CN113111264B

CN113111264B - Interface content display method and device, electronic equipment and storage medium

Info

Publication number: CN113111264B
Application number: CN202110662144.3A
Authority: CN
Inventors: 邓锐涛; 常向月; 刘云峰
Original assignee: Shenzhen Zhuiyi Technology Co Ltd
Current assignee: Shenzhen Zhuiyi Technology Co Ltd
Priority date: 2021-06-15
Filing date: 2021-06-15
Publication date: 2021-09-07
Anticipated expiration: 2041-06-15
Also published as: CN113111264A

Abstract

The embodiment of the application provides an interface content display method and device, electronic equipment and a storage medium, and relates to the technical field of information. The method comprises the following steps: acquiring a push content list, wherein the push content list comprises a plurality of preset push contents; acquiring each user message input by a historical user; performing semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content; and determining target push content in the plurality of preset push contents according to the data of the user message matched with each preset push content, wherein the target push content is used for being pushed and displayed on a conversation interface of the current user. The target push content of the current user can be determined in the preset push content according to the user information of the historical user, so that the target push content is more consistent with the user intention of the current user, accurate push is realized, and the user experience is improved.

Description

Interface content display method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of information technologies, and in particular, to an interface content display method and apparatus, an electronic device, and a storage medium.

Background

With the development of internet technology, intelligent customer service technology establishes a fast and effective communication mode based on natural language for enterprises and mass users, and is widely applied in various industries at present. The intelligent customer service can push and display preset push content in the process of interacting with the user, for example, the push content can be commodity service of an enterprise. However, the current pushing mode is single, pushing content needing to be displayed needs to be manually set, the pushing content is fixed, and user experience is poor.

Disclosure of Invention

In view of the foregoing problems, the present application provides an interface content display method, an interface content display apparatus, an electronic device, and a storage medium to improve the above drawbacks.

In a first aspect, an embodiment of the present application provides an interface content display method, including: acquiring a push content list, wherein the push content list comprises a plurality of preset push contents; acquiring each user message input by a historical user; performing semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content; and determining target push content in the plurality of preset push contents according to the data of the user message matched with each preset push content, wherein the target push content is used for being pushed and displayed on a conversation interface of the current user.

Further, the target push content includes a preset text, and after determining the target push content in the plurality of preset push contents according to the data of the user message matched with each preset push content, the method further includes: acquiring an image template corresponding to the target push content and the preset text; synthesizing the image template and the preset text to obtain a target image; and sending the target image to the dialog interface of the current user.

Further, the determining, according to the data of the user message matched with each of the preset push contents, a target push content in the plurality of preset push contents includes: according to the number of the user messages matched with each preset push content, sequencing the preset push contents in a descending order; and determining the preset push content ranked at the top as the target push content.

Further, the performing semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content includes: acquiring entity words contained in each preset push content; acquiring entity representation corresponding to each entity word and semantic representation corresponding to each user message; matching each entity representation with each semantic representation to obtain the confidence that each user message contains each entity word; if the confidence is greater than a specified threshold, judging that the preset push content corresponding to the entity word is matched with the user message; and acquiring the data of the user message matched with each preset push content.

Further, if the confidence is greater than a specified threshold, determining that the preset push content corresponding to the entity word matches the user message, including: if the confidence is greater than the designated threshold, performing emotion analysis on the user message according to the entity words to obtain the emotion polarity of the user message on the entity words; and if the emotion polarity is positive emotion, judging that the preset push content corresponding to the entity word is matched with the user message.

Further, the obtaining data of the user message matched with each preset push content includes: judging whether the historical user corresponding to the user message interacts with the preset push content or not for the user message matched with each preset push content; if yes, determining the weight value of the user message as a first numerical value; if not, determining the weight value of the user message as a second numerical value, wherein the first numerical value is larger than the second numerical value; weighting and summing the number of the user messages matched with each preset push content to obtain a recommendation value of each preset push content; the determining, according to the data of the user message matched with each of the preset push contents, a target push content in the plurality of preset push contents includes: sorting the plurality of preset push contents in a descending order according to the recommended values; and determining the preset push content ranked at the top as the target push content.

Further, prior to said obtaining each user message of historical user input, the method further comprises: acquiring an entrance identifier of the dialog interface of the current user; acquiring a plurality of historical dialog logs corresponding to the entry identifier, wherein the plurality of historical dialog logs comprise user messages input by a plurality of historical users; the obtaining of each user message of the historical user input comprises: extracting each user message of the plurality of historical user inputs in the plurality of historical dialog logs.

Further, the performing semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content includes: acquiring entity words contained in each preset push content, and determining a service type identifier of each preset push content according to the entity words; acquiring a target service type corresponding to the entrance identifier; screening the plurality of preset push contents in the push content list according to the target service type to obtain a target push content list, wherein the target push content list comprises at least one preset push content of which the service type identification is matched with the target service type; and performing semantic recognition on the at least one preset push content in the target push content list and each user message to obtain the number of the user messages matched with the at least one preset push content in the target push content list.

Further, the obtaining of each user message of the historical user input includes: every preset time interval, acquiring each user message of the appointed time input by the historical user; the semantic recognition of each preset push content and each user message to obtain the data of the user message matched with each preset push content includes: performing semantic recognition on each preset push content and each user message at the appointed time to obtain data of the user message at the appointed time matched with each preset push content; the determining, according to the data of the user message matched with each of the preset push contents, a target push content in the plurality of preset push contents includes: and updating the target push content according to the data of the user message at the appointed time matched with each preset push content.

In a second aspect, an embodiment of the present application provides an interface content display method, including: the method comprises the steps that a server obtains a push content list, wherein the push content list comprises a plurality of preset push contents; the server acquires each user message input by a historical user; the server carries out semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content; the server determines target push contents in the plurality of preset push contents according to the data of the user message matched with each preset push content; if the terminal equipment detects a conversation request of a current user, acquiring the target push content from a server; and the terminal equipment displays the target push content on a conversation interface.

Further, the target push content includes a preset text, the terminal stores an image template, and the terminal device displays the target push content on a dialog interface, including: the terminal equipment acquires the preset text and the image template; the terminal equipment synthesizes the image template and the preset text to obtain a target image; and the terminal equipment displays the target image on the conversation interface.

Further, the target push content is linked to a preset interface, and after the target push content is displayed on the dialog interface, the method further includes: and if the terminal equipment detects the touch operation of the current user on the target image, switching the conversation interface to the preset interface.

In a third aspect, an embodiment of the present application provides an interface content display apparatus, including: the device comprises a list acquisition module, a push content acquisition module and a push content display module, wherein the list acquisition module is used for acquiring a push content list which comprises a plurality of preset push contents; the message acquisition module is used for acquiring each user message input by a historical user; the semantic recognition module is used for performing semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content; and the content determining module is used for determining target push content in the plurality of preset push contents according to the data of the user message matched with each preset push content, wherein the target push content is used for being pushed and displayed on a conversation interface of the current user.

Further, the target push content includes a preset text, and after determining the target push content in the plurality of preset push contents according to the data of the user message matched with each preset push content, the interface content display apparatus further includes: the image template acquisition module is used for acquiring an image template corresponding to the target push content and the preset text; the target image synthesis module is used for synthesizing the image template and the preset text to obtain a target image; and the image sending module is used for sending the target image to the conversation interface of the current user.

Further, the content determination module includes: the first sequencing submodule is used for sequencing the plurality of preset push contents in a descending order according to the number of the user messages matched with each preset push content; and a first target content determining submodule, configured to determine a preset push content ranked in the top as the target push content.

Further, the semantic recognition module comprises: the entity word obtaining submodule is used for obtaining entity words contained in each preset push content; the representation acquisition module is used for acquiring entity representations corresponding to each entity word and semantic representations corresponding to each user message; the confidence coefficient acquisition sub-module is used for matching each entity representation with each semantic representation to obtain the confidence coefficient of each user message containing each entity word; the confidence judgment submodule is used for judging that the preset push content corresponding to the entity word is matched with the user message if the confidence is greater than a specified threshold; and the data acquisition submodule is used for acquiring the data of the user message matched with each preset push content.

Further, the confidence level judgment sub-module includes: an emotion polarity acquisition unit, configured to perform emotion analysis on the user message according to the entity word if the confidence is greater than the specified threshold, to obtain an emotion polarity of the user message on the entity word; and the positive emotion judging unit is used for judging that the preset push content corresponding to the entity word is matched with the user message if the emotion polarity is positive emotion.

Further, the data acquisition sub-module includes: the interaction judging unit is used for judging whether the historical user corresponding to the user message interacts with the preset push content or not for the user message matched with each preset push content; a first numerical value determining unit, configured to determine, if yes, a weight value of the user message as a first numerical value; a second value determining unit, configured to determine, if the user message is not a first value, the weight value of the user message as a second value, where the first value is greater than the second value; the weighted summation unit is used for carrying out weighted summation on the number of the user messages matched with each preset push content to obtain a recommended value of each preset push content; the content determination module includes: the second sorting submodule is used for sorting the plurality of preset push contents in a descending order according to the recommended value; and the second target content determining submodule is used for determining the preset push content which is sequenced at the top as the target push content.

Further, before said obtaining each user message of the historical user input, the interface content display apparatus further comprises: an entry identifier obtaining module, configured to obtain an entry identifier of the dialog interface of the current user; the dialogue log acquisition module is used for acquiring a plurality of historical dialogue logs corresponding to the entry identifier, and the historical dialogue logs comprise user messages input by a plurality of historical users; the message acquisition module comprises a message extraction submodule for extracting each user message input by the plurality of historical users in the plurality of historical dialog logs.

Further, the semantic recognition module comprises: the content identification determining submodule is used for acquiring entity words contained in each preset push content and determining the service type identification of each preset push content according to the entity words; a service type determining submodule, configured to obtain a target service type corresponding to the entry identifier; a list screening submodule, configured to screen the multiple preset push contents in the push content list according to the target service type, so as to obtain a target push content list, where the target push content list includes at least one preset push content whose service type identifier matches the target service type; and the message matching sub-module is used for performing semantic recognition on the at least one preset push content in the target push content list and each user message to obtain the number of the user messages matched with the at least one preset push content in the target push content list.

Further, the message obtaining module comprises a message updating submodule for obtaining each user message of the designated time input by the historical user at each preset time interval; the system comprises a semantic recognition module and a data updating sub-module, wherein the semantic recognition module is used for performing semantic recognition on each preset push content and each user message at the appointed time to obtain data of the user message at the appointed time matched with each preset push content; the content determining module comprises a content updating submodule and is used for updating the target push content according to the data of the user message of the appointed time matched with each preset push content.

In a fourth aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the methods of the first or second aspects described above.

In a fifth aspect, embodiments of the present application provide a computer-readable storage medium, in which program code is stored, and the program code can be called by a processor to execute the method according to the first aspect or the second aspect.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic diagram of an application environment suitable for use in embodiments of the present application;

FIG. 2 illustrates an interactive interface of a client application provided by an embodiment of the present application;

FIG. 3 illustrates a dialog interface of a client application provided by an embodiment of the present application;

FIG. 4 is a flowchart illustrating an interface content display method according to an embodiment of the present disclosure;

FIG. 5 is a flowchart illustrating an interface content display method according to another embodiment of the present application;

FIG. 6 is a flow chart illustrating a method for displaying interface content according to another embodiment of the present application;

FIG. 7 shows a schematic flow chart of step S460 in FIG. 6;

fig. 8 shows a schematic flow chart of step S470 in fig. 6;

FIG. 9 is a flowchart illustrating an interface content display method according to yet another embodiment of the present application;

FIG. 10 shows a flowchart of step S550 in FIG. 9;

FIG. 11 is a process diagram illustrating an interface content display method according to an embodiment of the present disclosure;

FIG. 12 is a flowchart illustrating an interface content display method according to a further embodiment of the present application;

FIG. 13 is a flowchart illustrating an interface content display method according to yet another embodiment of the present application;

FIG. 14 is a flow chart illustrating an interface content display method according to yet another embodiment of the present application;

fig. 15 is a block diagram illustrating a structure of an interface content display apparatus according to an embodiment of the present application;

fig. 16 is a block diagram illustrating a structure of an electronic device according to an embodiment of the present application, the electronic device being configured to execute an interface content display method according to an embodiment of the present application;

fig. 17 illustrates a storage unit for storing or carrying program codes for implementing the interface content display method according to the embodiment of the present application.

Detailed Description

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 of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

With the development of science and technology, artificial intelligence technology is more and more popular, and services such as appointments, consultations and the like in daily life are changed from artificial services to machine services. Compared with manual service, the service efficiency is greatly improved through machine service, and great convenience is brought to daily life of people.

The intelligent customer service can provide services for the user in a way of conversation with the user. Specifically, the user may input a question on a dialog interface that has a dialog with the smart customer service, and the smart customer service may recognize the question input by the user based on natural language understanding and push an answer to the user. In the conversation process, the intelligent customer service can display preset push content on a conversation interface. For example, the preset push content may be an advertisement in the form of a picture or text. However, the preset push content is usually set manually by service personnel, a large amount of labor cost is consumed, and the push content is usually fixed, so that the user experience is not good.

In order to improve the above problem, the inventor proposes an interface content display method, an apparatus, an electronic device, and a storage medium in the embodiments of the present application. The user information input by each historical user is obtained in the service process of the intelligent customer service. Because the user message can reflect the real interactive intention of the user, the selection of the push content can be guided according to the user message input by the historical user, and the content needing to be pushed is determined in the preset push content, so that the push content is more in line with the intention of the user.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating an application environment suitable for the embodiment of the present application. The interface content display method provided by the embodiment of the application can be applied to the interface content display system 10 shown in fig. 1. The interface content display system 10 includes at least one terminal device 100 and a server 200, the terminal device 100 and the server 200 are located in a wireless network or a wired network, and the terminal device 100 and the server 200 perform data interaction, where the interaction data includes, but is not limited to, audio, video, text, images, and the like.

The terminal device 100 may be a mobile terminal device, and may include, for example, a smart phone, a tablet computer, an e-book reader, a laptop portable computer, a vehicle-mounted computer, a wearable mobile terminal, and so on. The server 200 may be an individual server, a server cluster, a server center formed by a plurality of servers, a local server, or a cloud server. The server 200 may be used to provide a background service for the user, which may include, but is not limited to, push content, and the like.

In some embodiments, the terminal device 100 may have a client application installed thereon, and the user may communicate with the server 200 based on the client application (e.g., APP, etc.). Specifically, the terminal device 100 may obtain input information of a user, and based on a client application program on the terminal device 100 communicating with the server 200, the server 200 may process the received input information of the user, and the server 200 may further return corresponding output information to the terminal device 100 according to the information, and the terminal device 100 may perform an operation corresponding to the output information. The input information of the user may be voice information, touch operation information based on a screen, gesture information, action information, and the like, and the output information may be an image, a video, a text, an audio, and the like, which is not limited herein.

Specifically, the client application program on the terminal device includes a plurality of interactive interfaces, different contents are displayed on different interactive interfaces, an icon or a key of a session entry may be set on the interactive interface, and the current interactive interface may be switched to the session interface in response to a trigger operation of a user on the session entry. That is, the dialog interface of the current user is the next level interface of the current interactive interface. For example, fig. 2 illustrates an interactive interface of a client application provided by an embodiment of the present application. The interactive interface in fig. 2 is a card application interface, and a "customer service" button is displayed at the upper end of the card application interface, and is used for responding to the operation of the button by the user, that is, a conversation request of the user, and entering a conversation interface of the intelligent customer service. As shown in fig. 3, fig. 3 illustrates a dialog interface of a client application provided by an embodiment of the present application. The dialog interface of fig. 3 is provided with a preset display area for displaying preset push content, for example, the push content may be advertisement content of "card a" and "card B" in text or picture form. Optionally, when an interactive operation of the user on the push content in the preset display area is obtained, for example, a click operation or a voice control instruction, the details of the push content may be displayed on the current dialog interface, and the current dialog interface may also be skipped to the details of the push content.

The server 200 is capable of collecting user data of a user at a client application, and in particular, the user data may include a portal identifier corresponding to a user session request, and a session log of the user. Alternatively, the server 200 may push information for the user of the terminal device 100 according to the collected dialog logs; the server 200 may also transmit the collected conversation log to the terminal device 100 so that the terminal device 100 determines push information from the conversation log.

The above application environments are only examples for facilitating understanding, and it is to be understood that the embodiments of the present application are not limited to the above application environments.

The following describes in detail interface content display methods, apparatuses, electronic devices, and media provided in embodiments of the present application with specific embodiments.

Referring to fig. 4, fig. 4 is a schematic flowchart of an interface content display method according to an embodiment of the present application, and is applied to the server. The interface content display method includes S210 to S240.

S210: and acquiring a push content list.

The push content list comprises a plurality of preset push contents. The preset push content is preset content information waiting to be pushed to the terminal equipment. The preset push content may be presented in a variety of media forms. For example, the preset push content may be video, images, text, audio, and the like.

Alternatively, the push content list may be obtained in a variety of ways. The push content list may be entered by the business person. For example, the preset push content may be advertisement content information. The push content list may be content automatically obtained over a network. For example, the preset push content may be news information or the like read from the internet by a crawler.

In some implementations, the push content list can include description information for describing the preset push content. For example, the description information may include text information such as a title, an abstract, a comment, a service identifier, a detailed description, and may also include information such as an image and a link.

S220: each user message of historical user input is obtained.

The historical user is a user who uses the dialogue interface to carry out dialogue, and the user message is historical user message input by the historical user. For example, user a and user B have used the dialog interface to have a dialog, and both user a and user B are history users. It will be appreciated that when the current user is user a, the user messages that user a has previously entered using the conversation interface will also be identified as each user message that was entered by the historical user.

In some embodiments, similar users close to the current user can be screened from historical users according to the user characteristic information, and the user messages input by the similar users are determined as the user messages input by each historical user. Wherein, the user characteristic information may be user identity information, such as gender, age, region, etc.; the user characteristic information can also be user behavior information, such as purchasing behavior, browsing records and the like; the user may also be a user portrait obtained by combining user identity information and user behavior information.

In some implementations, the server can obtain each user message of the historical user input by reading a historical conversation log of the conversation interface. The historical conversation logs are in a text format, and each historical conversation log records a real conversation process between a historical user and the intelligent/artificial customer service. Alternatively, the server may directly read the dialog log in the text format from the database, or may record the dialog in the voice format, and obtain the dialog log in the text format through voice recognition.

It is to be understood that the user message is not limited to the message input during the customer service session, and may be the user message input in other scenarios. For example, the user message may be answer text input by the user under the question and answer platform, or may be chat text, etc.

S230: and performing semantic recognition on each preset push content and each user message to obtain the data of the user message matched with each preset push content.

The server can obtain the matching relation between the preset push content and the user message based on semantic identification, obtain the data of the user message matched with each preset push content according to the matching relation, and the data can represent the recommendation degree of the preset push content.

As an embodiment, the data may characterize the hotness of the preset push content. For example, the data may be the number of user messages matched with each preset push content, may be the percentage of the number of user messages matched with each preset push content to the total number of user messages, and may be the number of historical users matched with each preset push content. As another embodiment, the data may also be a recommended value obtained according to the user message and a preset rule. For example, the user messages may be given different weights according to the historical user behavior, and the recommendation values may be obtained by weighting and summing the matched user messages. Specifically, please refer to the following embodiments.

In some embodiments, the server may extract semantic feature vectors for each preset push content and each user message based on the semantic recognition model, and obtain the user message matched with each preset push content by matching the semantic feature vectors. Specifically, word segmentation processing may be performed on the user message to obtain a word sequence, and feature extraction may be performed on the spliced word sequence to obtain a semantic feature vector corresponding to the user message, where the semantic feature vector may represent the semantics of the user message. Likewise, a semantic feature vector of the preset push content can be obtained. And obtaining semantic similarity based on the semantic feature vectors of the preset push content and the user message, and if the semantic similarity is greater than a preset threshold, judging that the preset push content is matched with the user message.

In some embodiments, each preset push content corresponds to at least one entity word, and the matching relationship between the preset push content and the user message may be determined based on entity identification.

As an embodiment, the server may perform keyword matching on each user message according to the entity words. And if the user message contains the entity word, judging that the user message is matched with the preset push content corresponding to the entity word.

As another embodiment, the server may obtain entity words included in each preset push content, obtain entity representations corresponding to each entity word and semantic representations corresponding to each user message, match each entity representation with each semantic representation, obtain a confidence level that each user message includes each entity word, and determine that the preset push content corresponding to the entity word matches the user message if the confidence level is greater than a specified threshold. Specifically, please refer to the following embodiments.

In some embodiments, after the user message is acquired, if a preset standard text matching the user message exists in the preset knowledge base, the user message is updated to the preset standard text. The preset standard text is a text with a standard format and content and can be accurately identified, so that the accuracy of semantic identification and matching is improved.

S240: and determining target push contents in the plurality of preset push contents according to the data of the user message matched with each preset push content.

The target push content is used for being pushed and displayed on a conversation interface of a current user. According to the data of the user message matched with each preset push content, the preset push contents in the push content list can be sequenced, and the specified number of the preset push contents with higher recommendation degree is determined as the target push contents. The target push content may be one preset push content with the highest recommendation degree, or may be multiple preset push contents. The specified number may be a number configured by an operator, or may be a maximum number that can be displayed on the dialog interface, where the number of the preset push contents in the target push contents is not limited.

In some embodiments, the plurality of preset push contents may be sorted in a descending order according to the number of user messages matched with each preset push content; and determining the preset push content ranked at the top as the target push content. The number of the preset push contents can represent the popularity of the preset push contents, the push contents ranked in the front are the preset push contents with higher popularity, and the user may be more interested in the preset push contents. Specifically, the target push content may be a specified number of preset push contents ordered top. Alternatively, the specified number may be one, that is, the preset push content with the largest number of matched user messages is determined as the target push content.

In some embodiments, when the target push content includes a plurality of preset push contents, the user characteristic information of the current user may be acquired, one preset push content is screened from the plurality of preset push contents according to the user characteristic information, and the screened preset push content is pushed to the terminal device and displayed, so that more targeted push is realized. The user characteristic information may include at least one of user identity information, user behavior information, user representation, and the like.

According to the interface content display method provided by the embodiment of the application, a push content list is obtained, and the push content list comprises a plurality of preset push contents; acquiring each user message input by a historical user; performing semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content; and determining target push content in the plurality of preset push contents according to the data of the user message matched with each preset push content, wherein the target push content is used for being pushed and displayed on a conversation interface of the current user, and the push content pushed to the current user can be determined according to the user message input by the historical user, so that the push content is more in line with the intention of the user, and the pushing accuracy is improved.

Referring to fig. 5, fig. 5 is a schematic flowchart of an interface content display method according to an embodiment of the present application, and is applied to the server. The interface content display method includes S310 to S370.

S310: and acquiring a push content list.

S320: each user message of historical user input is obtained.

S330: and performing semantic recognition on each preset push content and each user message to obtain the data of the user message matched with each preset push content.

S340: and determining target push contents in the plurality of preset push contents according to the data of the user message matched with each preset push content.

S350: and acquiring an image template and a preset text corresponding to the target push content.

The targeted push content may include preset text. The preset text may be description information of the preset push content. For example, the preset text may be text information such as a title of the preset push content.

The server stores at least one image template for generating an image. When the number of the image templates is plural, after the target push content is determined, the image template may be determined among a plurality of templates according to the target push content. For example, an appropriate image template may be determined according to the service type of the target push content, preset text, and other information. The image template may have a preset background image, the background image may also be adjusted as needed, and the image template may be added with contents such as characters, images, symbols, links, and the like to obtain an image with the contents.

In some embodiments, the preset text of the target push content may be generated based on a text generation model according to the target push content and the matched user message. Because the user message is a text actually input by the historical user, the preset text generated according to the user message can better accord with the preference of the user.

S360: and synthesizing the image template and the preset text to obtain the target image.

The image template can be provided with a preset text filling area, and a preset text can be filled into the text filling area to generate a target image containing the preset text. Optionally, a link corresponding to the target push content may also be acquired, and the link is added to the target image. The link may be invisible, and when a touch operation of the user on the target image is detected, the interface corresponding to the link may be skipped to. For example, the interface after jumping may be a detail interface of the target push content, and the like.

In some embodiments, the text length of the preset text may be obtained, font attributes of the preset text, such as font style, font size, color, and the like, and an arrangement manner of the preset text, such as line feed, space, alignment manner, and the like, may be determined according to the text length and the text filling area size of the image template.

In some embodiments, a picture corresponding to the target push content may also be obtained, and the picture is determined as a foreground image. And adding the foreground image and a preset text in the image template to obtain a target image. For example, the target push content is a financial product a, the preset text is a title "financial product a" and an abstract "high benefit, low risk", and the picture corresponding to the target push content is a mark of the financial product a. The server can synthesize information such as titles, abstracts and pictures into a picture through the image template, and add connection corresponding to the detailed interface of the financial product A on the picture, so that the target image is obtained.

By means of automatic synthesis of the target image, the image corresponding to the preset push content can be generated according to the preset text and the image template without manual intervention, image generation efficiency is improved, and cost is reduced. It can be understood that, in the process of generating the target image, adjustment can be performed according to needs, so that the method is more flexible.

S370: and sending the target image to the conversation interface of the current user.

The server can send the target image to the conversation interface of the current user and display the target image on the conversation interface. In some embodiments, when the target image includes the link, if the terminal device detects a touch operation of the user on the target image, the server may push and display an interface corresponding to the link to the terminal device.

It should be noted that, for portions of the foregoing method steps that are not described in detail, please refer to the foregoing embodiments, and further description is omitted here.

According to the interface content display method provided by the embodiment of the application, a push content list is obtained; acquiring each user message input by a historical user; performing semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content; determining target push contents in a plurality of preset push contents according to the data of the user message matched with each preset push content; acquiring an image template and a preset text corresponding to target push content; synthesizing an image template and a preset text to obtain a target image; and the target image is sent to the conversation interface of the current user, so that the target image corresponding to the pushed content can be automatically generated, the cost of manually making the image is reduced, and the use experience of the user is improved.

Referring to fig. 6, fig. 6 is a schematic flowchart of an interface content display method according to an embodiment of the present application, and is applied to the server. The interface content display method includes S410 to S480.

S410: and acquiring a push content list.

S420: each user message of historical user input is obtained.

S430: and acquiring entity words contained in each preset push content.

Each preset push content in the preset push list corresponds to an entity, and the entity word is a word corresponding to the entity. An entity may generally refer to a particular thing, subject, and supporter of a phenomenon, etc., such as a person's name, a thing name, a place name, an organization name, a concept, etc.

In some embodiments, a dictionary including a plurality of core entity words may be preset, and the core entity words are used as entity words to be acquired. The core entity word may reflect the core of the preset push content. For example, in a credit card push scenario, a "gold card" is set as a core entity word, a preset push content "gold card can enjoy supermarket discount" in which "gold card" will be determined as an entity word, and "supermarket" does not serve as an entity word.

In some implementations, the at least one entity word included in the preset push content can be identified based on natural language understanding. As one approach, recognition of entity words based on preset semantic and grammatical rules may be employed. As another way, an unsupervised learning method may be adopted to identify entity words contained in the preset push content. Specifically, different clusters can be obtained according to the text similarity based on a clustering method, and represent category groups corresponding to different entity words. As yet another way, entity words corresponding to the preset push content may be identified based on the deep learning model. In other embodiments, at least one entity word may be marked by manually labeling each preset push content.

In some embodiments, a dictionary containing generalized words corresponding to entity words may be preset, and the entity words contained in the preset push content may further include the generalized words of the entity words. For example, if the predetermined push content is "diamond card" which is a credit card, the predetermined push content may include the entity words "diamond card" and "credit card".

S440: and acquiring entity representation corresponding to each entity word and semantic representation corresponding to each user message.

Based on the semantic understanding model, the feature vectors corresponding to the entity words and the user messages can be respectively obtained, and the entity representation corresponding to each entity word and the semantic representation corresponding to each user message are obtained. The semantic understanding model can be a Recurrent Neural Networks (RNN), a BERT model, a BilSTM-CRF model, and the like. For different semantic understanding models, the feature vector, namely the entity representation and the semantic representation, can be a word level representation, a character level representation, or a mixed representation introducing information such as word similarity and semantic dependency relationship.

In some embodiments, a dictionary containing entity words of the preset push content may be obtained, the user message is segmented based on the dictionary, a word vector sequence of the user message may be more accurately obtained according to the entity words, and then a semantic representation corresponding to the user message may be obtained according to the word vector sequence.

S450: and matching each entity representation with each semantic representation to obtain the confidence that each user message contains each entity word.

After the entity representation and the semantic representation are obtained, semantic matching can be performed on each entity representation and each semantic representation respectively to obtain the confidence that each user message contains each entity word. The confidence degree can represent how likely the user message contains the entity word corresponding to the entity representation, and the higher the confidence degree is, the more likely the user message contains the entity word is. Alternatively, the confidence level may be derived from semantic similarity between the entity representation and the semantic representation.

In some embodiments, each entity representation may be matched with each semantic representation using a label decoder, and the entity representation and the semantic representation are used as input to obtain a confidence that the semantic representation includes the entity representation, i.e., a confidence that the user message includes the entity word. The label decoder may be a Conditional Random Field (CRF), RNN, Pointer Networks, or the like.

S460: and if the confidence is greater than the specified threshold, judging that the preset push content corresponding to the entity word is matched with the user message.

And if the confidence is greater than the specified threshold, judging that the preset push content corresponding to the entity word is matched with the user message, and if the confidence is less than the specified threshold, filtering the preset push content. Wherein, the designated threshold is a preset threshold in the server.

In some embodiments, as shown in fig. 7, S460 may further include S461 to S462.

S461: and if the confidence coefficient is greater than the specified threshold value, carrying out emotion analysis on the user message according to the entity words to obtain the emotion polarity of the user message on the entity words.

If the confidence is greater than the designated threshold, the server can perform emotion analysis on the user message based on the emotion analysis model to obtain the emotion polarity of the user message on the entity words. Emotion analysis can be used to discover subjective emotions expressed in user messages. The emotion polarity may include positive and negative emotions.

In some embodiments, an emotion dictionary containing emotion words may be constructed in advance. Optionally, the emotion dictionary may further include words related to emotional expressions, such as a degree word, a negative word, and the like. In one embodiment, words such as emotion words may be extracted from the user message based on the emotion dictionary, and the emotion polarity of the user message may be determined according to the extraction result. As another embodiment, the emotion words may be used as feature words, the user messages may be subjected to text matrixing, and the user messages may be classified by means of logistic regression, naive bayes, support vector machines, and the like.

In some implementations, the emotion dictionary can be constructed based on entity words in the preset push content list. Specifically, the emotion words related to the entity words can be determined according to the characteristics of the entities corresponding to the entity words, namely, the entity attributes, so as to construct the emotion dictionary. For example, if the entity word is "credit card" and the entity attributes are card fee and amount, the emotion word related to the card fee can be cheap and expensive, and the emotion word related to the amount can be large, high, low, etc. If the confidence is greater than the designated threshold, determining the emotional words corresponding to the entity words, and further performing emotion analysis on the user message based on the emotional words. The emotion polarity of the user on the entity word can be more accurately acquired by performing emotion analysis on the user message based on the entity attribute.

S462: and if the emotion polarity is positive emotion, judging that the preset push content corresponding to the entity word is matched with the user message.

And when the emotion polarity of the user message to the entity word is positive, judging that the preset push content corresponding to the entity word is matched with the user message. When the emotion polarity is positive emotion, the matching of the push content and the user message is judged, the content push can be carried out by considering the emotion state of the user, the push content which is more consistent with the intention of the user is displayed, and the user experience is improved.

S470: and acquiring the data of the user message matched with each preset push content.

Please refer to step S330 for a specific implementation of obtaining data of the user message matched with each preset push content, which is not described herein again.

In some embodiments, as shown in fig. 8, S470 may further include S471 to S474.

S471: judging whether a history user corresponding to the user message interacts with the preset push content or not for the user message matched with each preset push content;

for the user message matched with each preset push content, the user behavior information of the historical user corresponding to the user message can be acquired. According to the user behavior information, whether the historical user performs interactive operation with preset push content or not can be judged. The interactive operation can be clicking, browsing, purchasing, commenting and the like. Alternatively, the interactive operation may be an operation actively initiated by the historical user, such as a purchase operation, and the actively initiated operation may more accurately indicate that the historical user is interested in the preset push content.

S472: if yes, determining the weight value of the user message as a first numerical value.

And if the historical user corresponding to the user message interacts with the preset push content, determining the weight value of the user message as a first numerical value.

S473: if not, determining the weight value of the user message as a second numerical value, wherein the first numerical value is larger than the second numerical value.

And if the historical user corresponding to the user message does not interact with the preset push content, determining the weight value of the user message as a second numerical value. Wherein the first value is greater than the second value. For example, the user message "how this bank card handles

The kinds of the 'and' bank cards

"all contain the entity word" bank card ", how this bank card handles

"the user clicks the bank card displayed on the dialogue interface to transact, then the user message is given with the weight value with larger numerical value," which kinds of bank cards are

"if the user does not have a bank card, the user message is given a weight value with a smaller numerical value.

S474: and carrying out weighted summation on the number of the user messages matched with each preset push content to obtain a recommendation value of each preset push content.

According to the weighted value of the user message, the number of the user messages matched with each preset push content can be weighted and summed to obtain the recommended value of each preset push content. The recommendation value may represent a recommendation level of the preset push content. The interactive user message can show that the user message has strong association with the preset push content, and the recommendation degree of each preset push content can be reflected more accurately by endowing the user message of the historical user who has interacted with the preset push content with a larger weight value.

S480: and determining target push contents in the plurality of preset push contents according to the data of the user message matched with each preset push content.

In some embodiments, when the data is a recommended value, sorting the plurality of preset push contents in a descending order according to the recommended value; and determining the preset push content ranked at the top as the target push content. The detailed implementation is similar to the case when the number of data is equal, please refer to the above embodiments, and further description is omitted here.

Compared with the interface content display method shown in fig. 4, the information push method provided by the embodiment of the application can also obtain entity words contained in each push content; acquiring entity representation corresponding to each entity word and semantic representation corresponding to each user message; matching each entity representation with each semantic representation to obtain the confidence that each user message contains each entity word; if the confidence is greater than the specified threshold, judging that the preset push content corresponding to the entity word is matched with the user message; and acquiring the data of the user message matched with each preset push content. The user intention in the user message can be more accurately acquired through entity identification, the accuracy rate of matching the push content and the user message is improved, and the push content is further more accurately determined.

Referring to fig. 9, fig. 9 is a schematic flowchart of an interface content display method according to an embodiment of the present application, and is applied to the server. The interface content display method includes S510 to S550.

S510: and acquiring a push content list.

S520: and acquiring the entrance identification of the dialog interface of the current user.

The portal identification is used to identify a dialog interface for conducting a dialog with a user. Specifically, each dialog interface corresponds to a dialog entry, the dialog entries are arranged on the upper-level interactive interface of the dialog interface, each dialog entry corresponds to an entry identifier, and the entry identifiers can identify the dialog interfaces which realize dialog with the user.

As an embodiment, each dialog entry has an entry identifier, that is, the user interface and the entry identifier are in a one-to-one correspondence. As another example, multiple conversation portals may correspond to the same portal identification. Wherein the plurality of conversation portals may be interactive interfaces having similar content. For example, the similar contents can be similar service types, the entrance identifications of various credit card application interfaces are the same, and the entrance identifications of various financial product detail interfaces are the same.

S530: and acquiring a plurality of historical dialog logs corresponding to the entry identifiers.

The server may obtain a plurality of conversation logs corresponding to the portal identification, the plurality of historical conversation logs including a plurality of historical user-entered user messages. That is, the server may determine that the entry identifier corresponds to an entry into a dialog interface on the interactive interface, and obtain a plurality of historical dialog logs generated by a plurality of historical users on the dialog interface.

S540: each user message of the plurality of historical user inputs in the plurality of historical dialog logs is extracted.

After obtaining the plurality of historical dialog logs, each user message entered by the plurality of historical users in the plurality of historical dialog logs may be extracted. That is, each of the obtained user messages is a history user message generated by the history user on the dialog interface corresponding to the entry identifier.

It can be understood that, usually, when a user has a problem in the process of interacting with the current interactive interface, the user triggers the dialog entry of the current interactive interface to enter into a dialog interface and customer service dialog. The user conversation intentions corresponding to the same entrance identifier are similar, the preset push contents which the user may be interested in are also similar, and the user message is analyzed according to the entrance identifier, namely the interactive interface, so that the user intention can be determined more accurately, and the push can be performed accurately.

S550: and performing semantic recognition on each preset push content and each user message to obtain the data of the user message matched with each preset push content.

In some embodiments, as shown in fig. 10, S550 may include S551 to S554.

S551: and acquiring entity words contained in each preset push content, and determining the service type identifier of each preset push content according to the entity words.

Each preset push content may correspond to at least one entity word. As an implementation manner, when the preset push content list is set, the preset push content may be manually marked, and the entity word corresponding to each preset push content is accurately obtained through manual marking. As another embodiment, the entity words included in the preset push content may be automatically obtained based on the entity recognition. Specifically, please refer to step S430.

The service type identifier is used for identifying the service type of each preset push content. The service type may be a plurality of service types preset according to the push content list. As an implementation manner, a corresponding relationship between the entity word and the service type may be preset, and after the entity word included in each preset push content is obtained, the service type corresponding to the entity word is determined according to the corresponding relationship, so as to obtain the service type identifier matched with each preset push content. For example, when a named entity word is set, the service type may be determined as an entity category, and after the entity word is obtained, the entity category of the entity word may be determined as the service type. For example, the preset push contents respectively include entity words "deposit card", "credit card" and "supermarket", wherein the service type corresponding to the "deposit card" and the "credit card" is "card", and the service type corresponding to the "supermarket" is "shopping".

In some implementation ways, the topic model is trained according to the service type and the preset push content, and the preset content is classified based on the topic model to obtain the service type identifier of each preset content, so that the service type identifier can be obtained without acquiring an entity word. The topic model may be a Probabilistic Latent Semantic index (PLST) model, Latent Dirichlet Allocation (LDA) model, or the like.

S552: and acquiring a target service type corresponding to the entrance identifier.

The target service type is at least one service type corresponding to the entrance identifier. As an implementation manner, the content of the interactive interface corresponding to the entry identifier may be obtained, and the target service type may be determined by analyzing the service content of the interactive interface corresponding to the entry identifier. For example, the interface content may be analyzed based on the topic model to obtain the target business type. As another way, the user messages corresponding to the entry identifiers may be classified based on the service types, the number of user messages corresponding to each service type is obtained, and the specified number of service types with a larger number is determined as the target service type. As another way, the target service type corresponding to the entry identifier may be manually set.

S553: and screening a plurality of preset push contents in the push content list according to the target service type to obtain a target push content list.

After the target service type is obtained, the preset push content in the push content list can be screened according to the target service type, so that a target push content list is obtained. The target push content list comprises at least one preset push content with the service type identification matched with the target service type. Therefore, the data size needing to be matched can be reduced, and the matching efficiency is improved. For example, when the target service type is "card", the preset push content with the service type identified as "card" in the push content list, that is, the target push content list, is obtained through screening.

S554: and performing semantic recognition on at least one preset push content in the target push content list and each user message to obtain the number of the user messages matched with the at least one preset push content in the target push content list.

Please refer to the foregoing embodiment for a specific implementation of performing semantic recognition on at least one preset push content in the target push content list and each user message, which is not described herein again.

S560: and determining target push contents in the plurality of preset push contents according to the data of the user message matched with each preset push content.

Please refer to the foregoing embodiments for specific implementation of determining a target push content among a plurality of preset push contents, which is not described herein again.

After determining the target push content, the server may push the target push content to a session interface corresponding to the portal identifier. Referring to fig. 11, fig. 11 is a processing diagram illustrating an interface content display method according to an embodiment of the present application. As shown in FIG. 11, the credit card application interface is provided with a dialogue portal "customer service" button, which has a portal identification of 1. The server acquires a plurality of historical conversation logs corresponding to the entry identifier 1, extracts each user information input by a plurality of historical users in the plurality of historical logs, performs semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content, and determines a target push content, namely a card A, in the plurality of preset push contents according to the data. And pushing the target push content to a dialogue interface corresponding to the portal identification 1 for displaying. And the terminal equipment responds to the triggering operation of the user on the conversation inlet of the inlet identifier 1 on the credit card application interface, and switches the current credit card application interface into the conversation interface corresponding to the inlet identifier 1, namely the intelligent customer service interface with the 'card A' displayed. As shown in fig. 5, the shopping mall interface and the personal information interface are also respectively provided with a session entry, and the session entries respectively correspond to entry identifiers, and similarly, target push content corresponding to the entry identifiers can be respectively pushed and displayed for user interfaces corresponding to other entry identifiers.

It can be understood that the target push content on each dialog interface is determined in the preset push content list according to the user message corresponding to the portal identification, different portal identifications can correspond to different target push contents, the user intention of triggering the dialog portal can be hit more accurately, and the push accuracy is improved. In practical application, the process of determining the target push content can be automatically performed by the server, a large number of conversation entries can be launched in a business scene, the conversation scene corresponding to each conversation entry can be divided into fine granularity, the push content on the user interface corresponding to the entry identifier conforms to the intention of the user triggering the conversation entry with a large probability, and the push accuracy can be improved.

Compared with the interface content display method shown in fig. 4, the information push method provided by the embodiment of the application can acquire the entry identifier of the dialog interface of the current user; and acquiring a plurality of historical dialog logs corresponding to the entry identifiers, wherein the plurality of historical dialog logs comprise user messages input by a plurality of historical users. Therefore, the push content of the entrance identifier can be generated more specifically according to the user message of the entrance identifier, and the accuracy of the push content is improved.

Referring to fig. 12, fig. 12 is a schematic flowchart of an interface content display method according to an embodiment of the present application, and is applied to the server. The interface content display method includes S610 to S640.

S610: and acquiring a push content list.

S620: and acquiring each user message of the appointed time input by the historical user at preset time intervals.

The preset time is a preset time interval for updating the acquired user message, and can represent the frequency of updating the user message. The designated time is the preset time length of the acquired dialog log. The preset time and the designated time may be set by the server by default or may be configured by the operator. Alternatively, the server may save the updated user message and remove the previous user message to save storage space. By updating the user message at preset time intervals, the conversation log with better timeliness can be obtained, and data support is provided for accurately determining target push content subsequently. For a specific implementation of obtaining each user message input by the historical user, please refer to the foregoing embodiment, which is not described herein again.

As an embodiment, the specified time may be a length of time from the current time. For example, the preset time is 1 hour, and the specified time is 24 hours from the current time, that is, every 1 hour, the user messages input by the historical users in the past 24 hours are re-read.

In some embodiments, the server may determine whether each user message at a specified time satisfies a preset updating condition, and if so, update the user message. As one way, the preset update condition may be a preset number threshold, and when the number of user messages at a specified time is greater than the number threshold, it is determined that the preset update condition is satisfied. Therefore, when the number of the newly added user messages is small, subsequent processing is not performed, and the data processing efficiency is improved.

S630: and performing semantic recognition on each preset push content and each user message at the appointed time to obtain the data of the user message at the appointed time matched with each preset push content.

The server may perform semantic recognition on each preset push content and each user message at the specified time to obtain data of the user message at the specified time matched with each preset push content, that is, update the data of the user message matched with each preset push content. Specifically, please refer to the foregoing embodiments, which are not described herein again.

S640: and updating the target push content according to the data of the user message at the appointed time matched with each preset push content.

The server can update the target push content according to the data of the user message at the appointed time matched with each preset push content, and push the updated target push content to the terminal equipment. In particular, please refer to the foregoing embodiments. The updating target push content can more accurately capture the time-dependent change of the user intention under the condition of considering the time-dependent information, and the information push accuracy is higher.

According to the interface content display method provided by the embodiment of the application, a push content list is obtained; every preset time interval, acquiring each user message of appointed time input by a historical user; performing semantic recognition on each preset push content and each user message at the appointed time to obtain data of the user message at the appointed time matched with each preset push content; and updating the target push content according to the data of the user message at the appointed time matched with each preset push content. The user information can be updated every preset time, so that the target push content is determined in real time according to the updated user information, and the timeliness of the push content is improved.

Referring to fig. 13, fig. 13 is a schematic flowchart of an interface content display method according to an embodiment of the present application, and is applied to the server and the terminal device. The interface content display method includes S710 to S760.

S710: the server obtains a push content list.

The push content list comprises a plurality of preset push contents.

S720: the server obtains each user message of the historical user input.

S730: and the server carries out semantic recognition on each preset push content and each user message to obtain the data of the user message matched with each preset push content.

S740: and the server determines target push contents in the plurality of preset push contents according to the data of the user message matched with each preset push content.

S750: and if the terminal equipment detects the conversation request of the current user, acquiring the target push content from the server.

The dialogue request is used for representing the operation of triggering the dialogue entrance by the user in the man-machine interaction process. Specifically, a dialog entry is arranged on some interactive interfaces of the client application program, and a dialog request of a user in a man-machine interaction process is responded, and the current interactive interface can jump to the dialog interface. After detecting the dialog request of the current user, the terminal device may acquire the target push content from the server.

In some implementations, each dialog interface corresponds to a dialog entry, each dialog entry corresponds to an entry identification, and the entry identification can be used to identify the user interface. When a dialog request of a user is detected, a dialog entry triggered by the user can be determined, an entry identifier of the dialog entry is determined as an entry identifier of a user interface for realizing dialog with the user, and target push content corresponding to the entry identifier is obtained from a server.

In some embodiments, the terminal device may send the dialog log to the server. The dialog log is a historical dialog record of the user in text format, the dialog log may include at least one user message and at least one system message, and the dialog log may include only the user message. Optionally, the dialog log may also include an entry identification of the user interface that generated the dialog, the time of each message or the user identification of the current terminal device, etc.

S760: and the terminal equipment displays the target push content on the conversation interface.

And a preset area is arranged on the conversation interface and is used for displaying the target push content. In some embodiments, the number of push contents that can be displayed on the user interface is at most the number of the acquired target push contents. When the number of the target push contents is multiple, the terminal device may further obtain an arrangement order of the target push contents, and display the target push contents in the arrangement order. The arrangement sequence can represent the recommendation degree of the pushed content, and according to the reading habit and the arrangement sequence of the user, the target pushed content with higher recommendation degree can be displayed at a position which is easy to see first, so that the reading habit of the user is better met, and the user experience is improved.

It should be noted that, for portions of the foregoing method steps that are not described in detail, please refer to the foregoing embodiments, and further description is omitted here. The method steps corresponding to the server may refer to the foregoing embodiments, and are not described herein again.

According to the interface content display method provided by the embodiment of the application, a server acquires a push content list, wherein the push content list comprises a plurality of preset push contents; the method comprises the steps that a server obtains each user message input by a historical user, semantically identifies each preset push content and each user message to obtain data of the user message matched with each preset push content, and determines target push content in a plurality of preset push contents according to the data of the user message matched with each preset push content; and if the terminal equipment detects the conversation request of the current user, acquiring the target push content from the server, and displaying the target push content on a conversation interface. The content pushed to the current user can be determined according to the user information input by the historical user, so that the pushed content is more in line with the intention of the user, and the pushing accuracy is improved.

Referring to fig. 14, fig. 14 is a schematic flowchart of an interface content display method according to an embodiment of the present application, and is applied to the server and the terminal device. The interface content display method includes S810 to S860.

S810: the server acquires a push content list, wherein the push content list comprises a plurality of preset push contents.

S820: the server obtains each user message of the historical user input.

S830: and the server carries out semantic recognition on each preset push content and each user message to obtain the data of the user message matched with each preset push content.

S840: and the server determines target push contents in the plurality of preset push contents according to the data of the user message matched with each preset push content.

S850: and if the terminal equipment detects the conversation request of the current user, acquiring the target push content from the server.

S860: the terminal equipment acquires a preset text and an image template.

In some embodiments, the target push content includes a preset text, wherein the preset text may be description information of the preset push content. Optionally, at least one image template may be stored in the terminal device, or the image template may be acquired from the server. When the number of the image templates is multiple, the terminal device may determine, according to the preset text, an image template corresponding to the preset text in the multiple image templates. Specifically, please refer to step S350. When the terminal equipment stores the image template, only the preset text sent by the server is acquired, so that the information quantity required to be transmitted is reduced, and the information transmission efficiency is improved.

S870: and the terminal equipment synthesizes the image template and the preset text to obtain the target image.

Please refer to step S360 for a specific embodiment of synthesizing the image template and the predetermined text.

S880: the terminal device displays the target image on the dialog interface.

In some embodiments, after the terminal device displays the target image on the dialog interface, if the terminal device detects a touch operation of a current user on the target image, the dialog interface is switched to a preset interface. Specifically, in some embodiments, the target image includes a link corresponding to the target push content, and the link is used to jump the current dialog interface to a preset interface corresponding to the target push content. If the touch operation of the current user on the target image is detected, the conversation interface can be switched to the preset interface. The quick jump is realized through the touch image, the operation is simple, and the conversion rate of a user can be improved.

Compared with the interface content display method shown in fig. 13, the interface content display method provided by the embodiment of the application has the advantages that the terminal device obtains the preset text and the image template, synthesizes the image template and the preset text to obtain the target image, and displays the target image on the conversation interface, so that the terminal device can locally generate and display the target image, and the data volume transmitted by the server is reduced.

It should be understood that the foregoing examples are merely illustrative of the application of the method provided in the embodiments of the present application in a specific scenario, and do not limit the embodiments of the present application. The method provided by the embodiment of the application can also be used for realizing more different applications.

Referring to fig. 15, fig. 15 is a block diagram illustrating a structure of an interface content display apparatus according to an embodiment of the present application. As will be explained below with respect to the block diagram shown in fig. 15, the interface content display apparatus 900 includes: list acquisition module 910, message acquisition module 920, semantic recognition module 930, and content determination module 940, wherein: a list obtaining module 910, configured to obtain a push content list, where the push content list includes a plurality of preset push contents; a message obtaining module 920, configured to obtain each user message input by a historical user; a semantic recognition module 930, configured to perform semantic recognition on each preset push content and each user message to obtain data of the user message matched with each preset push content; and a content determining module 940, configured to determine, according to the data of the user message matched with each preset push content, a target push content in the plurality of preset push contents, where the target push content is used to be pushed and displayed on a dialog interface of a current user.

Further, the target push content includes a preset text, and after determining the target push content in the plurality of preset push contents according to the data of the user message matched with each preset push content, the interface content display apparatus 900 further includes: the image template acquisition module is used for acquiring an image template corresponding to the target push content and the preset text; the target image synthesis module is used for synthesizing the image template and the preset text to obtain a target image; and the image sending module is used for sending the target image to the conversation interface of the current user.

Further, the content determining module 940 includes: the first sequencing submodule is used for sequencing the plurality of preset push contents in a descending order according to the number of the user messages matched with each preset push content; and a first target content determining submodule, configured to determine a preset push content ranked in the top as the target push content.

Further, the semantic recognition module 930 includes: the entity word obtaining submodule is used for obtaining entity words contained in each preset push content; the representation acquisition module is used for acquiring entity representations corresponding to each entity word and semantic representations corresponding to each user message; the confidence coefficient acquisition sub-module is used for matching each entity representation with each semantic representation to obtain the confidence coefficient of each user message containing each entity word; the confidence judgment submodule is used for judging that the preset push content corresponding to the entity word is matched with the user message if the confidence is greater than a specified threshold; and the data acquisition submodule is used for acquiring the data of the user message matched with each preset push content.

Further, before the acquiring each user message of the historical user input, the interface content display apparatus 900 further includes: an entry identifier obtaining module, configured to obtain an entry identifier of the dialog interface of the current user; the dialogue log acquisition module is used for acquiring a plurality of historical dialogue logs corresponding to the entry identifier, and the historical dialogue logs comprise user messages input by a plurality of historical users; the message obtaining module 920 includes a message extracting sub-module, configured to extract each user message input by the multiple historical users in the multiple historical dialog logs.

Further, the semantic recognition module 930 includes: the content identification determining submodule is used for acquiring the entity words contained in each preset push content and determining the service type identification of each preset push content according to the entity words; a service type determining submodule, configured to obtain a target service type corresponding to the entry identifier; a list screening submodule, configured to screen the multiple preset push contents in the push content list according to the target service type, so as to obtain a target push content list, where the target push content list includes at least one preset push content whose service type identifier matches the target service type; and the message matching sub-module is used for performing semantic recognition on the at least one preset push content in the target push content list and each user message to obtain the number of the user messages matched with the at least one preset push content in the target push content list.

Further, the message obtaining module 920 includes a message updating sub-module, configured to obtain each user message of the specified time input by the historical user at each preset time interval; the semantic recognition module 930 includes a data update sub-module, configured to perform semantic recognition on each preset push content and each user message at the specified time to obtain data of the user message at the specified time matched with each preset push content; the content determining module 940 includes a content updating sub-module, configured to update the target push content according to the data of the user message at the specified time matched with each preset push content.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and modules 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, the coupling between the modules may be electrical, mechanical or other type of coupling.

Referring to fig. 16, a block diagram of an electronic device according to an embodiment of the present disclosure is shown. The electronic device 1000 may be an electronic device capable of running an application, such as a smart phone, a tablet computer, and an electronic book. The electronic device 1000 in the present application may include one or more of the following components: a processor 1010, a memory 1020, and one or more applications, wherein the one or more applications may be stored in the memory 1020 and configured to be executed by the one or more processors 1010, the one or more programs configured to perform a method as described in the aforementioned method embodiments.

Processor 1010 may include one or more processing cores. The processor 1010 interfaces with various components throughout the electronic device 1000 using various interfaces and circuitry to perform various functions of the electronic device 1000 and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1020 and invoking data stored in the memory 1020. Alternatively, the processor 1010 may be implemented in hardware using at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1010 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 1010, but may be implemented by a communication chip.

The Memory 1020 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 1020 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 1020 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The data storage area may also store data created by the electronic device 1000 during use (e.g., phone book, audio-video data, chat log data), and the like.

Referring to fig. 17, a block diagram of a computer-readable storage medium according to an embodiment of the present disclosure is shown. The computer-readable storage medium 1100 stores therein program code that can be called by a processor to execute the methods described in the above-described method embodiments.

The computer-readable storage medium 1100 may be an electronic memory such as a flash memory, an electrically-erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a hard disk, or a ROM. Alternatively, the computer-readable storage medium 1000 includes a non-volatile computer-readable storage medium. The computer readable storage medium 1100 has storage space for program code 1110 for performing any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 1110 may be compressed, for example, in a suitable form.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. An interface content display method, comprising:

acquiring a push content list, wherein the push content list comprises a plurality of preset push contents;

acquiring entry identifiers of conversation interfaces of current users, wherein each conversation entry of the conversation interface corresponds to one entry identifier, and the conversation entry is arranged on an upper-level interaction interface of the conversation interface;

obtaining a plurality of historical dialog logs corresponding to the entry identifier, wherein the plurality of historical dialog logs comprise user messages input by a plurality of historical users;

extracting each user message of a plurality of historical user inputs in the plurality of historical dialog logs;

performing semantic recognition on each preset push content and each user message to obtain the number of the user messages matched with each preset push content; and

and determining target push content in the plurality of preset push contents according to the number of the user messages matched with each preset push content, wherein the target push content is used for being pushed and displayed on the conversation interface of the current user.

2. The method of claim 1, wherein the target push content comprises preset text, and after determining the target push content from the plurality of preset push contents according to the data of the user message matched with each preset push content, the method further comprises:

acquiring an image template corresponding to the target push content and the preset text;

synthesizing the image template and the preset text to obtain a target image; and

and sending the target image to the dialog interface of the current user.

3. The method of claim 1, wherein the determining the target push content among the plurality of preset push contents according to the number of the user messages matched with each preset push content comprises:

according to the number of the user messages matched with each preset push content, sequencing the preset push contents in a descending order; and

and determining the preset push content ranked at the top as the target push content.

4. The method according to claim 1, wherein the semantically recognizing each of the preset push contents and each of the user messages to obtain a number of the user messages matched with each of the preset push contents comprises:

acquiring entity words contained in each preset push content;

acquiring entity representation corresponding to each entity word and semantic representation corresponding to each user message;

matching each entity representation with each semantic representation to obtain the confidence that each user message contains each entity word;

if the confidence is greater than a specified threshold, judging that the preset push content corresponding to the entity word is matched with the user message;

and acquiring the number of the user messages matched with each preset push content.

5. The method of claim 4, wherein determining that the preset pushed content corresponding to the entity word matches the user message if the confidence is greater than a specified threshold comprises:

if the confidence is greater than the designated threshold, performing emotion analysis on the user message according to the entity words to obtain the emotion polarity of the user message on the entity words;

and if the emotion polarity is positive emotion, judging that the preset push content corresponding to the entity word is matched with the user message.

6. The method according to claim 4, wherein after the obtaining the number of the user messages matched with each of the preset push contents, the method further comprises:

judging whether the historical user corresponding to the user message interacts with the preset push content or not for the user message matched with each preset push content;

if yes, determining the weight value of the user message as a first numerical value;

if not, determining the weight value of the user message as a second numerical value, wherein the first numerical value is larger than the second numerical value; and

carrying out weighted summation on the number of the user messages matched with each preset push content to obtain a recommendation value of each preset push content;

the determining, according to the data of the user message matched with each of the preset push contents, a target push content in the plurality of preset push contents includes:

sorting the plurality of preset push contents in a descending order according to the recommended values;

7. The method according to claim 1, wherein the semantically recognizing each of the preset push contents and each of the user messages to obtain a number of the user messages matched with each of the preset push contents comprises:

acquiring entity words contained in each preset push content, and determining a service type identifier of each preset push content according to the entity words;

acquiring a target service type corresponding to the entrance identifier;

screening the plurality of preset push contents in the push content list according to the target service type to obtain a target push content list, wherein the target push content list comprises at least one preset push content of which the service type identification is matched with the target service type; and

and performing semantic recognition on the at least one preset push content in the target push content list and each user message to obtain the number of the user messages matched with the at least one preset push content in the target push content list.

8. The method of claim 1, wherein said extracting each user message of a plurality of historical user inputs in said plurality of historical dialog logs comprises:

every preset time interval, acquiring each user message of the appointed time input by the historical user;

the semantic recognition of each preset push content and each user message to obtain the data of the user message matched with each preset push content includes:

performing semantic recognition on each preset push content and each user message at the appointed time to obtain data of the user message at the appointed time matched with each preset push content;

and updating the target push content according to the data of the user message at the appointed time matched with each preset push content.

9. An interface content display method, comprising:

the method comprises the steps that a server obtains a push content list, wherein the push content list comprises a plurality of preset push contents;

if the terminal equipment detects a conversation request of a current user, determining an entry identifier of a conversation interface of the current user, wherein each conversation entry of the conversation interface corresponds to one entry identifier, and the conversation entry is arranged on an upper-level interactive interface of the conversation interface;

the server acquires the entrance identifier;

the server acquires a plurality of historical conversation logs corresponding to the entrance identifier, wherein the plurality of historical conversation logs comprise user messages input by a plurality of historical users;

the server extracting each user message of a plurality of historical user inputs in the plurality of historical dialog logs;

the server carries out semantic recognition on each preset push content and each user message to obtain the number of the user messages matched with each preset push content;

the server determines target push contents in the plurality of preset push contents according to the number of the user messages matched with each preset push content;

the terminal equipment acquires the target push content from a server; and

and the terminal equipment displays the target push content on the conversation interface.

10. The method according to claim 9, wherein the target push content comprises preset text, the terminal device stores an image template, and the terminal device displays the target push content on the dialog interface, including:

the terminal equipment acquires the preset text and the image template;

the terminal equipment synthesizes the image template and the preset text to obtain a target image; and

and the terminal equipment displays the target image on the conversation interface.

11. The method of claim 10, wherein the target push content is linked to a preset interface, and after the target push content is displayed on the dialog interface, the method further comprises:

and if the terminal equipment detects the touch operation of the current user on the target image, switching the conversation interface to the preset interface.

12. An interface content display apparatus, comprising:

the device comprises a list acquisition module, a push content acquisition module and a push content display module, wherein the list acquisition module is used for acquiring a push content list which comprises a plurality of preset push contents;

the system comprises an entrance identifier acquisition module, a conversation interface acquisition module and a conversation interface management module, wherein the entrance identifier acquisition module is used for acquiring entrance identifiers of conversation interfaces of current users, each conversation entrance of the conversation interface corresponds to one entrance identifier, and the conversation entrance is arranged on an upper-level interaction interface of the conversation interface;

a dialog log obtaining module, configured to obtain multiple historical dialog logs corresponding to the entry identifier, where the multiple historical dialog logs include user messages input by multiple historical users;

a message extraction module for extracting each user message of a plurality of historical user inputs in the plurality of historical dialog logs;

the semantic recognition module is used for performing semantic recognition on each preset push content and each user message to obtain the number of the user messages matched with each preset push content; and

a content determining module, configured to determine, according to the number of the user messages matched with each preset push content, a target push content in the plurality of preset push contents, where the target push content is used to be pushed and displayed on the dialog interface of the current user.

13. An electronic device, comprising:

one or more processors;

a memory; and

one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-8.

14. A computer-readable storage medium, characterized in that a program code is stored in the computer-readable storage medium, which program code can be called by a processor to perform the method according to any of claims 1-8.