WO2022095377A1

WO2022095377A1 - Online self-service dialogue method and apparatus, computer device, and computer readable medium

Info

Publication number: WO2022095377A1
Application number: PCT/CN2021/091277
Authority: WO
Inventors: 赵凌燕
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-11-03
Filing date: 2021-04-30
Publication date: 2022-05-12
Also published as: CN112306326A

Abstract

The present application relates to the technical field of intelligent decision making. The present application provides an online self-service dialogue method and apparatus, a computer device, and a computer readable storage medium. The method comprises: in response to an online operation of a user, obtaining module information contained in a page module corresponding to the online operation; according to the module information, identifying a dialogue scene corresponding to the online operation; and on the basis of the dialogue scene, obtaining a preset verbal skill corresponding to the dialogue scene, and pushing a dialogue according to the preset verbal skill.

Description

Online self-help dialogue method, apparatus, computer equipment and computer readable medium

This application claims the priority of the Chinese patent application with the application number 202011209905.1 and the application title "Online Self-Service Dialogue Method, Device, Computer Equipment and Computer-readable Media" filed with the China Patent Office on November 03, 2020, all of which are The contents are incorporated herein by reference.

technical field

The present application relates to the technical field of artificial intelligence, in particular to the technical field of intelligent decision-making, and in particular to an online self-service dialogue method, device, computer equipment and computer-readable storage medium.

Background technique

At present, when a self-help dialogue is conducted online through a robot, after the user takes the initiative to click the robot, the robot makes a corresponding preset response according to the customer's question. For example, in a robot in the insurance industry, the general user does not know what kind of problem the robot can solve. Even if the user actively clicks on the robot, the robot can only answer according to the user's question, according to the preset response corresponding to the question. The user and the inventor realized that such a dialogue method leads to low efficiency and poor effect of self-help dialogue.

SUMMARY OF THE INVENTION

The present application provides an online self-help dialogue method, device, computer equipment and computer-readable storage medium, which can solve the problem of low efficiency of online self-help dialogue in the traditional technology.

In a first aspect, the present application provides an online self-service dialogue method, the method includes: in response to an online operation of a user, the page module is a page selected by a user from a plurality of page modules on the online operation page module, obtain the module information contained in the page module corresponding to the online operation; identify the dialogue scene corresponding to the online operation according to the module information; obtain the dialogue scene corresponding to the dialogue scene based on the dialogue scene the preset speech, and push the dialogue according to the preset speech.

In a second aspect, the present application also provides an online self-service dialogue device, comprising: an acquisition unit, configured to respond to a user's online operation, wherein the page module is selected by the user among a plurality of page modules on the online operation page. The selected page module obtains the module information contained in the page module corresponding to the online operation; the identification unit is used for identifying the dialogue scene corresponding to the online operation according to the module information; the push unit is used for based on For the dialogue scene, a preset dialogue corresponding to the dialogue scene is acquired, and the dialogue is pushed according to the preset dialogue.

In a third aspect, the present application also provides a computer device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program: in response to a user's online operation, and obtain the module information contained in the page module corresponding to the online operation, the page module is the page module selected by the user among the multiple page modules on the online operation page; according to the module information, identify the Dialogue scene corresponding to the online operation; based on the dialogue scene, obtain a preset speech corresponding to the dialogue scene, and push the dialogue according to the preset speech.

In a fourth aspect, the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the processor executes the following steps: in response to a user the online operation, obtain the module information contained in the page module corresponding to the online operation, the page module is the page module selected by the user among the multiple page modules on the online operation page; according to the module information, Identifying a dialogue scene corresponding to the online operation; obtaining a preset dialogue corresponding to the dialogue scene based on the dialogue scene, and pushing a dialogue according to the preset dialogue.

The present application provides an online self-help dialogue method, device, computer equipment and computer-readable storage medium. By responding to a user's online operation, the module information contained in the page module corresponding to the online operation is obtained, and the module information contained in the page module corresponding to the online operation is obtained according to the The module information is used to identify the dialogue scene corresponding to the online operation, based on the dialogue scene, obtain the preset dialogue corresponding to the dialogue scene, and push the dialogue according to the preset dialogue. For the dialogue scene corresponding to the module where the user is located, the module scene in which the user is located is used as an important parameter for the push of the dialogue corresponding to the dialogue. Using the technique label to recall the most suitable words for this scene, to achieve different scenarios, the words have different purposes, and improve the accuracy of the dialogue and the efficiency of conversational communication.

Description of drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. For those of ordinary skill, other drawings can also be obtained from these drawings without any creative effort.

1 is a schematic flowchart of an online self-service dialogue method provided by an embodiment of the present application;

2 is a schematic diagram of a first sub-flow of an online self-help dialogue method provided by an embodiment of the present application;

3 is a schematic diagram of a second sub-flow of the online self-service dialogue method provided by the embodiment of the present application;

4 is a schematic diagram of a third sub-flow of the online self-service dialogue method provided by the embodiment of the present application;

5 is a schematic diagram of a fourth sub-flow of the online self-service dialogue method provided by the embodiment of the present application;

6 is a schematic diagram of a fifth sub-flow of the online self-help dialogue method provided by the embodiment of the present application;

FIG. 7 is a schematic block diagram of an online self-service dialogue device provided by an embodiment of the present application; and

FIG. 8 is a schematic block diagram of a computer device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of an online self-service dialogue method provided by an embodiment of the present application. As shown in Figure 1, the method includes the following steps S11-S13:

S11. In response to the user's online operation, acquire module information contained in a page module corresponding to the online operation, where the page module is a page module selected by the user among multiple page modules on the online operation page.

Specifically, in response to the user's online operation, the module information can be directly obtained, or the page information contained in the page corresponding to the online operation and the module information contained in the page module corresponding to the online operation can be obtained, The page module is a module operated by a user in several modules included on the online operation page, the page information includes a page ID, and the module information includes a module ID, and then the page corresponding to the online operation is obtained. Module information contained in the module.

In general, since a website will have multiple web pages, each page will have multiple modules, each page corresponds to a page ID and page theme, and each module can also correspond to a module ID and module theme, that is, a A page corresponds to a major theme, and a module corresponds to a small theme contained in the major theme, that is, corresponds to a specific scene. For the specific content contained in the scene, there will be specific dialogue content, so that a module corresponds to a conversation scene. . The dialog scene corresponding to the module can be determined according to the module to which the user slides. When a user enters a web page and performs online operations on the web page, if the user performs online operations through input devices such as desktops or notebooks, including a mouse, or the user performs gesture actions on smart terminals such as smartphones, etc. When performing an online operation, the user's online operation on the page can be monitored, and along with the user's online operation, the page information contained in the page corresponding to the online operation can be obtained, and the page information can include the page of the page. ID and the page module ID where the user's mouse is located, etc. For example, when the self-service dialogue method based on scene recognition is applied to the marketing of insurance products through the intelligent robot on the webpage, for all insurance products on sale, after the user enters the page and before entering the robot dialogue interface, because the user enters the page and Before entering the robot dialogue interface, it will involve online operations on the page. After monitoring the user's online operations on the page, the front end of the page can display the page ID corresponding to the user's page and the module's theme of the module. The page information such as the module ID is sent to the robot background, so that the robot background obtains the page information and module information of the page corresponding to the online operation, and according to the page information and module information, for example, according to the page ID and module ID, module Content and other module information, identify the dialogue scene corresponding to the module where the user is located.

S12. Identify the dialogue scene corresponding to the online operation according to the module information.

Specifically, the dialogue scene corresponding to the online operation can be identified according to the page information and module information corresponding to the online operation. After obtaining the page information and module information where the user operates online, for example, after obtaining the page ID and module ID, since the page information and module information have a preset corresponding relationship with the dialogue scene, according to the page information and module information information, the dialogue scene corresponding to the online operation can be identified. For example, on the insurance sales webpage, for an insurance product, there will be scenarios such as benefit demonstration scenarios, scenarios of filling in the insured information, scenarios of insurance details, etc. Each of the above scenarios is displayed by a separate module on the page. , each module will correspond to a page ID and a module ID on the page, etc. There is a preset correspondence between the page information and module information corresponding to each module and the scene corresponding to the module. According to the page information and module Information, you can get the scene corresponding to the module, the scene is the benefit demonstration scene, the insured person information filling scene or the guarantee details scene, etc., and then determine the dialogue scene corresponding to the dialogue according to the scene corresponding to the module. In an example, as shown in Table 1 below, each scene corresponds to preset page information:

Table 1

S13 . Based on the dialogue scene, obtain a preset dialogue corresponding to the dialogue scene, and push the dialogue according to the preset dialogue.

Specifically, for each scene, the scene is the dialogue scene in which the corresponding dialogue is located. According to the theme and content associated with the scene, a preset vocabulary corresponding to the scene is set. The mapping relationship between the preset words, after identifying the scene corresponding to the online operation, the preset words associated with the scene are called, and the most suitable words for this scene can be recalled according to the words tags , for example, based on features such as semantics and popularity, the most suitable words are recalled for this scene, and the dialogue is pushed according to the preset words, so as to realize the recommended words based on the scene. For different scenarios corresponding to different pages, the words are also Different from each other, to achieve the accurate correspondence between the words and the scene, so as to improve the accuracy of the dialogue and the efficiency of communication.

In the embodiment of the present application, by responding to the online operation of the user, the module information contained in the page module corresponding to the online operation is obtained, and the dialogue scene corresponding to the online operation is identified according to the module information, Based on the dialogue scene, a preset dialogue corresponding to the dialogue scene is acquired, and the dialogue is pushed according to the preset dialogue. Since the dialogue scene corresponding to the module where the user is located is identified, the module where the user is located is The scene is an important parameter for the push of the words corresponding to the dialogue scene. According to the recognized dialogue scene, the mapping relationship between the dialogue scene and the words is established, and the words that are most suitable for this scene are recalled according to the label of the words, so as to realize different scenarios. The words have different purposes. Compared with the traditional technology, the specific scene of the user entering the robot is not used as a parameter, which causes the user to enter different insurance product pages and different positions on the page (such as filling in the insurance applicant information module and insurance details module, etc.) The questions the user wants to ask may be different) when entering the robot, the predicted questions (the robot "guess what you want to ask") are not different. The embodiment of the present application improves the accuracy of the dialogue and the efficiency of conversational communication.

Further, referring to Table 2, it is also possible to set different speeches with preset priorities for the same scene. The priorities can be set according to the order of business logic of specific services, and the preset priority corresponding to the speeches can be set. Ranking and communication planning with users, and push them in descending order of the preset priorities corresponding to the words.

Form 2

Please refer to FIG. 2 , which is a schematic diagram of a first sub-flow of the online self-service dialogue method provided by the embodiment of the present application. In this embodiment, the module information includes module content, and the module content includes content such as text, pictures, voice, and forms. In response to the user's online operation, the information of the page module corresponding to the online operation is obtained. The steps to include module information include:

S21, detect the sliding track of the online operation; S22, identify the target position where the sliding track currently stays; S23, identify the target page area to which the target position belongs according to the target position; S24, according to the target Page area, obtain the module ID to which the target page area belongs; S25 , obtain the module content corresponding to the module ID according to the module ID.

Wherein, the online operation may be the sliding track of the mouse, or may be the sliding track of the gesture operation on the smart device.

Specifically, when a user performs an online operation on a page, the user can monitor the specific area of the page where the user is located to detect the sliding trajectory of the online operation, and identify the current target position of the sliding trajectory. the target position, identify the target page area to which the target position belongs, obtain the module ID to which the target page area belongs according to the target page area, and according to the module ID, based on the preset module ID and the module content The association relationship can be obtained, the module content corresponding to the module ID can be obtained, and the module information contained in the page module corresponding to the online operation can be obtained in response to the user's online operation.

Please refer to FIG. 3 , which is a schematic diagram of a second sub-flow of the online self-help dialogue method provided by the embodiment of the present application. In this embodiment, the step of identifying the target page area to which the target position belongs according to the target position includes: S31, according to the target position, identifying the target page to which the target position belongs; S32, according to the target position The target page is determined, and the target module included in the target page to which the target location belongs is determined; S33, the target module is used as a target page area.

Specifically, for the situation that the same webpage contains different modules to correspond to different scenarios, different scenarios can be described by different modules. When identifying the target page area to which the target position belongs according to the target position, first According to the target position, identify the target page to which the target position belongs, and then according to the target page, determine the target module included in the target page to which the target position belongs, and use the target module as the target page area . For example, on the insurance sales web page, for all insurance products on sale, after the user enters the page and before entering the robot dialogue interface, the front end of the page will put the product ID corresponding to the user's page and the module corresponding to the page location (such as benefits The module corresponding to the demo scene, the module corresponding to the scene where the insured information is filled in, or the module corresponding to the guarantee details scene, etc.) are sent to the robot backend in the form of parameters, so that the robot backend can identify the specific scene of the module where the user is located. Thus, the scene where the user is located can be accurately identified, thereby providing accurate words according to the scene.

Please refer to FIG. 4 , which is a schematic diagram of a third sub-flow of the online self-service dialogue method provided by the embodiment of the present application. In this embodiment, the step of recognizing the target page to which the target position belongs according to the target position includes: S41 , obtaining a distance between a preset page and a preset page position range corresponding to the preset page. S42, according to the target position, determine whether the target position is included in the preset page position range; S43, if the target position is included in the preset page position range, determine the preset page is a target page; S44, if the target position is not included in the preset page position range, determine that the preset page is not a target page.

Specifically, preset a corresponding preset page position range for each page, that is, which page belongs to which position, and after obtaining the target position, obtain the preset page and the preset page position range corresponding to the preset page According to the target position, it is determined whether the target position is included in the preset page position range, and if the target position is included in the preset page position range, it is determined that the preset page is Target page, if the target position is not included in the preset page position range, it is determined that the preset page is not a target page until the target page corresponding to the target position is identified.

Please refer to FIG. 5 , which is a schematic diagram of a fourth sub-flow of the online self-help dialogue method provided by the embodiment of the present application. In this embodiment, the step of obtaining the module content corresponding to the module ID according to the module ID includes: S51. Obtaining the text corresponding to the module ID according to the module ID; S52. Named entity recognition is performed on the text to identify the named entities contained in the text.

Among them, Named Entity Recognition (English for Named Entity Recognition, NER for short), also known as "proper name recognition", refers to the identification of entities with specific meanings in the text, mainly including names of persons, places, institutions, proper nouns, etc.

Specifically, after the target page is determined, the module where the user is located is determined according to the target page, and the module ID corresponding to the module is obtained, and according to the module ID, based on the mapping relationship between the module ID and the module content , obtain the text corresponding to the module ID, and perform named entity recognition on the text to identify the named entity contained in the text, and then identify the scene corresponding to the target page according to the named entity ( That is, the dialogue scene), and then based on the scene, obtain a preset speech corresponding to the scene, and push the dialogue according to the preset speech.

Further, the step of identifying the dialogue scene corresponding to the online operation according to the module information includes: according to the named entity, filtering out a target named entity that matches the theme corresponding to the page module; According to the target named entity, the dialogue scene corresponding to the page module is determined, so as to identify the dialogue scene corresponding to the online operation.

Specifically, after obtaining the module ID of the module where the user is located, the module corresponding to the module ID is the target module where the user is located, then multiple named entities in the target module are obtained, and the subject of the target module can also be obtained, According to the named entity, a target named entity matching the theme corresponding to the page module is filtered out, and according to the target named entity, the session scene corresponding to the page module is determined, thereby identifying the online operation site. the corresponding dialogue scene. For example, monitor the area corresponding to the specific page module of the page where the user is located, identify the named entity on the page module, identify the named entity, obtain the part that the user is most interested in, and predict the most likely user based on the principle of collaborative recommendation. Ask questions, or recommend questions that users are most interested in. Among them, collaborative recommendation, also known as collaborative filtering, is to use the preferences of a group with similar interests and common experience to recommend information that users are interested in. Individuals respond to the information to a considerable extent (such as ratings) through a cooperative mechanism and record it. To achieve the purpose of filtering and help others filter information, the response is not necessarily limited to those of particular interest, and the record of information of particular interest is also very important.

Please refer to FIG. 6 , which is a schematic diagram of a fifth sub-flow of the online self-service dialogue method provided by the embodiment of the present application. In this embodiment, before the step of acquiring a preset speech corresponding to the dialogue scene based on the dialogue scene, and pushing the dialogue according to the preset speech, the method further includes: S61. S62, determine whether the dwell time is greater than or equal to a preset time threshold; S63, if the dwell time is greater than or equal to a preset time threshold, execute the based on the scene , obtain the preset speech technique corresponding to the scene, and push the dialogue according to the preset speech technique; S64, if the stay time is less than the preset time threshold, do not perform the step of obtaining the scenario based on the The preset language corresponding to the scene, and the step of pushing the dialogue according to the preset language, can further count the stay time of the sliding track at the target position, until the stay time is greater than or equal to the preset time. A time threshold is set, or the user leaves the target location.

Specifically, when the user clicks on the conversation interface, based on the dialogue scene corresponding to the module where the user is located, the preset dialogue scene corresponding to the dialogue scene can be obtained, and the dialogue can be pushed to the user according to the preset dialogue method. It can actively push the preset speech corresponding to the dialogue scene to the user, so as to help the user to understand the content corresponding to the webpage module by actively pushing the speech, and the user can stay at the target location for more than the preset time. When the threshold is reached, it is judged that the user is interested in the content of the webpage at the target location. At this time, the user is involved in the understanding of the content of the page, and based on the scene, the preset words corresponding to the dialogue scene are obtained, and according to the The preset conversation pushes the dialogue, and the user's stay time at the target position can be determined by counting the stay time of the sliding track at the target position, and whether the stay time is greater than or equal to the preset time threshold, if the The stay time is greater than or equal to a preset time threshold, and the step of obtaining a preset speech corresponding to the scene based on the scene, and pushing a dialogue according to the preset speech, if the stay time If less than the preset time threshold, the step of obtaining the preset speech corresponding to the scene based on the scene, and pushing the dialogue according to the preset speech is not performed, and the sliding track can be further counted at the location. The stay time at the target position is determined until the stay time is greater than or equal to a preset time threshold, or the user leaves the target position. For example, when self-service is provided through an intelligent robot on a webpage, the user can be prompted to get help through active bubbling, so that not only can the user see scenario-based recommendations after clicking the robot, but also the user can click on a certain webpage on the page. Or when a module in the webpage stays for a certain period of time, it triggers bubbling to actively guide the customer, so that the user is not interested in a certain part of the page, but doubts whether the robot can understand its own problem, and does not ask questions actively, which can solve the problem when the user is not interested in a certain part of the page. When the questioning robot still has some psychological thresholds, after gaining insight into the most likely questions of users, it will take the initiative to bubble up prompts, which will be more likely to hit the users’ doubts at this time, lower the psychological threshold, and guide users when they encounter doubts. Looking for robot consultation from time to time to improve the service efficiency of self-service dialogue.

Further, in an embodiment, the step of acquiring a preset dialogue corresponding to the dialogue scene based on the dialogue scene, and pushing the dialogue according to the preset dialogue includes: based on the dialogue scene , obtain the preset question options corresponding to the dialogue scene, and push the preset question options to the user for the user to select and conduct a dialogue.

Specifically, it can be combined with the scene to predict the question that the user is most likely to ask in the scene, or the question corresponding to the content the user wants to know, and show it to the user in advance, and the user can see the answer just by clicking, reducing the number of users The online operation entered by oneself is more intelligent in experience, and improves the accuracy and efficiency of dialogue. Compared with traditional technology, unless the user actively clicks on the robot, the user does not know what kind of problem the robot can solve, and lacks active guidance. , a self-service dialogue mode that can only be handled passively, the embodiment of the present application can improve the service efficiency of self-service dialogue through active guidance.

Further, before the step of acquiring a preset speech technique corresponding to the dialogue scene based on the dialogue scene, and pushing the dialogue according to the preset speech technique, the method further includes: receiving dialogue information input by a user; Determine whether the dialogue information is clear; if the dialogue information is unclear, predict the complete dialogue information corresponding to the dialogue information based on the dialogue scene, and execute the based on the dialogue scene according to the complete dialogue information , obtain the preset speech technique corresponding to the dialogue scene, and push the dialogue steps according to the preset speech technique.

Specifically, due to differences in user language habits, it is impossible for all users to use a unified standard language for dialogue. It is necessary to cover all language expressions in order to provide the most accurate service possible for a full range of users. After receiving the dialogue information input by the user, the dialogue information can be text information or voice information. If it is voice information, the voice information needs to be converted into text information through voice recognition, and then the text information is judged as follows, and then Determine whether the dialogue information is clear and complete, that is, determine whether the intention described by the user's information can be understood. If the dialogue information is clear and complete, directly according to the user's dialogue information and based on the dialogue scene, obtain the information related to the dialogue scene. Corresponding preset words, and push the dialogue according to the preset words, if the dialogue information is unclear, based on the dialogue scene, predict the complete dialogue information corresponding to the dialogue information, so as to convert the user's dialogue information. complete, and according to the complete dialogue information, perform the steps of obtaining the preset dialogue corresponding to the dialogue scene based on the dialogue scene, and pushing the dialogue according to the preset dialogue, so as to update the dialogue scene. It is possible to understand users more accurately with a large probability, and by actively predicting the user's dialogue information intentions, it can improve the service efficiency of self-service dialogues. For example, on the display page of an insurance product, you can understand the user's intention by referring to the auto-completion entity. Since the user scenario is already known, when the user asks a question with an unclear reference, such as "What can this be insured?", The robot can automatically fill in the dialogue intention that the user asks which product can be insured according to the specific scene corresponding to the page the user is on. , so as to improve the response accuracy rate in the conversation and improve the service efficiency of self-service dialogue. In the embodiment of the present application, the active insight and entity automatic completion based on the dialogue scene can make the robot easier to understand the user's input and intention, and improve the robot's response. Accuracy and better user experience. Compared with the passive response method based on self-service dialogue in traditional technologies, due to the lack of user guidance and entity completion, users who actually come to ask questions will be more open in questioning and will By omitting the subject, etc., only passive dialogue can be conducted according to the actual question content of the user, resulting in a low recognition rate of the robot, reducing the efficiency of self-service dialogue, and affecting user experience. The embodiment of the present application can improve the service efficiency of self-service dialogue and improve user experience. .

It should be noted that, for the online self-service dialogue methods described in the above-mentioned embodiments, the technical features contained in different embodiments can be recombined as required to obtain a combined implementation scheme, but all of them are protected by the protection required by this application. within the range.

Please refer to FIG. 7 , FIG. 7 is a schematic block diagram of an online self-service dialogue apparatus provided by an embodiment of the present application. Corresponding to the above-mentioned online self-help dialogue method, an embodiment of the present application further provides an online self-help dialogue device. As shown in FIG. 7 , the online self-service dialogue apparatus includes a unit for executing the above-mentioned online self-service dialogue method, and the online self-service dialogue apparatus can be configured in a computer device. Specifically, please refer to FIG. 7 , the online self-service dialogue device 70 includes an acquisition unit 71 , an identification unit 72 and a push unit 73 .

Wherein, the obtaining unit 71 is configured to, in response to the online operation of the user, obtain the module information contained in the page module corresponding to the online operation, where the page module is one of the multiple page modules on the online operation page that the user owns. The selected page module; the identification unit 72 is used to identify the dialogue scene corresponding to the online operation according to the module information; the push unit 73 is used to obtain the dialogue scene corresponding to the dialogue scene based on the Preset speeches, and push dialogues according to the preset speeches.

In one embodiment, the acquisition unit 71 includes: a detection subunit for detecting the sliding track of the online operation; a first identification subunit for identifying the target position where the sliding track currently stays;

The second identification subunit is used to identify the target page area to which the target position belongs according to the target position; the first acquisition subunit is used to obtain the module ID to which the target page area belongs according to the target page area ; The second obtaining subunit is used for obtaining the module content corresponding to the module ID according to the module ID.

In one embodiment, the second identification subunit includes: a third identification subunit for identifying the target page to which the target position belongs according to the target position; and a first determination subunit for identifying the target page to which the target position belongs according to the target position; The target page is used to determine the target module included in the target page to which the target location belongs; the second determination subunit is used to use the target module as a target page area.

In one embodiment, the third identifying subunit includes: a third obtaining subunit, configured to obtain a correspondence between a preset page and a preset page position range corresponding to the preset page; a judging subunit , for determining whether the target position is included in the preset page position range according to the target position; the determination subunit is used for determining whether the target position is included in the preset page position range if the target position is included in the preset page position range. Let the page be the target page.

In one embodiment, the second obtaining subunit includes: a fourth obtaining subunit, used for obtaining the text corresponding to the module ID according to the module ID; Named entity recognition to identify named entities contained in the text.

In one embodiment, the online self-service dialogue device 70 further includes: a statistics unit for counting the stay time of the sliding track at the target position; a judgment unit for judging whether the stay time is greater than or equal to a preset time threshold; an execution unit, configured to execute the based on the scene, obtain the preset speech corresponding to the scene if the stay time is greater than or equal to the preset time threshold, and according to the preset Steps to push conversations with words.

In one embodiment, the pushing unit 73 is specifically configured to obtain preset question options corresponding to the dialog scene based on the dialog scene, and push the preset question options to the user for the user to use. Make a selection to have a conversation.

It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned online self-service dialogue device and each unit may refer to the corresponding descriptions in the foregoing method embodiments. For the convenience and brevity of description, here No longer.

At the same time, the division and connection methods of each unit in the above-mentioned online self-service dialogue device are only used for illustration. Each unit in the device adopts different connection sequences and methods to complete all or part of the functions of the above-mentioned online self-service dialogue device.

The above-mentioned online self-service dialogue apparatus can be implemented in the form of a computer program, and the computer program can be executed on a computer device as shown in FIG. 8 .

Please refer to FIG. 8 , which is a schematic block diagram of a computer device provided by an embodiment of the present application. The computer device 500 may be a computer device such as a desktop computer or a server, or may be a component or component in other devices.

8, the computer device 500 includes a processor 502, a memory and a network interface 505 connected through a system bus 501, wherein the memory may include a non-volatile storage medium 503 and an internal memory 504, and the memory may also be a volatile computer Readable storage medium.

The nonvolatile storage medium 503 can store an operating system 5031 and a computer program 5032 . When executed, the computer program 5032 can cause the processor 502 to execute an online self-help dialogue method described above.

The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

The internal memory 504 provides an environment for running the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an online self-help dialogue method.

The network interface 505 is used for network communication with other devices. Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than shown, or combine certain components, or have a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structures and functions of the memory and the processor are the same as those of the embodiment shown in FIG. 8 , which will not be repeated here.

The processor 502 is configured to run the computer program 5032 stored in the memory, so as to implement the online self-help dialogue method described in the embodiments of the present application.

It should be understood that, in this embodiment of the present application, the processor 502 may be a central processing unit (Central Processing Unit, CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Wherein, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like.

It can be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program, and the computer program can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the flow steps of the above-described method embodiments.

Therefore, the present application also provides a computer-readable storage medium. The computer-readable storage medium may be a non-volatile computer-readable storage medium, or a volatile computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by the processor The processor is caused to execute the steps of the online self-help dialogue method described in the above embodiments.

The storage medium is a physical, non-transitory storage medium, such as a U disk, a removable hard disk, a read-only memory (Read-Only Memory, ROM), a magnetic disk or an optical disk and other physical storage that can store computer programs. medium.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. Interchangeability, the above description has generally described the components and steps of each example in terms of function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

The above are only specific implementations of the present application, but the scope of protection disclosed in the present application is not limited to this. Any person skilled in the art can easily think of various equivalents within the technical scope disclosed in the present application. Modifications or substitutions of the present application shall be included within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

An online self-help dialogue method, including:

In response to the user's online operation, acquiring module information contained in a page module corresponding to the online operation, where the page module is a page module selected by the user among multiple page modules on the online operation page;

Identifying the dialogue scene corresponding to the online operation according to the module information;

Based on the dialogue scene, a preset dialogue corresponding to the dialogue scene is acquired, and a dialogue is pushed according to the preset dialogue.
The online self-help dialogue method according to claim 1, wherein the step of acquiring module information contained in a page module corresponding to the online operation in response to the online operation of the user comprises:

detecting the sliding trajectory of the online operation;

Identify the target position where the sliding track currently stays;

According to the target position, identify the target page area to which the target position belongs;

According to the target page area, obtain the module ID to which the target page area belongs;

According to the module ID, the module content corresponding to the module ID is acquired.
The online self-help dialogue method according to claim 2, wherein the step of identifying the target page area to which the target position belongs according to the target position comprises:

According to the target position, identify the target page to which the target position belongs;

According to the target page, determine the target module included in the target page to which the target location belongs;

The target module is used as the target page area.
The online self-help dialogue method according to claim 3, wherein the step of identifying the target page to which the target position belongs according to the target position comprises:

obtaining the correspondence between the preset page and the preset page position range corresponding to the preset page;

According to the target position, determine whether the target position is included in the preset page position range;

If the target position is included in the preset page position range, it is determined that the preset page is a target page.
The online self-help dialogue method according to claim 2, wherein the step of acquiring the module content corresponding to the module ID according to the module ID comprises:

According to the module ID, obtain the text corresponding to the module ID;

Named entity recognition is performed on the text to identify named entities contained in the text.
The online self-help dialogue method according to claim 5, wherein the step of identifying the dialogue scene corresponding to the online operation according to the module information comprises:

According to the named entity, filter out the target named entity that matches the theme corresponding to the page module;

According to the target named entity, the dialogue scene corresponding to the page module is determined, so as to identify the dialogue scene corresponding to the online operation.
The online self-help dialogue method according to claim 2, wherein, before the step of acquiring a preset dialogue corresponding to the dialogue scene based on the dialogue scene, and pushing the dialogue according to the preset dialogue ,Also includes:

Counting the stay time of the sliding track at the target position;

judging whether the stay time is greater than or equal to a preset time threshold;

If the stay time is greater than or equal to a preset time threshold, the step of acquiring a preset speech corresponding to the scene based on the scene, and pushing a dialogue according to the preset speech is performed.
The online self-help dialogue method according to claim 1, wherein the step of acquiring a preset dialogue corresponding to the dialogue scene based on the dialogue scene, and pushing the dialogue according to the preset dialogue comprises:

Based on the dialogue scene, the preset question options corresponding to the dialogue scene are acquired, and the preset question options are pushed to the user for selection by the user to conduct a dialogue.
An online self-service dialogue device, comprising:

an obtaining unit, configured to obtain the module information contained in the page module corresponding to the online operation in response to the online operation of the user;

an identification unit, configured to identify the dialogue scene corresponding to the online operation according to the module information;

and a pushing unit, configured to acquire a preset speech corresponding to the dialogue scene based on the dialogue scene, and push the dialogue according to the preset speech.
A computer device comprising a memory and a processor connected to the memory; wherein the memory is used to store a computer program; the processor is used to run the computer program to perform the following steps:

In response to the user's online operation, acquiring module information contained in a page module corresponding to the online operation, where the page module is a page module selected by the user among multiple page modules on the online operation page;

Identifying the dialogue scene corresponding to the online operation according to the module information;

Based on the dialogue scene, a preset dialogue corresponding to the dialogue scene is acquired, and a dialogue is pushed according to the preset dialogue.
The computer device according to claim 10, wherein the step of acquiring the module information contained in the page module corresponding to the online operation in response to the online operation of the user comprises:

detecting the sliding trajectory of the online operation;

Identify the target position where the sliding track currently stays;

According to the target position, identify the target page area to which the target position belongs;

According to the target page area, obtain the module ID to which the target page area belongs;

According to the module ID, the module content corresponding to the module ID is acquired.
The computer device according to claim 11, wherein the step of identifying the target page area to which the target position belongs according to the target position comprises:

According to the target position, identify the target page to which the target position belongs;

According to the target page, determine the target module included in the target page to which the target location belongs;

The target module is used as the target page area.
The computer device according to claim 12, wherein the step of identifying the target page to which the target position belongs according to the target position comprises:

obtaining the correspondence between the preset page and the preset page position range corresponding to the preset page;

According to the target position, determine whether the target position is included in the preset page position range;

If the target position is included in the preset page position range, it is determined that the preset page is a target page.
The computer device according to claim 11, wherein the step of acquiring the module content corresponding to the module ID according to the module ID comprises:

According to the module ID, obtain the text corresponding to the module ID;

Named entity recognition is performed on the text to identify named entities contained in the text.
The computer device according to claim 14, wherein the step of identifying the dialogue scene corresponding to the online operation according to the module information comprises:

According to the named entity, filter out the target named entity that matches the theme corresponding to the page module;

According to the target named entity, the dialog scene corresponding to the page module is determined, so as to identify the dialog scene corresponding to the online operation.
The computer device according to claim 11, wherein, before the step of acquiring a preset speech corresponding to the dialogue scene based on the dialogue scene, and pushing the dialogue according to the preset speech, the method further comprises: :

Counting the stay time of the sliding track at the target position;

judging whether the stay time is greater than or equal to a preset time threshold;

If the stay time is greater than or equal to a preset time threshold, the step of acquiring a preset speech corresponding to the scene based on the scene, and pushing a dialogue according to the preset speech is performed.
The computer device according to claim 10, wherein the step of acquiring a preset speech corresponding to the dialogue scene based on the dialogue scene, and pushing the dialogue according to the preset speech comprises:

Based on the dialogue scene, the preset question options corresponding to the dialogue scene are acquired, and the preset question options are pushed to the user for selection by the user to conduct a dialogue.
A computer-readable storage medium, the storage medium stores a computer program, and the computer program can implement the following steps when executed by a processor:

In response to the user's online operation, acquiring module information contained in a page module corresponding to the online operation, where the page module is a page module selected by the user among multiple page modules on the online operation page;

Identifying the dialogue scene corresponding to the online operation according to the module information;

Based on the dialogue scene, a preset dialogue corresponding to the dialogue scene is acquired, and a dialogue is pushed according to the preset dialogue.
The computer-readable storage medium according to claim 18, wherein the step of acquiring module information included in a page module corresponding to the online operation in response to an online operation of the user comprises:

detecting the sliding trajectory of the online operation;

Identify the target position where the sliding track currently stays;

According to the target position, identify the target page area to which the target position belongs;

According to the target page area, obtain the module ID to which the target page area belongs;

According to the module ID, the module content corresponding to the module ID is acquired.
The computer-readable storage medium according to claim 19, wherein the step of identifying the target page area to which the target position belongs according to the target position comprises:

According to the target position, identify the target page to which the target position belongs;

According to the target page, determine the target module included in the target page to which the target location belongs;

The target module is used as the target page area.