Data processing method, device and device for data processing

Abstract

Embodiments of the present invention provide a data processing method, apparatus, and device for data processing. The method specifically includes: determining a screen image in response to a user operation; determining an answer corresponding to a question in the screen image; and displaying the answer. Embodiments of the present invention can reduce the time required to obtain an answer and improve the efficiency of obtaining an answer.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a data processing method, device, and device for data processing. Background Art

[0002] With the development of communication technology, online communication has become an important means for users to communicate, and the application of IM (Instant Messenger) is becoming increasingly widespread. Currently, customer service systems can answer various questions for users. For example, customer service systems can provide online customer service. After logging in, customer service staff can communicate with users in real time via IM.

[0003] Currently, online customer service is typically handled by customer service personnel. Specifically, user questions are assigned to corresponding customer service personnel, who then provide answers to the questions. Providing high-quality answers requires extensive professional knowledge and, due to the wide variety of questions, requires a good memory.

[0004] However, in practice, customer service agents are often unable to provide high-quality answers due to limitations in their expertise and memory. In these cases, they must obtain answers from others or search for them in a database, which increases the time required to obtain answers and hinders the efficiency of answer delivery. Summary of the Invention

[0005] Embodiments of the present invention provide a data processing method, an apparatus, and an apparatus for data processing, which can reduce the time for obtaining an answer and improve the efficiency of obtaining an answer.

[0006] In order to solve the above problems, an embodiment of the present invention discloses a data processing method, including:

[0007] determining a screen image in response to a user operation;

[0008] determining an answer corresponding to the question in the screen image;

[0009] Show the answer.

[0010] In order to solve the above problems, an embodiment of the present invention discloses a data processing method, including:

[0011] Identify problems in screen images;

[0012] Determine a first representation vector corresponding to the problem;

[0013] Determining a target preset question corresponding to the question based on a matching degree between the first representation vector and a second representation vector corresponding to the preset question;

[0014] Determine the answer to the question based on the answer to the target preset question

[0015] On the other hand, an embodiment of the present invention discloses a data processing device, including:

[0016] A screen image determination module, configured to determine a screen image in response to a user operation;

[0017] an answer determination module, configured to determine an answer corresponding to the question in the screen image; and

[0018] The answer display module is used to display the answer.

[0019] On the other hand, an embodiment of the present invention discloses a data processing device, including:

[0020] a problem determination module for determining problems in the screen image;

[0021] A first representation vector determination module, configured to determine a first representation vector corresponding to the problem;

[0022] a target preset problem determining module, configured to determine a target preset problem corresponding to the problem based on a degree of matching between the first representation vector and a second representation vector corresponding to the preset problem; and

[0023] The answer determination module is used to determine the answer corresponding to the question based on the answer corresponding to the target preset question.

[0024] In another aspect, an embodiment of the present invention discloses a device for data processing, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, and include instructions for performing the following operations:

[0025] determining a screen image in response to a user operation;

[0026] determining an answer corresponding to the question in the screen image;

[0027] Show the answer.

[0028] In another aspect, an embodiment of the present invention discloses a device for data processing, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, and include instructions for performing the following operations:

[0029] Identify problems in screen images;

[0030] Determine a first representation vector corresponding to the problem;

[0031] Determining a target preset question corresponding to the question based on a matching degree between the first representation vector and a second representation vector corresponding to the preset question;

[0032] Determine the answer to the question based on the answer to the target preset question.

[0033] On the other hand, an embodiment of the present invention discloses a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes a device to perform one or more of the data processing methods described above.

[0034] The embodiments of the present invention include the following advantages:

[0035] The embodiment of the present invention can provide the user with the answer corresponding to the question in the screen image in response to the user's operation, which can reduce the cost of the user looking for the answer through the question, thereby reducing the time to obtain the answer and improving the efficiency of obtaining the answer. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. 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 paying any creative labor.

[0037] Figure 1 This is a schematic diagram of an application environment of a data processing method according to an embodiment of the present invention;

[0038] Figure 2 This is a flowchart of the steps of a data processing method according to a first embodiment of the present invention;

[0039] Figure 3 This is a flow chart of the steps of Embodiment 2 of a data processing method of the present invention;

[0040] Figure 4 This is a flowchart of the steps of Embodiment 3 of a data processing method of the present invention;

[0041] Figure 5 is a structural block diagram of an embodiment of a data processing device of the present invention;

[0042] Figure 6 is a structural block diagram of an embodiment of a data processing device of the present invention;

[0043] Figure 7 is a block diagram of an apparatus 800 for data processing according to the present invention; and

[0044] Figure 8 It is a schematic diagram of the structure of the server in some embodiments of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] In response to the problem of long time required to obtain answers in related technologies, an embodiment of the present invention provides a data processing solution, which specifically includes: determining a screen image in response to a user's operation; determining the answer corresponding to the question in the screen image; and displaying the answer.

[0047] The embodiment of the present invention can provide the user with the answer corresponding to the question in the screen image in response to the user's operation, which can reduce the cost of the user looking for the answer through the question, thereby reducing the time to obtain the answer and improving the efficiency of obtaining the answer.

[0048] The applicable scenarios of the embodiments of the present invention may include: question-answering scenarios, etc. In the question-answering scenario, the screen content may include questions, and the embodiments of the present invention can automatically detect the questions in the screen content and provide answers corresponding to the questions.

[0049] The aforementioned question-and-answer scenarios may include: customer service scenarios, where the user, as a customer service representative, can provide customer service. Alternatively, the aforementioned question-and-answer scenarios may include: conversation scenarios, where the user, as a conversationalist, can provide responses.

[0050] It should be noted that questions in a Q&A scenario can be placed in a window, such as a communication window or a browser window. Communication windows can include instant messaging windows, etc. A browser window can present a question from the Q&A platform, which can be posted by a first user and answered by a second user.

[0051] The data processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, Figure 1 As shown, the client 100 and the server 200 are located in a wired or wireless network, and the client 100 and the server 200 perform data interaction through the wired or wireless network.

[0052] Optionally, the client 100 can be run on a device. For example, the client 100 can be an APP running on the device, such as a short message APP, an e-commerce APP, an instant messaging APP, a question-and-answer APP, an input method APP, or an APP provided by the operating system. The embodiments of the present application do not limit the specific APP corresponding to the client. Optionally, the client 100 can provide a question-and-answer function that can quickly provide answers in response to user operations.

[0053] Optionally, the device may include a screen that can be used to display content, and the content may include answers, etc. Specifically, the device may include, but is not limited to, smartphones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, car computers, desktop computers, set-top boxes, smart TVs, wearable devices, smart speakers, and the like. It is understood that the embodiments of the present application are not limited to specific devices.

[0054] Method Example 1

[0055] Reference Figure 2 , shows a flowchart of the steps of a data processing method according to the present invention, which may specifically include the following steps:

[0056] Step 201: Determine a screen image in response to a user operation;

[0057] Step 202: Determine the answer corresponding to the question in the screen image;

[0058] Step 203: Display the answer.

[0059] Figure 2 At least one step of the illustrated embodiment can be executed by a client, and the client can refer to a client corresponding to the user. The client can correspond to any APP, such as an input method APP, etc. Among them, the input method APP, as a host program, can be hosted in any APP environment, so it has cross-application characteristics. Therefore, when the method of the embodiment of the present invention is executed by the input method APP, the embodiment of the present invention can be applied to any application scenario, and the above-mentioned application scenarios may include: customer service scenarios, instant messaging scenarios, etc., wherein the fields corresponding to the customer service scenarios may include: e-commerce, printers, computers, etc., and the embodiment of the present invention does not limit the specific fields.

[0060] In step 201, a user's operation may be used to trigger the method of an embodiment of the present invention. The embodiment of the present invention does not limit the specific operation. For example, the above operation may include: touch operation, gesture operation, or voice operation.

[0061] In an optional embodiment of the present invention, the above-mentioned user operation may specifically include: a user triggering operation on a preset control in the input method interface.

[0062] Input methods are encoding methods used to input various text into computers or other devices (such as mobile phones and tablets). The input method interface is a UI (User Interface), which serves as the medium for interaction and information exchange between the system and the user. Controls encapsulate data and methods. Controls can have their own properties and methods. Properties are simple accessors to control data, while methods are simple, visible functions of a control.

[0063] The embodiment of the present invention can set the properties of the preset controls in the input method interface to execute the method of the embodiment of the present invention in response to the user's operation.

[0064] The embodiment of the present invention does not limit the preset control. For example, the preset control may be a function control in the input method interface, and the preset control may be a search control, etc.

[0065] Of course, the above-mentioned user triggering operation on the preset control in the input method interface is only an optional embodiment. In fact, the above-mentioned user operation may also include: preset gestures, or preset key combinations, etc.

[0066] The screen image may refer to an image corresponding to the screen content. The screen image may be obtained using a screenshot function. In practical applications, the screen image may be obtained by calling a screenshot function interface provided by the operating system.

[0067] In the embodiment of the present invention, the permission of the screenshot function can be granted by the user. In the case of not uninstalling the APP, if the user authorization is obtained once, the permission of the screenshot function can be continuously obtained.

[0068] In the embodiment of the present invention, optionally, the screen image may include: screen content of one screen or multiple screens.

[0069] In actual applications, the screen content of one screen or the screen content of multiple screens may correspond to different operations. For example, the triggering operation of the first preset control corresponds to the screen content of one screen; for another example, the triggering operation of the second preset control corresponds to the screen content of multiple screens, etc.

[0070] In an embodiment of the present invention, the screen content corresponding to the screen image may be determined based on the window content.

[0071] According to one embodiment, if the length of the window content does not exceed a length threshold, the screen image may include one screenful of screen content. For example, if the communication window includes only M (M is a natural number) messages, and the length of the M messages does not exceed the length threshold, the screen image may include one screenful of screen content.

[0072] According to another embodiment, if the length of the window content exceeds a length threshold, the screen image may include: the screen content of multiple screens. For example, if the communication window includes multiple messages and the length of the multiple messages exceeds the length threshold, the screen image may include: the screen content of multiple screens.

[0073] Optionally, in determining the screen image, the publication time of the window content may be considered, and the screen content may be determined from the window content in descending order of publication time. For example, the window content whose publication time falls within a preset time period may be used as the screen content. The end time of the preset time period may be the current time, and the length of the preset time period may be determined by those skilled in the art based on actual application requirements. For example, the length of the preset time period may be 12 hours, 24 hours, or even 8 hours, 1 hour, etc.

[0074] In step 202, optionally, OCR (Optical Character Recognition) technology may be used to determine text in the screen image and identify the problem from the text. OCR technology can find image areas containing text and recognize the text in the image areas.

[0075] In practical applications, the screen image may include one or more questions. The embodiment of the present invention may determine a target question from the multiple questions and determine the answer corresponding to the target question. The target question may refer to a question that has not yet been answered.

[0076] For example, in a customer service scenario, multiple questions are received, some of which have been answered. Whether a question has been answered can be determined by determining whether the text contains the corresponding answer. Alternatively, whether a question has been answered can be determined based on the time it was posted. For example, if the question was posted the latest and no reply has appeared after it, then the question has not been answered.

[0077] In an optional embodiment of the present invention, the screen image may include: multiple questions. When the correlation between the multiple questions exceeds the correlation threshold, the multiple questions can be answered together, that is, one answer can be provided for multiple questions. This can reduce the number of times the user views the answer, avoid redundancy between multiple answers, and improve the user experience.

[0078] For example, the two questions in the screen image include: "Printer cannot print" and "Displays offline". Since the two questions have a certain correlation, the two questions can be answered together.

[0079] The embodiment of the present invention can determine corresponding representations for multiple questions in the screen image, where the representations can be keywords or word vectors, and can determine the relevance between the multiple questions based on the similarity between the representations corresponding to the multiple questions.

[0080] The process of combining answers to multiple questions can be found in Figure 3 In the illustrated method embodiment, the process may include: determining first representation vectors corresponding to multiple questions; determining target preset questions corresponding to the questions based on the degree of matching between the first representation vectors and second representation vectors corresponding to the preset questions; and determining answers corresponding to the questions based on the answers corresponding to the target preset questions.

[0081] In the process of combining answers to multiple questions, you can combine your understanding of the multiple questions and provide an answer based on the combined understanding results.

[0082] In an embodiment of the present invention, the client may obtain the answer corresponding to the question in the screen image, or the client may send the screen image to the server so that the server obtains the answer corresponding to the question in the screen image.

[0083] In an optional embodiment of the present invention, the answer may be obtained based on the answer corresponding to the target preset question, and the degree of matching between the first representation vector corresponding to the question and the second representation vector corresponding to the target preset question meets a preset condition.

[0084] Preset questions can refer to existing questions or questions for which answers already exist. In practical applications, the preset questions and their corresponding answers can be collected. For example, the preset questions and their corresponding answers can be collected by crawling the internet. In another example, the preset questions and their corresponding answers can be obtained from suppliers through collaboration. For example, in a customer service scenario, the customer service supplier can provide the preset questions and their corresponding answers. It will be understood that the embodiments of the present invention do not limit the specific method for obtaining the preset questions and their corresponding answers.

[0085] Embodiments of the present invention can determine a target preset problem that meets preset conditions from multiple preset problems. The preset conditions can be used to constrain a first representation vector corresponding to the problem and a second representation vector corresponding to the target preset problem, so that the problem and the target preset problem match. Because the target preset problem is an existing problem, its corresponding answer is often reasonable and effective, and the target preset problem matches the problem. Therefore, the answer to the target preset problem can be used as the basis for determining the answer to the problem.

[0086] For example, if question A is "The printer is offline and cannot print," its corresponding target preset question A is "The printer shows offline and cannot print." Since the question and target preset question A are highly similar, the answer to question A can be determined based on the answer to target preset question A. For example, the answer to target preset question A can include the steps to solve question A for the user's reference.

[0087] It can be understood that the above-mentioned obtaining the answer to the question based on the answer to the target preset question is only an optional embodiment. In fact, those skilled in the art can use other methods to determine the answer to the question according to actual application requirements. For example, in some embodiments, the search results corresponding to the first keyword can be determined based on the first keyword corresponding to the question, and the answer to the question can be obtained from the above search results, wherein the search results are the results obtained by searching with the first keyword as the search term, and the types of search results can include: web pages or documents.

[0088] In step 203, the answer may be displayed to allow the user to view the answer.

[0089] According to one embodiment, the above-mentioned answer may include: one answer, in which case the answer may be directly displayed.

[0090] According to another embodiment, the above-mentioned answer may include: multiple answers, and step 203 of displaying the answers may specifically include: displaying the first answer and a sliding control in the answer area.

[0091] The slide control can be used to slide and switch answers, allowing users to view multiple answers by sliding.

[0092] Optionally, the sliding control may include a first-direction sliding control and / or a second-direction sliding control, wherein the first-direction sliding control is used to switch the answer in the first direction, and the second-direction sliding control is used to switch the answer in the second direction. The first direction may be left, and the second direction may be right. Alternatively, the first direction may be upward, and the second direction may be downward.

[0093] In an optional embodiment of the present invention, displaying the answer may further include: displaying a second answer in the answer area in response to a user operating the slide control. For example, in response to a rightward slide control operation, the second answer may be displayed in the answer area, and the second answer may be located to the right of the first answer. For another example, in response to a leftward slide control operation, the second answer may be displayed in the answer area, and the second answer may be located to the left of the first answer.

[0094] In an embodiment of the present invention, optionally, the answer area can be an area of ​​the input method interface. For example, the input method interface may include: a toolbar area and a key area, wherein the toolbar area may include: tool controls such as preset controls, and the key area may include: multiple keys, such as letter keys, symbol keys, etc. In an embodiment of the present invention, a mask layer may be set on the key area as the answer area, and the answer may be displayed through the answer area. The mask layer refers to a layer with a certain transparency value, and the parameters of the mask layer may include size, display position, and transparency value. The mask layer in the embodiment of the present invention covers the key area, so that the display elements of the mask layer and the key area can be displayed simultaneously through the parameters of the mask layer.

[0095] It can be understood that the above-mentioned answer area is located above the button area, which is only an optional embodiment. In fact, the answer area can be any interface area, and the embodiment of the present invention does not limit the specific answer area.

[0096] In an optional embodiment of the present invention, the above method may further include:

[0097] In response to a first operation of the user on the answer, outputting the answer corresponding to the first operation into the input box; or

[0098] In response to the user's second operation on the answer, sending the answer corresponding to the first operation to the communication peer.

[0099] In an embodiment of the present invention, in response to the first operation, the answer may be output to an input box. The input box may refer to an input box of a host application in which the input method is hosted. Inputting the answer into the input box may allow the user to edit the answer in the input box.

[0100] In embodiments of the present invention, an answer can be sent in response to the second operation. Specifically, the answer corresponding to the first operation can be sent to the communication peer to achieve rapid delivery of the answer. For example, in customer service or instant messaging scenarios, the communication peer can refer to the party that asks the question. In another example, in a question-and-answer scenario, the communication peer can refer to the server of the question-and-answer platform.

[0101] The embodiment of the present invention does not limit the first operation and the second operation. Optionally, the first operation can be an operation on a control.

[0102] For example, the answer area may be provided with an on-screen control, and in response to an operation on the on-screen control, the answer in the answer area may be output to the input box. For another example, the answer area may be provided with a send control, and in response to an operation on the send control, the answer in the answer area may be sent to the communication peer.

[0103] Of course, the first operation and the second operation may also correspond to shortcut keys, gestures, or voice, etc. The embodiment of the present invention does not limit the first operation and the second operation.

[0104] In summary, the data processing method of the embodiment of the present invention can provide the user with the answer corresponding to the question in the screen image in response to the user's operation, which can reduce the cost of the user to find the answer through the question, thereby reducing the time to obtain the answer and improving the efficiency of obtaining the answer.

[0105] Moreover, the screen image of the embodiment of the present invention can be obtained through the screenshot function, and the permission of the screenshot function can be granted by the user. If the APP is not uninstalled, if the user authorization is obtained once, the permission of the screenshot function can be continuously obtained. Therefore, the embodiment of the present invention can reduce the difficulty of obtaining the screen image, and thus can increase the scope of application of the solution.

[0106] In addition, the embodiment of the present invention can support users in editing and sending answers. In actual applications, questions usually come from the communication counterpart. Therefore, the embodiment of the present invention, on the basis of providing answers corresponding to questions, also responds to user triggers and quickly sends answers corresponding to questions to the communication counterpart, thereby helping users to respond to questions conveniently.

[0107] Method Example 2

[0108] Reference Figure 3 , shows a flow chart of the steps of a second embodiment of a data processing method of the present invention, which may specifically include the following steps:

[0109] Step 301: Determine the problem in the screen image;

[0110] Step 302: Determine a first representation vector corresponding to the problem;

[0111] Step 303: Determine a target preset question corresponding to the question based on a matching degree between the first representation vector and a second representation vector corresponding to the preset question;

[0112] Step 304: Determine the answer corresponding to the question based on the answer corresponding to the target preset question.

[0113] Figure 3 At least one step of the illustrated embodiment may be executed by a client or a server. Figure 3 The illustrated embodiment can be used to determine the answer corresponding to the question in the screen image, that is, the process of determining the answer corresponding to the question in the screen image in the embodiment of the present invention may include: determining the question in the screen image; determining the first representation vector corresponding to the question; determining the target preset question corresponding to the question based on the matching degree between the first representation vector and the second representation vector corresponding to the preset question; and determining the answer corresponding to the question based on the answer corresponding to the target preset question.

[0114] The embodiment of the present invention can determine the target preset question based on the matching degree between the first representation vector corresponding to the question and the second representation vector corresponding to the preset question, and then determine the answer corresponding to the question based on the answer corresponding to the target preset question.

[0115] Since the target preset question is an existing question, the corresponding answer is often reasonable and effective, and the target preset question matches the question. Therefore, the answer corresponding to the target preset question can be used as the basis for determining the answer corresponding to the question, thereby improving the accuracy of the answer corresponding to the question.

[0116] In an embodiment of the present invention, optionally, a knowledge base may store preset questions and their corresponding answers. Then, step 303 may match the first representation vector with the second representation vector corresponding to the preset question in the knowledge base to obtain a corresponding matching degree.

[0117] This embodiment of the present invention converts text into a fixed-length vector representation to facilitate processing. The first representation vector can be used to represent a question, and the second representation vector can be used to represent a preset question. The dimensions of the first or second representation vector can be one, two, or three dimensions.

[0118] The first or second representation vector can be a one-hot vector, a word embedding vector, or a high-level representation vector. Word embedding involves finding a mapping or function to generate an expression in a new space, which is called a word representation.

[0119] In an optional embodiment of the present invention, the process of determining the first representation vector may include: determining the word embedding vector corresponding to the question, and processing the word embedding vector using a neural network to obtain a high-level representation vector corresponding to the question. Among them, by processing the word embedding vector using a neural network, the deep-level features of the word embedding vector can be extracted, thereby improving the richness of the first representation vector. Optionally, the word embedding vector can be processed using a neural network such as CNN (Convolutional Neural Network) or LSTM (Long Short-Term Memory). As for the process of determining the second representation vector, since it is similar to the process of determining the first representation vector, it will not be described here in detail, and can be referred to each other.

[0120] A similarity metric between vectors may be used to determine the degree of match between the first representation vector and the second representation vector corresponding to the preset question. The similarity metric may include angle cosine, Euclidean distance, and the like.

[0121] In the embodiment of the present invention, one or more preset questions with the greatest matching degree may be used as target preset questions.

[0122] In an optional embodiment of the present invention, the first keyword corresponding to the question matches the second keyword corresponding to the preset question. Since the knowledge base typically has a large number of preset questions, this embodiment of the present invention can first filter the preset questions in the knowledge base based on the matching between the first keyword and the second keyword; then, step 303 is performed for the preset questions that pass the filter. This filtering can reduce the amount of computation required, thereby increasing computation speed.

[0123] In one embodiment, the preset questions in the knowledge base can be screened based on the matching between the first keyword and the second keyword. Assuming that the preset question that passes the screening is the first preset question, the target preset question corresponding to the question can be determined based on the matching degree between the first representation vector and the second representation vector corresponding to the first preset question. The matching between the first preset question and the question can include: matching of domain keywords, and / or matching of intent keywords, and / or matching of slot keywords.

[0124] In the embodiment of the present invention, optionally, the first keyword corresponding to the question may specifically include:

[0125] Domain keywords; and / or

[0126] Intent keywords; and / or

[0127] Slot keyword.

[0128] In the embodiment of the present invention, the field may refer to the scope of data. Optionally, the field may refer to the application scenario or category of data. The field may include but is not limited to: printers, computers, encyclopedias, news, music, videos, movies, games, sports, e-commerce, education and learning, FM (Frequency Modulation), SMS (Short Messaging Service), control, travel, books, weather, gallery, etc. It can be understood that the field can be subdivided to obtain subdivided fields. For example, the subdivided fields of the encyclopedia field may include: the meanings corresponding to the polysemous words in the encyclopedia, etc. Optionally, the field may be related to the corresponding APP or service, and the embodiment of the present invention does not limit the specific field.

[0129] Embodiments of the present invention can identify domain keywords from the text corresponding to the question. Optionally, the text corresponding to the question can be segmented and the segmentation results can be matched with the domain keywords. Alternatively, a classification model can be used to determine the domain to which the question belongs.

[0130] The above-mentioned classification model can be a machine learning model. In a broad sense, machine learning is a method that can give machines the ability to complete functions that cannot be completed by direct programming. However, in a practical sense, machine learning is a method that uses data to train a model and then uses the model to make predictions. Machine learning methods can include: decision tree method, linear regression method, logistic regression method, neural network method, k-nearest neighbor method, etc. It can be understood that the embodiments of the present invention do not limit the specific machine learning methods. The above-mentioned classification model can have the ability to classify domains.

[0131] Intent is the process of determining what task a user wishes to accomplish based on a sentence they express. Alternatively, a classification model can be used to identify the intent keywords corresponding to the question.

[0132] Slots define key information within a user's expression. For example, in an expression for booking a flight, slots might include "departure time," "origin," and "destination." Alternatively, in an expression describing a computer failure, slots might include "blue screen."

[0133] In the embodiment of the present invention, it is optional to use intent extraction technology to determine the intent keywords corresponding to the question. Optionally, slot filling technology can be used to determine the slot keywords corresponding to the question. This will not be described in detail here.

[0134] Any of the domain keywords, intent keywords and slot keywords can reflect the information of the question, so any one of the domain keywords, intent keywords and slot keywords or a combination thereof can be used as the first keyword corresponding to the question.

[0135] Similarly, the second keyword can specifically include:

[0136] Domain keywords; and / or

[0137] Intent keywords; and / or

[0138] Slot keyword.

[0139] The embodiment of the present invention can save corresponding second keywords for preset questions in the knowledge base.

[0140] In summary, the data processing method of the embodiment of the present invention determines the target preset question based on the matching degree between the first representation vector corresponding to the question and the second representation vector corresponding to the preset question, and then determines the answer corresponding to the question based on the answer corresponding to the target preset question.

[0141] Since the target preset question is an existing question, the corresponding answer is often reasonable and effective, and the target preset question matches the question. Therefore, the answer corresponding to the target preset question can be used as the basis for determining the answer corresponding to the question, thereby improving the accuracy of the answer corresponding to the question.

[0142] Method Example 3

[0143] Reference Figure 4 , shows a flowchart of the steps of a data processing method according to embodiment 3 of the present invention, which may specifically include the following steps:

[0144] Step 401: The client determines a screen image in response to a user operation.

[0145] Step 402: The client sends the screen image to the server;

[0146] Step 403: The server determines a problem in the screen image;

[0147] Step 404: The server determines a first representation vector corresponding to the question;

[0148] Step 405: The server determines a target preset question corresponding to the question based on a matching degree between the first representation vector and a second representation vector corresponding to the preset question;

[0149] Step 406: The server determines the answer to the question based on the answer to the target preset question.

[0150] Step 407: The server sends the answer to the question to the client.

[0151] Step 408: The client displays the answer corresponding to the question.

[0152] In an embodiment of the present invention, after determining the screen image, the client can send the screen image to the server so that the server can determine the answer corresponding to the question in the screen image. This can take advantage of the server's abundant computing resources and further improve the efficiency and accuracy of answer acquisition. Of course, in other embodiments of the present invention, the client can determine the answer corresponding to the question in the screen image. This embodiment of the present invention does not limit the specific execution entity corresponding to the answer corresponding to the question in the screen image.

[0153] In an embodiment of the present invention, the client can respond to user actions and display the corresponding answer to the question. After receiving the user's action and before displaying the corresponding answer to the question, a corresponding waiting prompt can be provided to improve the user's patience and user experience. For example, the waiting prompt can be "Loading, please wait" or "Please wait, the answer will be here soon."

[0154] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0155] Device embodiment

[0156] Reference Figure 5 , shows a structural block diagram of an embodiment of a data processing device of the present invention, which may specifically include:

[0157] A screen image determination module 501 is configured to determine a screen image in response to a user operation;

[0158] an answer determination module 502, configured to determine an answer corresponding to the question in the screen image; and

[0159] The answer display module 503 is used to display the answer.

[0160] Optionally, the user's operation may include:

[0161] The user triggers the operation of the preset controls in the input method interface.

[0162] Optionally, the answer is obtained based on the answer corresponding to the target preset question, and the matching degree between the first representation vector corresponding to the question and the second representation vector corresponding to the target preset question meets a preset condition.

[0163] Optionally, the answer may include: multiple answers, and the answer display module may include:

[0164] The first answer display module is used to display the first answer and the sliding control in the answer area.

[0165] Optionally, the answer display module may further include:

[0166] The second answer display module is configured to display a second answer in the answer area in response to a user operation on the sliding control.

[0167] Optionally, the device may further include:

[0168] an answer output module, configured to output the answer corresponding to the first operation to the input box in response to the user's first operation on the answer; or

[0169] The answer sending module is used to send the answer corresponding to the first operation to the communication peer in response to the user's second operation on the answer.

[0170] Optionally, the screen image may include: screen content of one screen or multiple screens.

[0171] Reference Figure 6 , shows a structural block diagram of an embodiment of a data processing device of the present invention, which may specifically include:

[0172] Problem determination module 601, for determining problems in the screen image;

[0173] A first representation vector determining module 602 is configured to determine a first representation vector corresponding to the problem;

[0174] The target preset question determination module 603 is used to determine the target preset question corresponding to the question based on the matching degree between the first representation vector and the second representation vector corresponding to the preset question; and the answer determination module 604 is used to determine the answer corresponding to the question based on the answer corresponding to the target preset question.

[0175] Optionally, the first keyword corresponding to the question matches the second keyword corresponding to the preset question.

[0176] Optionally, the first keyword corresponding to the question may include:

[0177] Domain keywords; and / or

[0178] Intent keywords; and / or

[0179] Slot keyword.

[0180] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0181] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0182] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0183] An embodiment of the present invention provides a device for data processing, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: determining a screen image in response to a user's operation; determining an answer corresponding to a question in the screen image; and displaying the answer.

[0184] Figure 7 FIG1 is a block diagram of an apparatus 800 for data processing according to an exemplary embodiment. For example, the apparatus 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0185] Reference Figure 7 , the device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0186] The processing component 802 generally controls the overall operation of the device 800, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 802 may include one or more modules to facilitate interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

[0187] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 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 disk, or optical disk.

[0188] The power supply component 806 provides power to the various components of the device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 800.

[0189] The multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0190] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), which is configured to receive external audio signals when the device 800 is in an operating mode, such as a call mode, a recording mode, and a voice data processing mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0191] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0192] The sensor assembly 814 includes one or more sensors for providing various aspects of the status assessment of the device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the device 800. The sensor assembly 814 can also detect changes in the position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration / deceleration of the device 800, and temperature changes of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0193] The communication component 816 is configured to facilitate wired or wireless communication between the device 800 and other devices. The device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency data processing (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0194] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0195] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by the processor 820 of the apparatus 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0196] Figure 81 is a schematic diagram of the structure of a server in some embodiments of the present invention. The server 1900 may vary greatly due to different configurations or performance, and may include one or more central processing units (CPUs) 1922 (for example, one or more processors) and memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage medium 1930 can be temporary storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), each module may include a series of instruction operations on the server. Furthermore, the central processing unit 1922 can be configured to communicate with the storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.

[0197] The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input and output interfaces 1958, one or more keyboards 1956, and / or one or more operating systems 1941, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0198] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of a device (server or terminal), enables the device to perform Figure 2 or Figure 3 or Figure 4 The data processing method shown.

[0199] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of a device (server or terminal), enables the device to perform a data processing method, the method comprising: determining a screen image in response to a user's operation; determining an answer corresponding to a question in the screen image; and displaying the answer.

[0200] The embodiment of the present invention discloses A1, a data processing method, the method comprising:

[0201] determining a screen image in response to a user operation;

[0202] determining an answer corresponding to the question in the screen image;

[0203] Show the answer.

[0204] A2. The method according to A1, wherein the user's operation includes:

[0205] The user triggers the operation of the preset controls in the input method interface.

[0206] A3. According to the method described in A1, the answer is obtained based on the answer corresponding to the target preset question, and the matching degree between the first representation vector corresponding to the question and the second representation vector corresponding to the target preset question meets the preset conditions.

[0207] A4. The method according to A1, wherein the answer comprises: a plurality of answers, and the displaying of the answer comprises:

[0208] Display the first answer and the slide control in the answer area.

[0209] A5. The method according to A4, wherein displaying the answer further comprises:

[0210] In response to a user operation on the sliding control, a second answer is displayed in the answer area.

[0211] A6. The method according to any one of A1 to A5, further comprising:

[0212] In response to a first operation of the user on the answer, outputting the answer corresponding to the first operation into the input box; or

[0213] In response to the user's second operation on the answer, sending the answer corresponding to the first operation to the communication peer.

[0214] A7. According to any one of the methods A1 to A5, the screen image includes: screen content of one screen or multiple screens.

[0215] The embodiment of the present invention discloses B8, a data processing method, the method comprising:

[0216] Identify problems in screen images;

[0217] Determine a first representation vector corresponding to the problem;

[0218] Determining a target preset question corresponding to the question based on a matching degree between the first representation vector and a second representation vector corresponding to the preset question;

[0219] Determine the answer to the question based on the answer to the target preset question.

[0220] B9. According to the method described in B8, the first keyword corresponding to the question is matched with the second keyword corresponding to the preset question.

[0221] B10. According to the method of B9, the first keyword corresponding to the question includes:

[0222] Domain keywords; and / or

[0223] Intent keywords; and / or

[0224] Slot keyword.

[0225] The embodiment of the present invention discloses C11, a data processing device, comprising:

[0226] A screen image determination module, configured to determine a screen image in response to a user operation;

[0227] an answer determination module, configured to determine an answer corresponding to the question in the screen image; and

[0228] The answer display module is used to display the answer.

[0229] C12. The apparatus according to C11, wherein the user operation comprises:

[0230] The user triggers the operation of the preset controls in the input method interface.

[0231] C13. According to the device described in C11, the answer is obtained based on the answer corresponding to the target preset question, and the matching degree between the first representation vector corresponding to the question and the second representation vector corresponding to the target preset question meets the preset conditions.

[0232] C14. The device according to C11, wherein the answer comprises: a plurality of answers, and the answer display module comprises:

[0233] The first answer display module is used to display the first answer and the sliding control in the answer area.

[0234] C15. The device according to C11, wherein the answer display module further comprises:

[0235] The second answer display module is configured to display a second answer in the answer area in response to a user operation on the sliding control.

[0236] C16. The device according to any one of C11 to C15, further comprising:

[0237] an answer output module, configured to output the answer corresponding to the first operation to the input box in response to the user's first operation on the answer; or

[0238] The answer sending module is used to send the answer corresponding to the first operation to the communication peer in response to the user's second operation on the answer.

[0239] C17. According to the device described in any one of C11 to C15, the screen image includes: screen content of one screen or multiple screens.

[0240] The embodiment of the present invention discloses D18, a data processing device, comprising:

[0241] a problem determination module for determining problems in the screen image;

[0242] A first representation vector determination module, configured to determine a first representation vector corresponding to the problem;

[0243] a target preset problem determining module, configured to determine a target preset problem corresponding to the problem based on a degree of matching between the first representation vector and a second representation vector corresponding to the preset problem; and

[0244] The answer determination module is used to determine the answer corresponding to the question based on the answer corresponding to the target preset question.

[0245] D19. According to the device described in D18, the first keyword corresponding to the question matches the second keyword corresponding to the preset question.

[0246] D20. According to the device described in D19, the first keyword corresponding to the question includes:

[0247] Domain keywords; and / or

[0248] Intent keywords; and / or

[0249] Slot keyword.

[0250] An embodiment of the present invention discloses E21, a device for data processing, the device being applied to a server, the device comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations:

[0251] determining a screen image in response to a user operation;

[0252] determining an answer corresponding to the question in the screen image;

[0253] Show the answer.

[0254] E22. The device according to E21, wherein the user operation comprises:

[0255] The user triggers the operation of the preset controls in the input method interface.

[0256] E23. The device according to E21 is characterized in that the answer is obtained based on the answer corresponding to the target preset question, and the matching degree between the first representation vector corresponding to the question and the second representation vector corresponding to the target preset question meets the preset conditions.

[0257] E24. The device according to E21, wherein the answer comprises: a plurality of answers, and the displaying of the answer comprises:

[0258] Display the first answer and the slide control in the answer area.

[0259] E25. The device according to E24, wherein displaying the answer further comprises:

[0260] In response to a user operation on the sliding control, a second answer is displayed in the answer area.

[0261] E26. The device according to any one of E21 to E25, further comprising:

[0262] In response to a first operation of the user on the answer, outputting the answer corresponding to the first operation into the input box; or

[0263] In response to the user's second operation on the answer, sending the answer corresponding to the first operation to the communication peer.

[0264] E27. The device according to any one of E21 to E25, wherein the screen image includes: screen content of one screen or multiple screens.

[0265] An embodiment of the present invention discloses F28, a device for data processing, characterized in that the device is applied to a server, the device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations:

[0266] Identify problems in screen images;

[0267] Determine a first representation vector corresponding to the problem;

[0268] Determining a target preset question corresponding to the question based on a matching degree between the first representation vector and a second representation vector corresponding to the preset question;

[0269] Determine the answer to the question based on the answer to the target preset question.

[0270] F29. The device according to F28, wherein the first keyword corresponding to the question matches the second keyword corresponding to the preset question.

[0271] F30. The device according to F29, wherein the first keyword corresponding to the question includes:

[0272] Domain keywords; and / or

[0273] Intent keywords; and / or

[0274] Slot keyword.

[0275] An embodiment of the present invention discloses G31, a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes a device to perform a data processing method as described in one or more of A1 to A7.

[0276] An embodiment of the present invention discloses H32, a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes the device to execute the data processing method as described in one or more of B8 to B10.

[0277] Other embodiments of the present invention will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

[0278] It should be understood that the present invention is not limited to the exact construction described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0279] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0280] The data processing method, data processing device and device for data processing provided by the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A data processing method, characterized in that: The method comprises: In response to a user operation, determining window content in a window on a screen whose release time is within a preset time period; if the length of the window content does not exceed a length threshold, using the screen content of one screen as a screen image; if the length of the window content exceeds the length threshold, using the screen content of multiple screens as the screen image; wherein the user operation includes a user triggering an operation on a preset control in a toolbar area of ​​an input method interface, the input method interface is displayed on the screen, a problem is displayed in a window on the screen, and the window is located in an area of ​​the screen other than the input method interface; In a case where the screen image includes multiple questions, a correlation between the multiple questions is determined based on similarities between representations corresponding to the multiple questions; in a case where the correlation exceeds a correlation threshold, the preset questions are screened based on a match between a first keyword corresponding to the multiple questions and a second keyword corresponding to the preset question to obtain a first preset question that passes the screening; target preset questions corresponding to the multiple questions are determined based on a match between first representation vectors corresponding to the multiple questions and a second representation vector corresponding to the first preset question; answers corresponding to the multiple questions are determined based on answers corresponding to the target preset question, so as to achieve a combined answer to the multiple questions; When there are multiple answers, a mask is set on the key area in the input method interface as an answer area, and the answer and a sliding control are displayed in the answer area, and the sliding control is used to slide and switch the answers; In response to the user's first operation on the first target control, the answer in the answer area is output to the input box for the user to edit; or, in response to the user's second operation on the second target control, the answer in the answer area is sent to the communication peer.

2. A data processing method, characterized in that: The method is used to determine the answer in claim 1 and includes: Determining a problem in a screen image; wherein, when the length of window content in a window of the screen whose release time is within a preset time period does not exceed a length threshold, the screen image includes screen content of one screen; when the length of the window content exceeds the length threshold, the screen image includes screen content of multiple screens; When the screen image includes a plurality of questions, determining a correlation between the plurality of questions based on a similarity between representations corresponding to the plurality of questions; when the correlation exceeds a correlation threshold, screening the preset questions based on a match between a first keyword corresponding to the plurality of questions and a second keyword corresponding to the preset question to obtain a first preset question that passes the screening; determining a target preset question corresponding to the plurality of questions based on a match between a first representation vector corresponding to the plurality of questions and a second representation vector corresponding to the first preset question; Based on the answers corresponding to the target preset questions, the answers corresponding to the multiple questions are determined to achieve a combined answer to the multiple questions.

3. A data processing device, characterized in that: The device comprises: a screen image determination module, configured to, in response to a user operation, determine window content in a window on a screen whose release time is within a preset time period; if the length of the window content does not exceed a length threshold, use the screen content of one screen as the screen image; and if the length of the window content exceeds the length threshold, use the screen content of multiple screens as the screen image; wherein the user operation includes a user triggering an operation on a preset control in a toolbar area of ​​an input method interface, the input method interface is displayed on the screen, there is a problem with the display in a window on the screen, and the window is located in an area of ​​the screen other than the input method interface; an answer determination module for, when the screen image includes multiple questions, determining a correlation between the multiple questions based on a similarity between representations corresponding to the multiple questions; screening the preset questions based on a match between a first keyword corresponding to the multiple questions and a second keyword corresponding to the preset question to obtain a first preset question that passes the screening, when the correlation exceeds a correlation threshold; determining target preset questions corresponding to the multiple questions based on a match between first representation vectors corresponding to the multiple questions and a second representation vector corresponding to the first preset question; and determining answers corresponding to the multiple questions based on answers corresponding to the target preset questions, thereby achieving a combined answer to the multiple questions; and an answer display module, configured to, when there are multiple answers, set a mask on the key area in the input method interface as an answer area, displaying the answer and a sliding control in the answer area, wherein the sliding control is used to slide and switch between answers; An answer output module is used to output the answer in the answer area to an input box for user editing in response to a user's first operation on a first target control; or, an answer sending module is used to send the answer in the answer area to a communication counterpart in response to a user's second operation on a second target control.

4. A data processing device, characterized in that: The apparatus is used to determine the answer in claim 3 and comprises: a problem determination module, configured to determine a problem in a screen image; wherein, when the length of window content in a window on the screen whose release time is within a preset time period does not exceed a length threshold, the screen image includes the screen content of one screen; and when the length of the window content exceeds the length threshold, the screen image includes the screen content of multiple screens; A first representation vector determining module, configured to determine first representation vectors corresponding to a plurality of questions when the screen image includes a plurality of questions; a target preset question determination module, configured to, if the screen image includes multiple questions, determine the correlation between the multiple questions based on the similarity between the representations corresponding to the multiple questions; if the correlation exceeds a correlation threshold, filter the preset questions based on the matching between the first keywords corresponding to the multiple questions and the second keywords corresponding to the preset questions to obtain first preset questions that pass the screening; and determine the target preset questions corresponding to the multiple questions based on the matching between the first representation vectors corresponding to the multiple questions and the second representation vector corresponding to the first preset question; and The answer determination module is used to determine the answers corresponding to the multiple questions based on the answers corresponding to the target preset questions, so as to achieve a combined answer to the multiple questions.

5. A device for data processing, characterized in that The device is applied to a server and includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: In response to a user operation, determining window content in a window on a screen whose release time is within a preset time period; if the length of the window content does not exceed a length threshold, using the screen content of one screen as a screen image; if the length of the window content exceeds the length threshold, using the screen content of multiple screens as the screen image; wherein the user operation includes a user triggering an operation on a preset control in a toolbar area of ​​an input method interface, the input method interface is displayed on the screen, a problem is displayed in a window on the screen, and the window is located in an area of ​​the screen other than the input method interface; In a case where the screen image includes multiple questions, a correlation between the multiple questions is determined based on similarities between representations corresponding to the multiple questions; in a case where the correlation exceeds a correlation threshold, the preset questions are screened based on a match between a first keyword corresponding to the multiple questions and a second keyword corresponding to the preset question to obtain a first preset question that passes the screening; target preset questions corresponding to the multiple questions are determined based on a match between first representation vectors corresponding to the multiple questions and a second representation vector corresponding to the first preset question; answers corresponding to the multiple questions are determined based on answers corresponding to the target preset question, so as to achieve a combined answer to the multiple questions; When there are multiple answers, a mask is set on the key area in the input method interface as an answer area, and the answer and a sliding control are displayed in the answer area, and the sliding control is used to slide and switch the answers; In response to the user's first operation on the first target control, the answer in the answer area is output to the input box for the user to edit; or, in response to the user's second operation on the second target control, the answer in the answer area is sent to the communication peer.

6. A device for data processing, characterized in that The device is applied to a server, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory. The device is used to determine the answer in claim 5 and is configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: Determining a problem in a screen image; wherein, when the length of window content in a window of the screen whose release time is within a preset time period does not exceed a length threshold, the screen image includes screen content of one screen; when the length of the window content exceeds the length threshold, the screen image includes screen content of multiple screens; When the screen image includes a plurality of questions, determining a correlation between the plurality of questions based on a similarity between representations corresponding to the plurality of questions; when the correlation exceeds a correlation threshold, screening the preset questions based on a match between a first keyword corresponding to the plurality of questions and a second keyword corresponding to the preset question to obtain a first preset question that passes the screening; determining a target preset question corresponding to the plurality of questions based on a match between a first representation vector corresponding to the plurality of questions and a second representation vector corresponding to the first preset question; Based on the answers corresponding to the target preset questions, the answers corresponding to the multiple questions are determined to achieve a combined answer to the multiple questions.

7. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes a device to perform the data processing method according to claim 1.

8. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes a device to perform the data processing method according to claim 2.

Images