Website registration method and device, electronic equipment and storage medium

Abstract

The application provides a website registration method and device, electronic equipment and storage medium, and relates to the technical field of communication. The method comprises the following steps: when website registration is performed, the registration information can be added in the multiple information input boxes based on the types of the multiple information input boxes of the registration webpage of the website, and the registration information is sent to the website server; and the registration prompt information sent by the website server is received; when the registration prompt information indicates that at least one registration information is inconsistent with the corresponding registration specification, the registration prompt information is input into the attribute fusion deep learning model to obtain the target prompt type and the target registration specification; the target registration information is corrected based on the target prompt type and the target registration specification; and the website registration is performed based on the registration information consistent with the registration specification and the corrected target registration information. The technical scheme provided by the application can effectively improve the registration efficiency of the website.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and particularly relates to a website registration method and device, electronic equipment and storage medium. BACKGROUND

[0002] The Internet is a huge network covering hundreds of millions of users worldwide, which connects people together and realizes information sharing, exchange and cooperation. Websites are the most important part of the Internet, which provide various information and services to users through web pages.

[0003] With the continuous development of Internet technology, the content and form of websites are increasingly rich and diverse. From early static web pages to current dynamic interactive web pages, whether it is to obtain news, shopping, socializing or working, websites are indispensable. In order to use the services provided by these websites, users need to register, which not only facilitates users to obtain personalized services, but also helps websites to manage and maintain user information.

[0004] The traditional website registration method usually requires users to manually fill in a large amount of registration information, which results in low registration efficiency. SUMMARY

[0005] The present application provides a website registration method, device, electronic equipment and storage medium, which solves the problem that users need to manually fill in a large amount of registration information in the prior art, resulting in low registration efficiency.

[0006] The present application provides a website registration method applied to an electronic device, the method comprising:

[0007] Based on the types of a plurality of information input boxes of a registration webpage of a website, adding registration information in the plurality of information input boxes respectively, and sending each registration information to a website server;

[0008] Receiving registration prompt information sent by the website server, the registration prompt information being determined based on each registration information and a corresponding registration specification of each information input box;

[0009] In the case where the registration prompt information indicates that there is at least one registration information inconsistent with the corresponding registration specification, inputting the registration prompt information into an attribute fusion deep learning model to obtain a target prompt type and a target registration specification, the target prompt type being a type corresponding to a target registration information inconsistent with the registration specification, and the target registration specification being a registration specification corresponding to the target registration information;

[0010] Based on the target prompt type and the target registration specification, the target registration information is corrected, and website registration is performed based on the registration information consistent with the registration specification and the corrected target registration information.

[0011] According to the website registration method provided in the application, the registration prompt information includes HTML text, style attributes of nodes in the website, and a hierarchical structure of the nodes.

[0012] The target prompt type and the target registration specification corresponding to the target registration information inconsistent with the registration specification are obtained by inputting the registration prompt information into the attribute fusion deep learning model.

[0013] The HTML text is input into a first embedding layer in the attribute fusion deep learning model to obtain a first text feature vector, and the first text feature vector is input into an activation layer to obtain the target registration specification.

[0014] The style attributes of the nodes are input into a second embedding layer in the attribute fusion deep learning model to obtain a string feature vector.

[0015] The hierarchical structure of the nodes is input into a third embedding layer in the attribute fusion deep learning model to obtain a string feature matrix.

[0016] The first text feature vector, the string feature vector, and the string feature matrix are input into a post-processing module in the attribute fusion deep learning model to obtain the target prompt type.

[0017] According to the website registration method provided in the application, the style attributes of the nodes include numerical types and category types.

[0018] The style attributes of the nodes are input into a second embedding layer in the attribute fusion deep learning model to obtain a string feature vector, including:

[0019] The style attributes of the nodes are input into a second embedding layer in the attribute fusion deep learning model, the numerical type of the style attributes is normalized to obtain normalized style attributes.

[0020] The category type of the style attributes is encoded to obtain encoded style attributes.

[0021] The normalized style attributes and the encoded style attributes are spliced to obtain the string feature vector.

[0022] According to a website registration method provided in the application, the hierarchical structure of the nodes is input into a third embedding layer in the attribute fusion deep learning model to obtain a character string feature matrix, which comprises:

[0023] The hierarchical structure of the nodes is input into a third embedding layer in the attribute fusion deep learning model to determine the character strings corresponding to each node.

[0024] Based on the character string set composed of the character strings corresponding to each node, a character-level feature matrix corresponding to the hierarchical structure of the nodes is determined, and based on the character string set, a word-level feature matrix corresponding to the hierarchical structure of the nodes is determined.

[0025] The character-level feature matrix and the word-level feature matrix are weightedly spliced to obtain the character string feature matrix.

[0026] According to a website registration method provided in the application, the character-level feature matrix corresponding to the hierarchical structure of the nodes is determined based on the character string set composed of the character strings corresponding to each node, which comprises:

[0027] Tokenization is performed on each character string in the character string set composed of the character strings corresponding to each node to obtain a tokenization result set.

[0028] A character-level vector corresponding to the character string set is generated according to the frequency of the appearance of character elements in the tokenization result set.

[0029] The dimensions of all vectors in the character-level vector are adjusted to obtain a vector set, and the dimensions of all vectors in the vector set are the same.

[0030] All vectors in the vector set are encoded, and the matrix obtained by encoding is processed by dimension reduction to obtain a dense matrix.

[0031] The dense matrix is subjected to feature extraction to obtain the character-level feature matrix.

[0032] According to a website registration method provided in the application, the word-level feature matrix corresponding to the hierarchical structure of the nodes is determined based on the character string set, which comprises:

[0033] Tokenization is performed on each character string in the character string set composed of the character strings corresponding to each node to obtain a tokenization matrix, and the lengths of all tokenization results in the tokenization matrix are the same.

[0034] The website word vector matrix corresponding to the tokenization matrix is processed by dimension reduction to obtain a low-dimensional word vector matrix.

[0035] The low-dimensional word vector matrix is subjected to feature extraction to obtain the word-level feature matrix.

[0036] According to the website registration method provided in the application, the target registration information is modified based on the target prompt type and the target registration specification, comprising:

[0037] The label sequence of all nodes in the website is converted into a corresponding index vector, and the index vector is spliced with the HTML text to obtain a fusion sequence;

[0038] The fusion sequence is input into a large language model to obtain a modification strategy of the target registration information;

[0039] The target registration information is modified based on the target prompt type, the target registration specification and the modification strategy.

[0040] According to the website registration method provided in the application, the target registration information is modified based on the target prompt type and the target registration specification, comprising:

[0041] For each information input box, in response to a click operation on the information input box, a target solution is determined in the case of an output modal dialog box;

[0042] The modal dialog box is processed based on the target solution, and the registration information is added to the information input box in the case that the modal dialog box has been processed.

[0043] The application also provides a website registration device applied to an electronic device, comprising:

[0044] A first processing unit is configured to add registration information to each of a plurality of information input boxes of a website registration webpage based on the type of each information input box;

[0045] A sending unit is configured to send each registration information to a website server;

[0046] A receiving unit is configured to receive registration prompt information sent by the website server, wherein the registration prompt information is determined based on each registration information and the corresponding registration specification of each information input box;

[0047] A second processing unit is configured to input the registration prompt information into an attribute fusion deep learning model to obtain a target prompt type and a target registration specification in the case that the registration prompt information indicates that at least one registration information is inconsistent with the corresponding registration specification, wherein the target prompt type is the type corresponding to the target registration information inconsistent with the registration specification, and the target registration specification is the registration specification corresponding to the target registration information.

[0048] The registration unit corrects the target registration information based on the target prompt type and the target registration specification, and performs website registration based on the registration information consistent with the registration specification and the corrected target registration information.

[0049] The application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the website registration method according to any one of the above when executing the computer program.

[0050] The application further provides a non-transitory computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the website registration method according to any one of the above.

[0051] The application further provides a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the website registration method according to any one of the above.

[0052] The website registration method, device, electronic device and storage medium provided by the application can add registration information in multiple information input boxes of a registration webpage of a website based on the types of the multiple information input boxes, and send the registration information to a website server, receive registration prompt information sent by the website server, input the registration prompt information into an attribute fusion deep learning model when the registration prompt information indicates that at least one registration information is inconsistent with a corresponding registration specification, obtain a target prompt type and a target registration specification, correct target registration information based on the target prompt type and the target registration specification, and perform website registration based on the registration information consistent with the registration specification and the corrected target registration information. Thus, the attribute fusion deep learning model can be used to automatically correct the target registration information based on the target prompt type and the target registration specification when at least one registration information is inconsistent with a corresponding registration specification, which not only solves the problem that a user needs to manually fill in a large amount of registration information in the prior art, resulting in low registration efficiency, but also solves the problem that the process is interrupted due to unsuccessful website registration, thereby effectively improving the registration efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the application or the prior art, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0054] Figure 1A flowchart of a website registration method provided in an embodiment of the present application.

[0055] Figure 2 A processing framework diagram of a modal dialog box appearing when a click operation is performed on an information input box provided in an embodiment of the present application.

[0056] Figure 3 A flowchart of obtaining a target prompt type and a target registration specification provided in an embodiment of the present application.

[0057] Figure 4 A structure diagram of an attribute fusion deep learning model provided in an embodiment of the present application.

[0058] Figure 5 A structure diagram of a website registration device provided in an embodiment of the present application.

[0059] Figure 6 A physical structure diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0061] In the embodiments of the present application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In the textual description of the present application, the character " / " generally represents an "or" relationship between the associated objects before and after it.

[0062] The technical solutions provided in the embodiments of the present application can be applied to the website registration scenario. In order to use the services provided by the website, the user needs to register the website, which not only facilitates the user to obtain personalized services, but also helps the website to manage and maintain user information.

[0063] The traditional website registration method usually requires the user to manually fill in a large amount of registration information, which will result in low registration efficiency.

[0064] In order to realize the automatic registration of the website, thereby improving the registration efficiency, the embodiment of the present application provides a website registration method. In the following, the website registration method provided by the present application will be described in detail through the following specific embodiments. It can be understood that the following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described in some embodiments.

[0065] Figure 1 The flowchart of the website registration method provided by the embodiment of the present application is applied to an electronic device. For example, as shown in the figure, the website registration method can include the following steps. Figure 1

[0066] S101, based on the types of the plurality of information input boxes of the registration webpage of the website, adding registration information in the plurality of information input boxes respectively, and sending each registration information to the website server.

[0067] For example, the plurality of information input boxes can include a username input box, a password input box, a verification code input box or other input boxes, etc. Correspondingly, the types of the information input boxes can include a username prompt type, a password prompt type, a verification code prompt type or other prompt types, etc. The specific types can be set according to actual needs.

[0068] In order to realize the automatic registration of the website, the electronic device can add registration information in the plurality of information input boxes respectively based on the types of the plurality of information input boxes. For example, when the type of the information input box is the username prompt type, the user can input the username to be registered in the information input box; when the type of the information input box is the password prompt type, the user can input the password in the information input box; when the type of the information input box is the verification code prompt type, the user can input the verification code in the information input box.

[0069] For example, in the embodiment of the present application, when the username and the password to be registered are input, the username and the password can be automatically generated based on a pre-constructed user information library. The user information library is usually constructed by analyzing the registration prompts of a plurality of websites to meet the registration requirements of most websites.

[0070] After adding the registration information in the plurality of information input boxes respectively, the added registration information can be sent to the registration server, so that the registration server determines whether the received registration information meets the corresponding registration specification based on the registration specification, and sends the registration prompt information to the electronic device based on the determination result.

[0071] S102, receiving the registration prompt information sent by the website server, the registration prompt information being determined based on each registration information and the corresponding registration specification of each information input box.

[0072] ​For example, the registration prompt information can be used to represent that the registration is successful, that is, each registration information is consistent with the corresponding registration specification and meets the registration requirements. Alternatively, the registration prompt information can also be used to represent that among the plurality of registration information, there is at least one registration information inconsistent with the corresponding registration specification. In this case, the electronic device can determine the target prompt type and the target registration specification by means of the attribute fusion deep learning model, that is, perform the following S103:

[0073] S103, in the case where the registration prompt information is used to represent that there is at least one registration information inconsistent with the corresponding registration specification, inputting the registration prompt information into the attribute fusion deep learning model to obtain the target prompt type and the target registration specification.

[0074] The target prompt type is a type corresponding to the target registration information inconsistent with the registration specification, and the target registration specification is a registration specification corresponding to the target registration information.

[0075] For example, in the embodiments of the present application, the target prompt type can be a username prompt type, a password prompt type, a verification code prompt type, or other prompt types, etc., which can be set according to actual needs.

[0076] For example, the attribute fusion deep learning model can be a deep learning-based model, which can be set according to actual needs.

[0077] For example, if the target prompt type output by the attribute fusion deep learning model is a username prompt type, it means that the target registration information inconsistent with the registration specification is a username, and the corresponding target registration specification is the registration specification corresponding to the username information input box, for example, a string composed of letters and numbers. If the target prompt type output by the attribute fusion deep learning model is a password prompt type, it means that the target registration information inconsistent with the registration specification is a password, and the corresponding target registration specification is the registration specification corresponding to the password information input box, for example, a string composed of uppercase letters, lowercase letters, and numbers with a length of not less than 8. If the target prompt type output by the attribute fusion deep learning model is a verification code prompt type, it means that the target registration information inconsistent with the registration specification is a verification code, and the corresponding target registration specification is the registration specification corresponding to the verification code information input box, for example, a string composed of 6 digits.

[0078] After determining the target prompt type and the target registration specification by means of the attribute fusion deep learning model, the target registration information inconsistent with the registration specification can be corrected based on the target prompt type and the target registration specification, that is, performing the following S104, to realize the automatic registration of the website and solve the problem of low registration efficiency caused by the need for manual filling of a large amount of registration information in the prior art, thereby effectively improving the registration efficiency.

[0079] S104, based on the target prompt type and the target registration specification, correcting the target registration information, and based on the registration information consistent with the registration specification and the corrected target registration information, performing website registration.

[0080] For example, if the target prompt type output by the attribute fusion deep learning model is a username prompt type, the target registration information inconsistent with the registration specification can be determined to be a username based on the target prompt type, and the added username is corrected to obtain a corrected username in combination with the corresponding username registration specification, such as a string composed of letters and numbers, and then the website is registered in combination with the registration information consistent with the registration specification, such as a password and a verification code.

[0081] For example, if the target prompt type output by the attribute fusion deep learning model is a password prompt type, the target registration information inconsistent with the registration specification can be determined to be a password based on the target prompt type, and the added password is corrected to obtain a corrected password in combination with the corresponding registration specification of the password information input box, such as a string composed of uppercase letters, lowercase letters, and numbers, and the length of the string is not less than 8, and then the website is registered in combination with the registration information consistent with the registration specification, such as a username and a verification code.

[0082] It can be seen that in the embodiments of the present application, when performing website registration, the types of the plurality of information input boxes of the registration webpage of the website can be used to add registration information in the plurality of information input boxes respectively, and each registration information is sent to the website server; and the registration prompt information sent by the website server is received; when the registration prompt information indicates that at least one registration information is inconsistent with the corresponding registration specification, the registration prompt information is input into the attribute fusion deep learning model to obtain a target prompt type and a target registration specification, and then the target registration information is corrected based on the target prompt type and the target registration specification, and the website is registered based on the registration information consistent with the registration specification and the corrected target registration information. In this way, with the help of the attribute fusion deep learning model, the target registration information can be automatically corrected based on the target prompt type and the target registration specification when there is at least one registration information inconsistent with the corresponding registration specification, which not only solves the problem of low registration efficiency caused by the need for users to manually fill in a large amount of registration information in the prior art, but also solves the problem of process interruption caused by unsuccessful website registration prompts, thereby effectively improving the registration efficiency.

[0083] Based on the above Figure 1In the illustrated embodiment, in S101, based on the types of the plurality of information input boxes of the registration webpage of the website, when adding the registration information in the plurality of information input boxes respectively, considering that many websites (including illegal websites) usually display activities and preferential policies on the webpage to guide new users to register and encourage existing users to continue to participate, these information generally appears in the form of a modal dialog box, and in view of the characteristics of the modal dialog forced interaction, in the embodiment of the present application, a modal exception automatic correction branch process can be added, specifically including: for each information input box, in response to a click operation on the information input box, determining a target solution in the case of outputting a modal dialog box; processing the modal dialog box based on the target solution, and adding the registration information in the information input box in the case that the modal dialog box has been processed, so that it can be automatically started without manual intervention, and the influence of the exception on the website automation process can be minimized.

[0084] For example, the target solution can be an exception capture processing solution of an element outside the information input box, which can be set according to actual needs.

[0085] For example, reference can be made to Figure 2 As shown, Figure 2A processing framework for appearing a modal dialog box when a click operation is performed on an information input box is provided in the embodiments of the present application. When a click operation is performed on an information input box, it can be first determined whether the click operation is successfully clicked. In the case of successful clicking, the Document Object Model (DOM) structure before and after the click operation is compared to determine whether the registration page has changed, so as to determine whether the click operation is effective. The DOM displays an HTML document in a tree structure, including elements, attributes and text nodes, and reflects all page changes. Through depth-first traversal, the HTML text is parsed and all nodes are saved in the form of [node label, node object, [list of child nodes]]. Through breadth-first traversal, the changed nodes can be compared and identified level by level to determine whether there is addition or deletion. If the nodes have addition or deletion, it is determined that the registration page has changed. In the case of change of the registration page, the click operation is implemented. In the case of unsuccessful clicking, it is determined that the output modal dialog box interrupts the website automatic registration process and has feedback. The feedback is further analyzed and the target solution is automatically determined. In the case that the target solution successfully processes the modal dialog box, the click operation on the information input box is performed again, and the click operation is implemented. In the case that the target solution does not successfully process the modal dialog box, the whole page is analyzed and the target solution is determined again. The click operation on the information input box is performed again, and the click operation is implemented. In the case that the registration page does not change, it is determined that the output modal dialog box interrupts the website automatic registration process and has no feedback. The whole page is further analyzed and the target solution is determined again. The click operation on the information input box is performed again, and the click operation is implemented. In this way, by adding a modal exception automatic correction branch process, the problem that some users are forced to respond in a certain form before other operations can be performed, resulting in process interruption, is solved. The process can be started automatically without manual intervention, and the influence of the exception on the website automatic process can be minimized.

[0086] For example, in the embodiments of the present application, the click operation identification for triggering a specific function on the registration page can be defined as a "button", and the buttons described below belong to such identification. The buttons can be divided into three categories: image buttons, whose functions are triggered by clicking the image elements in the webpage; non-image buttons, whose working mode is similar to the former; and submit buttons, which have various presentation modes but all realize the form submission function, and are different from the above two types of buttons.

[0087] For example, the image button retrieval logic follows a three-stage process: first, the filtering of label elements is performed; second, the extraction of source file paths and image class names and the keyword-based filtering are performed; and third, the corresponding paths of the determined elements are parsed and output.

[0088] Based on the above Figure 1 ​In the embodiment shown, the registration prompt information may, for example, include HyperText Markup Language (HTML) text, style attributes of nodes in a website, and a hierarchy of nodes.

[0089] The style attributes of the nodes may, for example, include a location of the nodes, a size of a figure, a pop-up display manner, and the like; and the hierarchy of the nodes may include labels and attribute values of all child nodes in the nodes, and a tree structure of the entire nodes.

[0090] In the case where the registration prompt information includes the HTML text, the style attributes of the nodes in the website, and the hierarchy of the nodes, in S103, the registration prompt information is input to the attribute fusion deep learning model to obtain the target prompt type and the target registration specification. For related implementation, refer to the following Figure 2 embodiment shown.

[0091] Figure 3 A flowchart for obtaining a target prompt type and a target registration specification provided by the embodiment of the present application may include the following steps.

[0092] S301, input the HTML text to a first embedding layer in the attribute fusion deep learning model to obtain a first text feature vector; and input the first text feature vector to an activation layer to obtain a target registration specification.

[0093] For example, in the embodiment of the present application, as shown in Figure 4 Figure 4 A structure diagram of an attribute fusion deep learning model provided by the embodiment of the present application may include a first embedding layer, a second embedding layer, a third embedding layer, an activation layer, and a post-processing module.

[0094] In the case where the target registration specification is obtained through the HTML text, the HTML text may be input to the first embedding layer in the attribute fusion deep learning model, the HTML text is converted into a first text feature vector through the first embedding layer, and the converted first text feature vector is input to the activation layer to obtain the target registration specification. In this way, the target registration specification corresponding to the target registration information inconsistent with the registration specification can be obtained based on the HTML text.

[0095] ​Next, in combination with the following S302-S304, the target prompt type corresponding to the target registration information inconsistent with the registration specification can be obtained, so that subsequent automatic correction of the target registration information can be based on the target prompt type and the target registration specification. Not only does it solve the problem of low registration efficiency caused by the need for users to manually fill in a large amount of registration information in the prior art, but it also solves the problem of process interruption caused by unsuccessful website prompts. Thus, the registration efficiency is effectively improved.

[0096] S302, input the style attribute of the node into the second embedding layer in the attribute fusion deep learning model to obtain a string feature vector.

[0097] For example, in the embodiments of the present application, the style attribute of the node includes numerical and categorical types. When the style attribute of the node is input into the second embedding layer in the attribute fusion deep learning model to obtain a string feature vector, the style attribute of the node can be first input into the second embedding layer in the attribute fusion deep learning model. For numerical style attributes, the numerical style attributes are normalized to obtain normalized style attributes. For categorical style attributes, the categorical style attributes are encoded to obtain encoded style attributes. The normalized style attributes and the encoded style attributes are spliced to obtain a string feature vector.

[0098] For example, for numerical style attributes such as node positioning or size, the numerical style attributes can be normalized, as shown in the following formula 1:

[0099] Formula 1

[0100] wherein, represents the normalized style attribute, represents the numerical style attribute, represents the smallest style attribute, represents the largest style attribute.

[0101] For example, for categorical style attributes such as display mode and element transformation attributes, the categorical style attributes can be one-hot encoded to obtain encoded style attributes. The normalized style attributes and the encoded style attributes are spliced to obtain a string feature vector.

[0102] Assuming that the numerical style attribute can be denoted as , and the categorical style attribute can be denoted as , wherein, , and , the normalized style attributes and the encoded style attributes are spliced to obtain a string feature vector: ] -> . represents the style attribute of the first numeric type, represents the style attribute of the first category type.

[0103] S303, input the hierarchy of the node into a third embedding layer in the attribute fusion deep learning model to obtain a string feature matrix.

[0104] For example, in the embodiment of the present application, when the hierarchy of the node is input into the third embedding layer in the attribute fusion deep learning model to obtain the string feature matrix, the hierarchy of the node can be first input into the third embedding layer in the attribute fusion deep learning model to determine the string corresponding to each node, the string corresponding to the node including the label and attribute value of the node; and based on the string set composed of the string corresponding to each node, determine the character-level feature matrix corresponding to the hierarchy of the node; and based on the string set, determine the word-level feature matrix corresponding to the hierarchy of the node; then the character-level feature matrix and the word-level feature matrix are weighted and spliced to obtain the string feature matrix.

[0105] Generally, the hierarchy of the node will allocate a unique identifier to each node of the tree structure thereof, and a vector is created for each node, the vector being a string composed of the label and attribute value of the node, therefore, when the hierarchy of the node is input into the third embedding layer in the attribute fusion deep learning model to determine the string corresponding to each node, it is assumed that the attribute value of node 1 can be represented by the string and , then the string corresponding to node 1 can be recorded as ; it is assumed that the attribute value of node 2 can be represented by the string , then the string corresponding to node 2 can be recorded as ; it is assumed that the attribute value of node 3 can be represented by the string and , then the string corresponding to node 3 can be recorded as .

[0106] After the string corresponding to each node is determined, the string corresponding to each node can be converted into a corresponding string set based on the hierarchy of the node, for example, in the embodiment of the present application, the string set can be recorded as U.

[0107] For example, in the embodiment of the present application, when determining the character-level feature matrix corresponding to the hierarchical structure of the nodes based on the string set composed of the strings corresponding to the nodes, the tokenization operation can be performed on each string in the string set composed of the strings corresponding to the nodes to obtain a tokenization result set; the character-level vector corresponding to the string set is generated according to the frequency of the character elements in the tokenization result set; the dimensions of all vectors in the character-level vector are adjusted to obtain a vector set, and the dimensions of all vectors in the vector set are the same; all vectors in the vector set are encoded, and the matrix obtained by the encoding is processed by dimension reduction to obtain a dense matrix; the character-level feature matrix is obtained by feature extraction on the dense matrix.

[0108] For example, when determining the character-level feature matrix based on the string set composed of the strings corresponding to the nodes, the tokenization operation can be performed on all tags in the string set U by characters, and the tokenization result set is denoted as V, which represents the set of all characters appearing in the tag set. The frequency of the character elements in the tokenization result set V is assigned a number 1, 2, …, n, and the character-level vector corresponding to the string set is generated to form a character-level vector, where the value of n can be set according to actual needs. Secondly, padding operation is performed on all vectors in the character-level vector to fix the dimensions of all tag vectors. For vectors with insufficient length, 0 is added in front of the vectors, and for vectors with excessive length, the part exceeding the vector is truncated, and finally a vector set W is formed. Please refer to formula 2 shown below, where the dimensions of all vectors in the vector set W are the same.

[0109] W={w1,w2,w3,...,wi} Formula 2

[0110] where w1 represents the first vector, and wi represents the i-th vector.

[0111] In addition, one-hot encoding is performed on all vectors in the vector set to form a one-hot matrix G. In order to construct a dense low-dimensional feature matrix, the matrix G is processed by dimension reduction to obtain a dense matrix S, which can be seen from formula 3 shown below:

[0112] Formula 3

[0113] where is a dimension reduction matrix, which is used to reduce the dimension of the matrix with a dimension of to a dimension of to obtain the dense matrix .

[0114] The dense matrix S is subjected to feature extraction by one-dimensional convolution of the TextCNN to obtain a character-level feature matrix CV, which can be seen from the following formula 4:

[0115] CV={cv1, cv2, cv3,..., cvi} Formula 4

[0116] Wherein, cv1 represents the first character-level feature, and cvi represents the ith character-level feature.

[0117] For example, in the embodiment of the application, when determining the word-level feature matrix corresponding to the hierarchical structure of the node based on the string set, the strings in the string set corresponding to each node can be segmented first to obtain a segmentation matrix, and the lengths of all segmentation results in the segmentation matrix are the same; the website word vector matrix corresponding to the segmentation matrix is subjected to dimension reduction processing to obtain a low-dimensional word vector matrix; and the low-dimensional word vector matrix is subjected to feature extraction to obtain a word-level feature matrix.

[0118] For example, when determining the word-level feature matrix corresponding to the hierarchical structure of the node based on the string set, the strings in the string set U can be segmented according to the corpus of the BERT pre-training model, a maximum segmentation length is set, the part exceeding the maximum length is directly deleted, and the part less than the maximum length is automatically supplemented with 0 in subsequent input to the BERT model to obtain a segmentation matrix T.

[0119] T={t1, t2, t3,..., ti} Formula 5

[0120] Wherein, t1 represents the first segmentation, and ti represents the ith segmentation.

[0121] Secondly, each row ti in the segmentation matrix T is converted into idSequence to obtain an ids matrix, and then 12 hidden layers are obtained by using the pre-trained BERT model, and a 768-dimensional website word vector matrix Word facing prompt information is obtained by summing the last four rows, which can be seen from the following formula 6:

[0122] Word={word1, word2, word3,..., wordi} Formula 6

[0123] Wherein, word1 represents the first website word vector, and wordi represents the ith website word vector.

[0124] Then, the high-dimensional website word vector matrix Word is subjected to dimension reduction processing by using a full connection layer to obtain a low-dimensional word vector matrix R, which can be seen from the following formula 7:

[0125] Formula 7

[0126] wherein, represents a high-dimensional website word vector matrix Word, is a dimension reduction matrix, used to reduce the dimension of the high-dimensional website word vector matrix Word from the high dimension to the low dimension, to obtain a low-dimensional word vector matrix R.

[0127] The low-dimensional word vector matrix R is subjected to feature extraction by TextCNN one-dimensional convolution to obtain a word-level feature matrix WV, which can be seen from the following formula 8:

[0128] WV={wv1,wv2,wv3,...,wvi} Formula 8

[0129] wherein, wv1 represents the first word-level feature, and wvi represents the i-th word-level feature.

[0130] The character-level feature matrix CV and the word-level feature matrix WV are then weighted and spliced to obtain a string feature matrix.

[0131] In combination with the above description, after obtaining the first text feature vector, the string feature vector and the string feature matrix respectively, the following S304 can be performed:

[0132] S304, input the first text feature vector, the string feature vector and the string feature matrix into a post-processing module in the attribute fusion deep learning model to obtain a target prompt type.

[0133] It should be noted that in the embodiments of the present application, the operation of inputting the first text feature vector into the activation layer to obtain the target registration specification in the above S301 has no sequence with the operation of obtaining the target prompt type in the above S302-S304. In this embodiment of the present application, only the operation of inputting the first text feature vector into the activation layer to obtain the target registration specification, and then performing the operation of obtaining the target prompt type in the above S202-S304 is described as an example, but it does not mean that the embodiments of the present application are limited to this.

[0134] As shown in the above Figure 4 For example, in the embodiments of the present application, the post-processing module can include a convolution layer, a max-pooling layer, a regularization layer and an activation layer connected in sequence, which can be set according to actual needs.

[0135] ​When the first text feature vector, the string feature vector, and the string feature matrix are input into the post-processing module in the attribute fusion deep learning model, the first text feature vector, the string feature vector, and the string feature matrix can be subjected to global pooling and a full connection layer for each feature first; secondly, a connection activation function is used to generate feature weight scores, so as to achieve the effect of weighting for each feature; thirdly, a global self-attention module is used to obtain better global information. Then, a convolution layer is used to capture local patterns in the vector, a pooling layer is used to reduce the dimension of the feature vector, and a dropout layer is used to avoid model overfitting; finally, the target prompt type is output.

[0136] In the case where at least one registration information is inconsistent with the corresponding registration specification, after the target prompt type and the target registration specification are determined by means of the attribute fusion deep learning model, the target registration information can be corrected based on the target prompt type and the target registration specification, that is, S104 described above is executed.

[0137] For example, in S104 described above, when the target registration information is corrected based on the target prompt type and the target registration specification, the label sequence of all nodes in the website can be first converted into a corresponding index vector, and the index vector and the HTML text can be fused and spliced to obtain a fusion sequence; the fusion sequence can be input into a large language model to obtain a correction strategy for the target registration information; and the target registration information can be corrected based on the target prompt type, the target registration specification, and the correction strategy. In this way, not only is the problem of low registration efficiency caused by the need for users to manually fill in a large amount of registration information in the prior art solved, but also the problem of process interruption caused by unsuccessful website registration prompts is solved, thereby effectively improving the registration efficiency.

[0138] For example, when the label sequence of all nodes in the website is converted into a corresponding index vector, a label dictionary for registration information prompts can be constructed in advance, wherein all information prompt related labels in the current HTML specification and five special identifiers [SEP], [LEFT], [RIGHT], [UNK], and [PAD] are screened, a total of 64. In this way, the label dictionary can be combined to convert and map the label sequence of all nodes into a corresponding index vector, and the index vector and the HTML text can be fused and spliced to obtain a fusion sequence, which is ready to be input into a large language model to output a correction strategy for the target registration information by the large language model.

[0139] For example, in the embodiments of the present application, in order to enable the large language model to fully understand the vertical scene of website registration, the prompt paradigm enhancement method of multi-concept combination is adopted, the prompt type is replaced by a set of concept words or phrases with the same meaning, for example, "character length" is replaced by "password length", "username length", "within a certain number of characters", etc., to enrich the semantic meaning of the target, so that the large language model obtained by pre-training can learn more related knowledge. Given the prompt template and the type word set V (character length, special character, uppercase letter, number, occupied, space, etc.), for the fusion sequence of each node and the concept word combination {concept1, concept2, …, conceptk}, where k represents the kth concept word. First, the fusion sequence of the node is combined with each concept word using the given prompt template and each concept word is mapped to the prompt input ; then each prompt input is fed into a separate large language model , respectively, to obtain the hidden layer representation of [MASK] , and then the probability of the registration prompt type at [MASK] is obtained as:

[0140]

[0141] where, represents the probability under , and is the encoding vector in the pre-trained large language model . After calculating the mask prediction probability, the probability is normalized using the softmax function.

[0142] Finally, the activation layer output of the large language model is the correction strategy of the target registration information. The label word probability learned by each concept word through prompting is different due to the different concept words and learned knowledge, so they need to be fused to obtain the overall type probability:

[0143]

[0144] By the above large language model, the correction strategy of the target registration information, i.e., the adjustment direction of the target registration information, can be determined, so that the target registration information is corrected based on the target prompt type and the target registration specification, and the target registration information is re-registered until the registration is successful. In this way, not only the problem of low registration efficiency caused by the need for manual filling of a large amount of registration information in the prior art is solved, but also the problem of process interruption caused by unsuccessful website registration is solved, thereby effectively improving the registration efficiency.

[0145] The website registration device provided in the present application is described below. The website registration device described below can be referred to in correspondence with the website registration method described above.

[0146] Figure 5 A structural schematic diagram of a website registration device provided in an embodiment of the present application is applied to an electronic device. For example, refer to FIG. 5. Figure 5 As shown in FIG. 5, the website registration device 50 can include:

[0147] A first processing unit 501 is configured to add registration information in a plurality of information input boxes of a registration webpage of a website based on a type of each of the plurality of information input boxes.

[0148] A sending unit 502 is configured to send each of the registration information to a website server.

[0149] A receiving unit 503 is configured to receive registration prompt information sent by the website server, the registration prompt information being determined based on each of the registration information and a corresponding registration specification of each of the information input boxes.

[0150] A second processing unit 504 is configured to input the registration prompt information to an attribute fusion deep learning model to obtain a target prompt type and a target registration specification when the registration prompt information indicates that at least one of the registration information is inconsistent with the corresponding registration specification, the target prompt type being a type corresponding to target registration information that is inconsistent with the registration specification, and the target registration specification being a registration specification corresponding to the target registration information.

[0151] A registration unit 505 is configured to correct the target registration information based on the target prompt type and the target registration specification, and perform website registration based on registration information consistent with the registration specification and the corrected target registration information.

[0152] For example, in an embodiment of the present application, the registration prompt information includes HTML text, style attributes of a node in the website, and a hierarchical structure of the node.

[0153] The second processing unit 504 is configured to input the registration prompt information into an attribute fusion deep learning model to obtain a target prompt type corresponding to target registration information inconsistent with a registration specification and the target registration specification.

[0154] The HTML text is input into a first embedding layer in the attribute fusion deep learning model to obtain a first text feature vector, and the first text feature vector is input into an activation layer to obtain the target registration specification.

[0155] The style attribute of the node is input into a second embedding layer in the attribute fusion deep learning model to obtain a string feature vector.

[0156] The hierarchical structure of the node is input into a third embedding layer in the attribute fusion deep learning model to obtain a string feature matrix.

[0157] The first text feature vector, the string feature vector, and the string feature matrix are input into a post-processing module in the attribute fusion deep learning model to obtain the target prompt type.

[0158] For example, in the embodiment of the present application, the style attribute of the node includes a numerical type and a category type.

[0159] The second processing unit 504 is configured to input the style attribute of the node into a second embedding layer in the attribute fusion deep learning model to obtain a string feature vector, including:

[0160] The style attribute of the node is input into a second embedding layer in the attribute fusion deep learning model, and for the numerical type of the style attribute, the numerical type of the style attribute is normalized to obtain a normalized style attribute.

[0161] For the category type of the style attribute, the category type of the style attribute is encoded to obtain an encoded style attribute.

[0162] The normalized style attribute and the encoded style attribute are spliced to obtain the string feature vector.

[0163] For example, in the embodiment of the present application, the second processing unit 504 is configured to input the hierarchical structure of the node into a third embedding layer in the attribute fusion deep learning model to obtain a string feature matrix, including:

[0164] The hierarchical structure of the node is input into a third embedding layer in the attribute fusion deep learning model to determine a string corresponding to each node.

[0165] determine a character-level feature matrix corresponding to the hierarchical structure of the nodes based on a string set composed of the strings corresponding to the nodes; and determine a word-level feature matrix corresponding to the hierarchical structure of the nodes based on the string set;

[0166] perform weighted splicing on the character-level feature matrix and the word-level feature matrix to obtain the string feature matrix.

[0167] For example, in the embodiments of the present application, the second processing unit 504 is configured to determine a character-level feature matrix corresponding to the hierarchical structure of the nodes based on a string set composed of the strings corresponding to the nodes, including:

[0168] performing a word segmentation operation on each string in the string set composed of the strings corresponding to the nodes to obtain a word segmentation result set;

[0169] generating a character-level vector corresponding to the string set according to the frequency of occurrence of character elements in the word segmentation result set;

[0170] adjusting the dimensions of all vectors in the character-level vector to obtain a vector set, wherein all vectors in the vector set have the same dimension;

[0171] encoding all vectors in the vector set and performing dimensionality reduction processing on the matrix obtained by the encoding to obtain a dense matrix;

[0172] performing feature extraction on the dense matrix to obtain the character-level feature matrix.

[0173] For example, in the embodiments of the present application, the second processing unit 504 is configured to determine a word-level feature matrix corresponding to the hierarchical structure of the nodes based on the string set, including:

[0174] performing a word segmentation operation on each string in the string set composed of the strings corresponding to the nodes to obtain a word segmentation matrix, wherein all word segmentation results in the word segmentation matrix have the same length;

[0175] performing dimensionality reduction processing on a website word vector matrix corresponding to the word segmentation matrix to obtain a low-dimensional word vector matrix;

[0176] performing feature extraction on the low-dimensional word vector matrix to obtain the word-level feature matrix.

[0177] For example, in the embodiments of the present application, the registration unit 505 is configured to correct the target registration information based on the target prompt type and the target registration specification, including:

[0178] convert the label sequence of all nodes in the website into a corresponding index vector, and splice the index vector with the HTML text to obtain a spliced sequence;

[0179] input the spliced sequence into a large language model to obtain a correction strategy of the target registration information;

[0180] Based on the target prompt type, the target registration specification and the correction strategy, the target registration information is corrected.

[0181] For example, in the embodiments of the present application, the first processing unit 501 is configured to add registration information in each of a plurality of information input boxes of a registration webpage of a website based on the type of each of the plurality of information input boxes, including:

[0182] For each information input box, in response to a click operation on the information input box, a target solution is determined in the case of an output modal dialog box;

[0183] Based on the target solution, the modal dialog box is processed, and in the case that the modal dialog box has been processed, the registration information is added in the information input box.

[0184] The website registration device 50 provided by the embodiments of the present application can execute the technical solutions of the website registration method in any of the above embodiments, and the implementation principles and beneficial effects thereof are similar to those of the website registration method. For details, refer to the implementation principles and beneficial effects of the website registration method, which will not be described here.

[0185] Figure 6 An entity structure schematic diagram of an electronic device provided by the embodiments of the present application is as follows: Figure 6As shown, the electronic device can include a processor 610, a communications interface 620, a memory 630, and a communications bus 640, wherein the processor 610, the communications interface 620, and the memory 630 complete communications with each other through the communications bus 640. The processor 610 can invoke a logical instruction in the memory 630 to execute a website registration method, which includes: based on a type of each of a plurality of information input boxes of a registration webpage of a website, adding registration information in the plurality of information input boxes respectively, and sending each of the registration information to a website server; receiving registration prompt information sent by the website server, the registration prompt information being determined based on each of the registration information and a corresponding registration specification of each of the information input boxes; in a case where the registration prompt information is used to represent that there is at least one of the registration information inconsistent with the corresponding registration specification, inputting the registration prompt information into an attribute fusion deep learning model to obtain a target prompt type and a target registration specification, the target prompt type being a type corresponding to a target registration information inconsistent with the registration specification, and the target registration specification being a registration specification corresponding to the target registration information; based on the target prompt type and the target registration specification, correcting the target registration information, and based on registration information consistent with the registration specification and the corrected target registration information, performing website registration.

[0186] In addition, the logical instruction in the memory 630 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0187] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer-readable storage medium, and the computer program, when executed by a processor, enables a computer to perform the website registration method provided by any of the above methods. The method comprises: based on the types of a plurality of information input boxes of a registration webpage of a website, adding registration information in the plurality of information input boxes respectively, and sending each of the registration information to a website server; receiving registration prompt information sent by the website server, the registration prompt information being determined based on each of the registration information and a corresponding registration specification; in a case where the registration prompt information is used to indicate that there is at least one registration information inconsistent with the corresponding registration specification, inputting the registration prompt information into an attribute fusion deep learning model to obtain a target prompt type and a target registration specification, the target prompt type being a type corresponding to a target registration information inconsistent with the registration specification, and the target registration specification being a registration specification corresponding to the target registration information; based on the target prompt type and the target registration specification, correcting the target registration information, and performing website registration based on the registration information consistent with the registration specification and the corrected target registration information.

[0188] In another aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and the computer program, when executed by a processor, enables a computer to perform the website registration method provided by any of the above methods. The method comprises: based on the types of a plurality of information input boxes of a registration webpage of a website, adding registration information in the plurality of information input boxes respectively, and sending each of the registration information to a website server; receiving registration prompt information sent by the website server, the registration prompt information being determined based on each of the registration information and a corresponding registration specification; in a case where the registration prompt information is used to indicate that there is at least one registration information inconsistent with the corresponding registration specification, inputting the registration prompt information into an attribute fusion deep learning model to obtain a target prompt type and a target registration specification, the target prompt type being a type corresponding to a target registration information inconsistent with the registration specification, and the target registration specification being a registration specification corresponding to the target registration information; based on the target prompt type and the target registration specification, correcting the target registration information, and performing website registration based on the registration information consistent with the registration specification and the corrected target registration information.

[0189] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0190] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, and the computer software products can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0191] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A website registration method, characterized in that, Applied to electronic devices, the method includes: Based on the types of the multiple information input boxes on the website's registration page, registration information is added to each of the multiple information input boxes, and the registration information is sent to the website server. The system receives registration prompt information sent by the website server. The registration prompt information is determined based on the registration information and the registration specifications corresponding to each information input box. The registration prompt information includes HTML text, style attributes of nodes in the website, and the hierarchical structure of the nodes. When the registration prompt information is used to represent that at least one piece of registration information is inconsistent with the corresponding registration specification, the registration prompt information is input into the attribute fusion deep learning model to obtain the target prompt type and the target registration specification. The target prompt type is the type corresponding to the target registration information that is inconsistent with the registration specification, and the target registration specification is the registration specification corresponding to the target registration information. Based on the target prompt type and the target registration specification, the target registration information is corrected, and website registration is performed based on the registration information consistent with the registration specification and the corrected target registration information.

2. The website registration method according to claim 1, characterized in that, The step of inputting the registration prompt information into the attribute fusion deep learning model to obtain the target prompt type and target registration specification includes: The HTML text is input into the first embedding layer of the attribute fusion deep learning model to obtain the first text feature vector; and the first text feature vector is input into the activation layer to obtain the target registration specification. The style attributes of the node are input into the second embedding layer of the attribute fusion deep learning model to obtain a string feature vector; The hierarchical structure of the nodes is input into the third embedding layer of the attribute fusion deep learning model to obtain the string feature matrix; The first text feature vector, the string feature vector, and the string feature matrix are input into the post-processing module of the attribute fusion deep learning model to obtain the target prompt type.

3. The website registration method according to claim 2, characterized in that, The style attributes of the nodes include numeric and categorical types; The step of inputting the style attributes of the node into the second embedding layer of the attribute fusion deep learning model to obtain a string feature vector includes: The style attributes of the node are input into the second embedding layer of the attribute fusion deep learning model. For numerical style attributes, the numerical style attributes are normalized to obtain normalized style attributes. For category-type style attributes, the category-type style attributes are encoded to obtain the encoded style attributes; The normalized style attribute and the encoded style attribute are concatenated to obtain the string feature vector.

4. The website registration method according to claim 2, characterized in that, The step of inputting the hierarchical structure of the nodes into the third embedding layer of the attribute fusion deep learning model to obtain the string feature matrix includes: The hierarchical structure of the nodes is input into the third embedding layer of the attribute fusion deep learning model to determine the string corresponding to each node; Based on the string set consisting of the strings corresponding to each node, determine the character-level feature matrix corresponding to the hierarchical structure of the node; and based on the string set, determine the word-level feature matrix corresponding to the hierarchical structure of the node. The character-level feature matrix and the word-level feature matrix are weighted and concatenated to obtain the string feature matrix.

5. The website registration method according to claim 4, characterized in that, The determination of the character-level feature matrix corresponding to the hierarchical structure of the nodes based on the string set composed of the strings corresponding to each node includes: In the string set consisting of the strings corresponding to each node, each string is segmented into words to obtain a set of segmentation results. Generate a character-level vector corresponding to the string set based on the frequency of occurrence of character elements in the word segmentation result set; The dimensions of all vectors in the character-level vector are adjusted to obtain a vector set in which all vectors have the same dimension. Encode all vectors in the vector set, and then reduce the dimensionality of the encoded matrix to obtain a dense matrix; Feature extraction is performed on the dense matrix to obtain the character-level feature matrix.

6. The website registration method according to claim 4, characterized in that, The step of determining the word-level feature matrix corresponding to the hierarchical structure of the nodes based on the string set includes: In the string set consisting of the strings corresponding to each node, each string is segmented into words to obtain a segmentation matrix, wherein all segmentation results in the segmentation matrix have the same length; The dimensionality of the website word vector matrix corresponding to the word segmentation matrix is ​​reduced to obtain a low-dimensional word vector matrix. Feature extraction is performed on the low-dimensional word vector matrix to obtain the word-level feature matrix.

7. The website registration method according to any one of claims 2-6, characterized in that, The step of modifying the target registration information based on the target prompt type and the target registration specification includes: The tag sequence of all nodes in the website is converted into a corresponding index vector, and the index vector is merged and concatenated with the HTML text to obtain a fused sequence; The fused sequence is input into a large language model to obtain the correction strategy for the target registration information; Based on the target prompt type, the target registration specification, and the correction strategy, the target registration information is corrected.

8. The website registration method according to any one of claims 1-6, characterized in that, The website-based registration page has multiple information input boxes of various types, and registration information is added to each of these input boxes, including: For each of the aforementioned information input boxes, in response to a click operation on the information input box, if a modal dialog box is output, a target solution is determined; The modal dialog box is processed based on the target solution, and the registration information is added to the information input box after the modal dialog box has been processed.

9. A website registration device, characterized in that, Applied to electronic devices, the device includes: The first processing unit is used to add registration information to the multiple information input boxes on the website's registration page, based on the respective types of those input boxes. The sending unit is used to send the registration information to the website server; A receiving unit is configured to receive registration prompt information sent by the website server. The registration prompt information is determined based on the registration information and the registration specifications corresponding to each information input box. The registration prompt information includes HTML text, style attributes of nodes in the website, and the hierarchical structure of the nodes. The second processing unit is configured to input the registration prompt information into the attribute fusion deep learning model to obtain the target prompt type and the target registration specification when the registration prompt information is used to represent that at least one piece of registration information is inconsistent with the corresponding registration specification. The target prompt type is the type corresponding to the target registration information that is inconsistent with the registration specification, and the target registration specification is the registration specification corresponding to the target registration information. The registration unit is used to modify the target registration information based on the target prompt type and the target registration specification, and to register the website based on the registration information consistent with the registration specification and the modified target registration information.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the website registration method as described in any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the website registration method as described in any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the website registration method as described in any one of claims 1 to 8.

Images