CN113794623A - Method and device for generating response message, electronic equipment and storage medium - Google Patents
Method and device for generating response message, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113794623A CN113794623A CN202111015147.4A CN202111015147A CN113794623A CN 113794623 A CN113794623 A CN 113794623A CN 202111015147 A CN202111015147 A CN 202111015147A CN 113794623 A CN113794623 A CN 113794623A
- Authority
- CN
- China
- Prior art keywords
- user
- message
- target response
- dialog
- interface
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
Abstract
The application provides a method and a device for generating a response message, electronic equipment and a storage medium, wherein a dialog interface for a first user to dialog with a second user is displayed in a graphical user interface of a mobile terminal used by the first user; when the conversation message sent by the second user to the first user meets a preset trigger condition, displaying at least one target response material for replying the conversation message; responding to the selection operation of the first user on at least one target response material, and displaying the target response material selected by the first user in an information input box of the conversation interface; and generating a response message for answering the dialogue message in response to the editing operation of the first user for the target response material displayed in the information input box. Therefore, the editable target response materials extracted according to the conversation messages are displayed on the conversation interface of the first user, so that the first user can select at least one target response material to generate the response message, and the response efficiency is improved.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method and an apparatus for generating a response message, an electronic device, and a storage medium.
Background
In recent years, as a large number of users are rapidly accumulated in social media and a large amount of fragment time of clients is occupied, and each enterprise is constantly motivated in social marketing, service personnel can frequently communicate with the clients through enterprise WeChat and carry out activities propaganda, question answering and other works in client groups, but due to the factors of large number of service personnel, high mobility and the like, a large amount of training is needed to achieve the purpose of uniform and professional dialogues of the service personnel, in order to reduce related training work, the recommendation functions of different materials such as dialogues, documents, pictures and the like are provided on enterprise WeChat side columns according to real-time conversation information, and the reply content of the service personnel is standardized and the personnel training is also assisted.
The function has a good display form at the PC end, but aiming at the condition that the screen size of the mobile end is limited and the operation mode is simplified, the mode adopted by the prior art is that a 'material library' module is marked above an input frame at the bottom of a conversation page for navigation, but the display mode can lead a service staff to switch a plurality of pages to find recommended materials when the materials are recommended, and only one material can be selected for sending at a time, if a plurality of materials are required to be sent, the selection needs to be switched repeatedly, so that the reply efficiency of the service staff is lower.
Disclosure of Invention
In view of this, an object of the present application is to provide a method, an apparatus, an electronic device, and a storage medium for generating a response message, in which a target response material extracted according to a dialog message is displayed on a dialog interface of a first user, and the displayed response material is an editable material, so that the first user selects at least one target response material to generate a response message, thereby improving response efficiency of the first user.
The embodiment of the application provides a method for generating a response message, wherein a dialog interface for dialog between a first user and a second user is displayed in a graphical user interface of a mobile terminal used by the first user; the generation method comprises the following steps:
when the dialogue message sent by the second user to the first user meets a preset trigger condition, displaying at least one target response material for replying the dialogue message;
in response to the selection operation of the first user on the at least one target response material, displaying the target response material selected by the first user in an information input box of the dialog interface in an editable manner;
and generating a response message for answering the dialogue message in response to the editing operation of the first user on the target response material displayed in the information input box.
Optionally, the step of the dialog message meeting the preset trigger condition includes: the dialog message comprises preset keywords and reply operation of the first user to the dialog message.
Optionally, before displaying at least one target response material for replying to the dialog message, the generating method further includes:
performing content identification on the conversation message, and determining a conversation intention of the conversation message;
and extracting at least one target response material from a pre-constructed material library by using a pre-constructed material recommendation model based on the preset keywords and the conversation intention.
Optionally, after extracting at least one target response story from the pre-constructed story library using the pre-constructed story recommendation model, the generating method further includes:
and displaying a material selection control in an input method interface in the dialog interface of the first user, so that at least one target response material is displayed on the dialog interface of the first user.
Optionally, the reply operation of the first user to the dialog message includes:
and the first user selects the material selection control to display at least one target response material indicated by the material selection control in the dialog interface of the first user.
Optionally, after responding to the selection operation of the first user on the at least one target response material, the generation method further includes:
binding at least one target response material selected by the first user with the dialogue message to serve as an optimized training sample of the material recommendation model; the optimization training sample is used for optimizing model parameters of the material recommendation model.
The embodiment of the application also provides a device for generating the response message, wherein a dialog interface for dialog between a first user and a second user is displayed in a graphical user interface of a mobile terminal used by the first user; the generation device comprises:
the material display module is used for displaying at least one target response material for replying the dialogue message when the dialogue message sent by the second user to the first user meets a preset trigger condition;
the display module is used for responding to the selection operation of the first user on the at least one target response material, and displaying the target response material selected by the first user in an information input box of the conversation interface;
and the message generating module is used for responding to the editing operation of the first user aiming at the target response material displayed in the information input box and generating a response message for answering the dialogue message.
Optionally, the step of the dialog message meeting the preset trigger condition includes: the dialog message comprises preset keywords and reply operation of the first user to the dialog message.
Optionally, the generating device further includes a story extracting module, where the story extracting module is configured to:
performing content identification on the conversation message, and determining a conversation intention of the conversation message;
and extracting at least one target response material from a pre-constructed material library by using a pre-constructed material recommendation model based on the preset keywords and the conversation intention.
Optionally, the generating apparatus further includes a control display module, where the control display module is configured to:
and displaying a material selection control in an input method interface in the dialog interface of the first user, so that at least one target response material is displayed on the dialog interface of the first user.
Optionally, the reply operation of the first user to the dialog message includes:
and the first user selects the material selection control to display at least one target response material indicated by the material selection control in the dialog interface of the first user.
Optionally, the generating apparatus further comprises a sample generating module, and the sample generating module is configured to:
binding at least one target response material selected by the first user with the dialogue message to serve as an optimized training sample of the material recommendation model; the optimization training sample is used for optimizing model parameters of the material recommendation model.
An embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the generating method as described above.
Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the generating method as described above.
According to the method, the device, the electronic equipment and the storage medium for generating the response message, a dialog interface for dialog between a first user and a second user is displayed in a graphical user interface of a mobile terminal used by the first user; the generation method comprises the following steps: when the dialogue message sent by the second user to the first user meets a preset trigger condition, displaying at least one target response material for replying the dialogue message; in response to the selection operation of the first user on the at least one target response material, displaying the target response material selected by the first user in an information input box of the dialog interface in an editable manner; and generating a response message for answering the dialogue message in response to the editing operation of the first user on the target response material displayed in the information input box.
Therefore, in the process of generating the response message, the application applies the response materials from the same material library, and can ensure the uniformity of answering the same question; secondary modification and multi-strip combination can be carried out aiming at the target response material, so that the flexibility of the service is ensured; when the method is applied to the display of the mobile terminal, the operation can be kept in the same screen, so that the response efficiency can be improved; in addition, behavior data are collected and recycled, and a material recommendation model is continuously optimized, so that recommendation accuracy can be further improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of a method for generating a response message according to an embodiment of the present application;
FIG. 2 illustrates a schematic diagram of a material configuration interface;
FIG. 3 illustrates a diagram showing a material selection control;
FIG. 4 is a diagram illustrating the display of targeted response material;
FIG. 5 is a diagram illustrating a selection operation in response to a user selecting targeted response material;
fig. 6 is a schematic structural diagram of an apparatus for generating a response message according to an embodiment of the present application;
fig. 7 is a second schematic structural diagram of an apparatus for generating a response message according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.
In recent years, as a large number of users are rapidly accumulated in social media and a large amount of fragment time of clients is occupied, and each enterprise is constantly motivated in social marketing, service personnel can frequently communicate with the clients through enterprise WeChat and carry out activities propaganda, question answering and other works in client groups, but due to the factors of large number of service personnel, high mobility and the like, a large amount of training is needed to achieve the purpose of uniform and professional dialogues of the service personnel, in order to reduce related training work, the recommendation functions of different materials such as dialogues, documents, pictures and the like are provided on enterprise WeChat side columns according to real-time conversation information, and the reply content of the service personnel is standardized and the personnel training is also assisted.
The function has a good display form at the PC end, but aiming at the condition that the screen size of the mobile end is limited and the operation mode is simplified, the mode adopted by the prior art is that a 'material library' module is marked above an input frame at the bottom of a conversation page for navigation, but the display mode can lead a service staff to switch a plurality of pages to find recommended materials when the materials are recommended, and only one material can be selected for sending at a time, if a plurality of materials are required to be sent, the selection needs to be switched repeatedly, so that the reply efficiency of the service staff is lower.
Based on this, the embodiment of the present application provides a response message method, where a target response material extracted according to a dialog message is displayed on a dialog interface of a first user, and the displayed response material is an editable material, so that the first user selects at least one target response material to generate a response message, thereby improving response efficiency of the first user.
Referring to fig. 1, fig. 1 is a flowchart of a method for generating a response message according to an embodiment of the present application. As shown in fig. 1, in a method for generating a response message provided in an embodiment of the present application, a dialog interface for a first user to dialog with a second user is displayed in a graphical user interface of a mobile terminal used by the first user, and the method includes:
s101, when the dialogue message sent to the first user by the second user meets a preset trigger condition, displaying at least one target response material for replying the dialogue message.
In this step, the first user may act as a service, leader, in the marketing system for the personnel at the enterprise end to complete marketing and service employment. The second user may serve a customer of the business to the first user, who is the subject of the first user's service through the marketing system. And displaying at least one target response material for replying a dialog message on a dialog interface between a first user and a second user in a graphical user interface of the mobile terminal used by the first user.
Here, the mobile terminal may be an electronic device such as a mobile phone and a tablet computer. The first user may be at least one and the second user may be at least one. The generation method can be applied to a single chat scene and can also be applied to a group chat scene.
Optionally, the step of the dialog message meeting the preset trigger condition includes: the dialog message comprises preset keywords and reply operation of the first user to the dialog message.
Optionally, the reply operation of the first user to the dialog message includes: and the first user selects the material selection control to display at least one target response material indicated by the material selection control in the dialog interface of the first user.
Optionally, before displaying at least one target response material for replying to the dialog message, the generating method further includes: performing content identification on the conversation message, and determining a conversation intention of the conversation message; and extracting at least one target response material from a pre-constructed material library by using a pre-constructed material recommendation model based on the preset keywords and the conversation intention.
In this step, when it is determined that a dialog message sent by the second user to the first user contains a preset keyword, content recognition in the manners of text analysis, dictionary matching, image recognition and the like is performed on the dialog message, a user dialog intention of the dialog message is determined, the contained preset keyword and the dialog intention corresponding to the dialog message are extracted, and the keyword and the dialog intention of the dialog message are acquired. And then, extracting at least one target response material from a pre-constructed material library based on the acquired preset keywords and the conversation intention by using a pre-constructed material recommendation model.
Here, the number of the acquired keywords may be at least one, and the type of the acquired target response materials may include a plurality of types of materials. The response materials stored in the material library can be pre-configured by the experts in the background.
When the content of the dialog message is identified, only a single sentence dialog in the current dialog message can be identified, and all dialogs in the dialog message between the first user and the second user can also be identified.
Referring to fig. 2, fig. 2 illustrates a schematic diagram of a material configuration interface. And (4) performing material management on the management background, and configuring standard materials including information such as types, specific material contents and application ranges of the materials by an expert on the management background. Expert-configured material types may include text, pictures, video, files, links, applets, and the like.
Optionally, after extracting at least one target response material from a pre-constructed material library based on the acquired preset keyword and the dialogue intention by using a pre-constructed material recommendation model, the generating method further includes: and determining the relevancy score of each target response material and the dialogue message based on the acquired preset keywords and the dialogue intention, and determining the display priority of each target response material based on the determined relevancy score.
Here, the determination of the display priority of the target response materials is to determine the display order of each target response material on the dialog interface of the mobile terminal of the first user. And sorting according to the relevance grade in a descending order, determining the display priority of each target response material, and preferentially displaying the target response material with high display priority to the first user.
Optionally, after extracting at least one target response story from the pre-constructed story library using the pre-constructed story recommendation model, the generating method further includes: and displaying a material selection control in an input method interface in the dialog interface of the first user, so that at least one target response material is displayed on the dialog interface of the first user.
In the step, after at least one target response material is extracted from a pre-constructed material recommendation based on keywords and conversation intention, in response to the clicking operation of a first user on an input box in a conversation interface in a first user mobile terminal, an input method interface is displayed on the conversation interface in the first user mobile terminal, a material selection control is displayed on the input method interface, and the user can click on the material selection control, so that at least one target response material under the material selection control can be displayed on the current conversation interface of the first user.
Here, the input method interface is an input method association interface and has an association function.
Therefore, when the triggering condition is the reply operation of the first user to the dialog message, namely the selection operation of the first user to the material selection control, the background receives the selection operation of the first user, determines that the first user needs to display the target response material, and then displays at least one target response material extracted from the material library under the control in the dialog interface of the first user.
By way of example, referring to fig. 3 and 4, fig. 3 illustrates a diagram showing a material selection control; fig. 4 is a diagram illustrating display of target response material. As shown in fig. 3, when the first user accepts a dialog message "want to know a knowledge-graph product" sent by the second user, the data center also obtains the dialog message, then performs content recognition on the dialog message, and performs content recognition on keywords, dialog intentions, and the like related to the selected target response materials, wherein the recognition process also performs recognition in combination with the dialog context, and then uses a pre-constructed material recommendation model to extract at least one target response material from a pre-constructed material library. And displaying the extracted at least one target response material on a dialogue interface of the first user. The first user clicks on the information input box in the dialog interface and may display an input method interface, where "knowledge" shown in fig. 3 is the material selection control.
After the first user selects the control "knowledge" selection for the material in fig. 3, at least one target response material related to the knowledge-graph is displayed in the dialog interface of the first user, as shown in fig. 4.
And S102, responding to the selection operation of the first user on the at least one target response material, and displaying the target response material selected by the first user in an information input box of the dialog interface.
In this step, the first user can determine which of the displayed targeted response materials are to be selected based on the content of the conversation message with the second user, and perform the selection operation. And the background receives the selection operation of the first user on the target response material, and displays the target response material selected by the first user in an information input box on a conversation interface on the mobile terminal of the first user.
Here, the first user may select one or more targeted response materials, which will be presented in the information input box for the first user to perform secondary editing. The target response material may be an editable material or a non-editable material.
When the type of the target response material displayed in the information input box is a text, the first user can edit the text content, and when the type of the target response material displayed in the information input box is a picture, the first user can not edit the text content.
For example, referring to fig. 5, fig. 5 is a schematic diagram illustrating a selection operation in response to a user selecting a target response material. As shown in fig. 5, the first user selects a first target response material from the target response materials, the background receives a selection operation of the user, and the content of the first target response material is displayed in the dialog input box for the first user to edit for the second time.
Therefore, after one or more target response materials are selected, the content of the response materials is displayed in the information input box and can be edited by the first user, the edited information is sent to the second user as a reply message, and the integrity of the message can be ensured.
It should be noted that whether and how the material can be edited can be set in advance by an expert when the material is stored in the material library. Whether the first user edits the information in the information input box can be determined autonomously.
Optionally, after responding to the selection operation of the first user on the at least one target response material, the generation method further includes: binding at least one target response material selected by the first user with the dialogue message to serve as an optimized training sample of the material recommendation model; the optimization training sample is used for optimizing model parameters of the material recommendation model.
In the step, the target response materials in the material library selected by the first user are bound with the corresponding dialogue messages by embedding points on the page of the material library to form training samples, the training samples are transmitted back to the background, and the background automatically optimizes the material recommendation model based on the received training samples, so that the material recommendation effect can be further improved and the overall service efficiency can be improved.
And S103, responding to the editing operation of the first user aiming at the target response material displayed in the information input box, and generating a response message for answering the conversation message.
In the step, the first user edits the target response material displayed in the input box, generates a response message for answering the dialogue message after the editing is finished, and sends the response message to the second user.
The embodiment of the application provides a method for generating a response message, wherein a dialog interface for dialog between a first user and a second user is displayed in a graphical user interface of a mobile terminal used by the first user; the generation method comprises the following steps: when the dialogue message sent by the second user to the first user meets a preset trigger condition, displaying at least one target response material for replying the dialogue message; responding to the selection operation of the first user on the at least one target response material, and displaying the target response material selected by the first user in an information input box of the dialog interface; and generating a response message for answering the dialogue message in response to the editing operation of the first user on the target response material displayed in the information input box.
Therefore, in the process of generating the response message, the application applies the response materials from the same material library, and can ensure the uniformity of answering the same question; secondary modification and multi-strip combination can be carried out aiming at the target response material, so that the flexibility of the service is ensured; when the method is applied to the display of the mobile terminal, the operation can be kept in the same screen, so that the response efficiency can be improved; in addition, behavior data are collected and recycled, and a material recommendation model is continuously optimized, so that recommendation accuracy can be further improved.
Referring to fig. 6 and 7, fig. 6 is a first schematic structural diagram of a device for generating a response message according to an embodiment of the present application, and fig. 7 is a second schematic structural diagram of a device for generating a response message according to an embodiment of the present application. As shown in fig. 6, a dialog interface for a first user to dialog with a second user is displayed in a graphical user interface of a mobile terminal used by the first user, and the generating device 600 includes:
a material display module 610, configured to display at least one target response material for replying to a dialog message sent by the second user to the first user when the dialog message meets a preset trigger condition;
a display module 620, configured to, in response to a selection operation of the first user on the at least one target response material, display the target response material selected by the first user in an information input box of the dialog interface;
a message generating module 630, configured to generate a response message for answering the dialog message in response to an editing operation of the first user on the target response material displayed in the information input box.
The dialog message meeting the preset trigger condition comprises the following steps: the dialog message comprises preset keywords and reply operation of the first user to the dialog message.
Optionally, as shown in fig. 7, the generating apparatus 600 further includes a story extracting module 640, where the story extracting module 640 is configured to:
performing content identification on the conversation message, and determining a conversation intention of the conversation message;
and extracting at least one target response material from a pre-constructed material library by using a pre-constructed material recommendation model based on the preset keywords and the conversation intention.
Optionally, the generating apparatus 600 further includes a control display module 650, where the control display module 650 is configured to:
and displaying a material selection control in an input method interface in the dialog interface of the first user, so that at least one target response material is displayed on the dialog interface of the first user.
Optionally, the reply operation of the first user to the dialog message includes:
and the first user selects the material selection control to display at least one target response material indicated by the material selection control in the dialog interface of the first user.
Optionally, the generating apparatus 600 further includes a sample generating module 660, and the sample generating module 660 is configured to:
binding at least one target response material selected by the first user with the dialogue message to serve as an optimized training sample of the material recommendation model; the optimization training sample is used for optimizing model parameters of the material recommendation model.
Referring to fig. 8, fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 8, the electronic device 800 includes a processor 810, a memory 820, and a bus 830.
The memory 820 stores machine-readable instructions executable by the processor 810, when the electronic device 800 runs, the processor 810 and the memory 820 communicate through the bus 830, and when the machine-readable instructions are executed by the processor 810, the steps in the method embodiments shown in fig. 1 to 5 may be performed.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the method embodiments shown in fig. 1 to 5 may be executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for generating a response message is characterized in that a dialog interface for a first user to dialog with a second user is displayed in a graphical user interface of a mobile terminal used by the first user; the generation method comprises the following steps:
when the dialogue message sent by the second user to the first user meets a preset trigger condition, displaying at least one target response material for replying the dialogue message;
responding to the selection operation of the first user on the at least one target response material, and displaying the target response material selected by the first user in an information input box of the dialog interface;
and generating a response message for answering the dialogue message in response to the editing operation of the first user on the target response material displayed in the information input box.
2. The generation method according to claim 1, wherein the dialog message satisfying a preset trigger condition comprises: the dialog message comprises preset keywords and reply operation of the first user to the dialog message.
3. The generation method of claim 2, wherein prior to displaying at least one targeted response material for replying to the dialog message, the generation method further comprises:
performing content identification on the conversation message, and determining a conversation intention of the conversation message;
and extracting at least one target response material from a pre-constructed material library by using a pre-constructed material recommendation model based on the preset keywords and the conversation intention.
4. The method of generating as claimed in claim 3, wherein after extracting at least one target response story from a pre-built story library using a pre-built story recommendation model, the method further comprises:
and displaying a material selection control in an input method interface in the dialog interface of the first user, so that at least one target response material is displayed on the dialog interface of the first user.
5. The generation method of claim 4, wherein the reply operation of the first user to the dialog message comprises:
and the first user selects the material selection control to display at least one target response material indicated by the material selection control in the dialog interface of the first user.
6. The method of generating as claimed in claim 3, wherein after responding to the first user's selection of the at least one targeted response material, the method further comprises:
binding at least one target response material selected by the first user with the dialogue message to serve as an optimized training sample of the material recommendation model; the optimization training sample is used for optimizing model parameters of the material recommendation model.
7. A response message generation device is characterized in that a dialogue interface for a first user to dialogue with a second user is displayed in a graphical user interface of a mobile terminal used by the first user; the generation device comprises:
the material display module is used for displaying at least one target response material for replying the dialogue message when the dialogue message sent by the second user to the first user meets a preset trigger condition;
the display module is used for responding to the selection operation of the first user on the at least one target response material, and displaying the target response material selected by the first user in an information input box of the conversation interface;
and the message generating module is used for responding to the editing operation of the first user aiming at the target response material displayed in the information input box and generating a response message for answering the dialogue message.
8. The generation apparatus of claim 7, further comprising a sample generation module configured to:
binding at least one target response material selected by the first user with the dialogue message to serve as an optimized training sample of the material recommendation model; the optimization training sample is used for optimizing model parameters of the material recommendation model.
9. An electronic device, comprising: processor, memory and bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is run, the machine-readable instructions when executed by the processor performing the steps of the generation method according to any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, performs the steps of the generation method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015147.4A CN113794623A (en) | 2021-08-31 | 2021-08-31 | Method and device for generating response message, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015147.4A CN113794623A (en) | 2021-08-31 | 2021-08-31 | Method and device for generating response message, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113794623A true CN113794623A (en) | 2021-12-14 |
Family
ID=79182467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111015147.4A Pending CN113794623A (en) | 2021-08-31 | 2021-08-31 | Method and device for generating response message, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113794623A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115460555A (en) * | 2022-09-01 | 2022-12-09 | 中国银行股份有限公司 | 5G message response processing method and device |
| CN115514728A (en) * | 2022-09-27 | 2022-12-23 | 平安科技（深圳）有限公司 | Message pushing method and device, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100332218A1 (en) * | 2009-06-29 | 2010-12-30 | Nokia Corporation | Keyword based message handling |
| CN109032381A (en) * | 2018-08-01 | 2018-12-18 | 平安科技（深圳）有限公司 | A kind of input method based on context, device, storage medium and terminal |
| CN110580342A (en) * | 2019-09-19 | 2019-12-17 | 苏州思必驰信息科技有限公司 | public number question-answer response method and device |
| CN111625632A (en) * | 2020-04-17 | 2020-09-04 | 北京捷通华声科技股份有限公司 | Question-answer pair recommendation method, device, equipment and storage medium |
| CN111741104A (en) * | 2020-06-18 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Method for determining response message, method for configuring response message, device, equipment and storage medium |
| CN111767371A (en) * | 2020-06-28 | 2020-10-13 | 微医云(杭州)控股有限公司 | Intelligent question and answer method, device, equipment and medium |
| CN112118169A (en) * | 2019-06-21 | 2020-12-22 | 腾讯科技（深圳）有限公司 | Message reply method, device, terminal and storage medium |
| CN112118168A (en) * | 2019-06-21 | 2020-12-22 | 腾讯科技（深圳）有限公司 | Message sending method, device, terminal and storage medium |
-
2021
- 2021-08-31 CN CN202111015147.4A patent/CN113794623A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100332218A1 (en) * | 2009-06-29 | 2010-12-30 | Nokia Corporation | Keyword based message handling |
| CN109032381A (en) * | 2018-08-01 | 2018-12-18 | 平安科技（深圳）有限公司 | A kind of input method based on context, device, storage medium and terminal |
| CN112118169A (en) * | 2019-06-21 | 2020-12-22 | 腾讯科技（深圳）有限公司 | Message reply method, device, terminal and storage medium |
| CN112118168A (en) * | 2019-06-21 | 2020-12-22 | 腾讯科技（深圳）有限公司 | Message sending method, device, terminal and storage medium |
| CN110580342A (en) * | 2019-09-19 | 2019-12-17 | 苏州思必驰信息科技有限公司 | public number question-answer response method and device |
| CN111625632A (en) * | 2020-04-17 | 2020-09-04 | 北京捷通华声科技股份有限公司 | Question-answer pair recommendation method, device, equipment and storage medium |
| CN111741104A (en) * | 2020-06-18 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Method for determining response message, method for configuring response message, device, equipment and storage medium |
| CN111767371A (en) * | 2020-06-28 | 2020-10-13 | 微医云(杭州)控股有限公司 | Intelligent question and answer method, device, equipment and medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115460555A (en) * | 2022-09-01 | 2022-12-09 | 中国银行股份有限公司 | 5G message response processing method and device |
| CN115514728A (en) * | 2022-09-27 | 2022-12-23 | 平安科技（深圳）有限公司 | Message pushing method and device, computer equipment and storage medium |
| CN115514728B (en) * | 2022-09-27 | 2024-05-03 | 平安科技（深圳）有限公司 | Message pushing method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113794623A (en) | Method and device for generating response message, electronic equipment and storage medium | |
| CN108595520B (en) | Method and device for generating multimedia file | |
| CN113360622A (en) | User dialogue information processing method and device and computer equipment | |
| CN109388506B (en) | Data processing method and electronic equipment | |
| CN109739974B (en) | Recommendation information acquisition method and device and storage medium | |
| JP7183600B2 (en) | Information processing device, system, method and program | |
| CN104346396A (en) | Data processing method, device, terminal and system of instant messaging client | |
| CN113379398B (en) | Project requirement generation method and device, electronic equipment and storage medium | |
| CN104915359A (en) | Theme label recommending method and device | |
| CN106899755B (en) | Information sharing method, information sharing device and terminal | |
| CN109189293B (en) | Evaluation interaction method and device for rich media content, electronic equipment and storage medium | |
| WO2022007798A1 (en) | Data display method and apparatus, terminal device and storage medium | |
| CN113362045A (en) | Conference schedule generation method and device, electronic equipment and readable storage medium | |
| CN112328905A (en) | Online marketing content pushing method and device, computer equipment and storage medium | |
| CN115033675A (en) | Conversation method, conversation device, electronic equipment and storage medium | |
| CN109683727A (en) | A kind of data processing method and device | |
| US11562121B2 (en) | AI driven content correction built on personas | |
| CN110535749B (en) | Dialogue pushing method and device, electronic equipment and storage medium | |
| CN115080039A (en) | Front-end code generation method, device, computer equipment, storage medium and product | |
| CN109254712B (en) | Information processing method and electronic equipment | |
| CN112527991A (en) | Information processing method, apparatus and medium | |
| CN112597760A (en) | Method and device for extracting domain words in document | |
| CN110737828A (en) | information pushing method and related device | |
| CN111897990A (en) | Method, device and system for acquiring expression information | |
| KR102160143B1 (en) | Electronic device for perfoming an analysis of a topic using a deep learning model a and machine learning model and method for operating thereof |
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 |