Information publishing method and device, computing equipment, storage medium and program product

Abstract

The embodiment of the invention provides an information release method and device, computing equipment, a storage medium and a program product, and the method comprises the steps: a server sends release prompt information to a client, so that the client displays the release prompt information on a user interface; and in response to an information generation request sent by a client for a related operation triggered by issuing the prompt information, obtaining at least one image, analyzing a target service category corresponding to each image by using a first artificial intelligence model, generating a target copywriting, sending the target copywriting and the target service category to the client, and sending the target copywriting and the target service category to the client. And displaying the information on the information generation interface by the client, responding to an information confirmation request sent by a confirmation operation triggered by the client for the information generation interface, generating information publishing content according to the images and the target copywriting, and publishing the information publishing content under a user account corresponding to the client. According to the embodiment, the information publishing content is automatically generated based on the image by using the artificial intelligence model, so that the publishing cost is reduced and the publishing efficiency is improved.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of computer technology, and in particular, to a method and apparatus for information publishing, a computing device, a storage medium, and a program product. Background Art

[0002] With the development of Internet technology, there are more and more service providers (such as merchants settled in an e-commerce service system) that cooperate with the e-commerce service system to provide services for consumers. For each service provider, it is necessary to publish content related to the services provided (such as service posts, etc.) on the e-commerce service system to promote its own services, thereby attracting consumers to purchase and improving the service conversion rate.

[0003] Currently, when a service provider wants to publish content on an e-commerce service system, it usually needs to conceive a copywriting and then manually input the conceived copywriting into the information publishing interface for publishing. The entire information publishing process is costly and inefficient, and there is an urgent need for improvement. Summary of the Invention

[0004] Embodiments of the present application provide a method and apparatus for information publishing, a computing device, a storage medium, and a program product, which are used to solve the problems of high cost and low efficiency in information publishing in the prior art on an e-commerce service system.

[0005] An information publishing method provided in an embodiment of the present application is applied to a server and includes:

[0006] Sending a publishing prompt message to a client so that the client displays the publishing prompt message in a user interface;

[0007] Receiving an information generation request sent by the client, where the information generation request includes at least one image; the at least one image is obtained by the client in response to an image upload operation triggered for the publishing prompt message;

[0008] Parsing a target service category corresponding to the at least one image by using a first artificial intelligence model;

[0009] Generating a target copywriting corresponding to the at least one image by using the first artificial intelligence model according to the target service category;

[0010] Sending the target copywriting and the target service category to the client so that the client displays the target copywriting and the target service category in an information generation interface;

[0011] In response to the information confirmation request sent by the client, generate information release content corresponding to the target service category according to the at least one image and the target copywriting; the information confirmation request is generated by the client in response to a confirmation operation triggered on the information generation interface.

[0012] Obtain the user account corresponding to the client, and publish the information release content under the user account.

[0013] An embodiment of the present application further provides an information release method, which is applied to a client and includes:

[0014] Receive the release prompt information sent by the server.

[0015] Display the release prompt information in the user interface.

[0016] In response to a trigger operation on the release prompt information, jump from the user interface to the image upload interface.

[0017] In response to an image upload operation on the image upload interface, obtain at least one image.

[0018] Based on the at least one image, send an information generation request to the server, so that the server uses a first artificial intelligence model to analyze the target service category corresponding to the at least one image, and generate the target copywriting corresponding to the at least one image according to the target service category.

[0019] Receive the target copywriting and target service category sent by the server.

[0020] Display the target copywriting and the target service category in the information generation interface.

[0021] In response to a confirmation operation triggered on the information generation interface, generate an information confirmation request.

[0022] Send the information confirmation request to the server, so that the server generates information release content corresponding to the target service category according to the at least one image and the target copywriting, and obtain the user account corresponding to the client, and publish the information release content under the user account.

[0023] An embodiment of the present application further provides an information release device, which is configured on the server and includes:

[0024] A first sending module, configured to send release prompt information to the client, so that the client displays the release prompt information in the user interface.

[0025] A first receiving module, configured to receive an information generation request sent by the client, where the information generation request includes at least one image; the at least one image is obtained by the client in response to an image upload operation triggered for the publishing prompt information;

[0026] A model running module, configured to use a first artificial intelligence model to parse a target service category corresponding to the at least one image;

[0027] The model running module is further configured to use the first artificial intelligence model to generate a target copy corresponding to the at least one image according to the target service category;

[0028] The first sending module is further configured to send the target copy and the target service category to the client, so that the client can display the target copy and the target service category on an information generation interface;

[0029] An information generation module, configured to generate information publishing content corresponding to the target service category according to the at least one image and the target copy in response to an information confirmation request sent by the client; the information confirmation request is generated by the client in response to a confirmation operation triggered for the information generation interface;

[0030] An information publishing module, configured to obtain a user account corresponding to the client and publish the information publishing content under the user account.

[0031] An embodiment of the present application further provides an information publishing device, configured on a client, including:

[0032] A second receiving module, configured to receive a publishing prompt information sent by a server;

[0033] An interface display module, configured to display the publishing prompt information in a user interface;

[0034] An interface jump module, configured to jump from the user interface to an image upload interface in response to a trigger operation for the publishing prompt information;

[0035] An image acquisition module, configured to acquire at least one image in response to an image upload operation for the image upload interface;

[0036] A second sending module, configured to send an information generation request to a server based on the at least one image, so that the server uses a first artificial intelligence model to parse a target service category corresponding to the at least one image and generate a target copy corresponding to the at least one image according to the target service category;

[0037] The second receiving module is further configured to receive the target copywriting and the target service category sent by the server;

[0038] The interface display module is further configured to display the target copywriting and the target service category on the information generation interface;

[0039] The request generation module is configured to generate an information confirmation request in response to a confirmation operation triggered for the information generation interface;

[0040] The second sending module is further configured to send the information confirmation request to the server, so that the server generates information release content corresponding to the target service category according to the at least one image and the target copywriting, and obtains the user account corresponding to the client, and publishes the information release content under the user account.

[0041] An embodiment of the present application further provides a computing device, including a processing component and a storage component; the storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the above information release method.

[0042] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processing component, the above information release method is implemented.

[0043] An embodiment of the present application further provides a computer program product, including a computer program or instruction, and when the computer program or instruction is executed by a processing component, the above information release method is implemented.

[0044] In an embodiment of the present application, the server sends a release prompt message to the client so that the client can display it on the user interface; in response to an information generation request sent by the client for a related operation triggered for the release prompt message, at least one image is obtained, and a first artificial intelligence model is used to analyze the target service category corresponding to the at least one image, and a target copywriting is generated according to the target service category, and the target copywriting and the target service category are sent to the client for the client to display on the information generation interface. In response to an information confirmation request sent by the client for a confirmation operation triggered for the information generation interface, information release content is generated according to the at least one image and the target copywriting, and is published under the user account corresponding to the client. The solution of the embodiment of the present application enables the service provider to upload at least one image through the guidance of the client even without copywriting editing experience, and then the server uses the artificial intelligence model to automatically analyze the target service category based on the image uploaded by the client, and generate a high-quality target copywriting that meets the target service category for the user to confirm and publish. The entire process does not require manual conception and editing operations, greatly improving the information release efficiency and reducing the release cost.

[0045] In addition, the artificial intelligence model cited in this solution can demonstrate powerful capabilities in the field of natural language generation through continuous training and optimization, thus ensuring the generation of high-quality and personalized target copywriting, avoiding the homogenization of copywriting content, enhancing the attractiveness of copywriting content, and further improving the service conversion rate.

[0046] These aspects or other aspects of this application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings described herein are used to provide a further understanding of this application, and constitute a part of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0048] Figure 1 The system architecture diagram for information publishing provided by the exemplary embodiment of this application is shown.

[0049] Figure 2 The flowchart of an information publishing method provided by the exemplary embodiment of this application is shown.

[0050] Figure 3 The schematic diagram of an information generation interface provided by the exemplary embodiment of this application is shown.

[0051] Figure 4 The schematic diagram of an image parsing interface provided by the exemplary embodiment of this application is shown.

[0052] Figure 5 The flowchart of an information publishing method provided by the exemplary embodiment of this application is shown.

[0053] Figure 6 The schematic diagram of a scenario interaction in an actual application provided by the exemplary embodiment of this application is shown.

[0054] Figure 7 The structural schematic diagram of an information publishing device provided by the exemplary embodiment of this application is shown.

[0055] Figure 8 The structural schematic diagram of an information publishing device provided by the exemplary embodiment of this application is shown.

[0056] Figure 9 The structural schematic diagram of a computing device for information publishing provided by this application is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0058] It should be noted that the technical solution of the embodiment of the present application is applicable to a network virtual environment, and the user described generally refers to a "virtual user". A real user can register a user account in the server through a registration method to obtain a user identity in the network environment. The same user account can log in to the server through different types of clients, so that the server can identify the same user. For example, the user of the embodiment of the present application can be a service provider stationed in the e-commerce service system.

[0059] The interaction between the server and the user can be implemented based on the user account, and the corresponding data received or sent by the server to the user is also implemented based on the user account. In fact, it is the client corresponding to the user account that receives or sends the corresponding data to the server. In addition, users can also communicate with each other through user accounts. Among them, users can refer to individuals or organizations, such as enterprises, etc., and this application does not impose specific restrictions on this.

[0060] It should be noted that, in the case of user information involved in the embodiments of the present application, the user information (including but not limited to user accounts, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse. In addition, the various artificial intelligence models involved in this application (including but not limited to visual models or large models) comply with relevant laws and standards.

[0061] In addition, it should be noted that, in the case where the embodiments of the present application involve user interaction operations or trigger operations, the user interaction operations or trigger operations involved in the embodiments of the present application include but are not limited to: touch operation, gesture operation, voice operation, head movement operation, eye movement operation and other interactive operations in various ways; among which, touch operation includes but is not limited to: click operation, double-click operation, long press operation, sliding operation, pinch operation or mouse hover operation, etc. Sliding operation includes but is not limited to: straight line sliding, curve sliding, etc.

[0062] Furthermore, it should be noted that, in the case where the embodiments of the present application involve the jump between the first interface and the second interface, the jump methods involved in the embodiments of the present application include but are not limited to: directly jumping from the first interface to the second interface, first jumping from the first interface to the task interface and then jumping to the second interface when corresponding task operations are completed on the task interface; the completion of the corresponding task operations on the task interface includes but is not limited to: when the task interface is implemented as a user interface, completing the operation of displaying a release prompt message on the user interface, and so on

[0063] Currently, when a service provider wants to publish content in an e-commerce service system, it usually needs to conceive a copywriting and then manually input the conceived copywriting into the information publishing interface for publication. The entire publishing process is costly and inefficient; in addition, there may also be problems such as poor content quality and serious homogenization in manually editing and publishing information. To address this technical problem, the present application provides a solution. The basic idea is that the server sends a release prompt message to the client so that the client can display it on the user interface; in response to the information generation request sent for the relevant operations triggered by the client for the release prompt message, at least one image is obtained, and the first artificial intelligence model is used to parse the target service category corresponding to at least one image, and a target copywriting is generated according to the target service category. The target copywriting and the target service category are sent to the client for the client to display on the information generation interface. In response to the information confirmation request sent for the confirmation operation triggered by the client for the information generation interface, information publishing content is generated according to at least one image and the target copywriting, and it is published under the corresponding user account of the client. The solution of the embodiments of the present application enables the service provider to upload at least one image through the guidance of the client even without copywriting editing experience, and then the server uses the artificial intelligence model to automatically parse the target service category based on the image uploaded by the client and generate a high-quality target copywriting that conforms to the target service category for the user to confirm and publish. The entire process does not require manual conception and editing operations, greatly improving the information publishing efficiency and reducing the publishing cost. In addition, the artificial intelligence model cited in this solution can show powerful capabilities in the field of natural language generation through continuous training and optimization, thereby ensuring the generation of high-quality and personalized target copywriting, avoiding the homogenization of copywriting content, enhancing the attractiveness of the copywriting content, and thus improving the service conversion rate.

[0064] Next, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0065] Figure 1The figure shows an architecture diagram of a technical solution of an embodiment of the present application that can be applied to information publishing. For example, the system can be an e-commerce service system. The system architecture can include a client 101 and a server 102. (Or: It may include a server and multiple clients; or it may include a server, a first client, and a second client, etc.)

[0066] Among them, a connection can be established between the client 101 and the server 102 through a network. The network provides a medium for the communication link between the client 101 and the server 102. The network can include various connection types, such as wired, wireless, or fiber optic cables, etc. The client 101 can interact with the server 102 through the network to receive or send messages, etc.

[0067] Among them, the client 101 can be a browser, an APP (Application), a web application such as an H5 (HyperText Markup Language 5) application, a light application (also known as a mini-program, a lightweight application program), or a cloud application, etc. The client 101 can be deployed in an electronic device and needs to rely on the device or certain apps in the device to run, etc. The electronic device can, for example, have a display screen and support information browsing, etc., such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, a smart speaker, a smart watch, etc. For the sake of easy understanding, Figure 1 the client is mainly represented by the image of the device in the figure. Various other types of applications can usually be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. The electronic device can refer to a device used by a user and having functions required by the user, such as computing, accessing the Internet, communicating, etc., such as a mobile phone, a tablet computer, a personal computer, a wearable device, etc. The electronic device usually can include at least one processing component and at least one storage component. The electronic device may also include basic configurations such as a network card chip, an IO (input / output) bus, and audio-video components. The present application does not limit this. Optionally, according to the implementation form of the electronic device, some peripheral devices can also be included, such as a keyboard, a mouse, a stylus, a printer, etc. The present application does not limit this.

[0068] The server 102 can include servers that provide various services, such as a server that processes requests sent by the client 101.

[0069] It should be noted that the server 102 can be implemented as a distributed server cluster composed of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), as well as big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0070] It should be noted that the information publishing method provided in the embodiments of the present application is generally jointly executed by the client 101 and the server 102. It should be understood that Figure 1 the numbers of the client and the server in [[ ]] are only illustrative. According to the implementation requirements, there can be any number of clients and servers.

[0071] The implementation details of the technical solutions of the embodiments of the present application are elaborated in detail below.

[0072] Figure 2 is a flowchart of an embodiment of an information publishing method provided by the present application. The technical solution of this embodiment can be executed by the server. As Figure 2 shown, the method may include the following steps:

[0073] S201, sending a publishing prompt message to the client so that the client can display the publishing prompt message in the user interface.

[0074] Among them, the publishing prompt message can be a prompt message used to remind the user of the client (such as the service provider registered in the e-commerce service system) that content can be published. For example, it can include, but is not limited to: trigger components for information publishing, text or icon and other prompt messages.

[0075] The user interface can be an interface provided by the e-commerce service system for the user to operate. For example, it can include, but is not limited to: the system home page, personal home page, service display page, etc.

[0076] In this embodiment, the server can send the publishing prompt message to the client when it detects that the client needs to display the user interface. At this time, the client will add the received publishing prompt message to the user interface and then display it to the user. The server can also send the publishing prompt message together when sending user interface-related data (such as interface text, images, components, etc.) to the client. At this time, the client can render the user interface-related data and the publishing prompt message to the user interface together.

[0077] Optionally, the way for the client to add a publishing prompt message to the user interface can be to add a trigger component for information publishing to a preset position in the user interface (such as the operation bar at the bottom of the interface), and then add a publishing icon and text to the trigger component. At this time, when the publishing prompt message is displayed in the user interface, it can be to display the trigger component with the publishing icon added at the preset position in the user interface, and the text "Publish" is displayed below the icon for the user to identify.

[0078] It should be noted that since the user interface in this embodiment may be various types of interfaces, the client needs to add and display the publishing prompt message in each type of user interface. Thus, it is realized to support the user to trigger an information generation request from multiple user interfaces to complete the information publishing operation. The convenience and flexibility of the information publishing trigger method are improved. In addition, in order to improve the diversity of the user interface, this embodiment can also add and display the publishing information through different rendering methods for different types of user interfaces. This is not limited here.

[0079] S202, receive the information generation request sent by the client.

[0080] Among them, the information generation request can be a request for the server to generate a text based on the images included in the request. The information generation request includes at least one image; the at least one image is obtained by the client in response to an image upload operation triggered by the publishing prompt message.

[0081] Optionally, when the client displays the user interface to the user, if a trigger operation for the publishing prompt message is detected, for example, a click operation on the publishing component in the user interface, it indicates that the user has a content publishing requirement at this time. At this time, the client will jump from the current user interface to the image upload interface, and then in response to the image upload operation on the image upload interface, obtain at least one image, and then based on the obtained at least one image, initiate an information generation request to the server.

[0082] Specifically, the image upload interface can be an interface that reminds the user to upload photos. It can be the thumbnail interface of the album on the terminal device where the client is located. At this time, the selection operation of the user for at least one album thumbnail can be used as the image upload operation for the image upload interface. That is to say, the client can obtain at least one thumbnail selected by the user for the selection operation of at least one album thumbnail as at least one image obtained. The image upload interface can also be the camera shooting interface of the terminal device where the client is located. At this time, the shooting operation triggered by the user for the camera shooting interface can be used as the image upload operation for the image upload interface. That is to say, the client can obtain at least one image taken for the shooting operation triggered by the camera shooting interface. To prevent a large number of images from affecting the efficiency of copywriting generation, in this embodiment, there can be an upper limit requirement for the number of images obtained by the client. For example, at most 6 images can be obtained.

[0083] After the client obtains at least one image, it can generate an information generation request including at least one obtained image and send the information generation request to the server. Correspondingly, the server will receive the information generation request sent by the client.

[0084] S203, Parse the target service category corresponding to at least one image using the first artificial intelligence model.

[0085] Among them, the first artificial intelligence model can be a model with the function of parsing the target service category corresponding to the image and generating the target copy corresponding to the target service category. This artificial intelligence model can be a language model (LM) or a multimodal model (LM) based on artificial intelligence, etc. The embodiments of the present application do not limit the number of model parameters supported by the model, and aim to meet the actual needs. If the number of model parameters is relatively large, the scale of the language model will be relatively large and the model performance will be relatively better. Of course, more time and resources will be consumed during inference or training; if the number of model parameters is relatively small, the scale of the model will be relatively small. When the performance meets the requirements, the model is more lightweight and consumes relatively less time and resources during inference or training. The artificial intelligence model involved in the embodiments of the present application can be a deep learning model used to process and generate natural language text or multimodal data. It can be implemented based on a neural network architecture and can be pre-trained on a large amount of data. In an optional implementation, the artificial intelligence model involved in this article can include an encoder, a decoder, a self-attention layer, and a feed-forward neural network, etc. The encoder is mainly used to convert the input data (usually in the form of a sequence) into a vector representation, and this process can capture the semantic features of the input data. The decoder is responsible for converting the intermediate representation generated by the encoder into output data (usually in the form of a sequence). The self-attention layer is a mechanism that enables the model to pay attention to other positions in the sequence to better encode the information of the current position; the feed-forward neural network is used to perform non-linear transformations on the output of the self-attention layer, etc., to enhance the model's expression ability. Each part works together to make the model constructed based on them perform well in various complex processing tasks, such as natural language processing, computer vision, speech recognition, machine translation, text summarization, and intelligent question answering, etc.

[0086] The target service category can be a second-level, third-level, or fourth-level subcategory of all services provided by the e-commerce service system. Among them, the second-level category can be an industry classification. For example, the cleaning industry, the repair industry, the moving industry, etc. The third-level category can be the service categories under each industry. For example, the service categories under the repair industry can further include: air conditioner repair, furniture repair, TV repair, etc.

[0087] Optionally, this embodiment may generate a prompt instruction based on role settings, at least one image, a task description, an output format indication, etc., and input it into the first artificial intelligence model to guide the artificial intelligence model to analyze the target service category corresponding to at least one image. Optionally, this embodiment may only identify the industry classification of at least one image, or only identify the service category of at least one image. It may also be to identify both the industry classification and the service category.

[0088] In some embodiments, to improve the accuracy of target service category recognition, this embodiment may use the first artificial intelligence model to perform content analysis on at least one image to obtain the image content corresponding to each of the at least one image; use the first artificial intelligence model to combine the image content corresponding to each of the at least one image to analyze the target service category corresponding to the at least one image. Specifically, it may be to first guide the artificial intelligence model to analyze the image content of each image through a prompt instruction, such as the text, objects, and scene features that appear, and then analyze the image content of each image, extract the core keywords related to the service scenario, and accurately express the service scenario represented by the image, and finally output the target industry category corresponding to the at least one image.

[0089] Optionally, there are many ways to use the first artificial intelligence model to combine the image content corresponding to each of the at least one image to analyze the target service category corresponding to the at least one image. For example, one implementable way may be to use the first artificial intelligence model to analyze at least one candidate service category corresponding to each image for each image content, and then count the number of times they appear for all the analyzed candidate service categories, and use the service category with the most occurrences as the target service category.

[0090] Another implementable way may be: use the first artificial intelligence model to perform service category recognition on the image content corresponding to each of the at least one image to obtain the candidate service categories corresponding to each of the at least one image and the confidence levels of the candidate service categories; screen the target service category from the candidate service categories according to the confidence levels of the candidate service categories.

[0091] Specifically, it may be to use the first artificial intelligence model to parse at least one candidate service category corresponding to each image for the image content of each image, and at the same time output the confidence that the image content belongs to each candidate service category. Then, based on the confidence of each candidate service category, score each candidate service category. For example, for each candidate service category, the confidence corresponding to the candidate service category may be summed or averaged to obtain the score value of the candidate service category. Then, the candidate service category with the highest score value is used as the target service category. In this implementation manner, when determining the target service category, the candidate service categories and their confidences of each image are parsed, and the target service category is filtered based on the confidence, which further improves the accuracy of determining the target service category.

[0092] Another implementable manner may be to first screen the target service category according to the number of occurrences of each candidate service category. If the number of candidate service categories with the highest number of occurrences is at least two, then based on the confidences corresponding to these at least two candidate service categories, select the candidate service category with a high confidence as the target service category.

[0093] It should be noted that if the target service category in this embodiment includes both the target industry classification and the target service category at the same time, for the target industry classification, the candidate industry classification and its corresponding confidence corresponding to each image can be parsed, and then based on a manner similar to the above embodiment, the target industry classification is screened from the candidate industry classifications according to the confidences corresponding to each candidate industry classification. For the target service category, the candidate service category and its corresponding confidence corresponding to each image can be parsed, and then based on a manner similar to the above embodiment, the target service category is screened from the candidate service categories according to the confidences corresponding to each candidate service category.

[0094] In some embodiments, in order to further improve the accuracy of the identified target service category, this embodiment may also obtain the user portrait information corresponding to the client; use the first model to parse the target service category corresponding to at least one image in combination with at least one image and the user portrait information. Specifically, the user portrait information may be a user portrait maintained by the e-commerce service system based on in-site information, such as including but not limited to: the service categories filled in by the user in the merchant information, the service categories followed by the user in the system, and the user's historical release information, etc. Specifically, based on the above embodiment, the user portrait information can be added as a prompt word to the prompt instruction to guide the artificial intelligence model to parse the target service category. Since the user portrait is further considered, the target service category parsed in this way will be more in line with the services provided by the user, thereby improving the accuracy of the target service category.

[0095] S204. Use the first artificial intelligence model to generate target copy for at least one image according to the target service category.

[0096] Among them, the target copy can be the copy used for information content release. Optionally, the target copy can be in text form.

[0097] In this embodiment, a prompt instruction can be generated based on role setting, the target service category corresponding to at least one image, task description, output format indication, etc., and input to the first artificial intelligence model to guide the artificial intelligence model to generate the target copy matching the target service category.

[0098] Optionally, in order to further improve the quality and originality of the generated target copy. This embodiment can also use the first artificial intelligence model to generate the target copy according to both the target service category and the image content of at least one image. At this time, the generated target copy not only conforms to the target service category, but also improves the relevance with at least one image, greatly improving the quality of the target copy. In addition, since the images uploaded by different users through the client are usually different, so this embodiment combines the image content when generating the target copy, which can further improve the originality of the target copy and avoid the appearance of homogeneous copy.

[0099] S205. Send the target copy and the target service category to the client so that the client can display the target copy and the target service category on the information generation interface.

[0100] Optionally, after generating the target copy based on the artificial intelligence model, the server can send the generated target copy and the identified target service category to the client together.

[0101] The client will display the target service category parsed by the artificial intelligence model and the target copy to the user on the information generation interface. For example, Figure 3 A schematic diagram of an information generation interface is shown, where 301 is the displayed target copy. The corresponding public decoration and design planning of 302 is the displayed target service category.

[0102] In some embodiments, in order to reduce the waiting anxiety of users, when generating the target copy based on the artificial intelligence model, the server of this embodiment can send the content of the generated target copy to the client in real time, so that the client can display the generated target copy in real time through the information generation interface during the process of the server generating the target copy. It should be noted that in order to allow users to view more quickly whether the target service category parsed by the artificial intelligence model is accurate, the server of this implementation can send it to the client for display after parsing the target service category. It can also be sent together with the target service category when sending the content of the target copy for the first time. There is no limitation on this.

[0103] S206. In response to an information confirmation request sent by the client, generate information release content corresponding to the target service category according to at least one image and the target copywriting.

[0104] Among them, the information confirmation request is generated by the client in response to a confirmation operation triggered on the information generation interface. Specifically, after the client displays the target copywriting and the target service category on the information generation interface, the user can view the target copywriting and the target service category automatically generated by the server on the information generation interface. If the user believes that the target copywriting and the target service category meet their needs and can be published, the user will trigger a confirmation operation on the information generation interface. For example, click the Figure 3 "Confirm and Publish" button in. After detecting the confirmation operation triggered on the information generation interface, the client will generate an information confirmation request and send it to the server.

[0105] The information release content can be the specific content published in the e-commerce service system. It includes at least: at least one image uploaded by the user sent by the client, and the target copywriting generated by the artificial intelligence model. Optionally, after receiving the information confirmation request sent by the client, the server can call the content release template, add at least one image and the target copywriting to the corresponding positions of the content release template, and generate the information release content.

[0106] To further improve the richness of the information release content, when sending the target copywriting and the target service category to the client in this embodiment, the target copywriting, the target service category, and the optional item prompt information can be sent to the client, so that the client can display the release content, the target service category, and the optional item prompt information on the information generation interface; obtain the optional content sent by the client. Correspondingly, when performing the operation of S206, the server can, in response to the information confirmation request sent by the client, generate information release content corresponding to the target service category according to at least one image, the target copywriting, and the optional content.

[0107] Among them, the optional item prompt information can be the information that prompts the user to fill in optionally when publishing the copywriting, and can be the name of the optional item, such as service area, address, contact information, price, etc. It can also be the name of the optional item and its corresponding optional content. For example, for the optional item name of service area, its corresponding optional content can be 34 provincial-level administrative regions in the country. The optional content is generated based on the filling operation of the optional item prompt information.

[0108] Specifically, the server can obtain the pre-set optional item prompt information and send it to the client together with the target copywriting and the target service category, so that the client can display it on the information generation interface. In this embodiment, different optional item prompt information can also be set for different target service categories. At this time, the server can obtain the optional item prompt information corresponding to the target service category and send it to the client together with the target copywriting and the target service category, so that the client can display it on the information generation interface. For example, Figure 3 The content in the square box 303 is the optional item prompt information displayed on the information generation interface. After the client displays the optional item prompt information, it can obtain the filling operation performed by the user on the optional item prompt information. For example, it can obtain the optional content entered by the user at the optional item prompt information, or select the optional content from the optional content corresponding to the optional item name. After the client obtains the optional content, it will send it to the server. After receiving the optional content, the server will further wait for the client to send an information confirmation request, and after receiving the information confirmation request, it will call the content publishing template to add at least one image, the target copywriting, and the optional content to the corresponding positions of the content publishing template to generate the information publishing content.

[0109] S207, obtain the user account corresponding to the client and publish the information publishing content under the user account.

[0110] Optionally, after generating the information publishing content, the server will obtain the user account corresponding to the client that sends the information confirmation request. Specifically, there are many ways for the server to obtain the user account corresponding to the client. For example, the client can carry the user account when sending the information confirmation request to the server, and at this time, the server can directly obtain it from the information confirmation request. It can also be that the client carries the client identifier when sending the information confirmation request to the server. At this time, the server can obtain the client identifier from the information confirmation request and then further search for the user account corresponding to the client identifier. After obtaining the user account, publish the generated information publishing content under the user account.

[0111] In some embodiments, in order to ensure the integrity of the content published under the user account, this embodiment can detect whether the generated information publishing content is complete before obtaining the user account corresponding to the client, such as whether it contains information such as a title, a description, a target service category, an image, etc. If it is complete, then perform the operation of obtaining the user account corresponding to the client and publishing the information publishing content under the user account.

[0112] In some embodiments, in order to let the user understand the information publishing status, the server in this embodiment can also feedback a publishing success prompt information to the client after publishing the information publishing content under the user account, so that the client can jump from the information generation interface to the information publishing interface and display the publishing success prompt information on the information publishing interface.

[0113] In this embodiment, the server sends a release prompt message to the client so that the client can display it on the user interface; in response to an information generation request sent for a related operation triggered by the client for the release prompt message, at least one image is obtained, and the first artificial intelligence model is used to parse the target service category corresponding to the at least one image, and a target copywriting is generated according to the target service category. The target copywriting and the target service category are sent to the client for the client to display on the information generation interface. In response to an information confirmation request sent for a confirmation operation triggered by the client for the information generation interface, an information release content is generated according to the at least one image and the target copywriting, and is released under the user account corresponding to the client. The solution of the embodiment of the present application enables the service provider to upload at least one image under the guidance of the client even without copywriting editing experience, and then the server uses the artificial intelligence model to automatically parse the target service category based on the image uploaded by the client, and generates a high-quality target copywriting that meets the target service category for the user to confirm and release. The entire process does not require manual conception and editing operations, greatly improving the information release efficiency and reducing the release cost. In addition, the artificial intelligence model cited in this solution can show powerful capabilities in the field of natural language generation through continuous training and optimization, so as to ensure the generation of high-quality and personalized target copywriting, avoid the homogenization of copywriting content, enhance the attractiveness of the copywriting content, and thus improve the service conversion rate.

[0114] In some embodiments, since there are many users in the e-commerce service system and the computing power of the artificial intelligence model is limited, in order to better provide users with the service of automatically generating and releasing information. This embodiment can classify users by level. For example, users can be classified by whether they have purchased the service, or users can be classified by the length of time they have joined the system. Correspondingly, when the server uses the first artificial intelligence model to parse the target service category corresponding to at least one image, it can obtain the level information of the user account corresponding to the client; when the level information meets the level requirements, the first artificial intelligence model is used to parse the target service category corresponding to at least one image.

[0115] Specifically, the server can first obtain the user account corresponding to the client (the specific obtaining method has been introduced in the above embodiments and will not be elaborated here), then determine the level information of the user account according to the pre-set level division rules, and then further determine whether the level information of the user account meets the level requirements for automatically generating and publishing information. For example, whether the user account is a membership account, or whether the registration duration of the user account is greater than or less than the preset duration, etc. If it is determined that the level requirements are met, then further execute parsing the target service category corresponding to at least one image by using the first artificial intelligence model. Thus, the function of automatically generating and publishing information is provided to the entitled users.

[0116] Based on the above embodiments, this embodiment can further screen the users who enjoy automatically generating and publishing information, that is, when the level information meets the level requirements, obtain the remaining parsing times corresponding to the user account; when the remaining parsing times meet the times requirements corresponding to the level information, use the first artificial intelligence model to parse the target service category corresponding to at least one image.

[0117] Specifically, in this embodiment, the remaining parsing times meeting the times requirements corresponding to the level information can be that the remaining parsing times are greater than 0, or different times requirements can be set for different level information. For example, for high-level users, when they use the function of automatically generating and publishing information once, the remaining parsing times are reduced by 1, and at this time, the times requirements corresponding to high-level users are greater than 0; for low-level users, when they use the function of automatically generating and publishing information once, the remaining parsing times are reduced by 2, and at this time, the times requirements corresponding to low-level users are greater than 1.

[0118] In this example, the server can, when determining that the level information meets the level requirements, further obtain the remaining parsing times corresponding to the user account; then, according to the level information corresponding to the user account, determine whether its remaining parsing times meet the times requirements corresponding to the level information. If so, use the first artificial intelligence model to parse the target service category corresponding to at least one image. By screening in two steps, it is determined whether the user of the client can enjoy the function of automatically generating and publishing information, so as to accurately provide intelligent publishing services for a small number of entitled customers.

[0119] In some embodiments, in order to enable the users of the client to understand the progress of the artificial intelligence model's parsing of images in real time, this embodiment may also generate parsing progress prompt information when using the first artificial intelligence model to parse the target service categories corresponding to at least one image and generating the target copy corresponding to at least one image according to the target service categories; send the parsing progress prompt information to the client, so that during the process of the server parsing the target service categories and generating the target copy corresponding to at least one image according to the target service categories, the client can display the parsing progress prompt information through the image parsing interface.

[0120] Optionally, when using the first artificial intelligence model to parse the target service categories corresponding to at least one image, the server may generate multi-step parsing progress prompt information based on the parsing logic of the artificial intelligence model. For example, the parsing information prompt information may be analyzing the target service categories and generating the target copy. It may also be analyzing the image content, analyzing the industry classification, analyzing the service category, and generating the target copy. Then send the generated parsing progress prompt information to the client, so that the client can display the parsing progress prompt information in a carousel through the image parsing interface. If the first artificial intelligence model outputs the parsing progress during the process of parsing the target service category and generating the target copy, the parsing progress output by the first artificial intelligence model in real time can be used as the parsing progress prompt information and sent to the client, so that the client can display the currently obtained parsing progress prompt information through the image parsing interface. Exemplarily, Figure 4 Region 401 in

[0121] In the above embodiment, if the user feels that it takes a long time for the artificial intelligence model to parse the image or generate the target copy, the user can choose to skip the intelligent analysis process. Specifically, it can be Figure 4 click the "Skip Intelligent Analysis" button on the

[0122] Specifically, during the process of the client parsing an image using an artificial intelligence model, a parsing progress prompt message will be displayed on the image parsing interface. When the client detects a parsing skip operation on the image parsing interface, it will generate a parsing skip instruction and send it to the server. The server will respond to this parsing skip instruction, first pause the operation currently being executed by the artificial intelligence model, and then send an interface jump instruction to the client. After receiving this interface jump instruction, the client will jump from the current image parsing interface to the copywriting input interface. It should be noted that the copywriting input interface at this time can be an interface for the user to manually enter the copywriting title and copywriting description content. After the client jumps to this copywriting input interface, the user can manually enter the relevant content of the copywriting (i.e., enter the copywriting) in this copywriting input interface. The client will display the entered copywriting in real time on the copywriting input interface. When the user finishes entering, a publishing operation will be triggered. After the client detects the publishing operation triggered by the user, it will generate a publishing confirmation request containing the entered copywriting and send it to the server. The server will extract the entered copywriting from the publishing confirmation request, combine it with at least one image previously sent by the client, generate information publishing content, then obtain the user account corresponding to the client, and publish this information publishing content under the user account. This embodiment can not only automatically generate and publish copywriting for the user, but also allow the user to independently publish copywriting according to the user's needs, which can meet the various needs of different users and improve the flexibility of the solution.

[0123] In some embodiments, to better meet the personalized needs of users and improve the flexibility of the solution. This solution can also support users to participate in the editing of the copywriting, which can be to receive a copywriting editing request sent by the client, and the copywriting editing request contains the editing content; use the first artificial intelligence model to generate the target copywriting in combination with the editing content. Specifically, it can include but is not limited to the following application scenarios:

[0124] Scenario 1: The user chooses to skip the intelligent analysis of the artificial intelligence model and needs to manually enter the copywriting on the copywriting input interface. If the user only has the copywriting title in mind but doesn't know how to write the content, at this time, the user can only enter the copywriting title and then click the trigger button for the copywriting editing request on the interface. Such as the "AI Helps You Write" button. After the client detects this operation, it will use the copywriting title manually entered by the user as the editing content, generate a copywriting editing request containing this copywriting title, and send it to the server. The server will respond to this request to obtain the copywriting title (i.e., the editing content), and use the first artificial intelligence model to generate the copywriting content based on this copywriting title.

[0125] Scenario 2: The user chooses to skip the intelligent analysis of the artificial intelligence model. After manually entering the copywriting title and content in the copywriting input interface, the user still wants the artificial intelligence model to polish the copywriting she wrote. At this time, the user can click the copywriting editing request trigger button in the interface, such as the "AI helps you polish" button. After the client detects this operation, it will use the copywriting title and content manually entered by the user as the editing content, generate a copywriting editing request containing this editing content, and send it to the server. The server will respond to this request to obtain the editing content and use the first artificial intelligence model to appropriately modify this editing content to generate the target copywriting.

[0126] Scenario 3: When generating the target copywriting corresponding to at least one image, the artificial intelligence model of this embodiment can set the copywriting style. The initial copywriting style can be selected by the user, randomly selected by the model, or determined according to the content of the image, etc. After the client displays the target copywriting automatically generated by the artificial intelligence model in the information generation interface, if the user is not satisfied with the style of the target copywriting, the user can choose to modify the copywriting style. For example, in Figure 3 the style selection area, adjust the R1 full blood version to the X1 passion version. At this time, the newly selected target style by the user can be used as the editing content, generate a copywriting editing request containing this editing content, and send it to the server. The server will respond to this request to obtain the editing content and use the first artificial intelligence model based on the target style to generate the target copywriting corresponding to at least one image.

[0127] It should be noted that after generating the target copywriting in this embodiment, the execution process of the above embodiment can be referred to. For example, send the target copywriting to the client so that the client can display it in the information generation interface or update the target copywriting currently displayed in the information generation interface; after the server receives the information confirmation request sent by the client, generate the information release content corresponding to the target service category according to at least one image and this target copywriting; and then obtain the user account corresponding to the client and publish the information release content under the user account.

[0128] In some embodiments, in order to provide users with more choices of copywriting versions and avoid the appearance of homogeneous copywriting, in this embodiment, the server can also provide multiple different artificial intelligence models for users to choose from. For example, the user can click the "switch" button in the Figure 3 interface shown, which can trigger the client to generate a model switching request and send it to the server. The server receives the model switching request sent by the client; determines the second artificial intelligence model corresponding to the model switching request, and uses the second artificial intelligence model in combination with the target service category to regenerate the target copywriting corresponding to at least one image; sends the regenerated target copywriting to the client so that the client can update the target copywriting displayed in the information generation interface.

[0129] Specifically, there are many ways for the server to determine the second artificial intelligence model corresponding to the model switching request. For example, it can be selected by the user himself. In this case, the model switching request sent by the client contains the second artificial intelligence model, and the server can directly obtain it from the model switching request. It can also be that the server selects one from other optional artificial intelligence models as the second artificial intelligence model according to a certain strategy.

[0130] After determining the second artificial intelligence model, the process of regenerating the target copywriting by using the second artificial intelligence model in combination with the target service category is similar to the process of generating the target copywriting by the first artificial intelligence model in the above embodiment, and will not be elaborated here. The target copywriting generated by the server will be sent to the client again so that the client can replace the target copywriting generated by the first artificial intelligence model with the target copywriting generated by the second artificial intelligence model in the information generation interface.

[0131] Figure 5 The flowchart of another embodiment of an information publishing method provided by this application, and the technical solution of this embodiment can be executed by the client. As Figure 5 shown, the method may include the following steps:

[0132] S501, Receive the publishing prompt information sent by the server.

[0133] S502, Display the publishing prompt information in the user interface.

[0134] S503, In response to the trigger operation for the publishing prompt information, jump from the user interface to the image upload interface.

[0135] S504, In response to the image upload operation for the image upload interface, obtain at least one image.

[0136] S505, Based on at least one image, send an information generation request to the server so that the server can use the first artificial intelligence model to parse the target service category corresponding to at least one image, and generate the target copywriting corresponding to at least one image according to the target service category.

[0137] S506, Receive the target copywriting and the target service category sent by the server.

[0138] S507, Display the target copywriting and the target service category in the information generation interface.

[0139] S508, In response to the confirmation operation triggered for the information generation interface, generate an information confirmation request.

[0140] S509. Send an information confirmation request to the server so that the server can generate information release content corresponding to the target service category based on at least one image and the target copywriting, and obtain the user account corresponding to the client, and release the information release content under the user account.

[0141] In some embodiments, in order to further improve the richness of the information release content, the steps of the above solutions S506 and S507 may further include: receiving the target copywriting, the target service category, and the optional item prompt information sent by the server, and displaying the release content, the target service category, and the optional item prompt information on the information generation interface.

[0142] Correspondingly, it further includes: generating optional content in response to an operation of filling in the optional item prompt information; generating an information confirmation request including the optional content after detecting an information confirmation operation, and sending the information confirmation request to the server so that the server can generate information release content corresponding to the target service category based on at least one image, the target copywriting, and the optional content in response to the information confirmation request.

[0143] In some embodiments, in order to enable the user of the client to understand the progress of the artificial intelligence model parsing the image in real time, before executing S506, it may further include: receiving the parsing progress prompt information sent by the server, and displaying the parsing progress prompt information through the image parsing interface during the process of the server parsing the target service category and generating the target copywriting corresponding to the at least one image according to the target service category.

[0144] In some embodiments, in order to meet the user's need for autonomous copywriting editing, the above solution further includes: generating a skip instruction in response to a parsing skip operation on the image parsing interface, and sending the skip instruction to the server; receiving the interface jump instruction sent by the server, and jumping from the image parsing interface to the copywriting input interface; obtaining the input copywriting generated by the input operation on the copywriting input interface, and generating a release confirmation request based on the input copywriting after detecting a release confirmation operation, and sending the release confirmation request to the server so that the server can generate information release content according to the at least one image and the input copywriting in response to the release confirmation request.

[0145] In some embodiments, in order to better meet the user's personalized needs and improve the flexibility of the solution. The above solution further includes: generating a copywriting editing request according to the editing content corresponding to the editing operation, and sending the copywriting editing request to the server so that the server can use the first artificial intelligence model to generate the target copywriting in combination with the editing content.

[0146] In some embodiments, in order to provide users with more options for copywriting versions and avoid the appearance of homogeneous copywriting, the above solution further includes: in response to a model switching operation triggered on the information generation interface, sending a model switching request to the server, so that the server determines a second artificial intelligence model corresponding to the model switching request, and using the second artificial intelligence model in combination with the target service category to regenerate the target copywriting corresponding to the at least one image;

[0147] Receive the target copywriting resent by the server and update the target copywriting displayed in the information generation interface.

[0148] It should be noted that the process and beneficial effects of the client in this embodiment implementing the above information prompt method have been introduced in the above embodiments and will not be elaborated here.

[0149] Figure 6 The signaling diagram of an information publishing method for an application scenario provided by an exemplary embodiment of the present application is shown. This method is jointly implemented by the client and the server. Specifically, it includes the following steps:

[0150] S601, the server sends a publishing prompt message to the client.

[0151] S602, the client displays the publishing prompt message in the user interface.

[0152] S603, in response to a trigger operation on the publishing prompt message, the client jumps from the user interface to the image upload interface.

[0153] S604, in response to an image upload operation on the image upload interface, the client obtains at least one image.

[0154] S605, based on the at least one image, the client sends an information generation request to the server.

[0155] S606, in response to the information generation request, the server obtains the level information of the user account corresponding to the client.

[0156] S607, when the level information meets the level requirements, the server obtains the remaining parsing times corresponding to the user account.

[0157] S608, when the remaining parsing times meet the times requirements corresponding to the level information, the server uses a first artificial intelligence model to parse the target service category corresponding to the at least one image, and generates the target copywriting corresponding to the at least one image according to the target service category.

[0158] Specifically, the first artificial intelligence model may infer the target service category in the following manner: use the first artificial intelligence model to perform content analysis on the at least one image to obtain the image content corresponding to each of the at least one image; then perform service category recognition on the image content corresponding to each of the at least one image to obtain the candidate service category corresponding to each of the at least one image and the confidence level of the candidate service category; finally, screen the target service category from the candidate service categories according to the confidence level of the candidate service category.

[0159] S609, the server generates a parsing progress prompt message and sends it to the client.

[0160] Optionally, if the user feels that it takes a long time for the artificial intelligence model to parse the image or generate the target copywriting, the user can choose to skip the intelligent analysis process, which has been introduced in the above embodiments and will not be elaborated here.

[0161] S610, the client displays the parsing progress prompt message through the image parsing interface.

[0162] S611, the server sends the target copywriting, service category, and optional item prompt message to the client.

[0163] S612, the client displays the published content, target service category, and optional item prompt message on the information generation interface.

[0164] Optionally, after the client displays the target copywriting, the client can also perform operations such as editing the target copywriting by the user and switching the model to regenerate the target copywriting, which have been introduced in the above embodiments and will not be elaborated here.

[0165] S613, the client generates optional content in response to the filling operation for the optional item prompt message, and generates an information confirmation request including the optional content after detecting the information confirmation operation.

[0166] S614, the client sends the information confirmation request to the server.

[0167] S615, the server generates information publishing content corresponding to the target service category in response to the information confirmation request according to the at least one image, target copywriting, and optional content.

[0168] S616, the server obtains the user account corresponding to the client and publishes the information publishing content under the user account.

[0169] The detailed implementation manners and beneficial effects of each step in the method of this embodiment have been described in detail in the foregoing embodiments and will not be elaborated here.

[0170] It should be noted that in some of the processes described in the above embodiments and the accompanying drawings, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 608, 609, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any order of execution. Additionally, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0171] Figure 7 The structural schematic diagram of an information publishing device provided by an exemplary embodiment of the present application is shown. The device is configured on the server side and includes:

[0172] A first sending module 701, configured to send a publishing prompt message to the client, so that the client displays the publishing prompt message in the user interface;

[0173] A first receiving module 702, configured to receive an information generation request sent by the client, where the information generation request includes at least one image; the at least one image is obtained by the client in response to an image upload operation triggered for the publishing prompt message;

[0174] A model running module 703, configured to use a first artificial intelligence model to parse the target service category corresponding to the at least one image;

[0175] The model running module 703 is further configured to use the first artificial intelligence model to generate a target copy corresponding to the at least one image according to the target service category;

[0176] The first sending module 701 is further configured to send the target copy and the target service category to the client, so that the client displays the target copy and the target service category in the information generation interface;

[0177] An information generation module 704, configured to generate information publishing content corresponding to the target service category according to the at least one image and the target copy in response to an information confirmation request sent by the client; the information confirmation request is generated by the client in response to a confirmation operation triggered for the information generation interface;

[0178] An information publishing module 705, configured to obtain the user account corresponding to the client and publish the information publishing content under the user account.

[0179] In an alternative embodiment, it further includes a level verification module configured to obtain the level information of the user account corresponding to the client; when the level information meets the level requirements, through the model operation module 703, use the first artificial intelligence model to parse the target service category corresponding to the at least one image.

[0180] In an alternative embodiment, the level verification module is specifically configured to, when the level information meets the level requirements, obtain the remaining parsing times corresponding to the user account; when the remaining parsing times meet the times requirements corresponding to the level information, through the model operation module 703, use the first artificial intelligence model to parse the target service category corresponding to the at least one image.

[0181] In an alternative embodiment, the first sending module 701 is specifically configured to send the target copywriting, the target service category, and the optional item prompt information to the client, so that the client can display the release content, the target service category, and the optional item prompt information on the information generation interface; the content acquisition module is configured to acquire the optional content sent by the client, where the optional content is generated based on the filling operation of the optional item prompt information; the information generation module 704 is specifically configured to, in response to the information confirmation request sent by the client, generate the information release content corresponding to the target service category according to the at least one image, the target copywriting, and the optional content.

[0182] In an alternative embodiment, it further includes: a progress determination module configured to generate a parsing progress prompt information when using the first artificial intelligence model to parse the target service category corresponding to the at least one image and generate the target copywriting corresponding to the at least one image according to the target service category; the first sending module 701 is further configured to send the parsing progress prompt information to the client, so that the client can display the parsing progress prompt information through the image parsing interface during the process of the server parsing the target service category and generating the target copywriting corresponding to the at least one image according to the target service category.

[0183] In an optional embodiment, the model operation module 703 is further configured to, if a skip instruction sent by the client is received, pause the operation of parsing the target service category and the operation of generating the target copy corresponding to the at least one image; the skip instruction is generated for the parsing skip operation of the image parsing interface; the first sending module 701 is further configured to send an interface jump instruction to the client to instruct the client to jump from the image parsing interface to the copy input interface; the first receiving module 702 is further configured to receive a release confirmation request sent by the client; the release confirmation request includes the input copy generated for the input operation of the copy input interface; the information generation module 704 is further configured to generate information release content according to the at least one image and the input copy; the release confirmation request is generated by the client in response to a confirmation operation triggered on the copy input interface.

[0184] In an optional embodiment, the first receiving module 702 is further configured to receive a copy editing request sent by the client, and the copy editing request includes editing content; the model operation module 703 is further configured to use the first artificial intelligence model to generate a target copy in combination with the editing content.

[0185] In an optional embodiment, the first receiving module 702 is further configured to receive a model switching request sent by the client; the model determination module is configured to determine a second artificial intelligence model corresponding to the model switching request, and the model operation module 703 is further configured to use the second artificial intelligence model to re-generate the target copy corresponding to the at least one image in combination with the target service category; the first sending module 701 is further configured to send the re-generated target copy to the client so that the client can update the target copy displayed in the information generation interface.

[0186] In an optional embodiment, the model operation module 703 is specifically configured to use the first artificial intelligence model to perform content parsing on the at least one image to obtain the image content corresponding to each of the at least one image; use the first artificial intelligence model to parse the target service category corresponding to the at least one image in combination with the image content corresponding to each of the at least one image.

[0187] In an optional embodiment, the model operation module 703 is specifically configured to use the first artificial intelligence model to perform service category recognition on the image content corresponding to each of the at least one image to obtain the candidate service categories corresponding to each of the at least one image and the confidence levels of the candidate service categories; screen the target service category from the candidate service categories according to the confidence levels of the candidate service categories.

[0188] Figure 7 The information publishing device described above can execute Figure 2The information publishing method described in the illustrated embodiment will not be elaborated on its implementation principle and technical effects. For the 7 devices in the above embodiments, the specific ways in which each module and unit perform operations have been described in detail in the embodiments related to this method, and will not be elaborated here.

[0189] Figure 8 The figure shows a schematic structural diagram of another information publishing device provided by an exemplary embodiment of the present application. This device is configured on the client side and includes:

[0190] A second receiving module 801, configured to receive the publishing prompt information sent by the server;

[0191] An interface display module 802, configured to display the publishing prompt information in the user interface;

[0192] An interface jump module 803, configured to, in response to a trigger operation on the publishing prompt information, jump from the user interface to an image upload interface;

[0193] An image acquisition module 804, configured to, in response to an image upload operation on the image upload interface, acquire at least one image;

[0194] A second sending module 805, configured to, based on the at least one image, send an information generation request to the server, so that the server uses a first artificial intelligence model to analyze the target service category corresponding to the at least one image, and generate a target copy corresponding to the at least one image according to the target service category;

[0195] The second receiving module 801 is further configured to receive the target copy and the target service category sent by the server;

[0196] The interface display module 802 is further configured to display the target copy and the target service category in an information generation interface;

[0197] A request generation module 806, configured to, in response to a confirmation operation triggered on the information generation interface, generate an information confirmation request;

[0198] The second sending module 805 is further configured to send the information confirmation request to the server, so that the server generates information publishing content corresponding to the target service category according to the at least one image and the target copy, and obtain the user account corresponding to the client, and publish the information publishing content under the user account.

[0199] In an alternative embodiment, the second receiving module 801 is specifically configured to receive the target copywriting, the target service category, and the fill-in option prompt information sent by the server. The interface display module 802 is specifically configured to display the release content, the target service category, and the fill-in option prompt information on the information generation interface. The request generation module 806 is further configured to generate fill-in content in response to a filling operation for the fill-in option prompt information; and generate an information confirmation request including the fill-in content after detecting an information confirmation operation. The second sending module 805 is further configured to send the information confirmation request to the server, so that the server, in response to the information confirmation request, generates information release content corresponding to the target service category according to at least one image, the target copywriting, and the fill-in content.

[0200] In an alternative embodiment, the second receiving module 801 is further configured to receive the parsing progress prompt information sent by the server. The interface display module 802 is further configured to display the parsing progress prompt information through the image parsing interface during the process that the server parses the target service category and generates the target copywriting corresponding to the at least one image according to the target service category.

[0201] In an alternative embodiment, it further includes an instruction generation module, configured to generate a skip instruction in response to a parsing skip operation for the image parsing interface. The second sending module 805 is further configured to send the skip instruction to the server. The second receiving module 801 is further configured to receive the interface jump instruction sent by the server. The interface jump module 803 is further configured to jump from the image parsing interface to the copywriting input interface. The request generation module 806 is further configured to obtain the input copywriting generated by an input operation for the copywriting input interface, and generate a release confirmation request based on the input copywriting after detecting a release confirmation operation. The second sending module 805 is further configured to send the release confirmation request to the server, so that the server, in response to the release confirmation request, generates information release content according to the at least one image and the input copywriting.

[0202] In an alternative embodiment, the request generation module 806 is further configured to generate a copywriting editing request according to the editing content corresponding to an editing operation. The second sending module 805 is further configured to send the copywriting editing request to the server, so that the server uses the first artificial intelligence model to generate the target copywriting in combination with the editing content.

[0203] In an alternative embodiment, the second sending module 805 is further configured to send a model switching request to the server in response to a model switching operation triggered for the information generation interface, so that the server determines a second artificial intelligence model corresponding to the model switching request, and uses the second artificial intelligence model to combine with the target service category to regenerate the target copy corresponding to the at least one image; the second receiving module 801 is further configured to receive the target copy resent by the server; the interface display module 802 is further configured to update the target copy displayed in the information generation interface.

[0204] Figure 8 The described information publishing device can execute Figure 5 the information publishing method described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated. For the 8 devices in the above embodiments, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0205] Figure 9 It is a schematic structural diagram of an embodiment of a computing device provided by the present application. As Figure 9 shown, in practice, the computing device may include: a storage component 901 and a processing component 902.

[0206] The storage component 901 is used to store computer programs and can be configured to store various other data to support operations on the computing device. Examples of such data include instructions for any application program or method for operating on the computing device, data structures, contact data, phone book data, messages, pictures, videos, etc.

[0207] The processing component 902 is coupled to the storage component 901 and is configured to execute the computer programs in the storage component 901 to implement the information publishing method as Figure 2 or Figure 5 shown.

[0208] Further, as Figure 9 shown, the computing device may further include: other components such as a communication component 903, a display component 904, a power supply component 905, an audio component 906, etc. Figure 9 Only some components are schematically shown, and it does not mean that the computing device only includes Figure 9 the components shown. Additionally, Figure 9The components within the dashed-line box are optional components, rather than mandatory components, and are specifically determined according to the product form of the specific computing device. The computing device in this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, or an IOT (Internet of Things) device, or can also be a server device such as a conventional server, a cloud server, or a server array. If the computing device in this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, or a smart phone, it may include Figure 9 the components within the dashed-line box; if the computing device in this embodiment is implemented as a server device such as a conventional server, a cloud server, or a server array, it may not include Figure 9 the components within the dashed-line box.

[0209] The above processing component includes one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for executing the above method.

[0210] The above storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0211] The above communication component is configured to facilitate communication between the device where the communication component is located and other devices in a wired or wireless manner. The device where the communication component is located can access a wireless network based on a communication standard, such as a mobile communication network, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.

[0212] The above display component may include a screen, and the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operation.

[0213] The above power supply component provides power for various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device where the power supply component is located.

[0214] The above audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals. The received audio signals can be further stored in the memory or sent via the communication component. In some embodiments, the audio component further includes a speaker for outputting audio signals.

[0215] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to be able to implement the steps in the above method embodiments. Among them, the computer-readable storage medium can be implemented by volatile or non-volatile or a combination thereof, and can be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, Phase-change Random Access Memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), flash memory or other memory technologies, Compact Disc Read Only Memory (CD-ROM), Digital Video Disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices or any other non-transmission medium

[0216] Accordingly, an embodiment of the present application further provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the processor is caused to implement each step in the above method embodiments. It should be understood that each process or the combination of multiple processes in the above method flow can be implemented by the computer program or instructions. In addition, these computer programs or instructions can be applied to the processors of general-purpose computers, special-purpose computers, embedded processors or other programmable data processing devices, so that the processors of general-purpose computers, special-purpose computers, embedded processors or other programmable data processing devices can be used as devices to implement the corresponding functions in the above method embodiments.

[0217] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0218] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

[0219] Finally, it should be noted that the above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An information publishing method, characterized in that, Applied to the server side, including: Sending a release prompt message to the client so that the client can display the release prompt message in the user interface; Receiving an information generation request sent by the client, where the information generation request includes at least one image; the at least one image is obtained by the client in response to an image upload operation triggered for the release prompt message; Parsing the target service category corresponding to the at least one image using a first artificial intelligence model; Generating a target copy corresponding to the at least one image according to the target service category using the first artificial intelligence model; Sending the target copy and the target service category to the client so that the client can display the target copy and the target service category in the information generation interface; Responding to the information confirmation request sent by the client, generating information release content corresponding to the target service category according to the at least one image and the target copy; the information confirmation request is generated by the client in response to a confirmation operation triggered for the information generation interface; Obtaining the user account corresponding to the client and publishing the information release content under the user account.

2. The method according to claim 1, wherein The parsing the target service category corresponding to the at least one image using the first artificial intelligence model includes: Obtaining the level information of the user account corresponding to the client; When the level information meets the level requirement, parsing the target service category corresponding to the at least one image using the first artificial intelligence model.

3. The method according to claim 2, characterized in that, When the level information meets the level requirement, the parsing the target service category corresponding to the at least one image using the first artificial intelligence model includes: When the level information meets the level requirement, obtaining the remaining parsing times corresponding to the user account; When the remaining parsing times meet the times requirement corresponding to the level information, parsing the target service category corresponding to the at least one image using the first artificial intelligence model.

4. The method according to claim 1, wherein Sending the target copy and the target service category to the client includes: Sending the target copy, the target service category, and optional item prompt information to the client so that the client can display the release content, the target service category, and the optional item prompt information in the information generation interface; Obtaining the optional content sent by the client, where the optional content is generated based on a filling operation for the optional item prompt information; Correspondingly, responding to the information confirmation request sent by the client, generating information release content corresponding to the target service category according to the at least one image and the target copy includes: Responding to the information confirmation request sent by the client, generating information release content corresponding to the target service category according to the at least one image, the target copy, and the optional content.

5. The method according to claim 1, wherein It also includes: When parsing the target service category corresponding to the at least one image using the first artificial intelligence model and generating the target copy corresponding to the at least one image according to the target service category, generating a parsing progress prompt message; Send the parsing progress prompt information to the client, so that the client can display the parsing progress prompt information through the image parsing interface during the process of the server parsing the target service category and generating the target copy corresponding to the at least one image according to the target service category.

6. The method according to claim 5, characterized in that, It further includes: If a skip instruction sent by the client is received, pause the operation of parsing the target service category and the operation of generating the target copy corresponding to the at least one image; The skip instruction is generated for the parsing skip operation of the image parsing interface; Send an interface jump instruction to the client to instruct the client to jump from the image parsing interface to the copy input interface; Receive the release confirmation request sent by the client; the release confirmation request contains the input copy generated for the input operation of the copy input interface; Generate information release content according to the at least one image and the input copy; the release confirmation request is generated by the client in response to the confirmation operation triggered for the copy input interface.

7. The method according to claim 1, characterized in that, It further includes: Receive the copy editing request sent by the client, and the copy editing request contains the editing content; Use the first artificial intelligence model to generate the target copy in combination with the editing content.

8. The method according to claim 1, wherein It further includes: Receive the model switching request sent by the client; Determine the second artificial intelligence model corresponding to the model switching request, and use the second artificial intelligence model to regenerate the target copy corresponding to the at least one image in combination with the target service category; Send the regenerated target copy to the client, so that the client can update the target copy displayed in the information generation interface.

9. The method according to claim 1, characterized in that The parsing of the target service category corresponding to the at least one image by using the first artificial intelligence model includes: Use the first artificial intelligence model to perform content parsing on the at least one image to obtain the image content corresponding to each of the at least one image; Use the first artificial intelligence model to parse the target service category corresponding to the at least one image in combination with the image content corresponding to each of the at least one image.

10. The method according to claim 9, wherein The parsing of the target service category corresponding to the at least one image by using the first artificial intelligence model in combination with the image content corresponding to each of the at least one image includes: Use the first artificial intelligence model to perform service category recognition on the image content corresponding to each of the at least one image to obtain the candidate service categories corresponding to each of the at least one image and the confidence levels of the candidate service categories; Screen the target service category from the candidate service categories according to the confidence levels of the candidate service categories.

11. An information publishing method, characterized in that, Applied to the client, it includes: Receive the release prompt information sent by the server; Display the release prompt information in the user interface; In response to the trigger operation for the release prompt information, jump from the user interface to the image upload interface; In response to the image upload operation for the image upload interface, obtain at least one image; Based on the at least one image, send an information generation request to the server, so that the server uses a first artificial intelligence model to analyze the target service category corresponding to the at least one image, and generates a target copy corresponding to the at least one image according to the target service category; Receive the target copy and the target service category sent by the server; Display the target copy and the target service category on the information generation interface; In response to a confirmation operation triggered for the information generation interface, generate an information confirmation request; Send the information confirmation request to the server, so that the server generates information release content corresponding to the target service category according to the at least one image and the target copy, and obtains the user account corresponding to the client, and publishes the information release content under the user account.

12. An information publishing device, characterized in that, Configured on the server, including: The first sending module is used to send a release prompt message to the client, so that the client displays the release prompt message in the user interface; The first receiving module is used to receive the information generation request sent by the client, and the information generation request includes at least one image; the at least one image is obtained by the client in response to an image upload operation triggered for the release prompt message; The model operation module is used to analyze the target service category corresponding to the at least one image by using a first artificial intelligence model; The model operation module is further used to generate a target copy corresponding to the at least one image by using the first artificial intelligence model according to the target service category; The first sending module is further used to send the target copy and the target service category to the client, so that the client displays the target copy and the target service category on the information generation interface; The information generation module is used to generate information release content corresponding to the target service category according to the at least one image and the target copy in response to the information confirmation request sent by the client; the information confirmation request is generated by the client in response to a confirmation operation triggered for the information generation interface; The information release module is used to obtain the user account corresponding to the client and publish the information release content under the user account.

13. An information publishing device, characterized in that, Configured on the client, including: The second receiving module is used to receive the release prompt message sent by the server; The interface display module is used to display the release prompt message in the user interface; The interface jump module is used to jump from the user interface to the image upload interface in response to a trigger operation for the release prompt message; The image acquisition module is used to acquire at least one image in response to an image upload operation for the image upload interface; The second sending module is used to send an information generation request to the server based on the at least one image, so that the server uses a first artificial intelligence model to analyze the target service category corresponding to the at least one image, and generates a target copy corresponding to the at least one image according to the target service category; The second receiving module is further used to receive the target copy and the target service category sent by the server; The interface display module is further configured to display the target copywriting and the target service category on the information generation interface; The request generation module is configured to generate an information confirmation request in response to a confirmation operation triggered for the information generation interface; The second sending module is further configured to send the information confirmation request to the server, so that the server generates information release content corresponding to the target service category according to the at least one image and the target copywriting, and obtains the user account corresponding to the client, and releases the information release content under the user account.

14. A computing device, characterized in that, It includes a processing component and a storage component; The storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the information release method according to any one of claims 1-11.

15. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and when the computer program is executed by the processing component, the information release method according to any one of claims 1-11 is implemented.

16. A computer program product, characterized in that, It includes a computer program or instruction, and when the computer program or instruction is executed by the processing component, the information release method according to any one of claims 1-11 is implemented.

Images