CN117350764A - Application method of intelligent intent analysis management system - Google Patents

Abstract

The invention discloses a use method of an intelligent intent analysis management system, which specifically comprises the following steps: (1) setting a project session node; (2) setting an item tag name; (3) Setting a project conversation scene and a reverse scene, and selecting corresponding labels; (4) setting a project three-level grouping scene; (5) matching the scene tag with the robot outbound result tag; and (6) inquiring and exporting the analysis result of the client intention. The invention belongs to the technical field of data analysis, and particularly provides a use method of an intelligent intent analysis management system which can intelligently customize intent analysis platforms according to different project requirements so as to improve the expertise and accuracy of the system on customer intent analysis and judgment.

Description

Application method of intelligent intent analysis management system

Technical Field

The invention belongs to the technical field of data analysis, and particularly relates to a use method of an intelligent intent analysis management system.

Background

In any industry, the client requirement is a motive force for driving the development of enterprises and is also a basis for the continuous development of the enterprises, so that the importance of the client requirement to the enterprises can be fully understood. At the same time, however, the customer is chosen to be far greater than the effort to persuade the customer, and the customer needs have explicit, explicit needs, and also uncertain, potential needs. Therefore, how to accurately analyze the intent of the clients and screen the intended clients, so as to firmly hold the needs of the clients, becomes a particular problem to be solved by enterprises.

In the electric marketing industry, the intelligent intent analysis management system is used in the fields of real estate, finance, education, banks, insurance, electronic commerce and the like, and the built-in speech technology and functions of the intelligent intent analysis management system are not matched with the marketing requirements of electronic products and other products in the IT field; when customer intention is analyzed, the system dictionary and the customer intention labels are not finely divided, and the aspects are not complete; and on different session nodes, thereby directly causing the results of customer intent analysis to be greatly affected.

Therefore, different business processes, speaking contents, speaking nodes, labels and scene groups can be customized according to different project requirements, and an autonomous and controllable intelligent intent analysis platform is built; the system dictionary and the client intention labels are divided more finely, comprehensively and systematically, and a plurality of model analysis strategies are adopted, so that the expertise and the accuracy of the system on the client intention analysis and judgment are improved, and the problem to be solved by the person skilled in the art is solved.

Disclosure of Invention

Aiming at the situation, in order to make up for the existing defects, the invention provides a use method of an intelligent intent analysis management system, which can intelligently customize intent analysis platforms according to different project requirements so as to improve the expertise and accuracy of the system on customer intent analysis judgment.

The invention provides the following technical scheme: the invention provides a use method of an intelligent intent analysis management system, which specifically comprises the following steps:

1. setting project session nodes

Under the node module, selecting a certain item, clicking setting, entering a node list under the item, filling in each node name and storing; when the filled nodes and the interference value are simultaneously generated during storage, selecting which label is selected according to the weight, and filling the two values according to the actual condition of the project as required; wherein the interference value refers to other names having a meaning similar to that of the node;

2. setting item tag names

Under the label name module, selecting and adding a label name, filling in the label name, the node and the weight, and storing and changing;

3. setting a project conversation scene and a reverse scene, and selecting a corresponding label

Selecting an item and clicking setting under a scene module, and entering a scene list under the item; clicking an added scene, filling in a scene name field, and saving the change;

in addition to editing and deleting a single scene, a label of each scene and the reverse scene thereof can be added; the meaning of the reverse scene is the scene opposite to the target scene, such as can be rejected;

because in a round of dialogue, the situation that the client can communicate just beginning, but then refuses to communicate for some reasons, the system adopts a model strategy for preferentially judging the reverse scene: when judging the client labels, the superposition degree of the client intention labels and the labels in the reverse scene is analyzed preferentially, and then the superposition degree of the labels in the scene corresponding to the reverse scene is analyzed, so that the efficiency and the accuracy of model analysis are improved;

4. setting up a project tertiary grouping scene

Under the grouping module, a certain item is selected, the setting is clicked, a three-level grouping scene list under the item can be entered, and the three-level grouping scene forms a comprehensive and systematic client intention analysis dictionary, so that powerful guarantee is provided for accurately analyzing the client intention;

the system can customize different business processes, speaking contents, speaking nodes, labels and scene grouping according to different project requirements, namely, the nodes, the label names, the scenes and the grouping modules are seen to meet the requirements of different projects, and further the accuracy of intent analysis is ensured;

5. scene tag and robot outbound result tag matching

Under a robot single task import database tab under the task import module, the robot outbound result tag data of each item can be imported;

6. querying and exporting customer intent analysis results

Under the inquiry tab, automatically generated customer intent analysis results can be inquired and exported.

The beneficial effects obtained by the invention by adopting the structure are as follows: the method for using the intelligent intent analysis management system can customize different business processes, speaking contents, speaking nodes, labels and scene groups according to different project requirements to construct an autonomous and controllable intelligent intent analysis platform; the system dictionary and the client intention labels are divided more finely, comprehensively and systematically, and the model strategy for preferentially judging the reverse scene is adopted, so that the expertise and accuracy of the system on the client intention analysis and judgment are improved.

Drawings

The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:

FIG. 1 is a flow chart of the use of the present invention;

FIG. 2 is a setup page diagram of a project session node of the present invention;

FIG. 3 is an illustration of an add page of the project call node of the present invention;

FIG. 4 is a diagram of an edit page of a project call node in the present invention;

FIG. 5 is a modified page diagram of a project session node of the present invention;

FIG. 6 is a diagram of an add page of item tag names in the present invention;

FIG. 7 is an edit page view of item tag names in the present invention;

FIG. 8 is a diagram of a modified page of item tag names in the present invention;

FIG. 9 is an add page diagram of a scenario in the present invention;

FIG. 10 is an edit page view of a scene in the present invention;

FIG. 11 is an edit page view of a scene tag of the present invention;

FIG. 12 is an edit page view of a scene opposite in the present invention;

FIG. 13 is a diagram of a page under a grouping module in accordance with the present invention;

FIG. 14 is a first grouping scenario list of the present invention;

FIG. 15 is a first grouping scenario list of the present invention;

FIG. 16 is a first grouping scenario list of the present invention;

FIG. 17 is a page view of a robot single task import database in the present invention;

FIG. 18 is a page view of a query tab in the present invention;

FIG. 19 is a page view of the results of the analysis of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention; all other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be noted that the words "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to directions in the drawings, and the words "inner" and "outer" refer to directions toward or away from, respectively, the geometric center of a particular component.

Referring to fig. 1, a flow chart of an intelligent intent analysis management system according to the present invention is shown.

In this embodiment, the present invention provides a method for using an intelligent intent analysis management system, which specifically includes the following steps:

1. setting project session nodes

As shown in fig. 2 and 3, under the "node" module, a certain item (here, a dell item is taken as an example) is selected, and the "setting" is clicked, so that the node list under the item can be accessed.

As in fig. 4, each node name is filled in and saved; wherein "interference value" refers to other names having a meaning similar to that of a node; the node label weight is that when the filled node and the interference value occur simultaneously, which label is selected according to the weight. These two values are filled in on demand according to the actual condition of the project.

As in fig. 5, individual nodes may also be edited and deleted.

2. Setting item tag names

As shown in fig. 6 and 7, under the "tag name" module, "add tag name" is selected, the tag name, node, and weight are filled in, and the change is "saved".

As in fig. 8, individual nodes may also be edited and deleted.

3. Setting a project conversation scene and a reverse scene, and selecting a corresponding label

As in fig. 9 and 10, under the "scene" module, an item is selected and "set" is clicked on, entering a list of scenes under the item.

Click "Add scene", fill in "scene name" field, and save the change.

As in fig. 11 and 12, in addition to editing and deleting a single scene, a tag for each scene and its reverse scene may be added thereto.

The meaning of the reverse scene is: the opposite scenario, such as "ok" and "reject", is the target scenario.

Because in a round of dialogue, the situation that the client just starts to say "can communicate", but then refuses to communicate for some reasons, the system adopts a model strategy for preferentially judging the reverse scene. When judging the client labels, the superposition degree of the client intention labels and the labels in the reverse scene is analyzed preferentially, and then the superposition degree of the labels in the scene corresponding to the reverse scene is analyzed, so that the efficiency and the accuracy of model analysis are improved.

4. Setting up a project tertiary grouping scene

As shown in fig. 13, 14, 15 and 16, under the "grouping" module, a certain item (here, a dell item is taken as an example) is selected, and the "setting" is clicked, so that the three-level grouping scene list under the item can be accessed.

It can be seen that under the scene grouping list of the dell project, two primary groupings are provided, three secondary groupings are respectively arranged under each primary grouping, and a plurality of corresponding tertiary groupings are arranged under each secondary grouping.

Wherein, according to the purchase plan of the customer, there are two first-class groups (LeadsGroup, contactableDataGroup); under the first level grouping LeadsGroup that the customer has a purchase plan, three secondary scenes of HotLeads-1, hotLeads-2 and Leads are set according to whether the customer informs budget and the time of the purchase (within one month, recently, within three months and within half year); the tertiary scenes are fields which are purchased before the clients are added on the basis of each secondary scene. It can be seen that each level of grouping scenes is more specific and detailed than before, and finally all scenes form a comprehensive and systematic customer intention analysis dictionary, so that powerful guarantee is provided for accurately analyzing the customer intention.

The system can customize different business processes, speaking contents, speaking nodes, labels and scene groups according to different project requirements, namely, four modules including a node, a label name, a scene and a grouping are seen, so that the requirements of different projects are met, and the accuracy of intent analysis is further ensured.

5. Scene tag and robot outbound result tag matching

As shown in fig. 17, under the "robot single task import database" tab under the "task import" module, the robot outbound result tag data for each item may be imported.

6. Querying and exporting customer intent analysis results

Under the "query" tab, automatically generated customer intent analysis results may be queried and derived, as in FIG. 18.

As shown in fig. 19, the following fields are included in the analysis result.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (1)

1. The application method of the intelligent intent analysis management system is characterized by comprising the following steps of:

(1) Setting project session nodes

Under the node module, selecting a certain item, clicking setting, entering a node list under the item, filling in each node name and storing; when the filled nodes and the interference value are simultaneously generated during storage, selecting which label is selected according to the weight, and filling the two values according to the actual condition of the project as required; wherein the interference value refers to other names having a meaning similar to that of the node;

(2) Setting item tag names

Under the label name module, selecting and adding a label name, filling in the label name, the node and the weight, and storing and changing;

(3) Setting a project conversation scene and a reverse scene, and selecting a corresponding label

Selecting an item and clicking setting under a scene module, and entering a scene list under the item; clicking an added scene, filling in a scene name field, and saving the change;

in addition to editing and deleting a single scene, a label of each scene and the reverse scene thereof can be added; the meaning of the reverse scene is the scene opposite to the target scene, such as can be rejected;

because in a round of dialogue, the situation that the client can communicate just beginning, but then refuses to communicate for some reasons, the system adopts a model strategy for preferentially judging the reverse scene: when judging the client labels, the superposition degree of the client intention labels and the labels in the reverse scene is analyzed preferentially, and then the superposition degree of the labels in the scene corresponding to the reverse scene is analyzed, so that the efficiency and the accuracy of model analysis are improved;

(4) Setting up a project tertiary grouping scene

Under the grouping module, a certain item is selected, the setting is clicked, a three-level grouping scene list under the item can be entered, and the three-level grouping scene forms a comprehensive and systematic client intention analysis dictionary, so that powerful guarantee is provided for accurately analyzing the client intention;

the system can customize different business processes, speaking contents, speaking nodes, labels and scene grouping according to different project requirements, namely, the nodes, the label names, the scenes and the grouping modules are seen to meet the requirements of different projects, and further the accuracy of intent analysis is ensured;

(5) Scene tag and robot outbound result tag matching

Under a robot single task import database tab under the task import module, the robot outbound result tag data of each item can be imported;

(6) Querying and exporting customer intent analysis results

Under the inquiry tab, automatically generated customer intent analysis results can be inquired and exported.