Website guide popup window generation method and device, equipment and storage medium

Abstract

The invention discloses a website guide pop-up window generation method, device and equipment and a storage medium, and belongs to the technical field of artificial intelligence, the method is executed by a client browser, and the method comprises the steps of obtaining a question text input by a user in a function search suspended window of a target website; sending the problem text to a large model server, so that the large model server obtains a matched text vector matched with the problem text according to the problem text; and receiving a matched text vector sent by the large model server, and analyzing the matched text vector to obtain a website guide pop-up window corresponding to the problem text. According to the method and the device, the problems that the existing complex web site guide content is solidified, the one-time guide content is excessive, the guide content is not comprehensive and the guide process is not intelligent enough are solved, the learning cost of a user for using the website is reduced, the flexibility and the intelligence of website guide are improved, the use experience of the user is improved, and the user experience is improved. And thus, the office efficiency of the user on the website is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and storage medium for generating a website guide pop-up window. Background Art

[0002] In order to let users understand how to use complex web sites and avoid users not knowing how to operate due to unfamiliarity with the site, a common solution is to initiate a guidance pop-up window when the user enters the site for the first time or logs in to the site for the first time. The functions of each button and module in the website are displayed to the user in the form of a pop-up window. The user clicks the "Got it" button in the pop-up window, and then another pop-up window will be displayed to introduce the functions of the next module. If the user enters the site again, the guidance pop-up window will no longer appear.

[0003] However, although this guidance method can help new users quickly understand the basic functions of the website, it crams too much guidance content into users at one time, and users often cannot remember it. In the subsequent use process, they still need to consult the website developers, which has a high learning cost and affects the user's office efficiency on the website. In addition, the guidance content of this guidance method is fixed and limited. It is impossible to introduce all the functions and operation steps of the website, and it is also impossible to guide users on the subsequent operation steps according to their current usage needs. Summary of the invention

[0004] The present invention provides a website guidance pop-up window generation method, device, equipment and storage medium to solve the problems of existing complex web website guidance content solidification, too much one-time guidance content, insufficient guidance content and insufficient intelligence of the guidance process, improve the flexibility and intelligence of website guidance, reduce the learning cost of users using the website, improve the user experience, and improve the user's office efficiency on the website.

[0005] According to one aspect of the present invention, a method for generating a website guide pop-up window is provided, the method being executed by a client browser and comprising:

[0006] Obtain the question text entered by the user in the function search window of the target website;

[0007] Send the question text to the big model server, so that the big model server obtains a matching text vector that matches the question text based on the question text;

[0008] Receive the matching text vector sent by the large model server, parse the matching text vector, and obtain the website guidance pop-up window corresponding to the question text.

[0009] According to one aspect of the present invention, a method for generating a website guide pop-up window is provided, and the method is executed by a large model server, comprising:

[0010] Receive the question text sent by the client browser;

[0011] Performing text segmentation on the question text to obtain at least one question text block;

[0012] Perform vectorization processing on each question text block respectively to obtain the question text vector corresponding to each question text block;

[0013] The question text vector corresponding to each question text block is matched with the pop-up window text vector in the vector search library for similarity, and a matching text vector matching the question text is obtained;

[0014] The matching text vector is sent to the client browser, so that the client browser generates a website guidance pop-up window corresponding to the question text according to the matching text vector.

[0015] According to another aspect of the present invention, a device for generating a website guide pop-up window is provided, and the device is applied to a client browser, comprising:

[0016] A question text acquisition module is used to acquire the question text entered by the user in the function search window of the target website;

[0017] A question text sending module is used to send the question text to the large model server, so that the large model server obtains a matching text vector that matches the question text according to the question text;

[0018] The website guidance pop-up window generation module is used to receive the matching text vector sent by the large model server, and parse the matching text vector to obtain the website guidance pop-up window corresponding to the question text.

[0019] According to another aspect of the present invention, a device for generating a website guide pop-up window is provided, and the device is applied to a large model server, comprising:

[0020] A question text receiving module is used to receive the question text sent by the client browser;

[0021] A question text block determination module is used to segment the question text to obtain at least one question text block;

[0022] A question text vector determination module is used to perform vectorization processing on each question text block respectively to obtain a question text vector corresponding to each question text block;

[0023] A matching text vector determination module is used to perform similarity matching between the question text vector corresponding to each question text block and the pop-up window text vector in the vector search library to obtain a matching text vector that matches the question text;

[0024] The matching text vector sending module is used to send the matching text vector to the client browser, so that the client browser generates a website guidance pop-up window corresponding to the question text according to the matching text vector.

[0025] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0026] at least one processor; and

[0027] a memory communicatively connected to at least one processor; wherein,

[0028] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the website guide pop-up window generation method of any embodiment of the present invention.

[0029] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the website guide pop-up window generation method of any embodiment of the present invention when executed.

[0030] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method for generating a website guide pop-up window according to any embodiment of the present invention is implemented.

[0031] The technical solution of the embodiment of the present invention obtains the question text entered by the user in the function search hanging window of the target website; sends the question text to the large model server, so that the large model server obtains the matching text vector matching the question text according to the question text; receives the matching text vector sent by the large model server, and parses the matching text vector to obtain the website guidance pop-up window corresponding to the question text. The above technical solution can generate a website guidance pop-up window corresponding to the question text according to the question text entered by the user in the function search hanging window of the target website to guide the user to operate in the target website. That is, according to the current use needs of the user, a website guidance pop-up window that meets the current use needs of the user can be flexibly generated, which solves the problems of solidified guidance content of existing complex web websites, too much one-time guidance content, insufficient guidance content and insufficient intelligence of the guidance process. Users can complete corresponding operations on the target website according to the website guidance pop-up window without consulting the website developer, thereby reducing the learning cost of users using the website, improving the flexibility and intelligence of website guidance, improving the user's use experience, and thus improving the user's office efficiency on the website.

[0032] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 This is a flow chart of a method for generating a website guide pop-up window according to the first embodiment of the present invention;

[0035] Figure 2 This is a flow chart of a method for generating a website guide pop-up window provided in accordance with Embodiment 2 of the present invention;

[0036] Figure 3 This is a flow chart of a method for generating a website guide pop-up window provided in accordance with Embodiment 3 of the present invention;

[0037] Figure 4 It is a structural schematic diagram of a device for generating a website guide pop-up window according to a fourth embodiment of the present invention;

[0038] Figure 5 This is a structural diagram of a device for generating a website guide pop-up window according to a fifth embodiment of the present invention;

[0039] Figure 6 It is a structural schematic diagram of an electronic device for implementing the website guide pop-up window generation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0041] It should be noted that the term "target" and the like in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0042] In addition, it should be noted that the collection, storage, use, processing, transmission, provision and disclosure of the LangChain framework involved in the technical solution of the present invention are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0043] Embodiment 1

[0044] Figure 1 This is a flow chart of a method for generating a website guide pop-up window provided in the first embodiment of the present invention. This embodiment can be applied to the case where a website guide pop-up window of a complex web site is generated according to the current usage requirements of the user. The method can be executed by a website guide pop-up window generating device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device with a client browser. Figure 1 As shown, the method is executed by the client browser and includes:

[0045] S101, obtaining the question text input by the user in the function search hanging window of the target website.

[0046] Among them, the function search window refers to a search box used to search how the target website implements a certain function; optionally, the function search window is obtained by executing a search window script. That is, the client browser can obtain the function search window of the target website by executing a search window script. Among them, the search window script refers to a script used to generate a function search window of the target website, which creates a function search window by using JavaScript to operate DOM (Document Object Model) to create page element nodes. For example, the search window script may include the following content:

[0047] var searchInput=document.createElement("input");

[0048] searchInput.type = "text";

[0049] searchInput.placeholder="Please enter the search content";

[0050] var searchButton=document.createElement("button");

[0051] searchButton.textContent = "Search";

[0052] var searchContainer=document.createElement("div");

[0053] searchContainer.appendChild(searchInput);

[0054] searchContainer.appendChild(searchButton);

[0055] document.body.appendChild(searchContainer);

[0056] It is understandable that by executing the search pop-up window script to obtain the function search pop-up window of the target website, it is convenient to subsequently personalize the function search pop-up window in real time according to the design requirements of the function search pop-up window.

[0057] The target website refers to a complex web site that the user needs to operate, and the question text refers to the text entered by the user in the function search window.

[0058] Specifically, the client browser can obtain the question text input by the user in the function search pop-up window of the target website through the input monitoring event corresponding to the function search pop-up window.

[0059] S102. Send the question text to the big model server, so that the big model server obtains a matching text vector that matches the question text based on the question text.

[0060] The large model server refers to a server for providing a text vector matching the question text. The matching text vector refers to a text vector matching the question text.

[0061] Specifically, the client browser can send the question text to the big model server through the preset communication interface, so that the big model server can obtain a matching text vector that matches the question text based on the question text. The preset communication interface refers to an interface for data interaction between the client browser and the big model server; optionally, the preset communication interface can be pre-set according to actual business needs, for example, the preset communication interface can be an http (Hypertext Transfer Protocol) interface, which is not specifically limited in the embodiment of the present invention.

[0062] S103: Receive the matching text vector sent by the large model server, and parse the matching text vector to obtain a website guidance pop-up window corresponding to the question text.

[0063] The website guide pop-up window refers to a pop-up window used to provide website guide information to users. It should be noted that the matching text vector exists in the data exchange format of JSON (JavaScript Object Notation) data. JSON data consists of at least one key-value pair and is a lightweight data exchange format.

[0064] Specifically, the client browser receives the matching text vector sent by the large model server through a preset communication interface, and after receiving the matching text vector, parses the matching text vector through a JSON data parsing algorithm to obtain a website guide pop-up window corresponding to the question text. Among them, the JSON data parsing algorithm can be pre-set according to actual business needs, and the embodiment of the present invention does not specifically limit it. For example, the matching text vector can be parsed through the following JSON data parsing algorithm to obtain a website guide pop-up window corresponding to the question text:

[0065]

[0066] Here, jsonData is a matching text vector in the data exchange format of JSON data.

[0067] Optionally, after obtaining the website guide pop-up window corresponding to the question text, the website guide pop-up window can also be displayed at a specified location of the target website based on a preset guide pop-up window display method to improve the user experience of using the target website.

[0068] For example, after obtaining the website guide pop-up window corresponding to the question text, the native DOM API (Application Programming Interface) is used to create the HTML (Hypertext Markup Language) element of the website guide pop-up window, and the created website guide pop-up window is mounted to the specified position of the target website through the document.appendChild() method. Among them, the DOM API is the Document Object Model Application Programming Interface, which is a set of programming interfaces for operating and managing the structure and content of Web documents.

[0069] The technical solution of the embodiment of the present invention obtains the question text entered by the user in the function search hanging window of the target website; sends the question text to the large model server, so that the large model server obtains the matching text vector matching the question text according to the question text; receives the matching text vector sent by the large model server, and parses the matching text vector to obtain the website guidance pop-up window corresponding to the question text. The above technical solution can generate a website guidance pop-up window corresponding to the question text according to the question text entered by the user in the function search hanging window of the target website to guide the user to operate in the target website. That is, according to the current use needs of the user, a website guidance pop-up window that meets the current use needs of the user can be flexibly generated, which solves the problems of solidified guidance content of existing complex web websites, too much one-time guidance content, insufficient guidance content and insufficient intelligence of the guidance process. Users can complete corresponding operations on the target website according to the website guidance pop-up window without consulting the website developer, thereby reducing the learning cost of users using the website, improving the flexibility and intelligence of website guidance, improving the user's use experience, and thus improving the user's office efficiency on the website.

[0070] Embodiment 2

[0071] Figure 2 This is a flowchart of a method for generating a website guide pop-up window provided in the second embodiment of the present invention. This embodiment can be applied to the case where a website guide pop-up window of a complex web site is generated according to the current usage requirements of the user. The method can be executed by a website guide pop-up window generating device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device with a large model server. It should be noted that for the parts not described in detail in the embodiments of the present invention, reference can be made to the relevant descriptions of other embodiments. Figure 2 As shown, the method is executed by the large model server, including:

[0072] S201, receiving a question text sent by a client browser.

[0073] Specifically, the large model server can receive the question text sent by the client browser through a preset communication interface.

[0074] S202: Segment the question text to obtain at least one question text block.

[0075] The question text block refers to the text block obtained after the question text is segmented.

[0076] Specifically, the large model server can use the RecursiveCharacterTextSplitter class in the LangChain framework to generate a text segmentation object; use the splitDocuments() method of this text segmentation object to segment the question text and obtain at least one question text block. It should be noted that when using the RecursiveCharacterTextSplitter class in the LangChain framework to generate a text segmentation object, the delimiter, block size, and block overlap size corresponding to the text segmentation object will be set at the same time. Among them, the delimiter refers to the delimiter used to separate the question text; the block size refers to the size of each question text block; the block overlap size refers to the size of the overlapping part between the question text block and the question text block.

[0077] For example, the large model server uses the RecursiveCharacterTextSplitter class in the LangChain framework to generate the text segmentation object splitterA, that is:

[0078] const splitterA=new RecursiveCharacterTextSplitter({

[0079] chunkSize:10,

[0080] chunkOverlap:1,

[0081] separators:[':',',','. ','! ',';','? '],

[0082] });

[0083] Among them, chunkSize indicates the chunk size; chunkOverlap indicates the chunk overlap size; and separators indicates separators.

[0084] After that, the question text is segmented using the splitDocuments() method of the text segmentation object splitterA to obtain at least one question text block, namely:

[0085] const docOutput=await splitterA.splitDocuments([new Document({pageContent:content})]);

[0086] Among them, content represents the question text; docOutput represents an array consisting of at least one question text block, and its data format is as follows: [

[0088] {pageContent:"Question text block 1",metadata:{loc:{lines:{from:1,to:1}}}},

[0089] {pageContent:"Question text block 2",metadata:{loc:{lines:{from:1,to:1}}}},

[0090] ......,

[0091] {pageContent:"Question text block N",metadata:{loc:{lines:{from:1,to:1}}}},

[0092] ].

[0093] Wherein, N is a positive integer, indicating the total number of question text blocks; metadata indicates the metadata of the question text block, providing the position information of the question text block in the question text.

[0094] S203, performing vectorization processing on each question text block respectively to obtain a question text vector corresponding to each question text block.

[0095] The question text vector refers to the text vector obtained after the question text block is vectorized.

[0096] Specifically, for each question text block obtained, the large model server can use the OpenAIEmbeddings class in the LangChain framework to generate a text embedding object; use the embedQuery() method of this text embedding object to vectorize the question text block to obtain the question text vector corresponding to the question text block.

[0097] For example, for the obtained question text block 1, the large model server can use the OpenAIEmbeddings class in the LangChain framework to generate a text embedding object embeddingsA, that is:

[0098] import{OpenAIEmbeddings}from"@langchain / openai";

[0099] const embeddingsA=new OpenAIEmbeddings();

[0100] After that, the embedQuery() method of the text embedding object embeddingsA is used to vectorize the question text block 1 to obtain the question text vector corresponding to the question text block 1, that is:

[0101] const res1 = await embeddingsA.embedQuery("Question Text Block 1");

[0102] Among them, res1 represents the question text vector corresponding to question text block 1.

[0103] S204: perform similarity matching on the question text vectors corresponding to each question text block and the pop-up window text vectors in the vector search library to obtain matching text vectors that match the question text.

[0104] The vector search library refers to a library in the large model server that is specifically used to perform vector similarity search. The pop-up window text vector refers to the text vector obtained after the configuration information of the pop-up window of each website in the target website is vectorized.

[0105] Specifically, for the question text vector corresponding to each question text block, the large model server can perform similarity matching between the question text vector and the pop-up text vector in the vector search library based on the vector similarity search algorithm corresponding to the vector search library, and obtain the pop-up text vector with the highest similarity to the question text vector in the vector search library, that is, obtain the matching vector corresponding to the question text vector; similarly, the matching vector corresponding to each question text vector can be obtained. Afterwards, the matching vectors corresponding to each question text vector are spliced ​​according to the mapping position of each question text vector in the question text to obtain a matching text vector that matches the question text. Among them, the vector similarity search algorithm can be pre-set according to actual business needs. For example, the vector similarity search algorithm can be a similaritySearch() method, which is not specifically limited in the implementation of the present invention.

[0106] Optionally, the process of constructing the vector search library is as follows: load pop-up configuration information from the background database; perform text segmentation on the pop-up configuration information to obtain at least one pop-up text block; perform vectorization processing on each pop-up text block to obtain a pop-up text vector corresponding to each pop-up text block; and construct a vector search library based on the pop-up text vector corresponding to each pop-up text block.

[0107] Among them, the pop-up window configuration information is composed of the configuration information of the website guide pop-up window corresponding to each function in the target website; optionally, the pop-up window configuration information is obtained through the configuration of the background configuration center; the pop-up window configuration information includes the pop-up window main title, pop-up window subtitle and pop-up window action. It should be noted that the configuration information of the website guide pop-up window corresponding to each function in the pop-up window configuration information includes the pop-up window main title, pop-up window subtitle and pop-up window action. For example, for the website guide pop-up window corresponding to the self-service customer service function, its configuration information can be as follows:

[0108] {

[0109]

[0110] Among them, title indicates the main title of the pop-up window, subTitle indicates the subtitle of the pop-up window, and Actions indicates the pop-up window action.

[0111] Among them, the background configuration center refers to an organization used to configure the configuration information of the website guide pop-up window corresponding to each function in the target website. It can be understood that the pop-up window configuration information is configured in advance through the background configuration center according to the actual functions of the target website, which improves the accuracy of the pop-up window text vector in the vector search library.

[0112] The pop-up window text block refers to the text block obtained after the pop-up window configuration information is segmented, and the pop-up window text vector refers to the text vector obtained after the pop-up window text block is vectorized.

[0113] Specifically, the large model server can use the TextLoader class in the LangChain framework to generate a document loader; use this document loader to load the configuration document where the pop-up window configuration information is located from the background database. For example, the large model server uses the TextLoader class in the LangChain framework to generate a document loader loaderA, and uses loaderA to load the configuration document where the pop-up window configuration information is located from the background database, that is:

[0114] import{TextLoader}from"langchain / document_loaders / fs / text";

[0115] const loaderA=new TextLoader("src / document_loaders / example_data / example.txt");

[0116] const docs=await loader.load();

[0117] Among them, src / document_loaders / example_data / example.txt indicates the configuration document where the pop-up window configuration information is located.

[0118] Afterwards, the large model server uses the RecursiveCharacterTextSplitter class in the LangChain framework to generate a text segmentation object; uses the splitDocuments() method of this text segmentation object to perform text segmentation on the pop-up configuration information to obtain at least one pop-up text block; for each pop-up text block obtained, the large model server uses the OpenAIEmbeddings class in the LangChain framework to generate an embedding object; uses the embedQuery() method of this embedding object to vectorize the pop-up text block to obtain the pop-up text vector corresponding to the pop-up text block; similarly, the pop-up text vector corresponding to each pop-up text block can be obtained; the large model server stores the pop-up text vector corresponding to each pop-up text block in an empty vector library to obtain a vector search library composed of the pop-up text vectors corresponding to each pop-up text block.

[0119] Among them, the large model server stores the pop-up text vectors corresponding to each pop-up text block into an empty database, and obtains a vector search library composed of the pop-up text vectors corresponding to each pop-up text block. Specifically, the large model server uses the MemoryVectorStore class in the LangChain framework to generate an empty vector library object; uses the fromDocuments() method of this empty vector library object to store the pop-up text vectors corresponding to each pop-up text block into this empty vector library object, and obtains the vector search library, that is:

[0120] import{MemoryVectorStore}from"langchain / vectorstores / memory";

[0121] import{OpenAIEmbeddings}from"@langchain / openai";

[0122] const vectorStore=await MemoryVectorStore.fromDocuments(

[0123] docs,

[0124] new OpenAIEmbeddings() );

[0126] Among them, vectorStore represents an empty vector store object.

[0127] It is understandable that by building a vector search library, it is possible to more accurately and quickly match the text vector that matches the question text, thereby improving the efficiency of generating the website guide pop-up window corresponding to the question text.

[0128] S205: Send the matching text vector to the client browser, so that the client browser generates a website guide pop-up window corresponding to the question text according to the matching text vector.

[0129] Specifically, the large model server sends the matching text vector to the client browser through a preset communication interface, so that the client browser generates a website guidance pop-up window corresponding to the question text according to the matching text vector.

[0130] The technical solution of the embodiment of the present invention is to receive the question text sent by the client browser; perform text segmentation on the question text to obtain at least one question text block; perform text segmentation on the question text to obtain at least one question text block; respectively perform similarity matching between the question text vector corresponding to each question text block and the pop-up window text vector in the vector search library to obtain a matching text vector matching the question text; and send the matching text vector to the client browser so that the client browser generates a website guide pop-up window corresponding to the question text according to the matching text vector. The above technical solution improves the accuracy of the matching text vector by intelligently generating a matching text vector matching the question text through the large model server, thereby improving the accuracy of the website guide pop-up window generated based on the matching text vector; at the same time, it solves the problems of solidified guidance content of existing complex web websites, too much one-time guidance content, insufficient guidance content and insufficient intelligence of the guidance process. Users can complete corresponding operations on the target website according to the website guide pop-up window without consulting the website developer, thereby reducing the learning cost of users using the website, improving the flexibility and intelligence of the website guidance, improving the user's experience, and thus improving the user's office efficiency on the website.

[0131] Embodiment 3

[0132] Figure 3 This is a flowchart of a method for generating a website guide pop-up window provided in the third embodiment of the present invention. This embodiment provides an optimal solution for generating a website guide pop-up window based on the above embodiment. It should be noted that for the parts not described in detail in the embodiment of the present invention, reference can be made to the relevant descriptions of other embodiments. Figure 3 As shown, the method includes:

[0133] S301. The client browser obtains the question text input by the user in the function search window of the target website.

[0134] Optionally, the function search overlay is obtained by executing the search overlay script.

[0135] S302: The client browser sends the question text to the large model server.

[0136] S303: The large model server receives the question text sent by the client browser.

[0137] S304: The large model server performs text segmentation on the question text to obtain at least one question text block.

[0138] S305. The large model server performs vectorization processing on each question text block respectively to obtain a question text vector corresponding to each question text block.

[0139] S306. The large model server performs similarity matching on the question text vector corresponding to each question text block and the pop-up window text vector in the vector search library to obtain a matching text vector that matches the question text.

[0140] Optionally, the process of constructing the vector search library is as follows: load pop-up configuration information from the background database; perform text segmentation on the pop-up configuration information to obtain at least one pop-up text block; perform vectorization processing on each pop-up text block to obtain a pop-up text vector corresponding to each pop-up text block; and construct a vector search library based on the pop-up text vector corresponding to each pop-up text block.

[0141] Optionally, the pop-up window configuration information is obtained through the background configuration center configuration; the pop-up window configuration information includes the pop-up window main title, pop-up window subtitle and pop-up window action.

[0142] S307: The large model server sends the matching text vector to the client browser.

[0143] S308. The client browser receives the matching text vector sent by the large model server, and parses the matching text vector to obtain a website guidance pop-up window corresponding to the question text.

[0144] The technical solution of the embodiment of the present invention can generate a website guidance pop-up window corresponding to the question text according to the question text entered by the user in the function search window of the target website, so as to guide the user to operate in the target website. That is, according to the current use needs of the user, a website guidance pop-up window that meets the current use needs of the user can be flexibly generated, which solves the problems of solidified guidance content of existing complex web websites, too much one-time guidance content, insufficient guidance content and insufficient intelligence of the guidance process. The user can complete the corresponding operation on the target website according to the website guidance pop-up window without consulting the website developer, thereby reducing the learning cost of the user to use the website, improving the flexibility and intelligence of the website guidance, improving the user's use experience, and further improving the user's office efficiency on the website.

[0145] Embodiment 4

[0146] Figure 4 This is a schematic diagram of the structure of a website guide pop-up window generation device provided by the fourth embodiment of the present invention. This embodiment can be applied to the case where a website guide pop-up window of a complex web site is generated according to the current usage requirements of the user. The device can be implemented in the form of hardware and / or software and can be configured in an electronic device with a client browser. Figure 4 As shown, the device is applied to a client browser and includes:

[0147] The question text acquisition module 401 is used to acquire the question text input by the user in the function search window of the target website;

[0148] The question text sending module 402 is used to send the question text to the large model server, so that the large model server obtains a matching text vector that matches the question text according to the question text;

[0149] The website guide pop-up window generation module 403 is used to receive the matching text vector sent by the large model server, and parse the matching text vector to obtain the website guide pop-up window corresponding to the question text.

[0150] The technical solution of the embodiment of the present invention obtains the question text entered by the user in the function search hanging window of the target website; sends the question text to the large model server, so that the large model server obtains the matching text vector matching the question text according to the question text; receives the matching text vector sent by the large model server, and parses the matching text vector to obtain the website guidance pop-up window corresponding to the question text. The above technical solution can generate a website guidance pop-up window corresponding to the question text according to the question text entered by the user in the function search hanging window of the target website to guide the user to operate in the target website. That is, according to the current use needs of the user, a website guidance pop-up window that meets the current use needs of the user can be flexibly generated, which solves the problems of solidified guidance content of existing complex web websites, too much one-time guidance content, insufficient guidance content and insufficient intelligence of the guidance process. Users can complete corresponding operations on the target website according to the website guidance pop-up window without consulting the website developer, thereby reducing the learning cost of users using the website, improving the flexibility and intelligence of website guidance, improving the user's use experience, and thus improving the user's office efficiency on the website.

[0151] Optionally, the function search overlay is obtained by executing the search overlay script.

[0152] The website guide pop-up window generation device provided in the embodiment of the present invention can execute the website guide pop-up window generation method provided in the first embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the website guide pop-up window generation method.

[0153] Embodiment 5

[0154] Figure 5 This is a schematic diagram of the structure of a website guide pop-up window generation device provided in the fifth embodiment of the present invention. This embodiment can be applied to the case where a website guide pop-up window of a complex web site is generated according to the current usage requirements of the user. The device can be implemented in the form of hardware and / or software and can be configured in an electronic device with a large model server. Figure 5 As shown, the device is applied to a large model server, including:

[0155] The question text receiving module 501 is used to receive the question text sent by the client browser;

[0156] A question text block determination module 502 is used to segment the question text to obtain at least one question text block;

[0157] The question text vector determination module 503 is used to perform vectorization processing on each question text block to obtain the question text vector corresponding to each question text block;

[0158] A matching text vector determination module 504 is used to perform similarity matching between the question text vector corresponding to each question text block and the pop-up window text vector in the vector search library to obtain a matching text vector that matches the question text;

[0159] The matching text vector sending module 505 is used to send the matching text vector to the client browser, so that the client browser generates a website guidance pop-up window corresponding to the question text according to the matching text vector.

[0160] The technical solution of the embodiment of the present invention is to receive the question text sent by the client browser; perform text segmentation on the question text to obtain at least one question text block; perform text segmentation on the question text to obtain at least one question text block; respectively perform similarity matching between the question text vector corresponding to each question text block and the pop-up window text vector in the vector search library to obtain a matching text vector matching the question text; and send the matching text vector to the client browser so that the client browser generates a website guide pop-up window corresponding to the question text according to the matching text vector. The above technical solution improves the accuracy of the matching text vector by intelligently generating a matching text vector matching the question text through the large model server, thereby improving the accuracy of the website guide pop-up window generated based on the matching text vector; at the same time, it solves the problems of solidified guidance content of existing complex web websites, too much one-time guidance content, insufficient guidance content and insufficient intelligence of the guidance process. Users can complete corresponding operations on the target website according to the website guide pop-up window without consulting the website developer, thereby reducing the learning cost of users using the website, improving the flexibility and intelligence of the website guidance, improving the user's experience, and thus improving the user's office efficiency on the website.

[0161] Optionally, the device further includes a vector search library construction module, wherein the vector search library construction module is specifically used to:

[0162] Load pop-up window configuration information from the backend database;

[0163] Performing text segmentation on the pop-up window configuration information to obtain at least one pop-up window text block;

[0164] Perform vectorization processing on each pop-up window text block respectively to obtain the pop-up window text vector corresponding to each pop-up window text block;

[0165] According to the pop-up text vectors corresponding to each pop-up text block, a vector search library is constructed.

[0166] Optionally, the pop-up window configuration information is obtained through the background configuration center configuration; the pop-up window configuration information includes the pop-up window main title, pop-up window subtitle and pop-up window action.

[0167] The website guide pop-up window generation device provided in the embodiment of the present invention can execute the website guide pop-up window generation method provided in the second embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the website guide pop-up window generation method.

[0168] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0169] Embodiment 6

[0170] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0171] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0172] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0173] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a website guide pop-up window generation method.

[0174] In some embodiments, the website guide pop-up window generation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the website guide pop-up window generation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the website guide pop-up window generation method in any other appropriate manner (e.g., by means of firmware).

[0175] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0176] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0177] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0178] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0179] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0180] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0181] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0182] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a website guide pop-up window, characterized in that: Executed by a client browser, the method includes: Obtain the question text entered by the user in the function search window of the target website; Sending the question text to the large model server, so that the large model server obtains a matching text vector that matches the question text according to the question text; Receive the matching text vector sent by the large model server, and parse the matching text vector to obtain a website guide pop-up window corresponding to the question text.

2. The method according to claim 1, characterized in that The function search hanging window is obtained by executing the search hanging window script.

3. A method for generating a website guide pop-up window, characterized in that: Executed by the large model server, the method includes: Receive the question text sent by the client browser; Performing text segmentation on the question text to obtain at least one question text block; Perform vectorization processing on each question text block respectively to obtain the question text vector corresponding to each question text block; Performing similarity matching on the question text vectors corresponding to each question text block and the pop-up window text vectors in the vector search library to obtain matching text vectors that match the question text; The matching text vector is sent to the client browser, so that the client browser generates a website guide pop-up window corresponding to the question text according to the matching text vector.

4. The method according to claim 3, characterized in that The construction process of the vector search library is as follows: Load pop-up window configuration information from the backend database; Performing text segmentation on the pop-up window configuration information to obtain at least one pop-up window text block; Perform vectorization processing on each pop-up window text block respectively to obtain the pop-up window text vector corresponding to each pop-up window text block; According to the pop-up text vectors corresponding to each pop-up text block, a vector search library is constructed.

5. The method according to claim 4, characterized in that The pop-up window configuration information is obtained through the configuration of the background configuration center; the pop-up window configuration information includes the pop-up window main title, pop-up window subtitle and pop-up window action.

6. A website guide pop-up window generation device, characterized in that: Applied to a client browser, the device comprises: A question text acquisition module is used to acquire the question text entered by the user in the function search window of the target website; A question text sending module, used for sending the question text to the large model server, so that the large model server obtains a matching text vector matching the question text according to the question text; The website guide pop-up window generation module is used to receive the matching text vector sent by the large model server, and parse the matching text vector to obtain the website guide pop-up window corresponding to the question text.

7. A website guide pop-up window generation device, characterized in that: Applied to a large model server, the device comprises: A question text receiving module is used to receive the question text sent by the client browser; A question text block determination module, used for performing text segmentation on the question text to obtain at least one question text block; A question text vector determination module is used to perform vectorization processing on each question text block respectively to obtain a question text vector corresponding to each question text block; A matching text vector determination module is used to perform similarity matching between the question text vector corresponding to each question text block and the pop-up window text vector in the vector search library to obtain a matching text vector that matches the question text; The matching text vector sending module is used to send the matching text vector to the client browser, so that the client browser generates a website guide pop-up window corresponding to the question text according to the matching text vector.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the website guide pop-up window generation method described in any one of claims 1-2, and / or the website guide pop-up window generation method described in any one of claims 3-5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the website guide pop-up window generation method described in any one of claims 1-2 and / or the website guide pop-up window generation method described in any one of claims 3-5 when executed.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the website navigation pop-up window generation method according to any one of claims 1 to 2, and / or the website navigation pop-up window generation method according to any one of claims 3 to 5.

Images