comprises dialogue files corresponding to the type cluster intention information one by one, namely after intentional clustering, the dialogue files with the same intention are used as a type cluster, the concrete dialogue files are stored in the dialogue file layer for dialogue mining tasks, and the intention of the type cluster is correspondingly stored in the type cluster intention information layer as the type cluster intention information.
The following general description of the process of mining conversational flows according to an embodiment of the application is based on the management structure of fig. 1. It is assumed that after the first round of mining is performed on the original virtual node a0, two first virtual nodes a11 and a12 are formed in the virtual node layer, and in terms of the first virtual node a11, one node intention information b11 corresponds to the node intention information layer, and the node intention information b11 has a mapping relationship with the first type of cluster intention information c11, c12 and c13 in the cluster intention information layer. The first-class cluster intention information c11, c12, and c13 corresponds to d11, d12, and d13 in the dialog file layer, respectively. After the first virtual node a11 triggers the second round of mining, d11, d12 and d13 in the dialogue file layer are used as a whole to be clustered, and intent clustering is performed, so that a corresponding second dialogue file d2 is obtained. Correspondingly, the second type cluster intention information c2 corresponding to the second dialog file d2 exists in the cluster intention information layer, the node intention information b2 having a mapping relation with the second type cluster intention information c2 exists in the node intention information layer, and the second virtual node a2 corresponding to the node intention information b2 exists in the virtual node layer. Then, the excavating sub-process of the subsequent rounds such as the 3 rd round is triggered for the virtual nodes in the virtual node layer according to the requirement, and the like, until the excavating flow is finished, and the description is omitted.
Referring to fig. 2, fig. 2 is a schematic view of a scene of a dialog flow mining method according to a first embodiment of the present application, and for convenience of understanding, an application scene of the dialog flow mining method according to the first embodiment of the present application is explained with reference to fig. 2.
The embodiment of the present application provides a visual interface as shown in fig. 2 (a), where the visual interface is used to display at least one virtual node (a first virtual node is illustrated in the figure and is not configured to limit the number of virtual nodes in the embodiment of the present application) and node intention information of the at least one virtual node, where the first virtual node is in a virtual node layer in fig. 1, and the corresponding node intention information is in a node intention information layer in fig. 1. When a user performs a triggering operation on a first virtual node, first cluster intention information (at a cluster-like intention information layer in fig. 2) having a mapping relation with node intention information of the first virtual node, and a first dialog file (at a dialog file layer in fig. 2) corresponding to the first cluster intention information are determined. Then, intent clustering is performed on the first dialog files, so as to obtain 2 second dialog files (only 2 second dialog files are illustrated in the figure as an example, and the number of the second dialog files is not limited), and second type cluster intent information corresponding to each second dialog file is obtained. Then, as shown in fig. 2 (b), initial node intention information corresponding to each second type cluster intention information and second initial virtual nodes corresponding to each initial node intention information are added to the visual interface, and each second initial virtual node is used as a downstream node of the first virtual node to form a topological connection relation between each virtual node. When receiving input of editing operation (such as merging operation) of a user on 2 second initial virtual nodes (2 second initial virtual nodes are illustrated in the figure and do not limit the number of the selected second initial virtual nodes) in the visual interface shown in fig. 2 (b), as shown in fig. 2 (c), adjusting the second initial virtual nodes to second updated virtual nodes to update the topological connection relationship, establishing a mapping relationship between node intention information of the second updated virtual nodes and second cluster intention information, and obtaining node intention information of each second updated virtual node based on the mapping relationship and displaying the node intention information.
In the embodiment of the present application, in the visual interface, a specific display form of the topological connection relationship between the virtual nodes is not limited, for example, the specific display form may be displayed in a flowchart form as shown in fig. 2, or may be displayed in other forms such as a table, and fig. 2 is only illustrated in a flowchart form and does not limit the embodiment of the present application.
The following describes a visual dialog mining procedure according to an embodiment of the application. Referring to fig. 3 to 5, embodiments of the present application may provide a visual interactive interface for displaying one or more virtual nodes and corresponding node intention information for a user to perform mining or editing operations. In the visual dialog flow mining process, a plurality of rounds of interactive mining subprocesses are usually required to be performed on an original dialog file so as to generate a dialog flow of a final task type dialog. For a single interactive mining sub-process, it typically includes two steps, a first step, triggering the mining task, and a second step, interactive labeling. Referring to fig. 3, the first step is that when a user performs a triggering operation on a certain node (such as a start node) through a visual interface, intent clustering is automatically performed on a dialog file corresponding to the node, so as to obtain a plurality of dialog subfiles and corresponding sub-nodes (such as nodes 1 to 5). In the second step, the user can perform manual intervention labeling on the mining result through the visual interaction interface, namely performing editing operation on the nodes, so as to obtain the labeled mining result, wherein the editing operation on the nodes can comprise merging operation, deleting operation and the like, referring to fig. 4.
Referring to fig. 5, fig. 5 is a schematic diagram of a multi-pass conversational flow mining process, which performs a 2-pass interactive mining sub-process in total. In the 1 st round, the user may perform a merging operation on the visual interactive interface, so that the newly generated node 2 and the newly generated node 3 are merged into the node 3', and simultaneously perform a deleting operation to delete the node 5, so as to finally obtain the node 1, the node 3' and the node 4. In round 2, the user may trigger the mining operations of node 1, node 3', and node 4, respectively, to generate node 1A and node 1B based on node 1, node 3' a based on node 3', and node 4A based on node 4.
Referring to fig. 6, fig. 6 is a flowchart illustrating steps of a method for mining a dialogue stream according to a first embodiment of the present application, and specifically, the method for mining a dialogue stream according to the present embodiment is used for mining an original dialogue file, where the original dialogue file may refer to a plurality of dialogue sentences input by a client, and each dialogue sentence may include dialogue data of a plurality of rounds.
The dialogue flow mining method comprises the following steps:
step 602, providing a visual interface, wherein the visual interface is used for displaying at least one virtual node and node intention information of the at least one virtual node.
In the embodiment of the application, the virtual nodes in the visual interface and the node intention information of the virtual nodes have a one-to-one correspondence. The node intent information of the virtual node characterizes the intent represented by the virtual node.
For example, the original dialogue file is a dialogue file between customer service and customer generated in the air ticket purchasing scene, and the node intention information can be travel time inquiry, travel number inquiry, travel identity information inquiry, air ticket type inquiry and the like.
In step 604, in response to a trigger operation on the first virtual node, first type cluster intention information having a mapping relationship with node intention information of the first virtual node is determined.
In the embodiment of the application, how to trigger the first virtual node is not limited, for example, operations such as clicking, dragging and the like of the first virtual node displayed in the visual interface can be used as trigger operations, so that the mining process of the conversation flow is triggered.
As noted above in the description of fig. 1, in an embodiment of the present application, there may be a one-to-one or one-to-many mapping relationship between the node intention information of the virtual node and the cluster-like intention information. Specifically, the node intention information of one virtual node may have a mapping relationship with only one cluster intention information, or may have a mapping relationship with a plurality of cluster intention information at the same time. When the node intention information of a virtual node has a mapping relationship with a plurality of cluster intention information, the node intention information of the virtual node may be aggregated from the plurality of cluster intention information, for example, the node intention information of the virtual node may be that an air ticket is purchased, and the cluster intention information having a mapping relationship with the node intention information may include 2 pieces, namely, that an air ticket of an a-airline is purchased and an air ticket of a B-airline is purchased.
In step 606, intent clustering is performed on the first dialogue files corresponding to the first type of cluster intent information, so as to obtain a plurality of second dialogue files and second type of cluster intent information corresponding to each second dialogue file.
The second type cluster intention information corresponds to the second dialogue files one by one, namely, one second dialogue file corresponds to one second type cluster intention information, and the second type cluster intention information represents the intention corresponding to the second dialogue file.
Further, in the embodiment of the present application, after obtaining a plurality of second session files, each second session file may be stored separately.
And 608, adding initial node intention information corresponding to each second type of cluster intention information and second initial virtual nodes corresponding to each initial node intention information in the visual interface, and taking the second initial virtual nodes as downstream nodes of the first virtual nodes to form topological connection relations among the virtual nodes.
In this step, for each second type of cluster intention information obtained in step 606, corresponding initial node intention information and corresponding second initial virtual nodes may be added in the visual interface, and the newly added second initial virtual nodes are used as child nodes (downstream nodes) of the original first virtual nodes in the visual interface, so as to form a topological connection relationship between the first virtual nodes and the second initial virtual nodes.
The initial node intention information displayed in the visual interface, the second initial virtual node displayed in the visual interface and the second cluster intention information which is not displayed in the visual interface form a one-to-one correspondence.
At step 610, edit manipulation input from a user to the selected one or more second initial virtual nodes is received.
In response to the editing operation on the selected second initial virtual nodes, step 612, each second initial virtual node is adjusted to a second updated virtual node to update the topological connection relationship.
Step 614, a mapping relationship between the node intention information of each second updated virtual node and the second class cluster intention information is established, and the node intention information of each second updated virtual node is obtained and displayed based on the mapping relationship.
Steps 610-614 are explained as follows:
After step 608, the second initial virtual nodes formed in the visual interface are all virtual nodes corresponding to the second type of cluster intention information obtained by the automatic intention clustering operation, that is, the mining process is automatically completed and not manually corrected. However, according to the different service categories actually provided by the user, the user may be required to make label correction on the mining result, for example, according to the initial node intention information, perform editing operations such as merging, deleting, recovering, and the like on the second initial virtual node, so as to obtain second updated virtual nodes, and adjust the mapping relationship between the node intention information of each second updated virtual node and the second type cluster intention information.
Taking the air ticket purchasing scene as an example, assume that 2 second initial virtual nodes are newly added in the visual interface through step 608, and the corresponding initial node intention information is respectively that the air ticket of the air company a is purchased and the air ticket of the air company B is purchased, and the service condition actually provided by the client is combined, so that the air ticket of the air company a is purchased and the air ticket of the air company B is purchased, and no substantial difference exists in the service processing flow, at this moment, the user can execute a merging operation on the 2 second initial virtual nodes, thereby updating the second initial virtual nodes into second updated virtual nodes in the visual interface, and adjusting the mapping relation between the node intention information of the second updated virtual nodes and the second cluster intention information.
For another example, assume that the initial node intention information corresponding to the 2 second initial virtual nodes is respectively to purchase an air ticket and transact a check-in service, and the check-in service is not included in the services actually provided by the current clients. At this time, the user may perform a delete operation on the second initial virtual node corresponding to the check-in service. Subsequently, with the continuous expansion of the types of services provided by clients, value-added services may be increased. At this time, the user may perform a restoration operation on the deleted second initial virtual node corresponding to the transacted value machine service, and adjust a mapping relationship between the node intention information of the restored second initial virtual node and the second class cluster intention information.
Further, in the embodiment of the present application, the editing operation is only used to adjust the mapping relationship between the node intention information of each second updated virtual node and the second cluster intention information, without changing the storage states of the plurality of second session files. For example, for the merging operation, only the mapping relationship between the node intention information of the second updated virtual node and the second type cluster intention information is adjusted, and the second session file itself is not merged. For the deletion operation, only the second initial virtual node to be deleted and the corresponding initial node intention information thereof are deleted, and any second session file itself is not deleted.
Optionally, in some embodiments, a mapping relationship between the node intent information of each second updated virtual node and the second type of cluster intent information may be adjusted based on a specific type of editing operation.
Specifically, for the merging operation, the obtaining process of the second updated virtual node and the adjusting process of the mapping relationship between the node intention information of the second updated virtual node and the second class of cluster intention information may include:
Deleting the selected plurality of second initial virtual nodes in response to the merging operation on the selected plurality of second initial virtual nodes, and adding the merged virtual nodes in the visual interface;
If the second updated virtual nodes are the merged virtual nodes, determining second-class cluster intention information corresponding to each selected second initial virtual node as second-class cluster intention information with a mapping relation with the second updated virtual nodes;
If the second updated virtual node is a non-selected second initial virtual node, the initial node intention information corresponding to the non-selected second initial virtual node is used as the node intention information of the second updated virtual node, and the second type cluster intention information corresponding to the non-selected second initial virtual node is determined as the second type cluster intention information with a mapping relation with the node intention information of the second updated virtual node.
For the deleting operation, the obtaining process of the second updated virtual node and the adjusting process of the mapping relationship between the node intention information of the second updated virtual node and the second type cluster intention information may include:
In response to the deleting operation of the selected second initial virtual node, deleting the selected second initial virtual node and initial node intention information corresponding to the selected second initial virtual node in a visual interface, reserving second type cluster intention information corresponding to the selected second initial virtual node as soft deleting second type cluster intention information, reserving a second dialogue file corresponding to the soft deleting second type cluster intention information, determining non-selected second initial virtual nodes as second updating virtual nodes, taking initial node intention information corresponding to each non-selected second initial virtual node as node intention information of each second updating virtual node, and respectively determining second type cluster intention information corresponding to each non-selected second initial virtual node as second type cluster intention information with a mapping relation with the node intention information of each second updating virtual node.
In addition, for the recovery operation, the virtual node update process and the adjustment process of the mapping relationship between the updated node intention information of the virtual node and the second type of cluster intention information may include:
The method comprises the steps of responding to the restoration operation of a deleted second initial virtual node, determining soft deletion second type cluster intention information corresponding to the deleted second initial virtual node, adding the restored second virtual node in a visual interface, determining the soft deletion second type cluster intention information corresponding to the deleted second initial virtual node as second type cluster intention with a mapping relation with node intention information of the restored second virtual node, and displaying the soft deletion second type cluster intention information corresponding to the deleted second initial virtual node as node intention information of the restored second virtual node.
In the embodiment of the application, the virtual nodes in the virtual node hierarchy and the corresponding node intention information in the node intention information hierarchy can be displayed in the visual interface so as to be used for the user to carry out interactive mining flow. When the first virtual node is triggered, namely the mining is started, the first cluster intention information with a mapping relation with the node intention information of the node and the corresponding first dialogue file are sequentially determined according to the association relation, then intention clustering is carried out on the first dialogue file, so that a second dialogue file and the corresponding second cluster intention information are obtained, initial node intention information corresponding to the second cluster intention information and the corresponding second initial virtual node (a downstream node of the first virtual node or a child node) are added in an interface, and a preliminary mining result is formed. When the selected second initial virtual node is triggered to edit, namely, when the user corrects the preliminary mining result, only the mapping relation among the virtual nodes in the virtual node hierarchy, the node intention information in the corresponding node intention information hierarchy, the corresponding node intention information and the cluster intention information in the cluster intention information hierarchy is adjusted, and the intention clustering is not needed to be carried out on the dialog files in the dialog file hierarchy again, so that the efficiency of dialog flow mining is improved.
Embodiment II,
Referring to fig. 7, fig. 7 is a block diagram illustrating a dialog flow mining apparatus according to a second embodiment of the present application. The dialog flow mining device provided by the embodiment of the application comprises a visual interface providing module 702, a display module and a display module, wherein the visual interface providing module is used for providing a visual interface for displaying at least one virtual node and node intention information of the at least one virtual node. The first type cluster intention information determining module 704 is configured to determine first type cluster intention information having a mapping relationship with node intention information of a first virtual node in response to a trigger operation on the first virtual node. The intention clustering module 706 is configured to perform intention clustering on the first dialog files corresponding to the first type of cluster intention information, so as to obtain a plurality of second dialog files and second type of cluster intention information corresponding to each second dialog file. The topology connection relationship obtaining module 708 is configured to add initial node intention information corresponding to each second type of cluster intention information and second initial virtual nodes corresponding to each initial node intention information respectively in the visualization interface, and use the second initial virtual nodes as downstream nodes of the first virtual nodes to form a topology connection relationship between the virtual nodes. And a receiving module 710, configured to receive edit manipulation input of the user on the selected one or more second initial virtual nodes. The topology link relation update module 712 is configured to adjust each second initial virtual node to a second updated virtual node in response to an editing operation on the selected second initial virtual node, so as to update the topology link relation. The mapping relation establishing and node intention information displaying module 714 is configured to establish a mapping relation between the node intention information of each second updated virtual node and the second type cluster intention information, and obtain and display the node intention information of each second updated virtual node based on the mapping relation.
Optionally, in some embodiments, the mapping relationship establishing and node intention information displaying module 714 is specifically configured to, when performing the step of establishing the mapping relationship between the node intention information of each second updated virtual node and the second type of cluster intention information, adjust the mapping relationship between the node intention information of each second updated virtual node and the second type of cluster intention information based on the type of editing operation.
Optionally, in some embodiments, the dialog flow mining device further includes a storage module for storing the plurality of second dialog files after the plurality of second dialog files are obtained, respectively.
Optionally, in some embodiments, the editing operation is configured to adjust a mapping relationship between the node intention information of each second updated virtual node and the second type of cluster intention information without changing a storage state of the plurality of second session files.
Optionally, in some of these embodiments, the type of editing operation includes a merge operation, a delete operation, or a restore operation.
Optionally, in some embodiments, the topology link update module 712 is specifically configured to, in response to a merging operation on the selected plurality of second initial virtual nodes, delete the selected plurality of second initial virtual nodes and add the merged virtual node in the visualization interface, and take the non-selected second initial virtual nodes and the merged virtual node as second updated virtual nodes.
Optionally, in some embodiments, the mapping relationship establishing and node intention information displaying module 714 is specifically configured to determine, if the second updated virtual node is a merged virtual node, second type cluster intention information corresponding to each selected second initial virtual node as second type cluster intention information having a mapping relationship with the second updated virtual node, and aggregate the second type cluster intention information corresponding to each selected second initial virtual node to obtain and display node intention information of the second updated virtual node.
Optionally, in some embodiments, the topology connection relation updating module 712 is specifically configured to delete the selected second initial virtual node and initial node intention information corresponding to the selected second initial virtual node in the visualization interface in response to a deletion operation of the selected second initial virtual node, retain second class cluster intention information corresponding to the selected second initial virtual node as soft-deleted second class cluster intention information, retain a second dialogue file corresponding to the soft-deleted second class cluster intention information, determine the unselected second initial virtual node as a second updated virtual node, and the mapping relation establishment and node intention information display module 714 is specifically configured to determine initial node intention information corresponding to each unselected second initial virtual node as node intention information of each second updated virtual node, and determine second class cluster intention information corresponding to each unselected second initial virtual node as second class cluster intention information having a mapping relation with the node intention information of each second updated virtual node.
Optionally, in some embodiments, the dialog flow mining device further comprises soft deletion second type cluster intention information, a restoration node adding module, a mapping relation determining module and a restoration node intention information display module, wherein the soft deletion second type cluster intention information is used for responding to a restoration operation of a deleted second initial virtual node, the restoration node adding module is used for adding a restored second virtual node in a visual interface, the mapping relation determining module is used for determining the soft deletion second type cluster intention information corresponding to the deleted second initial virtual node as a second type cluster intention with a mapping relation with node intention information of the restored second virtual node, and the restoration node intention information display module is used for displaying the soft deletion second type cluster intention information corresponding to the deleted second initial virtual node as node intention information of the restored second virtual node.
Optionally, in some embodiments, the topological connection relationship among the virtual nodes is shown in a flow chart form or a table form in a visual interface.
The dialog flow mining device in this embodiment is configured to implement the corresponding dialog flow mining methods in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again. In addition, the functional implementation of each module in the dialog flow mining apparatus of this embodiment may refer to the description of the corresponding portion in the foregoing method embodiment, which is not repeated herein.
Third embodiment,
Referring to fig. 8, a schematic structural diagram of an electronic device according to a third embodiment of the present application is shown, and the specific embodiment of the present application is not limited to the specific implementation of the electronic device.
As shown in FIG. 8, the electronic device may include a processor (processor) 802, a communication interface (Communications Interface) 804, a memory (memory) 806, and a communication bus 808. Processor 802, communication interface 804, and memory 806 communicate with each other via a communication bus 808. The communication interface 804 is used to communicate with other electronic devices or servers. The processor 802 is configured to execute the program 810, and may specifically perform relevant steps in the above-described dialog flow mining method embodiment. In particular, program 810 may include program code including computer operating instructions.
The processor 802 may be a CPU, or an Application-specific integrated Circuit ASIC (Application SPECIFIC INTEGRATED circuits), or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors included in the smart device may be the same type of processor, such as one or more CPUs, or different types of processors, such as one or more CPUs and one or more ASICs.
The memory 806 is used to store a program 810. The memory 806 may include high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 810 is specifically configured to cause the processor 802 to provide a visualization interface for displaying at least one virtual node and node intention information of the at least one virtual node, determine first type cluster intention information having a mapping relationship with the node intention information of the first virtual node in response to a trigger operation on the first virtual node, perform intention clustering on a first dialog file corresponding to the first type cluster intention information to obtain a plurality of second dialog files and second type cluster intention information corresponding to each second dialog file, add initial node intention information corresponding to each second type cluster intention information in the visualization interface, and second initial virtual nodes corresponding to each initial node intention information, respectively, and form a topological connection relationship between each virtual node by using the second initial virtual nodes as downstream nodes of the first virtual nodes, receive an edit operation input of a user on the selected one or more second initial virtual nodes, adjust each second initial virtual node to a second update virtual node in response to the edit operation on the selected second initial virtual nodes, update the topological connection relationship between each second initial virtual node, and the second update virtual nodes based on the second type intention information, and display the second type intention relationship between each second initial virtual node and the second type intention information.
The specific implementation of each step in the program 810 may refer to the corresponding steps and corresponding descriptions in the units in the above embodiment of the dialog flow mining method, which are not described herein. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and modules described above may refer to corresponding procedure descriptions in the foregoing method embodiments, which are not repeated herein.
According to the electronic equipment, virtual nodes in a virtual node hierarchy and corresponding node intention information in the node intention information hierarchy are displayed in a visual interface so that a user can perform an interactive mining flow, when the first virtual node is triggered, namely mining is started, according to the association relation, first type cluster intention information with a mapping relation with the node intention information of the node and corresponding first dialogue files are sequentially determined, intention clustering is performed on the first dialogue files, so that second dialogue files and corresponding second type cluster intention information are obtained, initial node intention information corresponding to the second type cluster intention information and corresponding second initial virtual nodes (downstream nodes of the first virtual node or sub-nodes) are added in the interface so that a preliminary mining result is formed, when the selected second initial virtual node is triggered to edit, namely, the user corrects the preliminary mining result, only the virtual nodes in the virtual node hierarchy, the corresponding node intention information in the node information hierarchy, the corresponding node intention information and class relation in the class cluster intention information are required to be adjusted, and the dialogue files in the dialogue intention hierarchy are not required to be rearranged, and the clustering efficiency of the dialogue files is improved.
The present application also provides a computer storage medium storing a computer program for dialog flow mining, which when executed by a processor implements any of the above-described method embodiments.
The embodiment of the application also provides a computer program product for dialog flow mining, which comprises computer instructions for instructing a computing device to execute the operations corresponding to any one of the above-mentioned dialog flow mining methods.
It should be noted that, according to implementation requirements, each component/step described in the embodiments of the present application may be split into more components/steps, or two or more components/steps or part of operations of the components/steps may be combined into new components/steps, so as to achieve the objects of the embodiments of the present application.
The above-described methods according to embodiments of the present application may be implemented in hardware, firmware, or as software or computer code storable in a recording medium such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk, or as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium and to be stored in a local recording medium downloaded through a network, so that the methods described herein may be stored on such software processes on a recording medium using a general purpose computer, special purpose processor, or programmable or special purpose hardware such as an ASIC or FPGA. It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a memory component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the conversational flow mining methods described herein. Further, when a general-purpose computer accesses code for implementing the dialog flow mining method shown herein, execution of the code converts the general-purpose computer into a special-purpose computer for executing the dialog flow mining method shown herein.
Those of ordinary skill in the art will appreciate that the elements and method steps of the examples described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or as a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present application.
The above embodiments are only for illustrating the embodiments of the present application, but not for limiting the embodiments of the present application, and various changes and modifications may be made by one skilled in the relevant art without departing from the spirit and scope of the embodiments of the present application, so that all equivalent technical solutions also fall within the scope of the embodiments of the present application, and the scope of the embodiments of the present application should be defined by the claims.
Claims (13)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210032825.6A CN114385816B (en) | 2022-01-12 | 2022-01-12 | Dialogue flow mining method, device, electronic device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210032825.6A CN114385816B (en) | 2022-01-12 | 2022-01-12 | Dialogue flow mining method, device, electronic device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114385816A CN114385816A (en) | 2022-04-22 |
| CN114385816B true CN114385816B (en) | 2025-06-17 |
Family
ID=81202579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210032825.6A Active CN114385816B (en) | 2022-01-12 | 2022-01-12 | Dialogue flow mining method, device, electronic device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114385816B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115238060B (en) * | 2022-09-20 | 2022-12-27 | 支付宝(杭州)信息技术有限公司 | Human-computer interaction method and device, medium and computing equipment |
| CN116882408B (en) * | 2023-09-07 | 2024-02-27 | 南方电网数字电网研究院有限公司 | Construction method and device of transformer graph model, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674287A (en) * | 2018-06-07 | 2020-01-10 | 阿里巴巴集团控股有限公司 | Method and device for establishing hierarchical intention system |
| CN111737408A (en) * | 2019-03-25 | 2020-10-02 | 阿里巴巴集团控股有限公司 | Dialogue method and equipment based on script and electronic equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8423538B1 (en) * | 2009-11-02 | 2013-04-16 | Google Inc. | Clustering query refinements by inferred user intent |
| CA3005324C (en) * | 2015-10-21 | 2021-06-15 | Greeneden U.S. Holdings Ii, Llc | Data-driven dialogue enabled self-help systems |
-
2022
- 2022-01-12 CN CN202210032825.6A patent/CN114385816B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674287A (en) * | 2018-06-07 | 2020-01-10 | 阿里巴巴集团控股有限公司 | Method and device for establishing hierarchical intention system |
| CN111737408A (en) * | 2019-03-25 | 2020-10-02 | 阿里巴巴集团控股有限公司 | Dialogue method and equipment based on script and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114385816A (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108632068B (en) | A network slice template generation, network slice template application method and device | |
| CN109951547B (en) | Transaction request parallel processing method, device, equipment and medium | |
| CN114385816B (en) | Dialogue flow mining method, device, electronic device and computer storage medium | |
| CN116720234B (en) | Curved surface grid generation method, device, equipment and storage medium | |
| CN113918637B (en) | A process engine platform creation method and system based on BPMN2.0 specification | |
| CN114448802B (en) | Gateway configuration method, device, electronic equipment and storage medium | |
| CN111258580A (en) | Task flow processing method and device, electronic equipment and storage medium | |
| CN113626192A (en) | Method, device and system for carrying out expansion and contraction capacity adjustment on operator nodes | |
| CN115168291A (en) | Hierarchical directory implementation method and device, electronic equipment and storage medium | |
| CN110175734B (en) | Graphical configuration method for business logic flow | |
| CN111814438A (en) | A system and method for drawing a network diagram | |
| CN113986866B (en) | A method, device, equipment and medium for processing large-scale point cloud data | |
| CN114792088A (en) | Editing method and device for digital earth workflow | |
| CN117971259A (en) | File reconstruction method, system and medium based on directed graph | |
| CN118733149A (en) | Data interaction method, device, electronic device and storage medium | |
| CN112486615B (en) | Method, device, equipment and storage medium for executing decision flow based on topological path | |
| CN115439640B (en) | Virtual Model Cloning Method and Apparatus | |
| CN115081228A (en) | BIM-based reinforcement data statistical method, device, equipment and readable storage medium | |
| CN105630634B (en) | Application system calamity is for switching method and apparatus | |
| CN116702066A (en) | Business processing method and device | |
| CN116226130A (en) | Graph updating method and device, electronic equipment and storage medium | |
| CN112036510B (en) | Model generation method, device, electronic equipment and storage medium | |
| CN111639741B (en) | Automatic service combination agent system for multi-objective QoS optimization | |
| CN116911763A (en) | Flow approval method, device, terminal equipment and storage medium | |
| CN115545627A (en) | Approval task processing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |