Object publishing content generation method, computing device, storage medium and computer program product

Abstract

The embodiment of the invention provides an object release content generation method, computing equipment, a computer readable storage medium and a computer program product. The object release content generation method comprises the following steps: sending object release prompt information to a client; obtaining an object picture sent by the client; identifying an object type to which the target object in the object picture belongs by using the first large model; performing information extraction from the object picture by using a second large model based on the object type to determine a first parameter value of at least one successfully extracted first attribute parameter and at least one unsuccessfully extracted second attribute parameter; sending the at least one second attribute parameter to the client; acquiring a second parameter value sent by the client; and generating object publishing content according to the at least one first parameter value and the at least one second parameter value. According to the technical scheme provided by the embodiment of the invention, the object publishing content which accurately and completely describes the target object can be generated.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular, to a method for generating object publishing content, a computing device, a computer-readable storage medium, and a computer program product. Background Art

[0002] As the digital economy is booming, object publishing platforms have brought great convenience to people's lives. Users can upload the object description information of the target object to be published to the object publishing platform, so that other users can understand the target object through the object description information.

[0003] However, when users publish target objects on object publishing platforms, they often do not know what kind of object description information can attract other users due to lack of knowledge and experience in object promotion.

[0004] In the related art, a common object publishing method is to allow users to upload object description information by referring to content uploaded by other users.

[0005] In the process of implementing the concept of this application, the inventor found that when referring to the content uploaded by other users, users need to spend a lot of time browsing a large amount of published information to filter out valuable parts and imitate them. However, the large amount of published content makes the screening process cumbersome, and it is difficult for users to grasp the key points of the publication, resulting in low accuracy of the published content. Summary of the invention

[0006] Embodiments of the present application provide a method for generating object publishing content, a computing device, a computer-readable storage medium, and a computer program product.

[0007] In a first aspect, an embodiment of the present application provides a method for generating object publishing content, which is applied to a server, and the method includes:

[0008] Send object publishing prompt information to the client;

[0009] Acquire an object picture sent by the client; the object picture is obtained by the client in response to a picture upload operation for publishing prompt information for the object;

[0010] Using the first large model to identify the object type to which the target object in the object image belongs;

[0011] Extracting information from the object image based on the object type using the second largest model to determine a first parameter value of at least one first attribute parameter that was successfully extracted and at least one second attribute parameter that failed to be extracted;

[0012] Sending the at least one second attribute parameter to the client;

[0013] Acquire a second parameter value sent by the client, where the second parameter value is determined by the client in response to a parameter supplement operation on the at least one second attribute parameter;

[0014] Object publishing content is generated according to at least one first parameter value and at least one second parameter value.

[0015] In a second aspect, an embodiment of the present application provides a method for generating object publishing content, which is applied to a client, and the method includes:

[0016] Send an object publishing request to the server;

[0017] Receiving object publishing prompt information provided by the server in response to the object publishing request;

[0018] In response to a picture upload operation for publishing prompt information for the object, an object picture is obtained;

[0019] Sending the object picture to the server, so that the server uses the first large model to identify the object type to which the target object in the object picture belongs, and uses the second large model to extract information from the object picture based on the object type to determine a first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that fails to be extracted;

[0020] Receiving at least one second attribute parameter sent by the server;

[0021] In response to the parameter supplementation operation on the at least one second attribute parameter, obtaining at least one second parameter value;

[0022] The at least one second parameter value is sent to the server, so that the server generates object publishing content according to the at least one second parameter value and at least one second parameter value.

[0023] In a third aspect, an embodiment of the present application provides an object publishing content generation device, which is applied to a server, and the device includes:

[0024] A prompt information sending module is used to send object publishing prompt information to the client;

[0025] A picture acquisition module, used to acquire the object picture sent by the client; the object picture is obtained by the client in response to a picture upload operation for publishing prompt information for the object;

[0026] A type recognition module, used to recognize the object type to which the target object in the object picture belongs by using the first large model;

[0027] an information extraction module, configured to extract information from the object image based on the object type using the second largest model, so as to determine a first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that is failed to be extracted;

[0028] A parameter sending module, used for sending the at least one second attribute parameter to the client;

[0029] a parameter acquisition module, configured to acquire a second parameter value sent by the client, wherein the second parameter value is determined by the client in response to a parameter supplement operation for the at least one second attribute parameter;

[0030] The content generation module is used to generate object publishing content according to at least one first parameter value and at least one second parameter value.

[0031] In a fourth aspect, an embodiment of the present application provides an object publishing content generation device, which is applied to a client, and the device includes:

[0032] A request sending module is used to send an object publishing request to the server;

[0033] An information receiving module, used for receiving object publishing prompt information provided by the server in response to the object publishing request;

[0034] A picture receiving module, used for obtaining a picture of the object in response to a picture uploading operation for publishing prompt information for the object;

[0035] A picture sending module, used for sending the object picture to the server, so that the server can use the first large model to identify the object type to which the target object in the object picture belongs, and use the second large model to extract information from the object picture based on the object type to determine a first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that fails to be extracted;

[0036] A parameter receiving module, used to receive at least one second attribute parameter sent by the server;

[0037] A parameter value receiving module, configured to obtain at least one second parameter value in response to a parameter supplementation operation on the at least one second attribute parameter;

[0038] The parameter value sending module is used to send the at least one second parameter value to the server, so that the server generates object publishing content according to the at least one second parameter value and at least one second parameter value.

[0039] In a fifth aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component;

[0040] The storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the object publishing content generation method provided in the embodiment of the present application.

[0041] In a sixth aspect, a computer-readable storage medium is provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processing component, the object publishing content generation method provided in an embodiment of the present application is implemented.

[0042] In a seventh aspect, a computer program product is provided in an embodiment of the present application, including a computer program or instructions, which, when executed by a processing component, implements the object publishing content generation method provided in an embodiment of the present application.

[0043] The embodiment of the present application provides a method for generating object publishing content, the basic idea of ​​which is: sending object publishing prompt information to a client; obtaining an object picture sent by the client; the object picture is obtained by the client in response to a picture upload operation for the object publishing prompt information; using a first large model to identify the object type to which the target object in the object picture belongs; using a second large model based on the object type, extracting information from the object picture to determine the first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that fails to be extracted; sending the at least one second attribute parameter to the client; obtaining a second parameter value sent by the client, the second parameter value being determined by the client in response to a parameter supplement operation for the at least one second attribute parameter; generating object publishing content according to at least one first parameter value and at least one second parameter value. Users only need to upload object pictures to generate object publishing content, without the need to organize language, which reduces the difficulty of generating object publishing content. In addition, by combining the first parameter value extracted from the object picture by the large model with the second parameter value supplemented by the user, an object publishing content that accurately and completely describes the target object can be generated, making the object publishing content more professional and attractive.

[0044] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 A system architecture diagram is shown in which the technical solution of an embodiment of the present application can be applied;

[0047] Figure 2 A flowchart of an embodiment of a method for generating object publishing content provided by the present application;

[0048] Figure 3 A flowchart of another embodiment of a method for generating object publishing content provided by the present application;

[0049] Figure 4 A block diagram of an embodiment of an object publishing content generating device provided by the present application;

[0050] Figure 5 A block diagram of an embodiment of an object publishing content generating device provided by the present application;

[0051] Figure 6 A block diagram of a computing device provided for the present application. DETAILED DESCRIPTION

[0052] 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.

[0053] 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, slide operation, pinch operation or mouse hover operation, etc. Slide operation includes but is not limited to: straight line sliding, curve sliding, etc.

[0054] As the digital economy is booming, object publishing platforms have brought great convenience to people's lives. Users can upload the object description information of the target object to be published to the object publishing platform, so that other users can understand the target object through the object description information.

[0055] However, when users publish target objects on object publishing platforms, they often do not know what kind of object description information can attract other users due to lack of knowledge and experience in object promotion.

[0056] In the related art, a common object publishing method is to allow users to upload object description information by referring to content uploaded by other users.

[0057] In the process of implementing the concept of this application, the inventor found that when referring to the content uploaded by other users, users need to spend a lot of time browsing a large amount of published information to filter out valuable parts and imitate them. However, the large amount of published content makes the screening process cumbersome, and it is difficult for users to grasp the key points of the publication, resulting in low accuracy of the published content.

[0058] In view of the technical problem of low accuracy of the existing object publishing content generation, the embodiment of the present application provides a solution, the basic idea is: send object publishing prompt information to the client; obtain the object picture sent by the client; the object picture is obtained by the client in response to the picture upload operation for the object publishing prompt information; use the first large model to identify the object type to which the target object in the object picture belongs; use the second large model based on the object type to extract information from the object picture to determine the first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that fails to be extracted; send at least one second attribute parameter to the client; obtain the second parameter value sent by the client, the second parameter value is determined by the client in response to the parameter supplement operation for at least one second attribute parameter; generate object publishing content according to at least one first parameter value and at least one second parameter value. Users only need to upload object pictures to generate object publishing content, without the need to organize language, which reduces the difficulty of generating object publishing content. In addition, by combining the first parameter value extracted from the object picture by the large model with the second parameter value supplemented by the user, an accurate and complete object publishing content describing the target object can be generated, making the object publishing content more professional and attractive.

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. 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 those skilled in the art without creative work are within the scope of protection of this application.

[0060] Figure 1 A system architecture diagram is shown in which the technical solution of an embodiment of the present application can be applied. The system architecture may include a client 101 and a server 102.

[0061] The client 101 and the server 102 may be connected via a network. The network provides a medium for a communication link between the client 101 and the server 102. The network may include various connection types, such as wired, wireless, or optical fiber cables, etc. The client 101 may interact with the server 102 via the network to receive or send messages, etc.

[0062] Among them, the client 101 can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, Hypertext Markup Language Version 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The client 101 can be deployed in an electronic device and needs to rely on the device to run or some apps in the device to run, etc. The electronic device can, for example, have a display screen and support information browsing, 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 ease of understanding, Figure 1 The client is mainly represented by a device image. Various other types of applications can usually be configured in electronic devices, 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. Electronic devices can refer to devices used by users, which have the functions of computing, surfing the Internet, communicating, etc. required by users, such as mobile phones, tablet computers, personal computers, wearable devices, etc. Electronic devices can usually include at least one processing component and at least one storage component. Electronic devices may also include basic configurations such as network card chips, IO (input / output) buses, audio and video components, which are not limited in this application. Optionally, according to the implementation form of the electronic device, some peripheral devices may also be included, such as keyboards, mice, input pens, printers, etc., which are not limited in this application.

[0063] The server 102 may include servers that provide various services, such as a server for background training that provides support for the model used on the client 101, or a server that processes interactive information sent by the client.

[0064] It should be noted that the server 102 can be implemented as a distributed server cluster consisting 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 networks (CDN), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0065] It should be noted that the object publishing content generation method provided in the embodiment of the present application is generally executed by the server 102, and the corresponding object publishing content generation device is generally set in the server 102. However, in other embodiments of the present application, the client 101 can also have similar functions to the server 102, so as to execute the object publishing content generation method provided in the embodiment of the present application.

[0066] It should be understood that Figure 1 The number of clients and servers in the example is only for illustration. Any number of clients and servers may be provided as required.

[0067] The implementation details of the technical solution of the embodiment of the present application are elaborated in detail below.

[0068] Figure 2 A flowchart of an embodiment of a method for generating content for object publishing provided by the present application. The technical solution of the present embodiment can be applied to a server. In a practical application, a system architecture applicable to the technical solution of the embodiment of the present application may include a client and a server;

[0069] The client and the server may establish a connection through a network, which may include various connection types, such as wired or wireless communication links or optical fiber cables, etc. The first client and the second client may establish a communication connection, such as an instant messaging connection, through the server to provide a session page on each display interface, and to send and receive session messages through interaction with the server.

[0070] Among them, the client can be a browser, an APP (Application), or a web application such as H5 (HyperText Markup Language5, Hypertext Markup Language Version 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The first client or the second client can be deployed in an electronic device, and needs to rely on the device to run or some apps in the device to run, etc. The electronic device can, for example, have an electronic display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, an intelligent speaker, a smart watch, etc. Various other types of applications can also 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, mailbox clients, social platform software, etc. Electronic devices can usually 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 bus, and audio and video components, which are not limited in this application. Optionally, according to the implementation form of the electronic device, some peripheral devices such as a keyboard, a mouse, an input pen, a printer, etc. may also be included, which are not limited in this application.

[0071] The service end may include servers that provide various services, such as a server that provides instant messaging, a server that provides audio and video communications, a proxy server that provides gateway services, etc.

[0072] It should be noted that the server can be implemented as a distributed server cluster consisting 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 networks (CDN), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0073] Figure 2 The object publishing content generation method shown may include the following steps:

[0074] 201: Send object publishing prompt information to the client.

[0075] When the server detects that certain conditions are met, such as receiving an object publishing request sent by a client, the server may send an object publishing prompt message to the client.

[0076] The object publishing prompt information is used to prompt and guide the user to perform operations related to the object publishing, such as prompting the user to upload a picture of the target object to be published. The object publishing prompt information may include a picture uploading method, requirements for the uploaded picture, etc.

[0077] Since factors such as image clarity, lighting conditions, and shooting angles will directly affect the results of information extraction, the object release prompt information can suggest users to upload high-quality images to avoid blurry, dark, or overly cluttered backgrounds that interfere with information extraction. In addition, users can also be prompted to upload the format of the object image to ensure transmission efficiency.

[0078] 202: Acquire the object image sent by the client; the object image is obtained by the client in response to an image upload operation for publishing prompt information for the object.

[0079] After receiving the object release prompt information, the client can display it to the user. The user can upload one or more pictures of the target object according to the requirements of the object release prompt information. The object picture can include, for example, the overall appearance picture, detailed picture, usage status picture, etc. of the target object.

[0080] In an embodiment of the present application, in order to improve the accuracy of information extraction, the user may be guided to upload multiple pictures of the target object to display the features of the target object from different angles.

[0081] 203: Using the first largest model to identify the object type to which the target object in the object image belongs.

[0082] Among them, the first large model can be an image recognition model generated through training with a large amount of data, which can extract features from pictures and match them with known category labels.

[0083] The first model can be generated based on a deep learning architecture using a large number of labeled image datasets. For example, the image dataset may contain a large number of images labeled as "coffee machine" and images labeled as "clothes", "mobile phone" and other categories. By continuously optimizing the model parameters, it can accurately identify different types of objects.

[0084] 204: Extract information from the object image based on the object type using the second largest model to determine a first parameter value of at least one first attribute parameter that is successfully extracted and at least one second attribute parameter that is failed to be extracted.

[0085] Among them, the second largest model can extract information from the object image based on the object type extracted by the first largest model, combining image recognition and natural language processing technology.

[0086] In an embodiment of the present application, information extraction may include visual feature extraction and text feature extraction. For example, the second largest model may extract observable attributes by analyzing features such as color, shape, and texture in an object image. If the object image contains text, the second largest model may extract the text to obtain corresponding information. For example, the feature of the "silver" shell may be identified from a picture of a coffee machine, and the brand features of the coffee machine may also be identified from the control panel of the coffee machine.

[0087] In some embodiments, using the second largest model to extract information from the object image based on the object type to determine the first parameter value of at least one first attribute parameter that is successfully extracted and at least one second attribute parameter that fails to be extracted can be specifically implemented as follows:

[0088] The object type and the object image are input into the second largest model so that the second largest model determines multiple attribute parameters mapped by the object type, and performs feature extraction on the object image based on the multiple attribute parameters to determine a first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that fails to be extracted.

[0089] In an embodiment of the present application, the second largest model can call a knowledge base or rules related to the object type to list multiple attribute parameters that need to be extracted. Among them, a list of common attribute parameters of different object types can be stored in the database, and the second largest model can dynamically generate a set of attribute parameters that need to be extracted from the object image according to the object type. For example, for an object type of "coffee machine", the attribute parameters may include: "brand", "color", "capacity", "power", "material", etc. If the object type is "dress", the system may list the following attribute parameters: "color", "size", "material", "style", "washing method", etc.

[0090] The second largest model can analyze each attribute parameter one by one and try to extract the corresponding value from the object image. If the second largest model can identify the parameter value corresponding to a certain attribute parameter from the object image, the attribute parameter can be marked as the first attribute parameter and the corresponding parameter value can be recorded. Otherwise, the attribute parameter is marked as the second attribute parameter.

[0091] In a possible implementation of the present application, the first large model and the second large model can be two independent large models, which are responsible for processing different tasks, but are not limited to this. They can also be integrated into one large model to complete the object type extraction and attribute parameter extraction tasks through a single large model.

[0092] 205: Send at least one second attribute parameter to the client.

[0093] 206: Acquire a second parameter value sent by the client, where the second parameter value is determined by the client in response to a parameter supplement operation for at least one second attribute parameter.

[0094] In an embodiment of the present application, the second largest model can be used to determine the second attribute parameter whose corresponding parameter value cannot be successfully extracted from the image.

[0095] By sending the second attribute parameter to the client, the user can supplement the missing parameter value according to the second attribute parameter to ensure the completeness and accuracy of the published content.

[0096] 207: Generate object publishing content according to at least one first parameter value and at least one second parameter value.

[0097] After receiving the second parameter value supplemented by the user, the server may merge the first parameter value and the second parameter value to generate a complete attribute data set.

[0098] The server can then use natural language generation (NLG) technology to convert the structured attribute data set into a fluent and professional natural language description to generate object publishing content.

[0099] In the embodiment of the present application, the user only needs to upload the object image to generate the object release content, without the effort of organizing the language, which reduces the difficulty of generating the object release content. In addition, by combining the first parameter value extracted from the object image by the large model with the second parameter value supplemented by the user, an object release content that accurately and completely describes the target object can be generated, making the object release content more professional and attractive.

[0100] In some embodiments, the method may further include:

[0101] A first parameter value of at least one first attribute parameter is sent to the client.

[0102] In an embodiment of the present application, after the first parameter value is successfully extracted from the object image using the first large model, the first parameter value may be sent to the client for the user to confirm the first parameter value.

[0103] When the user confirms that the first parameter value is accurate, the user can use the client to send a confirmation instruction to the server, so that the server continues the subsequent object publishing content generation process in response to the confirmation instruction.

[0104] In some embodiments, generating the object publishing content according to at least one first parameter value and at least one second parameter value may be specifically implemented as follows:

[0105] In response to a confirmation instruction for at least one first parameter value sent by the client, object publishing content is generated according to the at least one first parameter value and the at least one second parameter value.

[0106] After receiving the confirmation instruction, the server can confirm that the first parameter value extracted by the first large model is accurate, thereby combining the first parameter value with the second parameter value supplemented by the user to generate a complete object publishing content.

[0107] After the first parameter value is extracted, the first parameter value is sent to the client for user confirmation, thereby ensuring the accuracy of the generated published content.

[0108] In some embodiments, the method may further include:

[0109] Sending a first parameter value of at least one first attribute parameter to the client;

[0110] The updated first parameter value corresponding to at least one first attribute parameter sent by the client is obtained, and the updated first parameter value is determined by the client in response to a parameter update operation for at least one first parameter value.

[0111] In actual application, one or more first parameter values ​​extracted by the first large model from the object image may not be accurate enough. Therefore, after generating the first parameter value, the first parameter value may be sent to the client for the user to confirm the first parameter value.

[0112] After sending the first parameter value of at least one first attribute parameter to the client, if the user finds that one or more first parameter values ​​are inaccurate, these first parameter values ​​can be corrected through parameter update operations to generate more accurate updated first parameter values.

[0113] In some embodiments, generating the object publishing content according to at least one first parameter value and at least one second parameter value may be specifically implemented as follows:

[0114] The object publishing content is generated according to the updated at least one first parameter value and at least one second parameter value.

[0115] In some embodiments, using the first large model to identify the object type of the target object in the object picture can be specifically implemented as follows:

[0116] Constructing a first prompt word, the first prompt word including a processing requirement and a plurality of candidate object types, the processing requirement being used to prompt the first large model to determine an object type that matches the target object from the plurality of candidate object types;

[0117] The first prompt word and the object picture are input into the first large model so that the first large model outputs the object type according to the processing requirements.

[0118] The first prompt word may be an instruction issued to the first large model, which may include processing requirements and multiple candidate object types. The processing requirements are used to clearly tell the first large model the task to be completed. For example: "Please select a type from the following candidate object types that best matches the target object in the image.", "Please identify the target object in the image and determine which of the following types it belongs to." Multiple candidate object types can provide a set of possible object types for the first large model to select.

[0119] After the server inputs the first prompt word and the object picture into the first large model, the first large model can combine the information in the prompt word and the features in the object picture to complete the object type recognition task.

[0120] In some embodiments, the method may further include:

[0121] Sends the object type to the client.

[0122] In an embodiment of the present application, after the first large model identifies the object type of the target object, the object type may be sent to the client for the user to check and confirm.

[0123] In some embodiments, using the second largest model to extract information from the object image based on the object type to determine the first parameter value of at least one first attribute parameter that is successfully extracted and at least one second attribute parameter that fails to be extracted can be specifically implemented as follows:

[0124] In response to a first confirmation instruction for an object type sent by the client, information is extracted from the object image based on the object type using a second large model to determine a first parameter value of at least one first attribute parameter that was successfully extracted and at least one second attribute parameter that failed to be extracted.

[0125] After the user confirms that the object type is correct, the client can send a confirmation instruction to the server. If the user modifies the object type, the server can record the updated object type and perform information extraction based on the updated object type.

[0126] Through the user confirmation mechanism, the server can promptly detect and correct object type identification errors to ensure the accuracy of subsequent information extraction.

[0127] In some embodiments, the method may further include:

[0128] Send object publication content to the client;

[0129] Obtaining a second confirmation instruction returned by the client for the object publishing content;

[0130] In response to the second confirmation instruction, the object publishing content is published to the object publishing platform.

[0131] In a possible implementation of the present application, after the user confirms that the object publishing content is accurate and complete, the server can directly publish the object publishing content to the object publishing platform.

[0132] In another possible implementation of the present application, after the server generates the object publishing content, the object publishing content may be provided to the client, so that the user can use the client to publish the object publishing content to the object publishing platform.

[0133] In some embodiments, the method may further include:

[0134] The object publishing content is sent to the client so that the client can publish the object publishing content to the object publishing platform.

[0135] Figure 3 A flowchart of another embodiment of a method for generating object publishing content provided by the present application. The technical solution of the present embodiment can be applied to a client. In a practical application, a system architecture applicable to the technical solution of the embodiment of the present application may include a client and a server.

[0136] The client and the server may establish a connection through a network, which may include various connection types, such as wired or wireless communication links or optical fiber cables, etc. The first client and the second client may establish a communication connection, such as an instant messaging connection, through the server to provide a session page on each display interface, and to send and receive session messages through interaction with the server.

[0137] Among them, the client can be a browser, an APP (Application), or a web application such as H5 (HyperText Markup Language5, Hypertext Markup Language Version 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The first client or the second client can be deployed in an electronic device, and needs to rely on the device to run or some apps in the device to run, etc. The electronic device can, for example, have an electronic display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, an intelligent speaker, a smart watch, etc. Various other types of applications can also 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, mailbox clients, social platform software, etc. Electronic devices can usually 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 bus, and audio and video components, which are not limited in this application. Optionally, according to the implementation form of the electronic device, some peripheral devices such as a keyboard, a mouse, an input pen, a printer, etc. may also be included, which are not limited in this application.

[0138] The service end may include servers that provide various services, such as a server that provides instant messaging, a server that provides audio and video communications, a proxy server that provides gateway services, etc.

[0139] It should be noted that the server can be implemented as a distributed server cluster consisting 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 networks (CDN), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0140] Figure 3 The object publishing content generation method shown may include the following steps:

[0141] 301: Send an object publishing request to the server;

[0142] 302: receiving object publishing prompt information provided by the server in response to the object publishing request;

[0143] 303: in response to the picture upload operation for publishing prompt information for the object, obtaining the object picture;

[0144] 304: Send the object image to the server, so that the server can use the first large model to identify the object type to which the target object in the object image belongs, and use the second large model to extract information from the object image based on the object type, so as to determine a first parameter value of at least one first attribute parameter that is successfully extracted and at least one second attribute parameter that is failed to be extracted;

[0145] 305: receiving at least one second attribute parameter sent by the server;

[0146] 306: In response to the parameter supplementation operation on at least one second attribute parameter, obtaining at least one second parameter value;

[0147] 307: Send at least one second parameter value to the server, so that the server generates object publishing content according to the at least one second parameter value and the at least one second parameter value.

[0148] The detailed implementation and beneficial effects of each step in the method of this embodiment have been described in detail in the previous embodiments, and will not be elaborated here.

[0149] The following is a description of the specific implementation of the object publishing content generation method provided in the embodiment of the present application in combination with a specific application scenario. It should be noted that the following content is only used to help those skilled in the art understand the specific implementation of the object publishing content generation method provided in the embodiment of the present application, and is not any improper limitation.

[0150] The following is a complete example using a coffee machine as the target object:

[0151] For example, if a user wants to publish an idle coffee machine on a second-hand trading platform, the server can generate object publishing content using the object publishing content generation method provided in the embodiment of the present application.

[0152] The specific implementation steps are as follows:

[0153] Step 1: Send object to publish prompt information;

[0154] The server detects that the user has entered the second-hand item publishing interface and sends an object publishing prompt message to the client used by the user: "Hello! You can now publish your idle items. Please upload the item pictures."

[0155] Step 2: Get the object image;

[0156] After receiving the prompt message, the user can open the mobile phone album and select multiple clear photos of the coffee machine from different angles, including the front, side, and operation panel, and upload the pictures on the client. The client sends these pictures to the server, and the server successfully obtains the object pictures.

[0157] Step 3: Identify the object type to which the target object belongs;

[0158] Constructing the first prompt word: The server constructs the first prompt word, and the content of the first prompt word may include "Please determine the object type that matches the target object in the picture from the candidate object types such as coffee machine, juicer, soybean milk machine, and microwave oven."

[0159] Input the first model: The server inputs the first prompt word and the coffee machine picture uploaded by the user into the first model. After analysis, the first model outputs the object type as "coffee machine".

[0160] Confirm object type: The server sends the object type "coffee machine" to the client. After checking on the client, the user confirms that the object type is correct and clicks the confirmation button. The client sends the confirmation command back to the server.

[0161] Step 4: Information extraction;

[0162] Inputting the second largest model: In response to receiving the first confirmation instruction for the object type sent by the client, the server inputs the object type of "coffee machine" and the object image uploaded by the user into the second largest model.

[0163] Determine attribute parameters and parameter values: The second largest model determines multiple attribute parameters of the "coffee machine" type mapping, such as brand, appearance color, material, size, whether it has a bean grinding function, etc. Then, feature extraction is performed on the object image based on these attribute parameters. From the object image, the second largest model successfully extracted the brand as "A" and the appearance color as "silver". These two attribute parameters are the first attribute parameters, and the corresponding "A" and "silver" are the first parameter values ​​corresponding to the first attribute parameters. However, information such as the length of use, frequency of use, and whether the coffee machine has a maintenance history cannot be extracted from the image, which is the second attribute parameter.

[0164] Step 5: Send parameter information to the client;

[0165] Send the first parameter value of the first attribute parameter: the server sends the first parameter values ​​of the first attribute parameters such as "brand: same" and "appearance color: silver" to the client for the user to confirm.

[0166] Sending second attribute parameters: At the same time, the server sends second attribute parameters such as "usage duration", "usage frequency", and "whether there is a maintenance history" to the client, prompting the user to supplement this information.

[0167] Step 6: Get client feedback;

[0168] Obtain confirmation or update of the first parameter value: After the user checks the first parameter value on the client and confirms that it is correct, click the confirmation button, and the client sends the confirmation instruction for the first parameter value to the server. If the user finds that the first parameter value is incorrect, such as the color on the picture looks deviated due to lighting problems, and the actual color is "champagne", the user performs a parameter update operation on the client, and the client sends the updated first parameter value "Brand: A" and "Appearance color: Champagne" to the server.

[0169] Get the second parameter value: The user supplements the second parameter value on the client according to the actual situation, such as "duration of use: 1 year", "frequency of use: 2-3 times a week", and "no maintenance history". The client sends these second parameter values ​​to the server.

[0170] Step 7: Generate object publishing content;

[0171] The server generates the object publishing content based on the obtained first parameter value and second parameter value: "I am selling a brand A silver coffee machine. It has been used for 1 year and is used 2-3 times a week. It has no repair history. It looks new and functions normally. If you are interested, please contact me."

[0172] Step 8: The publishing object publishes the content;

[0173] Send content for confirmation: The server sends the generated object publishing content to the client. After the user views it on the client and feels that the content is complete and accurate, he clicks the confirmation button. The client then returns a second confirmation instruction for the object publishing content to the server.

[0174] Publish to the platform: In response to the confirmation instruction, the server publishes the object publishing content to the object publishing page of the second-hand trading platform, and other users can see the coffee machine information published by the user on the platform. Or after the server sends the object publishing content to the client, the client directly publishes the content to the object publishing platform.

[0175] Figure 4 A block diagram of an embodiment of an object publishing content generation device provided by the present application, such as Figure 4 As shown, the device may specifically include:

[0176] The prompt information sending module 401 is used to send object publishing prompt information to the client;

[0177] The picture acquisition module 402 is used to acquire the object picture sent by the client; the object picture is obtained by the client in response to the picture upload operation for publishing prompt information for the object;

[0178] A type identification module 403, used to identify the object type to which the target object in the object picture belongs using the first large model;

[0179] An information extraction module 404, configured to extract information from the object image based on the object type using the second largest model, so as to determine a first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that is failed to be extracted;

[0180] A parameter sending module 405, configured to send at least one second attribute parameter to a client;

[0181] A parameter acquisition module 406 is used to acquire a second parameter value sent by the client, where the second parameter value is determined by the client in response to a parameter supplement operation for at least one second attribute parameter;

[0182] The content generation module 407 is used to generate object publishing content according to at least one first parameter value and at least one second parameter value.

[0183] In some embodiments, the device may further include:

[0184] The first parameter value sending module is used to send a first parameter value of at least one first attribute parameter to the client.

[0185] In some embodiments, the content generation module 407 is specifically used to:

[0186] In response to a confirmation instruction for at least one first parameter value sent by the client, object publishing content is generated according to the at least one first parameter value and the at least one second parameter value.

[0187] In some embodiments, the device may further include:

[0188] A first parameter value sending module, used to send a first parameter value of at least one first attribute parameter to a client;

[0189] A parameter value updating module, used to obtain updated first parameter values ​​respectively corresponding to at least one first attribute parameter sent by the client, wherein the updated first parameter value is determined by the client in response to a parameter update operation for at least one first parameter value;

[0190] In some embodiments, the content generation module 407 is specifically used to:

[0191] The object publishing content is generated according to the updated at least one first parameter value and at least one second parameter value.

[0192] In some embodiments, the type identification module 403 is specifically used to:

[0193] Constructing a first prompt word, the first prompt word including a processing requirement and a plurality of candidate object types, the processing requirement being used to prompt the first large model to determine an object type that matches the target object from the plurality of candidate object types;

[0194] The first prompt word and the object picture are input into the first large model so that the first large model outputs the object type according to the processing requirements.

[0195] In some embodiments, the device may further include:

[0196] The type sending module is used to send the object type to the client.

[0197] In some embodiments, the information extraction module 404 is specifically used to:

[0198] In response to a first confirmation instruction for an object type sent by the client, information is extracted from the object image based on the object type using a second large model to determine a first parameter value of at least one first attribute parameter that was successfully extracted and at least one second attribute parameter that failed to be extracted.

[0199] In some embodiments, the information extraction module 404 is specifically used to:

[0200] The object type and the object image are input into the second largest model so that the second largest model determines multiple attribute parameters mapped by the object type, and performs feature extraction on the object image based on the multiple attribute parameters to determine a first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that fails to be extracted.

[0201] In some embodiments, the device may further include:

[0202] A first content sending module, used to send the object publishing content to the client;

[0203] Instruction acquisition instruction, used to obtain the second confirmation instruction returned by the client for the object publishing content;

[0204] The first object publishing module is used to publish the object publishing content to the object publishing platform in response to the confirmation instruction.

[0205] In some embodiments, the device may further include:

[0206] The second content sending module is used to send the object publishing content to the client, so that the client can publish the object publishing content to the object publishing platform.

[0207] Figure 4 The object publishing content generating device can execute Figure 2The implementation principle and technical effect of the object publishing content generation method described in the illustrated embodiment will not be described in detail. The specific way in which each module and unit performs operations in the object publishing content generation device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0208] Figure 5 A block diagram of an embodiment of an object publishing content generation device provided by the present application, such as Figure 4 As shown, the device may specifically include:

[0209] The request sending module 501 is used to send an object publishing request to the server;

[0210] An information receiving module 502 is used to receive object publishing prompt information provided by the server in response to the object publishing request;

[0211] The picture receiving module 503 is used to obtain the object picture in response to the picture uploading operation for the object publishing prompt information;

[0212] The picture sending module 504 is used to send the object picture to the server, so that the server can use the first large model to identify the object type to which the target object in the object picture belongs, and use the second large model to extract information from the object picture based on the object type to determine the first parameter value of at least one first attribute parameter that is successfully extracted and at least one second attribute parameter that fails to be extracted;

[0213] The parameter receiving module 505 is used to receive at least one second attribute parameter sent by the server;

[0214] A parameter value receiving module 506 is configured to obtain at least one second parameter value in response to a parameter supplementation operation on the at least one second attribute parameter;

[0215] The parameter value sending module 507 is used to send at least one second parameter value to the server, so that the server generates object publishing content according to the at least one second parameter value and at least one second parameter value.

[0216] Figure 5 The object publishing content generating device can execute Figure 3 The implementation principle and technical effect of the object publishing content generation method described in the illustrated embodiment will not be described in detail. The specific way in which each module and unit performs operations in the object publishing content generation device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0217] 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 client terminals, so that the server can identify the same user.

[0218] The interactive operation 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, the user corresponding to the user account 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.

[0219] It should be noted that in some of the processes described in the above embodiments and the accompanying drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel, and the sequence numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, 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 of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0220] Figure 6 This is a schematic diagram of a computing device according to an embodiment of the present application. Figure 6 As shown, in practice, the computing device may include: a storage component 601 and a processing component 602 .

[0221] Storage component 601 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 or method operating on the computing device, data structures, contact data, phone book data, messages, pictures, videos, etc.

[0222] Processing component 602, coupled to storage component 1001, is used to execute the computer program in storage component 501 to implement the following Figure 1 The object publishes the content generation method shown, or implements Figure 3 The object publishing content generation method shown.

[0223] Furthermore, the computing device may also include: a communication component, a display component, a power component, an audio component and other components. Figure 6 Only some components are shown schematically, which does not mean that the equipment only includes Figure 6 Components shown.

[0224] The processing components include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing components 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 to perform the above method.

[0225] The above-mentioned storage components can be implemented by any type of volatile or non-volatile storage devices or their combinations, 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 storage, flash memory, magnetic disk or optical disk.

[0226] The communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. 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.

[0227] The above-mentioned display component may include a screen, and the screen may include a liquid crystal display (Liquid Crystal Display, LCD) and a touch panel (Touch Panel, TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0228] The power supply assembly provides power to various components of the device where the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply assembly is located.

[0229] The above-mentioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (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 speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting an audio signal.

[0230] Accordingly, the embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the processor is enabled to implement each step in the above method embodiment. Among them, the computer-readable storage medium includes 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 (Phase-change Random Access Memory, PRAM), static random access memory (SRAM), dynamic random access memory (Dynamic Random Access Memory, DRAM), other types of random access memory (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 technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (Digital Video Disc, DVD) or other optical storage, magnetic cassette, tape disk storage or other magnetic storage device or any other non-transmission medium

[0231] Accordingly, the present application embodiment also provides a computer program product, the computer program product includes a computer program or an instruction, when the computer program or the instruction is executed by the processor, the processor is enabled to implement each step in the above method embodiment. It should be understood that each process or a combination of multiple processes in the above method flow can be implemented by a computer program or an instruction. In addition, these computer programs or instructions can be applied to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device, so that the processor of the general-purpose computer, the special-purpose computer, the embedded processor or other programmable data processing device can be implemented as a device for implementing the corresponding functions in the above method embodiment.

[0232] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0233] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0234] Finally, it should be noted that the above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for generating object publishing content, characterized in that: Applied to the server, the method includes: Send object publishing prompt information to the client; Acquire an object picture sent by the client; the object picture is obtained by the client in response to a picture upload operation for publishing prompt information for the object; Using the first large model to identify the object type to which the target object in the object image belongs; Extracting information from the object image based on the object type using the second largest model to determine a first parameter value of at least one first attribute parameter that was successfully extracted and at least one second attribute parameter that failed to be extracted; Sending the at least one second attribute parameter to the client; Acquire a second parameter value sent by the client, where the second parameter value is determined by the client in response to a parameter supplement operation on the at least one second attribute parameter; Object publishing content is generated according to at least one first parameter value and at least one second parameter value.

2. The method according to claim 1, characterized in that The method further comprises: Sending a first parameter value of the at least one first attribute parameter to the client; The generating object publishing content according to the at least one first parameter value and the at least one second parameter value comprises: In response to a confirmation instruction sent by the client for the at least one first parameter value, object publishing content is generated according to the at least one first parameter value and the at least one second parameter value.

3. The method according to claim 1, characterized in that The method further comprises: Sending a first parameter value of the at least one first attribute parameter to the client; Acquire updated first parameter values ​​respectively corresponding to the at least one first attribute parameter sent by the client, wherein the updated first parameter value is determined by the client in response to a parameter update operation for the at least one first parameter value; The generating object publishing content according to the at least one first parameter value and the at least one second parameter value comprises: The object publishing content is generated according to the updated at least one first parameter value and at least one second parameter value.

4. The method according to claim 1, characterized in that: The method of using the first large model to identify the object type to which the target object in the object picture belongs includes: Constructing a first prompt word, wherein the first prompt word includes a processing requirement and a plurality of candidate object types, wherein the processing requirement is used to prompt the first large model to determine an object type that matches the target object from the plurality of candidate object types; The first prompt word and the object picture are input into the first large model so that the first large model outputs the object type according to the processing requirement.

5. The method according to claim 4, characterized in that The method further comprises: sending the object type to the client; The extracting information from the object image based on the object type using the second largest model to determine the first parameter value of at least one first attribute parameter that is successfully extracted and at least one second attribute parameter that fails to be extracted includes: In response to a first confirmation instruction for the object type sent by the client, information is extracted from the object image based on the object type using a second large model to determine a first parameter value of at least one first attribute parameter that was successfully extracted and at least one second attribute parameter that failed to be extracted.

6. The method according to claim 5, characterized in that The extracting information from the object image based on the object type using the second largest model to determine the first parameter value of at least one first attribute parameter that is successfully extracted and at least one second attribute parameter that fails to be extracted includes: The object type and the object image are input into the second large model so that the second large model determines a plurality of attribute parameters mapped by the object type, and performs feature extraction on the object image according to the plurality of attribute parameters to determine a first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that is failed to be extracted.

7. The method according to claim 1, characterized in that The method further comprises: Sending the object publishing content to the client; Obtaining a second confirmation instruction returned by the client for the object publishing content; In response to the second confirmation instruction, the object publishing content is published to an object publishing platform.

8. The method according to claim 1, characterized in that: The method further comprises: The object publishing content is sent to the client so that the client publishes the object publishing content to an object publishing platform.

9. A method for generating object publishing content, characterized in that: Applied to a client, the method comprises: Send an object publishing request to the server; Receiving object publishing prompt information provided by the server in response to the object publishing request; In response to a picture upload operation for publishing prompt information for the object, an object picture is obtained; Sending the object picture to the server, so that the server uses the first large model to identify the object type to which the target object in the object picture belongs, and uses the second large model to extract information from the object picture based on the object type to determine a first parameter value of at least one first attribute parameter that is successfully extracted, and at least one second attribute parameter that fails to be extracted; Receiving at least one second attribute parameter sent by the server; In response to the parameter supplementation operation on the at least one second attribute parameter, obtaining at least one second parameter value; The at least one second parameter value is sent to the server, so that the server generates object publishing content according to the at least one second parameter value and at least one second parameter value.

10. A computing device, characterized in that 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 object publishing content generation method as described in any one of claims 1 to 8, or to implement the object publishing content generation method as described in claim 9.

11. 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 object publishing content generation method according to any one of claims 1 to 8 is implemented, or the object publishing content generation method according to claim 9 is implemented.

12. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processing component, implements the object publishing content generating method according to any one of claims 1 to 8, or implements the object publishing content generating method according to claim 9.

Images