Method and device for predicting and solving user questions and storage medium

Abstract

The invention relates to a user question prediction and solution method and device and a storage medium, and the method comprises the steps: obtaining the page content of a current page, carrying out the semantic analysis processing of the page content, and obtaining an entity contained in the page content and the content related to the entity; the entity and the content related to the entity are obtained based on semantic analysis, the questions of the user on the page content and the solutions of the questions are predicted, the questions possibly existing on the page content of the user can be automatically predicted, the corresponding solutions are given, the user is prevented from submitting a work order, the user experience is improved, and the user experience is improved. And the workload caused by processing the work order by the customer service staff is reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a method, device, and storage medium for predicting and resolving user questions. Background Art

[0002] When users use a business system (which can be exemplarily understood as a platform for processing work tasks or work matters) to complete work tasks or work matters, they often encounter some questions. For example, there is no response or an error after clicking a certain button on the page, or there are doubts about the accuracy of some data or content on the page. Currently, these questions are submitted to the customer service in the form of work orders, and the customer service gives solutions, resulting in a large workload for the customer service. Moreover, submitting questions through work orders is complex in operation, and the user experience is poor. Summary of the Invention

[0003] To solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a method, device, and storage medium for predicting and resolving user questions.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for predicting and resolving user questions, the method comprising:

[0005] Obtaining the page content of the current page;

[0006] Performing semantic analysis processing on the page content to obtain the entities included in the page content and the content related to the entities;

[0007] Based on the entities and the content related to the entities, predicting the user's questions about the page content and the solutions to the questions.

[0008] In some embodiments, the obtaining the page content of the current page includes:

[0009] Obtaining the HyperText Markup Language (HTML) data corresponding to the current page;

[0010] Obtaining at least one content block included on the page from the HTML data, and the relative position relationship of the at least one content block on the page;

[0011] Based on the relative position relationship, splicing the at least one content block to obtain the page content of the page.

[0012] In some embodiments, the predicting the user's questions about the page content and the solutions to the questions based on the entities and the content related to the entities includes:

[0013] Retrieve a target work order from the resolved historical work orders, as well as the solution corresponding to the target work order, where the target work order contains a question about the content of the entity;

[0014] Predict the question in the target work order as a question of the user about the page content;

[0015] Determine the solution corresponding to the target work order as the solution to the question.

[0016] In some embodiments, the predicting the question of the user about the page content and the solution to the question based on the entity and the content related to the entity includes:

[0017] Input the entity and the content of the entity into a preset prediction model, and predict, based on the prediction model, the question of the user about the page content and the solution to the question.

[0018] In some embodiments, the method further includes:

[0019] Obtain feedback information of the user on the solution;

[0020] In response to the feedback information indicating that the solution does not resolve the user's question about the page content, retrieve a target question and the solution corresponding to the target question from the resolved questions, where the similarity between the target question and the user's question about the page content is higher than a preset threshold;

[0021] Optimize and train the prediction model based on the target question and the solution corresponding to the target question to obtain an optimized prediction model.

[0022] In some embodiments, the method further includes:

[0023] Display the question and the solution.

[0024] In some embodiments, the inputting the entity and the content of the entity into a preset prediction model and predicting, based on the prediction model, the question of the user about the page content and the solution to the question includes:

[0025] Input the entity and the content of the entity into a preset prediction model, and predict, based on the prediction model, the question of the user about the page content, the question type corresponding to the question, and the solution to the question;

[0026] The displaying the question and the solution includes:

[0027] Present the query and the solution based on a presentation mode corresponding to the type of the query.

[0028] In some embodiments, the method further includes:

[0029] Present a first entry to the user, where the first entry is used to enter an editing interface for a work order;

[0030] In response to receiving the work order submitted by the user through the editing interface;

[0031] Send the work order to a target account, where the target account is used to provide a solution to the work order;

[0032] Present the solution provided by the target account to the user.

[0033] In some embodiments, the method further includes:

[0034] Optimize and train a prediction model based on the work order and the solution provided by the target account to obtain an optimized prediction model.

[0035] In a second aspect, an embodiment of the present disclosure provides a device for predicting and resolving user queries, and the device includes:

[0036] A first acquisition module, configured to: acquire the page content of the current page;

[0037] An analysis module, configured to perform semantic analysis processing on the page content to obtain the entities included in the page content and the content related to the entities;

[0038] A prediction module, configured to predict the user's query about the page content and the solution to the query based on the entities and the content related to the entities.

[0039] In some embodiments, the first acquisition module is configured to:

[0040] Acquire the hypertext markup language (HTML) data corresponding to the current page;

[0041] Acquire at least one content block included on the page from the HTML data, and the relative position relationship of the at least one content block on the page;

[0042] Based on the relative position relationship, splice the at least one content block to obtain the page content of the page.

[0043] In some embodiments, the prediction module is configured to:

[0044] Obtain a target work order from the resolved historical work orders, as well as the solution corresponding to the target work order, where the target work order contains a question about the content of the entity;

[0045] Predict the question in the target work order as a question of the user about the page content;

[0046] Determine the solution corresponding to the target work order as the solution to the question.

[0047] In some embodiments, a prediction module is configured to:

[0048] Input the entity and the content of the entity into a preset prediction model, and predict, based on the prediction model, the question of the user about the page content and the solution to the question.

[0049] In some embodiments, the apparatus may further include:

[0050] A second acquisition module, configured to acquire feedback information of the user on the solution;

[0051] A third acquisition module, configured to, in response to the feedback information indicating that the solution does not solve the user's question about the page content, acquire a target question and the solution corresponding to the target question from the resolved questions, where the similarity between the target question and the user's question about the page content is higher than a preset threshold;

[0052] A first optimization module, configured to optimize and train the prediction model based on the target question and the solution corresponding to the target question to obtain an optimized prediction model.

[0053] In some embodiments, the apparatus may further include:

[0054] A first display module, configured to display the question and the solution.

[0055] In some embodiments, a prediction module is configured to: input the entity and the content of the entity into a preset prediction model, and predict, based on the prediction model, the question of the user about the page content, the question type corresponding to the question, and the solution to the question;

[0056] A first display module, configured to display the question and the solution based on a display manner corresponding to the question type of the question.

[0057] In some embodiments, the apparatus may further include:

[0058] A second display module, configured to display a first entry for the user to enter an editing interface for a work order;

[0059] A transceiver module, configured to send the work order to a target account in response to receiving the work order submitted by the user through the editing interface, where the target account is used to provide a solution to the work order;

[0060] A third display module, configured to display the solution provided by the target account to the user.

[0061] In some embodiments, the device may further include:

[0062] A second optimization module, configured to optimize and train a prediction model based on the work order and the solution provided by the target account to obtain an optimized prediction model.

[0063] In a third aspect, an embodiment of the present disclosure provides a computer device, including:

[0064] A memory;

[0065] A processor; and

[0066] A computer program;

[0067] Wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement any method described in the first aspect.

[0068] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement any method described in the first aspect.

[0069] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including computer program instructions, and when the computer program instructions are executed by a processor, any method described in the first aspect can be implemented.

[0070] The method, device, and storage medium for predicting and resolving user questions provided by the embodiments of the present disclosure obtain the page content of the current page, perform semantic analysis processing on the page content to obtain the entities included in the page content and the content related to the entity; based on the entities and the content related to the entity obtained by semantic analysis, predict the user's questions about the page content and the solutions to the questions, can automatically predict the possible questions of the user about the page content, and give corresponding solutions, avoiding the user from submitting work orders, improving the user experience, and reducing the workload of the customer service due to processing work orders. Description of the Drawings

[0071] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0072] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or in the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0073] Figure 1 It is a flowchart of a method for predicting and resolving user questions provided by an embodiment of the present disclosure;

[0074] Figure 2 It is a flowchart of a method for predicting user questions about page content and solutions to the questions provided by an embodiment of the present disclosure;

[0075] Figure 3 It is a flowchart of another method for predicting and resolving user questions provided by an embodiment of the present disclosure;

[0076] Figure 4 It is a schematic diagram of a display interface provided by an embodiment of the present disclosure;

[0077] Figure 5 It is a schematic diagram of another display interface provided by an embodiment of the present disclosure;

[0078] Figure 6 It is a flowchart of another method for predicting and resolving user questions provided by an embodiment of the present disclosure;

[0079] Figure 7 It is a schematic structural diagram of another user question prediction and resolution device provided by an embodiment of the present disclosure;

[0080] Figure 8 It is a schematic structural diagram of an embodiment of a computer device provided by an embodiment of the present disclosure. Detailed implementation manners

[0081] In order to be able to more clearly understand the above objects, features, and advantages of the present disclosure, the following will further describe the solutions of the present disclosure. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0082] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all of the embodiments.

[0083] Figure 1 This is a flowchart of a method for predicting and resolving user questions provided by an embodiment of the present disclosure. This method can be exemplarily executed by a computer device, which can be understood as a device with computing and processing capabilities, such as a computer, a mobile phone, a tablet computer, etc., but is not limited to the devices listed here. A business system is installed on this computer device, and users can process work tasks or work matters on this business system. As Figure 1 shown, in some embodiments, the method for predicting and resolving user questions provided by the embodiments of the present disclosure may include Step 101 - Step 103.

[0084] Step 101: Obtain the page content of the current page.

[0085] Herein, the current page can be exemplarily understood as the page of the business system that the user is browsing. The business system may include multiple pages, and the page content of each page may include one or more to-be-processed and / or processed work matters or work tasks, as well as content associated with each work matter or work task, such as data involved in the work matter or work task, completion status, and function buttons, etc. The function button can be understood as a button for triggering or completing a certain operation of a work matter or work task, such as a submit button for submitting a work matter or work task, an edit button for editing the data of a work matter or work task, etc.

[0086] In the embodiments of the present disclosure, there are multiple ways to obtain the page content of the current page. Several exemplary ways are described below.

[0087] Way 1: Obtain the HyperText Markup Language (HTML) data of the current page; obtain at least one content block included on the page and the relative position relationship of these content blocks on the page from the HTML data of the page, and splice these content blocks based on the relative position relationship of these content blocks on the page to obtain the page content of the page.

[0088] Specifically, HTML data generally can include content blocks of a page, location information of the content blocks in the page, format information of the page, tags, and comments, etc. And in the HTML data, data such as the format and tags of the page will be identified by specific characters. On this basis, in some embodiments, based on the Document Object Model (DOM for short) parsing or HTML processing technology, the format, tags, and comments can be filtered out from the HTML data to obtain at least one content block included in the page and the relative position relationship between the content blocks. Among them, the content block can include at least one of the following information: work items or work tasks, and content associated with each work item or work task. Among them, the content associated with each work item or work task can be, for example, one or more of the data involved in the work item or work task, the completion status, and the function buttons.

[0089] Further, after obtaining at least one content block on the page and the relative position relationship between the content blocks, the content blocks can be spliced according to the relative position relationship between the content blocks to obtain the page content. For example, if content block 1 is directly above content block 2 and content block 3 is directly behind content block 2, then when splicing, content block 1 is spliced directly above content block 2 and content block 3 is spliced directly behind content block 2. Of course, this is only an example for illustration and not the only limitation.

[0090] Method 2: Take a screenshot of the current page and extract the page content from the screenshot of the current page through Optical Character Recognition (OCR) technology. Or input the screenshot of the current page into a preset model, and use the preset model to extract the content of the page from the screenshot. Among them, the preset model referred to in the embodiments of the present disclosure can be exemplarily understood as a multi-task recognition model, which can simultaneously extract text content and the image of the button from the screenshot of the current page. The training method of the preset model can refer to the related technology and will not be elaborated here.

[0091] Step 102: Perform semantic analysis processing on the page content to obtain the entities included in the page content and the content related to the entities. 3

[0092] Among them, the entity referred to in the embodiments of the present disclosure can be exemplarily understood as a work item or work task included in the page. The content related to the entity can be exemplarily understood as the data involved in the work item or work task, the completion status, and the function buttons, etc.

[0093] In some embodiments, an entity included in the page content and content related to the entity can be identified from the page content through a preset semantic analysis model. Among them, the semantic analysis model can be trained by using a model training method provided by related technologies, and the specific training process is not specifically limited in the embodiments of the present disclosure.

[0094] For example, if the page content is "not clocked in on a certain date", the work item or task (i.e., the entity) obtained through semantic analysis is "clock in", and the content related to the entity is: "not clocked in". Of course, this is only an example for illustration and not the only limitation.

[0095] Step 103: Predict the user's questions about the page content and solutions to the questions based on the entity obtained through semantic analysis and the content related to the entity.

[0096] In the embodiments of the present disclosure, there are various methods for predicting the user's questions about the page content and solutions to the questions based on the entity obtained through semantic analysis and the content related to the entity. The following uses several exemplary methods for illustration.

[0097] Method 1, Figure 2 is a flowchart of a method for predicting the user's questions about the page content and solutions to the questions provided by the embodiments of the present disclosure. As Figure 2 shown, in some embodiments, the user's questions and solutions to the questions can be predicted by the method of steps 201-203.

[0098] Step 201: Obtain a target work order and the corresponding solution to the target work order from the resolved historical work orders. The target work order contains questions about the content of the entity in the current page.

[0099] Among them, the historical work order can be understood as one or more work orders submitted by users within a preset historical time period. The historical work order includes questions about the entity and content related to the entity.

[0100] In the embodiments of the present disclosure, an entity and content related to the entity can be used as a key-value pair.

[0101] For any entity extracted from the page content of the current page, the entity and the content related to the entity can be used as a target key-value pair. For each target key-value pair, a work order containing the target key-value pair can be matched from historical work orders through content matching as the target work order. For example, in an exemplary implementation, the target key-value pair and historical work orders can be input into a preset content matching model, and the similarity between the key-value pairs included in the historical work orders and the target key-value pair can be determined through the content matching model, and the historical work order with the highest similarity between the key-value pair and the target key-value pair can be output and used as the target work order. Of course, this is only an example for illustration and not a unique limitation.

[0102] In some implementations, the historical work orders with resolved questions and the corresponding solutions are stored in a preset database in an associated manner. After obtaining the target work order, the solution corresponding to the target work order can be obtained from the database.

[0103] Step 202: Predict the question in the target work order as the question of the user regarding the page content of the current page.

[0104] For example, if the content of the target work order is "How to correct the punch record?", the entity included in the target work order is punch, and the content related to the entity is: "punch record", and the question is: "How to correct the punch record". Then, "How to correct the punch record" is predicted as the question of the user regarding the page content of the current page.

[0105] Step 203: Determine the solution corresponding to the target work order as the solution to the question of the user regarding the current page.

[0106] For example, assume that the question included in the target work order is "How to correct the punch record" and the solution is "Submit a screenshot of the punch record on the page corresponding to the "" link". Then, "Submit a screenshot of the punch record on the page corresponding to the "" link" is used as the solution to the question of the user regarding the current page.

[0107] By obtaining the target work order from the resolved historical work orders and predicting the question and solution corresponding to the target work order as the question and solution of the user regarding the page content of the current page, the data of the historical work orders can be fully utilized to improve the accuracy of question and solution prediction.

[0108] Method 2: Input the entities and related content in the page content of the current page into a preset prediction model, and obtain the user's questions about the page content and the solutions to the questions through the prediction model. Among them, the prediction model can be exemplarily understood as a large language model, but is not limited to a large language model. In some embodiments, the prediction model referred to in the embodiments of the present disclosure is trained to extract data from historical work orders and the corresponding solution plans based on the input entities and related content, and generate the user's questions and solution plans for the page content of the current page based on the extracted data. The training method of the prediction model in the embodiments of the present disclosure can refer to related technologies and will not be elaborated here.

[0109] By inputting the entities in the current page and the content related to the entities into a preset prediction model, and predicting the user's questions and solution plans based on the prediction model, the efficiency of predicting the user's questions and solution plans can be improved.

[0110] In some embodiments, after the prediction model outputs the prediction results, the user's feedback information can also be collected. When the information feedback by the user indicates that the solution plan output by the prediction model does not solve the user's question, the similarity between the question output by the prediction model and the questions in each historical work order (historical work orders with solved questions) can be calculated respectively. If the similarity between the question in the historical work order and the question output by the prediction model is higher than the preset threshold, the question in the historical work order is determined as the target question. Thus, the target question and the corresponding solution plan of the target question are used as training data to optimize and train the prediction model, and an optimized prediction model is obtained.

[0111] Optimizing and training the prediction model according to the user's feedback information can improve the accuracy of the prediction model.

[0112] Method 3: Method 1 and Method 2 are combined and used. For example, based on the method of Method 1, the target work order can be determined from the historical work orders, and the question and solution plan corresponding to the target work order are used as the prediction results. If the target work order is not matched in the historical work orders, the entities included in the page content and the content related to the entities can be input into the prediction model, and the prediction results are output through the prediction model, thereby improving the success rate of prediction.

[0113] Method 4: In some embodiments, a first entry can also be displayed to the user. The user can enter the work order editing interface by clicking the first entry. If a work order submitted by the user in the work order editing interface is received, the work order is sent to the target account, and the target account is used to provide the solution plan for the work order. If the solution plan provided by the target account is received, the solution plan is displayed to the user.

[0114] In the implementation of Method 4, if a work order submitted by a user is received, the work order submitted by the user and the solution provided by the target account can be used as training data to optimize the training of the prediction model in Method 2, thereby improving the accuracy of the prediction model. Among them, before optimizing the training of the prediction model based on the work order submitted by the user and the solution provided by the target account, authorization can also be requested from the user and / or the target account through a preset channel (such as email, short message, etc., but not limited to email and short message). After obtaining the authorization of the user and / or the target account, the prediction model is optimized and trained based on the work order and the solution.

[0115] In the embodiments of the present disclosure, by obtaining the page content of the current page, performing semantic analysis processing on the page content, and obtaining the entities included in the page content and the content related to the entity; based on the entities and the content related to the entity obtained by semantic analysis, predicting the user's questions about the page content and the solutions to the questions, it is possible to automatically predict the questions that the user may have about the page content and give corresponding solutions, avoiding the user from submitting a work order, improving the user experience, and reducing the workload of the customer service due to processing work orders.

[0116] Figure 3 It is a flowchart of another method for predicting and solving user questions provided by the embodiments of the present disclosure. As Figure 3 shown, in some embodiments, the method for predicting and solving user questions provided by the embodiments of the present disclosure may include Step 301 - Step 304.

[0117] Step 301, obtain the page content of the current page.

[0118] Step 302, perform semantic analysis processing on the page content to obtain the entities included in the page content and the content related to the entity.

[0119] Step 303, based on the entities and the content related to the entity obtained by semantic analysis, predict the user's questions about the page content and the solutions to the questions.

[0120] Among them, the execution manners and beneficial effects of Step 301 - Step 303 can refer to Step 101 - Step 103, which will not be elaborated here.

[0121] Step 304, display the predicted questions and solutions.

[0122] Exemplarily, in some embodiments, the detailed content of the predicted questions and solutions can be displayed in a preset area of the display interface. For example, Figure 4 It is a schematic diagram of a display interface provided by the embodiments of the present disclosure. As Figure 4As shown, the display interface 40 includes a display area 41, and the detailed content of all predicted questions and solutions is displayed on the display area 41. By way of example, in some embodiments, the display area 41 may further include a button 11 and a button 12. When a question is resolved, the user can click the button 11 to provide feedback indicating that the question has been resolved. When a question is not resolved, the user can click the button 12 to provide feedback indicating that the question has not been resolved. Of course Figure 4 This is only an example and not the only limitation of the display interface.

[0123] By way of example, in some other embodiments, a second entry may also be displayed on the display interface, and the user can click on this entry to enter the page for viewing questions and solutions. For example, Figure 5 is a schematic diagram of another display interface provided by an embodiment of the present disclosure. As Figure 5 shown, the display interface (a) includes a second entry 51. When the user clicks on the second entry 51, they enter the display interface (b), where all the predicted questions and the corresponding solutions are displayed. Similarly, the display interface (b) may include a button 21 and a button 22. When a question is resolved, the user can click the button 21 to provide feedback indicating that the question has been resolved. When a question is not resolved, the user can click the button 22 to provide feedback indicating that the question has not been resolved. Of course Figure 5 This is only an example and not the only limitation of the display interface.

[0124] By predicting the user's questions about the page content and the solutions to the questions, and displaying the predicted questions and solutions, it is convenient for the user to view the solutions to the corresponding questions, helps the user quickly resolve the questions, and improves the user experience.

[0125] Figure 6 is a flowchart of another method for predicting and resolving user questions provided by an embodiment of the present disclosure. As Figure 6 shown, in some embodiments, the method for predicting and resolving user questions provided by an embodiment of the present disclosure may include steps 601 - step 604.

[0126] Step 601: Obtain the page content of the current page.

[0127] Step 602: Perform semantic analysis on the page content to obtain the entities included in the page content and the content related to the entities.

[0128] Step 603: Input the entities obtained from the semantic analysis and the content related to the entities into a preset prediction model, and based on the prediction model, predict the user's questions about the page content, the question types corresponding to the questions, and the solutions to the questions.

[0129] Among them, the prediction model is trained to predict the user's questions about the page content, the question types corresponding to the questions, and the solutions to the questions based on the entities obtained through semantic analysis and the content related to the entities. The prediction model can be trained by using the model training methods provided by the prior art, and the specific training process is not specifically limited in the embodiments of the present disclosure.

[0130] Step 604: Display the questions and solutions based on the display manner corresponding to the question type of the question.

[0131] In the embodiments of the present disclosure, a mapping relationship between the question type and the display manner can be preset, and questions of different question types can be displayed in different ways. The display manners referred to in the embodiments of the present disclosure at least include one of the following: text, picture, and hyperlink. Among them, the number and types of question types can be set as needed, and no specific limitation is made in the embodiments of the present disclosure.

[0132] In the embodiments of the present disclosure, by displaying different types of questions and solutions in different display manners, the flexibility of displaying questions and solutions can be improved.

[0133] Figure 7 is a schematic structural diagram of another device for predicting and solving user questions provided by the embodiments of the present disclosure. As Figure 7 shown, in some embodiments, the device 70 for predicting and solving user questions provided by the embodiments of the present disclosure includes:

[0134] A first acquisition module 71, configured to: acquire the page content of the current page;

[0135] An analysis module 72, configured to perform semantic analysis processing on the page content to obtain the entities included in the page content and the content related to the entities;

[0136] A prediction module 73, configured to predict the user's questions about the page content and the solutions to the questions based on the entities and the content related to the entities.

[0137] In some embodiments, the first acquisition module 71 is configured to:

[0138] Acquire the hypertext markup language (HTML) data corresponding to the current page;

[0139] Acquire at least one content block included on the page and the relative position relationship of the at least one content block on the page from the HTML data;

[0140] Splice the at least one content block based on the relative position relationship to obtain the page content of the page.

[0141] In some embodiments, the prediction module 73 is configured to:

[0142] Obtain a target work order and the corresponding solution from the resolved historical work orders, where the target work order contains a question about the content of the entity;

[0143] Predict the question in the target work order as a question of the user about the page content;

[0144] Determine the solution corresponding to the target work order as the solution to the question.

[0145] In some embodiments, the prediction module 73 is configured to:

[0146] Input the entity and the content of the entity into a preset prediction model, and predict, based on the prediction model, the question of the user about the page content and the solution to the question.

[0147] In some embodiments, the user question prediction and solution device 70 may further include:

[0148] A second acquisition module, configured to acquire the feedback information of the user on the solution;

[0149] A third acquisition module, configured to, in response to the feedback information indicating that the solution does not solve the user's question about the page content, acquire a target question and the corresponding solution to the target question from the resolved questions, where the similarity between the target question and the user's question about the page content is higher than a preset threshold;

[0150] A first optimization module, configured to optimize and train the prediction model based on the target question and the solution corresponding to the target question to obtain an optimized prediction model.

[0151] In some embodiments, the user question prediction and solution device 70 may further include:

[0152] A first display module, configured to display the question and the solution.

[0153] In some embodiments, the prediction module is configured to: input the entity and the content of the entity into a preset prediction model, and predict, based on the prediction model, the question of the user about the page content, the question type corresponding to the question, and the solution to the question;

[0154] A first display module, configured to display the question and the solution based on a display manner corresponding to the question type of the question.

[0155] In some embodiments, the user question prediction and solution device 70 may further include:

[0156] A second display module, configured to display a first entry to the user, where the first entry is used to enter an editing interface of a work order;

[0157] A transceiver module, configured to, in response to receiving the work order submitted by the user through the editing interface, send the work order to a target account, where the target account is used to provide a solution to the work order;

[0158] A third display module, configured to display the solution provided by the target account to the user.

[0159] In some embodiments, the user question prediction and solution device 70 may further include:

[0160] A second optimization module, configured to optimize and train a prediction model based on the work order and the solution provided by the target account to obtain an optimized prediction model.

[0161] The user question prediction and solution device provided by the embodiments of the present disclosure may execute the methods in any of the above method embodiments, and its execution manners and beneficial effects are similar, and will not be elaborated here.

[0162] It should also be noted that the division of the modules in the user question prediction and solution device in the embodiments of the present disclosure is illustrative, and is only a logical function division. In actual implementation, there may be other division methods. In addition, in each embodiment of the present application, the functional modules may be integrated into a processing module, or each module may exist physically alone, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0163] If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may be stored in a processor-readable storage medium. Based on such an understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in the embodiments of the present disclosure.

[0164] Figure 8 This is a schematic structural diagram of an embodiment of a computer device provided by an embodiment of the present disclosure. As Figure 8As shown, the computer device includes a memory 121 and a processor 122.

[0165] The memory 121 is used to store programs. In addition to the above programs, the memory 121 can also be configured to store various other data to support operations on the computer device. Examples of such data include instructions for any application or method operating on the computer device, contact member data, phone book member data, messages, pictures, videos, etc.

[0166] The memory 121 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disks or optical discs.

[0167] In some embodiments, the processor 122 is coupled to the memory 121 and executes the programs stored in the memory 121 to perform the methods of any of the above method embodiments.

[0168] Furthermore, as Figure 8 shown, the computer device may further include: other components such as a communication component 123, a power supply component 124, an audio component 125, a display 126, etc. Figure 8 Only some components are schematically shown in Figure 8 shown, and it does not mean that the computer device only includes

[0169] The communication component 123 is configured to facilitate communication between the computer device and other devices in a wired or wireless manner. The computer device can access a wireless network based on communication standards, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 123 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 123 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0170] The power supply component 124 provides power for various components of the computer device. The power supply component 124 may include a power management system, one or more power supplies, and other components associated with generating, managing and distributing power for the computer device.

[0171] The audio component 125 is configured to output and / or input audio signals. For example, the audio component 125 includes a microphone (MIC), which is configured to receive external audio signals when the computer device is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 121 or transmitted via the communication component 123. In some embodiments, the audio component 125 further includes a speaker for outputting audio signals.

[0172] The display 126 includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operations.

[0173] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the method described in any one of the above method embodiments.

[0174] In an embodiment of the present disclosure, the above computer-readable storage medium can be any available medium or data storage device accessible by a processor, including but not limited to magnetic memories (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical memories (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor memories (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid state drives (SSD)).

[0175] Those skilled in the art should understand that embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, embodiments of the present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories and optical memories, etc.) containing computer-usable program code.

[0176] An embodiment of the present disclosure provides a computer program product, including computer program instructions, and when the computer program instructions are executed by a processor, the method described in any one of the above method embodiments can be implemented.

[0177] It should be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0178] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting and resolving user questions, characterized in that, The method includes: Obtain the page content of the current page; Perform semantic analysis processing on the page content to obtain the entities included in the page content and the content related to the entities; Based on the entities and the content related to the entities, predict the questions of the user about the page content and the solutions to the questions.

2. The method according to claim 1, wherein The obtaining the page content of the current page includes: Obtain the HyperText Markup Language (HTML) data corresponding to the current page; Obtain at least one content block included on the page and the relative positional relationship of the at least one content block on the page from the HTML data; Based on the relative positional relationship, splice the at least one content block to obtain the page content of the page.

3. The method according to claim 1, characterized in that The predicting the questions of the user about the page content and the solutions to the questions based on the entities and the content related to the entities includes: Obtain a target work order and the corresponding solution to the target work order from the resolved historical work orders, where the target work order contains questions about the content of the entity; Predict the questions in the target work order as the questions of the user about the page content; Determine the solution corresponding to the target work order as the solution to the question.

4. The method according to claim 1, wherein The predicting the questions of the user about the page content and the solutions to the questions based on the entities and the content related to the entities includes: Input the entity and the content of the entity into a preset prediction model, and predict the questions of the user about the page content and the solutions to the questions based on the prediction model.

5. The method according to claim 4, wherein The method further includes: Obtain the feedback information of the user on the solution; In response to the feedback information indicating that the solution does not solve the questions of the user about the page content, obtain a target question and the corresponding solution to the target question from the resolved questions, where the similarity between the target question and the questions of the user about the page content is higher than a preset threshold; Optimize and train the prediction model based on the target question and the corresponding solution to the target question to obtain an optimized prediction model.

6. The method according to any one of claims 1-4, characterized in that, The method further includes: Display the questions and the solutions.

7. The method according to claim 6, wherein The inputting the entity and the content of the entity into a preset prediction model, and predicting the questions of the user about the page content and the solutions to the questions based on the prediction model includes: Input the entity and the content of the entity into a preset prediction model, and predict the questions of the user about the page content, the question types corresponding to the questions, and the solutions to the questions based on the prediction model; The displaying the questions and the solutions includes: Display the questions and the solutions based on the display method corresponding to the question types of the questions.

8. The method according to claim 1, wherein The method further includes: Display a first entry to the user, where the first entry is used to enter the editing interface of the work order. In response to receiving the work order submitted by the user through the editing interface, send the work order to a target account, where the target account is used to provide a solution to the work order; Display the solution provided by the target account to the user.

9. The method according to claim 8, wherein The method further includes: Optimally train a prediction model based on the work order and the solution provided by the target account to obtain an optimized prediction model.

10. A computer device, characterized in that, The computer device includes: A memory; A processor; and A computer program; Wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1-9.

11. A computer-readable storage medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it implements the method according to any one of claims 1-9.

12. A computer program product, including computer program instructions, which implement the method according to any one of claims 1-9 when the computer program instructions are executed by the processor.

Images