Text content publishing method and device, electronic equipment and storage medium

Abstract

The application discloses a text content publishing method and device, electronic equipment and storage medium, and relates to the field of financial technology and other related technical fields. The method comprises the following steps: obtaining text content to be published; performing a content auditing operation on the text content, wherein the content auditing operation is used to audit whether the text content meets a text publishing rule; generating a virtual image in a display interface of a terminal device according to the text content in the case that the text content passes the auditing; controlling the terminal device to play target voice content, and controlling the virtual image to demonstrate a target sign language gesture in the process that the terminal device plays the target voice content, wherein the target voice content is voice content corresponding to the text content, and the target sign language gesture is a sign language gesture corresponding to the text content. The application solves the technical problem of low publishing efficiency in the prior art when publishing text content.

Description

Technical Field

[0001] This application relates to the fields of financial technology and other related technologies, and more specifically, to a method, apparatus, electronic device and storage medium for publishing text content. Background Technology

[0002] In existing technologies, the text content to be published is typically reviewed manually. After approval, the text is sent to bank branch staff in the form of brochures or electronic documents, who then explain it to customers. This method suffers from drawbacks such as long review times and poor accuracy, resulting in low efficiency in content publication. Furthermore, having staff explain the content of brochures or electronic documents to customers consumes a significant amount of their time, increasing their workload.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for publishing text content, in order to at least solve the technical problem of low publishing efficiency in the prior art when publishing text content.

[0005] According to one aspect of this application, a method for publishing text content is provided, comprising: acquiring text content to be published; performing a content review operation on the text content, wherein the content review operation is used to review whether the text content conforms to text publishing rules, the text publishing rules being used to at least specify the target format, target length, and prohibited target words that the text content must adhere to when published; if the text content passes the review, generating a virtual avatar on the display interface of a terminal device based on the text content; controlling the terminal device to play target audio content, and controlling the virtual avatar to demonstrate target sign language gestures during the playback of the target audio content, wherein the target audio content is audio content corresponding to the text content, and the target sign language gestures are sign language gestures corresponding to the text content.

[0006] Furthermore, the method for publishing text content also includes: obtaining the business processing content of the target outlet within a preset time period, wherein the business processing content includes at least N types of business processed by the target outlet within the preset time period and the number of transactions for each type of business, where N is a positive integer; determining the products to be recommended for the target outlet based on the business processing content; and generating the text content to be published based on the product information of the products to be recommended.

[0007] Furthermore, the method for publishing the text content also includes: determining the target business from N types of businesses based on the number of transactions corresponding to each type of business, wherein the number of transactions corresponding to the target business is greater than the number of transactions corresponding to other businesses, and other businesses are those other than the target business among the N types of businesses; obtaining the target user characteristics corresponding to the target business, wherein the target user characteristics are the user characteristics corresponding to the people who handle the target business; processing the target user characteristics through a first model to obtain the target financial products preferred by users with the target user characteristics, wherein the first model is a model trained using the characteristics of users who have already purchased financial products as training samples; and using the target financial products as the products to be recommended for the target outlet.

[0008] Furthermore, the method for publishing text content also includes: obtaining the geographical location information of the target outlets; and generating the text content to be published based on the product information and geographical location information of the product to be recommended.

[0009] Furthermore, the method for publishing text content also includes: performing a first detection operation, a second detection operation, and a third detection operation on the text content according to the text publishing rules. The first detection operation is used to detect whether the content format of the text content is the target format, the second detection operation is used to detect whether the text content contains the target words, and the third detection operation is used to detect whether the content length of the text content is less than or equal to the target length. If the content format of the text content is the target format, the text content does not contain the target words, and the content length of the text content is less than or equal to the target length, the text content is determined to have passed the review.

[0010] Furthermore, when conducting content review of text content, the following situations will result in failure to pass the review: the content format of the text content is not the target format, the text content contains target words, or the content length of the text content exceeds the target length.

[0011] Furthermore, the method for publishing text content also includes: before generating a virtual image on the display interface of the terminal device based on the text content, performing a speech conversion operation on the text content to obtain target speech content; and processing the text content through a second model to obtain target sign language gestures for expressing the text content, wherein the second model is a model trained using text content with known corresponding sign language gestures as training samples.

[0012] Furthermore, the method for publishing text content also includes: obtaining the playback duration of the target audio content and the demonstration duration of the target sign language gesture; using the maximum duration between the playback duration and the demonstration duration as the display duration of the virtual avatar; generating the virtual avatar in the display interface of the terminal device according to the display duration, wherein the virtual avatar stops being displayed in the display interface when the display duration ends.

[0013] According to another aspect of this application, a text content publishing device is also provided, comprising: an acquisition module for acquiring text content to be published; an approval module for performing content approval operations on the text content, wherein the content approval operation is used to check whether the text content conforms to text publishing rules, the text publishing rules being used to at least specify the target format, target length, and prohibited target words that the text content must adhere to when published; a generation module for generating a virtual avatar on the display interface of a terminal device based on the text content if the text content passes the approval; and a control module for controlling the terminal device to play target audio content, and controlling the virtual avatar to demonstrate target sign language gestures during the playback of the target audio content, wherein the target audio content is audio content corresponding to the text content, and the target sign language gestures are sign language gestures corresponding to the text content.

[0014] According to another aspect of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the above-described method for publishing text content when it is run.

[0015] According to another aspect of this application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the above-described method for publishing text content.

[0016] In this application, an automatic text content review method is adopted. First, the text content to be published is obtained, and then a content review operation is performed on the text content. The content review operation checks whether the text content conforms to the text publishing rules, which at least specify the target format, target length, and prohibited words that the text content must adhere to when published. Finally, if the text content passes the review, a virtual avatar is generated on the display interface of the terminal device based on the text content, and the terminal device is controlled to play the target audio content. During the playback of the target audio content, the virtual avatar is controlled to demonstrate the target sign language gestures. The target audio content is the audio content corresponding to the text content, and the target sign language gestures are the sign language gestures corresponding to the text content.

[0017] As described above, this application achieves the technical effects of shortening the review time and improving the accuracy of review by automatically reviewing text content, thereby solving the problem of low content publishing efficiency in existing technologies. Furthermore, this application also demonstrates target sign language gestures when the target audio content is played on a terminal device using a virtual avatar. This not only replaces real staff in explaining the text content but also provides services to deaf and mute individuals and other disabled people through sign language, reducing the burden on staff and improving the efficiency of content promotion.

[0018] Therefore, the technical solution of this application achieves the purpose of automatically reviewing and publishing text content, thereby shortening the publication time of text content and solving the technical problem of low publication efficiency in the prior art. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a flowchart of an optional method for publishing text content according to an embodiment of this application;

[0021] Figure 2 This is a flowchart illustrating an embodiment of this application for obtaining text content to be published;

[0022] Figure 3 This is a flowchart illustrating an optional method for determining the recommended products for a target branch based on the content of business transactions, according to an embodiment of this application.

[0023] Figure 4 This is a flowchart illustrating the generation of a virtual avatar on a display interface according to an embodiment of this application;

[0024] Figure 5 This is a schematic diagram of an optional text content publishing device according to an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties. For example, if there is an interface between this system and the relevant user or organization, before obtaining the relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving the consent information from the aforementioned user or organization.

[0028] The present application will be further described below with reference to various embodiments.

[0029] Example 1

[0030] According to an embodiment of this application, an embodiment of a method for publishing text content is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] Figure 1 This is a flowchart of an optional method for publishing text content according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0032] Step S101: Obtain the text content to be published.

[0033] In an optional embodiment, a content publishing system can be used as the execution subject of the text content publishing method in the embodiments of this application. The content publishing system can be a software system and can run on a terminal device.

[0034] Optionally, in the fintech field, the text content to be published includes, but is not limited to, introductions to wealth management products, financial news, introductions to financial knowledge, and other content that can be promoted to bank users.

[0035] Furthermore, after completing the text content, the editors can upload it to the content publishing system, allowing the system to access the text content to be published.

[0036] Step S102: Perform content review on the text content.

[0037] In step S102, the content review operation is used to review whether the text content conforms to the text publishing rules. The text publishing rules are used to specify at least the target format, target length, and prohibited target words that the text content must follow when it is published.

[0038] It should be noted that, due to the public nature of text content after publication, content publishing systems need to conduct content review of the text content to be published for information security and other purposes. Specifically, the content publishing system in this application can verify whether the content format conforms to the preset target format, whether the target length of the text content is less than or equal to the target length, and whether prohibited target words appear in the text content.

[0039] Furthermore, it should be noted that in existing technologies, text content review typically relies on manual methods, which not only results in lengthy review times but also leads to inconsistent review quality due to over-reliance on human experience. In this application, however, by automating text content review through a content publishing system, review time can be shortened, efficiency improved, and a consistent review standard ensured, thereby enhancing the quality of text content review.

[0040] Step S103: If the text content passes the review, a virtual avatar is generated on the display interface of the terminal device based on the text content.

[0041] Optionally, terminal devices include, but are not limited to, electronic devices such as smartphones, laptops, desktop computers, smart tablets, and smart wearable devices. Additionally, in the fintech field, terminal devices can also be smart ATMs, smart TVs, smart display devices, and smart business terminal devices in bank branches.

[0042] Furthermore, the aforementioned virtual images include, but are not limited to, virtual human figures, virtual animal figures, virtual cartoon characters, and various other virtual character images. Taking a virtual human figure as an example, it can be a virtual digital human, defined as a virtual character with a digital appearance. Unlike robots with physical bodies, virtual digital humans rely on display devices for their existence. Virtual digital humans possess the following three characteristics: first, they have a human appearance, possessing specific facial features, gender, and personality traits; second, they possess human behavior, having the ability to express themselves through language, facial expressions, and body language; and third, they possess human thought, having the ability to recognize the external environment and interact with others.

[0043] Step S104: Control the terminal device to play the target voice content, and control the virtual image to demonstrate the target sign language gestures while the terminal device is playing the target voice content.

[0044] In step S104, the target speech content is the speech content corresponding to the text content, and the target sign language gesture is the sign language gesture corresponding to the text content.

[0045] Optionally, after generating the virtual avatar on the terminal device's display interface, the content publishing system can control the terminal device's audio playback module to play the target audio content, which is audio content converted from text content. Additionally, while the terminal device is playing the target audio content, the content publishing system will also control the virtual avatar to demonstrate target sign language gestures, which are used to express the meaning of the text content.

[0046] Alternatively, in addition to displaying the virtual avatar on the display device of the terminal device, text content can also be displayed directly on the display device.

[0047] Therefore, this application can display text content through three methods: text, sign language, and voice. This not only replaces the actual staff in explaining the text content, but also provides services to people with disabilities such as the deaf and mute through sign language, thereby reducing the burden on staff and achieving the technical effect of improving the efficiency of content promotion.

[0048] Based on steps S101 to S104, this application employs an automatic text content review method. First, the text content to be published is obtained. Then, a content review operation is performed on the text content. This content review operation checks whether the text content conforms to text publishing rules. The text publishing rules at least specify the target format, target length, and prohibited words that the text content must adhere to when published. Finally, if the text content passes the review, a virtual avatar is generated on the terminal device's display interface based on the text content. The terminal device is then controlled to play the target audio content, and during the playback of the target audio content, the virtual avatar demonstrates the target sign language gestures. The target audio content is the audio content corresponding to the text content, and the target sign language gestures are the sign language gestures corresponding to the text content.

[0049] As described above, this application achieves the technical effects of shortening the review time and improving the accuracy of review by automatically reviewing text content, thereby solving the problem of low content publishing efficiency in existing technologies. Furthermore, this application also demonstrates target sign language gestures when the target audio content is played on a terminal device using a virtual avatar. This not only replaces real staff in explaining the text content but also provides services to deaf and mute individuals and other disabled people through sign language, reducing the burden on staff and improving the efficiency of content promotion.

[0050] Therefore, the technical solution of this application achieves the purpose of automatically reviewing and publishing text content, thereby shortening the publication time of text content and solving the technical problem of low publication efficiency in the prior art.

[0051] In one alternative embodiment, Figure 2 A flowchart illustrating an embodiment of this application for obtaining text content to be published is shown, such as... Figure 2 As shown, it includes the following steps:

[0052] Step S201: Obtain the business processing content of the target branch within a preset time period.

[0053] In step S201, the business processing content includes at least N types of business processed by the target branch within a preset time period and the number of times each type of business is processed, where N is a positive integer.

[0054] Optionally, the target branch can be any one of multiple bank branches, and the preset time period can be customized, such as the past month, the past year, etc. The N types of services include, but are not limited to, various financial services offered by the target branch, such as loan services, credit card services, deposit services, and social security card services.

[0055] Step S202: Determine the products to be recommended for the target outlet based on the business processing content.

[0056] Optionally, the content publishing system can analyze the business transactions of the target outlet within a preset time period to identify suitable financial products for marketing. These products may include, but are not limited to, fund products, bond products, loan products, and deposit products.

[0057] Step S203: Generate the text content to be published based on the product information of the product to be recommended.

[0058] Optionally, after determining the financial products suitable for marketing at the target outlets, the content publishing system can generate text content to be published based on the product information of the products to be recommended. The text content is used to promote the products to be recommended in order to attract potential users of the products to be recommended.

[0059] In one alternative embodiment, Figure 3 This document illustrates a flowchart of an optional method for determining the recommended products corresponding to a target branch based on the content of business transactions, according to an embodiment of this application. Figure 3 As shown, it includes the following steps:

[0060] Step S301: Determine the target business from N types of businesses based on the processing quantity corresponding to each type of business. The processing quantity corresponding to the target business is greater than the processing quantity corresponding to other businesses. Other businesses are those other than the target business among the N types of businesses.

[0061] Optionally, assume that the target branch offers N types of services: loan services, credit card services, deposit services, and social security card services. Within a preset time period, the number of loan transactions is 30, the number of credit card transactions is 20, the number of deposit transactions is 25, and the number of social security card transactions is 25. Based on this, the content publishing system can determine that loan services are the target service for this target branch.

[0062] Step S302: Obtain the target user characteristics corresponding to the target business, wherein the target user characteristics are the user characteristics corresponding to the people who handle the target business.

[0063] Optionally, since users need to retain some user information when conducting business, the content publishing system can extract target user characteristics corresponding to the target business based on the user information retained by users conducting the target business. For example, when the target business is a loan business, the content publishing system can extract user characteristics such as the loan applicant's age, occupation, and income level as target user characteristics based on the user information retained by the loan applicant.

[0064] Step S303: Process the target user features using the first model to obtain the target financial products that users with target user features prefer to purchase. The first model is a model trained using the features of users who have already purchased financial products as training samples.

[0065] Step S304: Select the target financial product as the product to be recommended for the target branch.

[0066] Optionally, the content publishing system can use the characteristics of users who have purchased financial products as training samples, and then use the financial products purchased by these users as label data. The training samples and label data are then input into a preset deep learning network for multiple iterations of training to obtain the first model.

[0067] Furthermore, after obtaining the target user characteristics, the content publishing system inputs these characteristics into the first model, which then outputs the target financial products preferred by users with these characteristics. Finally, the content publishing system can use these target financial products as recommended products for the target branches.

[0068] It should be noted that this application first uses the historical business processing content of the target branch as the analysis object. By analyzing the historical business processing content, the target business that the target branch frequently handles is determined, thereby identifying the target business that the target branch is good at or frequently handles. Then, this application continues to analyze the target user characteristics of the user group corresponding to the target business, and based on the target user characteristics and combined with a neural network model, predicts the financial products that users who handle the target business may be interested in, and then uses the financial product as the product to be recommended by the target branch.

[0069] It's easy to understand that since the products to be recommended for the target outlets are determined based on the user groups that the target outlets frequently encounter, marketing strategies can be developed more specifically for the user groups who frequently visit the target outlets. This allows for the recommendation of financial products that these users are more likely to be interested in, thereby increasing the success rate of financial product marketing.

[0070] In one alternative embodiment, the content publishing system can also obtain the geographic location information of the target site and generate the text content to be published based on the product information and geographic location information of the product to be recommended.

[0071] Optionally, the terminal device can also be a user's smartphone or other device. When a user sees the recommended product corresponding to the target outlet on their smartphone, if the user is interested in the recommended product, they may want to go to the target outlet to learn more about the recommended product. In order to help users determine the route to the target outlet more quickly, the content publishing system can obtain the geographical location information of the target outlet and add the geographical location information of the target outlet in addition to the product information of the recommended product in the generated text content.

[0072] In one optional embodiment, the content publishing system can perform a first detection operation, a second detection operation, and a third detection operation on the text content according to the text publishing rules. The first detection operation is used to detect whether the content format of the text content is the target format, the second detection operation is used to detect whether the text content contains target words, and the third detection operation is used to detect whether the content length of the text content is less than or equal to the target length.

[0073] Furthermore, if the text content is in the target format, does not contain the target words, and its length is less than or equal to the target length, the text content is deemed to have passed the review.

[0074] Optionally, when performing content review on text content, the following conditions must be met for the content to fail the review: the content format of the text content is not the target format, the text content contains target words, or the content length of the text content exceeds the target length.

[0075] Optionally, when reviewing text content, the content publishing system will only approve the text content if it simultaneously meets all three of the following conditions: the text content format is the target format, the text content does not contain the target keywords, and the text content length is less than or equal to the target length. If any one or more conditions are not met, the content publishing system will determine that the text content has failed the review.

[0076] Optionally, the length of the text content is limited because excessively long text content may lead to excessively long playback times for the corresponding audio content or for the virtual avatar to demonstrate the corresponding sign language gestures. Since the terminal device may also be used for other tasks, excessively long playback or demonstration times could interfere with its normal operation. Therefore, limiting the length of the text content is necessary to ensure the stability of the terminal device during task processing.

[0077] In addition, the reason for limiting the content format of the text to the target format is that text content in a non-target format may have problems with speech recognition and sign language recognition. Therefore, in order to ensure the accuracy of the target speech content and the accuracy of the target sign language gestures, it is necessary to limit the content format of the text to the target format.

[0078] In addition, prohibited words can be those related to information security. For example, user privacy information should be prohibited from appearing in text content to be published.

[0079] In one optional embodiment, before generating a virtual avatar on the terminal device's display interface based on the text content, the content publishing system can also perform a speech conversion operation on the text content to obtain the target speech content. Additionally, the content publishing system can also process the text content using a second model to obtain the target sign language gestures used to express the text content, wherein the second model is a model trained using text content with known corresponding sign language gestures as training samples.

[0080] Optionally, the second model is a pre-trained neural network model. During the training of the second model, the content publishing system can first acquire multiple text contents with known corresponding sign language gestures as training samples, then use the sign language gesture corresponding to each text content as the label data corresponding to that text content, and then input each training sample and the label data corresponding to each training sample into a preset deep learning network. After multiple iterations of training, the second model is obtained.

[0081] The content publishing system can input approved text content into the second model, and then the second model can output the target sign language gestures that can express the meaning of the text content.

[0082] In one alternative embodiment, Figure 4 A flowchart illustrating the generation of a virtual avatar on a display interface according to an embodiment of this application is shown, such as... Figure 4 As shown, it includes the following steps:

[0083] Step S401: Obtain the playback duration of the target audio content and the demonstration duration of the target sign language gesture;

[0084] Step S402: Use the maximum duration between the playback duration and the demonstration duration as the display duration of the virtual avatar;

[0085] Step S403: Generate a virtual image in the display interface of the terminal device according to the display duration, wherein the virtual image stops being displayed in the display interface when the display duration ends.

[0086] Optionally, after generating the target audio content and target sign language gestures, the content publishing system will obtain the playback duration of the target audio content and the demonstration duration of the target sign language gestures. The content publishing system will then use the maximum of the playback duration and the demonstration duration as the display duration of the virtual avatar. For example, if the playback duration of the target audio content is 5 minutes and the demonstration duration of the target sign language gestures is 6 minutes, then the display duration of the virtual avatar will be 6 minutes.

[0087] Furthermore, after determining the display duration of the virtual avatar, the content publishing system can generate the virtual avatar on the display interface of the terminal device, and the virtual avatar will continuously display the display duration on the display interface, and stop displaying the virtual avatar on the display interface when the display duration ends.

[0088] It should be noted that the terminal device can also display the virtual image on the display interface at preset intervals, with each display lasting for the duration mentioned above. The virtual image will demonstrate the target sign language gesture each time it is displayed.

[0089] As described above, this application achieves the technical effects of shortening the review time and improving the accuracy of review by automatically reviewing text content, thereby solving the problem of low content publishing efficiency in existing technologies. Furthermore, this application also demonstrates target sign language gestures when the target audio content is played on a terminal device using a virtual avatar. This not only replaces real staff in explaining the text content but also provides services to deaf and mute individuals and other disabled people through sign language, reducing the burden on staff and improving the efficiency of content promotion.

[0090] Example 2

[0091] This application also provides a text content publishing device. It should be noted that the text content publishing device of this application can be used to execute the text content publishing method provided in embodiment 1 of this application. The text content publishing device provided in this application will be described below.

[0092] Figure 5 This is a schematic diagram of an optional text content publishing device according to an embodiment of this application. Figure 5 As shown, the device includes: an acquisition module 501, an approval module 502, a generation module 503, and a control module 504.

[0093] Specifically, the acquisition module 501 is used to acquire the text content to be published; the review module 502 is used to perform content review operations on the text content, wherein the content review operation is used to review whether the text content conforms to the text publishing rules, and the text publishing rules at least specify the target format, target length and prohibited target words that the text content must follow when it is published; the generation module 503 is used to generate a virtual image on the display interface of the terminal device based on the text content if the text content passes the review; the control module 504 is used to control the terminal device to play the target audio content, and control the virtual image to demonstrate the target sign language gestures during the playback of the target audio content, wherein the target audio content is the audio content corresponding to the text content, and the target sign language gestures are the sign language gestures corresponding to the text content.

[0094] Optionally, the acquisition module includes: a first acquisition unit, a first determination unit, and a first generation unit. The first acquisition unit is used to acquire the business processing content of the target outlet within a preset time period, wherein the business processing content includes at least N types of business processed by the target outlet within the preset time period and the corresponding quantity of each type of business, where N is a positive integer; the first determination unit is used to determine the products to be recommended for the target outlet based on the business processing content; and the first generation unit is used to generate text content to be published based on the product information of the products to be recommended.

[0095] Optionally, the first determining unit includes: a first determining subunit, a first acquiring subunit, a feature processing subunit, and a product to be recommended determining subunit. The first determining subunit is used to determine a target business from N types of businesses based on the number of transactions corresponding to each type of business, wherein the number of transactions corresponding to the target business is greater than the number of transactions corresponding to other businesses, and the other businesses are those other than the target business among the N types of businesses; the first acquiring subunit is used to acquire the target user characteristics corresponding to the target business, wherein the target user characteristics are the user characteristics corresponding to the people who have processed the target business; the feature processing subunit is used to process the target user characteristics using a first model to obtain the target financial products preferred by users with the target user characteristics, wherein the first model is a model trained using the characteristics of users who have already purchased financial products as training samples; and the product to be recommended determining subunit is used to select the target financial product as the product to be recommended corresponding to the target branch.

[0096] Optionally, the first generation unit includes a second acquisition subunit and a first generation subunit. The second acquisition subunit is used to acquire the geographical location information of the target network; the first generation subunit is used to generate text content to be published based on the product information and geographical location information of the product to be recommended.

[0097] Optionally, the review module further includes a detection unit and a review unit. The detection unit performs a first detection operation, a second detection operation, and a third detection operation on the text content according to the text publishing rules. The first detection operation checks whether the text content's format is the target format; the second detection operation checks whether the text content contains target words; and the third detection operation checks whether the text content's length is less than or equal to the target length. The review unit determines that the text content passes the review if the text content's format is the target format, the text content does not contain target words, and the text content's length is less than or equal to the target length.

[0098] Optionally, when performing content review on text content, the following conditions must be met for the content to fail the review: the content format of the text content is not the target format, the text content contains target words, or the content length of the text content exceeds the target length.

[0099] Optionally, the text content publishing device further includes a speech conversion module and a sign language generation module. The speech conversion module performs speech conversion on the text content to obtain target speech content; the sign language generation module processes the text content using a second model to obtain target sign language gestures to express the text content, wherein the second model is a model trained using text content with known corresponding sign language gestures as training samples.

[0100] Optionally, the generation module includes: a second acquisition unit, a display duration determination unit, and a virtual avatar generation unit. The second acquisition unit is used to acquire the playback duration of the target audio content and the demonstration duration of the target sign language gesture; the display duration determination unit is used to use the maximum of the playback duration and the demonstration duration as the display duration of the virtual avatar; the virtual avatar generation unit is used to generate a virtual avatar on the display interface of the terminal device according to the display duration, wherein the virtual avatar stops displaying on the display interface when the display duration ends.

[0101] Example 3

[0102] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, which stores a computer program, wherein the computer program is configured to execute the method for publishing text content in Embodiment 1 above when it is run.

[0103] Example 4

[0104] According to another aspect of the embodiments of this application, an electronic device is also provided, which includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the text content publishing method in Embodiment 1 above.

[0105] Optionally, the processor is used to implement the following processes: acquiring text content to be published; performing content review on the text content, wherein the content review is used to review whether the text content conforms to the text publishing rules, and the text publishing rules at least specify the target format, target length, and prohibited target words that the text content must adhere to when it is published; if the text content passes the review, generating a virtual avatar on the display interface of the terminal device based on the text content; controlling the terminal device to play target audio content, and controlling the virtual avatar to demonstrate target sign language gestures during the playback of the target audio content, wherein the target audio content is the audio content corresponding to the text content, and the target sign language gestures are the sign language gestures corresponding to the text content.

[0106] Optionally, the processor is also used to implement the following process: obtaining the business processing content of the target outlet during a preset time period, wherein the business processing content includes at least N types of business processed by the target outlet during the preset time period and the number of transactions for each type of business, where N is a positive integer; determining the products to be recommended for the target outlet based on the business processing content; and generating text content to be published based on the product information of the products to be recommended.

[0107] Optionally, the processor is also configured to implement the following processes: determine the target business from N types of businesses based on the number of transactions corresponding to each type of business, wherein the number of transactions corresponding to the target business is greater than the number of transactions corresponding to other businesses, and other businesses are those other than the target business among the N types of businesses; obtain the target user characteristics corresponding to the target business, wherein the target user characteristics are the user characteristics corresponding to the people who handle the target business; process the target user characteristics through a first model to obtain the target financial products preferred by users with the target user characteristics, wherein the first model is a model trained using the characteristics of users who have already purchased financial products as training samples; and use the target financial products as the products to be recommended for the target branch.

[0108] Optionally, the processor is also used to perform the following processes: obtaining the geographic location information of the target outlet; and generating text content to be published based on the product information and geographic location information of the product to be recommended.

[0109] Optionally, the processor is also configured to perform the following process: perform a first detection operation, a second detection operation, and a third detection operation on the text content according to the text publishing rules, wherein the first detection operation is used to detect whether the content format of the text content is the target format, the second detection operation is used to detect whether the text content contains target words, and the third detection operation is used to detect whether the content length of the text content is less than or equal to the target length; if the content format of the text content is the target format, the text content does not contain target words, and the content length of the text content is less than or equal to the target length, the text content is determined to pass the review.

[0110] Furthermore, when conducting content review of text content, the following situations will result in failure to pass the review: the content format of the text content is not the target format, the text content contains target words, or the content length of the text content exceeds the target length.

[0111] Optionally, the processor is also used to implement the following process: before generating a virtual image in the display interface of the terminal device based on the text content, performing a speech conversion operation on the text content to obtain the target speech content; processing the text content through a second model to obtain the target sign language gesture for expressing the text content, wherein the second model is a model trained using text content with known corresponding sign language gestures as training samples.

[0112] Optionally, the processor is also configured to implement the following process: obtain the playback duration of the target speech content and the demonstration duration of the target sign language gesture; use the maximum duration of the playback duration and the demonstration duration as the display duration of the virtual avatar; generate the virtual avatar in the display interface of the terminal device according to the display duration, wherein the display of the virtual avatar in the display interface stops when the display duration ends.

[0113] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0114] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0116] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0118] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0119] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of publishing text content, characterized by, The method comprises the following steps: obtaining text content to be published; performing a content review operation on the text content, wherein the content review operation is used to review whether the text content meets a text publishing rule, and the text publishing rule at least defines a target format, a target length and a target vocabulary that needs to be followed when the text content is published; generating a virtual image in a display interface of a terminal device according to the text content in the case that the text content passes the review; controlling the terminal device to play target voice content and controlling the virtual image to demonstrate target sign language gestures in the process of playing the target voice content by the terminal device, wherein the target voice content is voice content corresponding to the text content, and the target sign language gestures are sign language gestures corresponding to the text content; wherein, before generating a virtual image in a display interface of a terminal device according to the text content, the method further comprises: performing a voice conversion operation on the text content to obtain the target voice content; processing the text content through a second model to obtain target sign language gestures for expressing the text content, wherein the second model is a model trained by using text content corresponding to known sign language gestures as training samples.

2. The method of claim 1, wherein, Obtaining text content to be published, comprising: obtaining business handling content of a target network point in a preset time period, wherein the business handling content at least includes N kinds of businesses handled by the target network point in the preset time period and the handling quantity corresponding to each kind of business, and N is a positive integer; determining a to-be-recommended product corresponding to the target network point based on the business handling content; generating the text content to be published according to product information of the to-be-recommended product.

3. The method of claim 2, wherein, Determining a to-be-recommended product corresponding to the target network point based on the business handling content, comprising: determining a target business from the N kinds of businesses according to the handling quantity corresponding to each kind of business, wherein the handling quantity corresponding to the target business is greater than the handling quantity corresponding to other businesses, and the other businesses are businesses other than the target business among the N kinds of businesses; obtaining target user features corresponding to the target business, wherein the target user features are user features corresponding to a crowd handling the target business; processing the target user features through a first model to obtain a target financial product preferred to be purchased by a user with the target user features, wherein the first model is a model trained by using features of users having purchased a financial product as training samples; taking the target financial product as the to-be-recommended product corresponding to the target network point.

4. The method of claim 2, wherein, Generating the text content to be published according to the product information of the to-be-recommended product, comprising: obtaining geographic location information of the target network point; generating the text content to be published according to the product information of the to-be-recommended product and the geographic location information.

5. The method of claim 1, wherein, Performing a content review operation on the text content, comprising: The first detection operation is used to detect whether the content format of the text content is the target format, the second detection operation is used to detect whether the text content contains the target vocabulary, and the third detection operation is used to detect whether the content length of the text content is less than or equal to the target length. In a case where the content format of the text content is the target format, the text content does not contain the target vocabulary, and the content length of the text content is less than or equal to the target length, it is determined that the text content passes the review.

6. The method of claim 5, wherein, In the content review operation on the text content, the failure to pass the review at least includes one of the following: the content format of the text content is a non-target format, the text content contains the target vocabulary, and the content length of the text content is greater than the target length.

7. The method of claim 1, wherein, According to the text content, a virtual image is generated in a display interface of a terminal device, including: Obtaining the playing time of the target voice content and the demonstration time of the target sign language posture; Taking the maximum time length of the playing time and the demonstration time as the display time length of the virtual image; According to the display time length, the virtual image is generated in the display interface of the terminal device, and the virtual image is stopped from being displayed in the display interface when the display time length ends.

8. A text content distribution apparatus characterized by comprising: Including: An acquisition module is configured to acquire text content to be published; An audit module is configured to perform a content review operation on the text content, wherein the content review operation is used to review whether the text content complies with a text publishing rule, and the text publishing rule is used to at least specify a target format, a target length, and a target vocabulary that is prohibited from appearing that need to be followed when the text content is published; A generation module is configured to generate a virtual image in a display interface of a terminal device according to the text content in a case where the text content passes the review; A control module is configured to control the terminal device to play target voice content and control the virtual image to demonstrate target sign language postures in a process in which the terminal device plays the target voice content, wherein the target voice content is voice content corresponding to the text content, and the target sign language postures are sign language postures corresponding to the text content; The device further includes a voice conversion module configured to perform a voice conversion operation on the text content to obtain target voice content, and a sign language generation module configured to process the text content by a second model to obtain target sign language postures used to express the text content, wherein the second model is a model trained by using text content corresponding to known sign language postures as training samples.

9. A computer-readable storage medium, characterized in that, A computer program is stored in a computer-readable storage medium, wherein the computer program is set to execute the text content publishing method in any one of claims 1 to 7 when running.

10. An electronic device, comprising: An apparatus, including one or more processors and memory storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7 for publishing text content.

Images