CN117973539A

CN117973539A - Question fusion method and device, electronic equipment and storage medium

Info

Publication number: CN117973539A
Application number: CN202410168635.6A
Authority: CN
Inventors: 周月
Original assignee: Douyin Vision Co Ltd
Current assignee: Douyin Vision Co Ltd
Priority date: 2024-02-05
Filing date: 2024-02-05
Publication date: 2024-05-03

Abstract

The embodiment of the disclosure provides a problem fusion method, a device, electronic equipment and a storage medium. The question-answer fusion method comprises the steps of displaying a fusion page, wherein the fusion page comprises a target question display area, a to-be-fused question display area and an answer display area, the target question is displayed in the target question display area, the to-be-fused question to be fused with the target question is displayed in the to-be-fused question display area, and the answer corresponding to the target question is displayed in the answer display area; responding to the adjustment operation of the answer in the answer display area, and displaying the adjusted answer in the answer display area; and responding to the triggering operation of the fusion control in the fusion page, and displaying a fusion result for question-answer model training, wherein the fusion result indicates that the answer of the question to be fused and the target question is a target answer, and the target answer is an answer determined based on the adjusted answer. The problem fusion method realizes the fusion of the problems and improves the reliability of the question-answering model.

Description

Question fusion method and device, electronic equipment and storage medium

Technical Field

The embodiment of the disclosure relates to computer technology, in particular to a problem fusion method, a device, electronic equipment and a storage medium.

Background

An artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) application refers to an application program built based on artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) technology, and mainly consists of a model, a dataset and a guide word. The AI application uses the trained model to analyze and process the input data and then generates a corresponding output based on the model's learning and understanding.

The ability of the model plays a decisive role in answering the effect when the user interacts with the AI application. However, the current model may have a situation that different questions for the same question output different answers in practical application, which reflects a problem that the reliability of the model is poor.

Disclosure of Invention

The disclosure provides a method, a device, electronic equipment and a storage medium for fusing questions, so that the fusion of the questions is realized, and the reliability of a question-answering model is improved.

In a first aspect, an embodiment of the present disclosure provides a problem fusion method, including:

Displaying a fusion page, wherein the fusion page comprises a target question display area, a to-be-fused question display area and an answer display area, the target question display area is internally provided with a target question, the to-be-fused question display area is internally provided with a to-be-fused question to be fused with the target question, and the answer display area is internally provided with an answer corresponding to the target question;

Responding to the adjustment operation of the answers in the answer display area, and displaying the adjusted answers in the answer display area;

And responding to the triggering operation of the fusion control in the fusion page, displaying a fusion result for question-answer model training, wherein the fusion result indicates that the answers of the questions to be fused and the target questions are target answers, and the target answers are answers determined based on the adjusted answers.

In a second aspect, an embodiment of the present disclosure further provides a problem fusion apparatus, including:

The first display module is used for displaying a fusion page, the fusion page comprises a target question display area, a to-be-fused question display area and an answer display area, the target question display area is internally provided with a target question, the to-be-fused question display area is internally provided with a to-be-fused question to be fused with the target question, and the answer display area is internally provided with an answer corresponding to the target question;

the second display module is used for responding to the adjustment operation of the answers in the answer display area and displaying the adjusted answers in the answer display area;

And the third display module is used for responding to the triggering operation of the fusion control in the fusion page, displaying a fusion result used for training the question-answer model, wherein the fusion result indicates that the answers of the questions to be fused and the target questions are target answers, and the target answers are answers determined based on the adjusted answers.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, including:

one or more processing devices;

Storage means for storing one or more programs,

The one or more programs, when executed by the one or more processing devices, cause the one or more processing devices to implement a problem fusion method as provided by embodiments of the present disclosure.

In a fourth aspect, the disclosed embodiments also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing a problem fusion method as provided by the disclosed embodiments.

According to the embodiment of the disclosure, through displaying a fusion page, the fusion page comprises a target question display area, a question to be fused display area and an answer display area, wherein a target question is displayed in the target question display area, a question to be fused with the target question is displayed in the question to be fused display area, and an answer corresponding to the target question is displayed in the answer display area; responding to the adjustment operation of the answers in the answer display area, and displaying the adjusted answers in the answer display area; and responding to the triggering operation of the fusion control in the fusion page, displaying a fusion result for training the question-answer model, wherein the fusion result indicates that the questions to be fused and the answers of the target questions are target answers, and the target answers are answers determined based on the adjusted answers, so that the problem that different answers are output according to different question methods of the same question is solved.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a flow chart of a problem fusion method provided by an embodiment of the present disclosure;

FIG. 2 is a flow chart of yet another problem fusion method provided by an embodiment of the present disclosure;

FIG. 3 is an interface schematic diagram of a fused page provided by an embodiment of the present disclosure;

FIG. 4 is a schematic illustration of an interface for adding pages provided by embodiments of the present disclosure;

Fig. 5 is a schematic page diagram of a page to be classified according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a processing page provided by an embodiment of the present disclosure;

FIG. 7 is an interface schematic of a question summary page provided by an embodiment of the present disclosure;

FIG. 8 is an interface diagram of a delete acknowledgement page provided by an embodiment of the present disclosure;

FIG. 9 is a schematic diagram of a problem fusion device according to an embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The answer effects of the model used by the AI application are closely related to the data set used to train the model. The data set may include documents uploaded by the user and question-answer pairs filled in by the user. The system where the question fusion method is located can be a system for realizing question-answering model training set processing, and the user can be a user of the system, and the training set is processed through the system, such as input, modification and the like. For example, the user can input the question and answer pair through the system. When the user of the system performs question and answer pair recording, the question can be rapidly recorded in the form of uploading a document and/or the question and answer pair.

When one user uploads a plurality of questions through the system, the control questions can be homogenized, but when n users with different roles upload different questions, the problem homogenization phenomenon exists, namely, one question has a plurality of question methods and a plurality of answers. Exemplary:

user a asks: what the designer's responsibility is. Answer: the designer's responsibility is to solve the user problem.

Asking user B: what kind of responsibilities the designer has. Answer: the designers are classified into product designers, interface designers, brand designers, etc., and the responsibility of the product designers is to analyze the product and then produce an effect map.

User C asks: the designer can play what role. Answer: the responsibility of the designer is mainly to beautify the page.

In such a case, if the questions are not interfered, the user may put forth a plurality of questions about the same question, and the answers may be different, so that the use effect of the user may be affected and the use desire of the user may be reduced.

In order to solve the above technical problems, the present disclosure provides a problem fusion method. Fig. 1 is a schematic flow chart of a problem fusion method provided by an embodiment of the present disclosure, where the embodiment of the present disclosure is applicable to a situation where problem fusion is performed, the method may be implemented by a problem fusion apparatus, where the apparatus may be implemented in a form of software and/or hardware, and optionally, implemented by an electronic device, where the electronic device may be a mobile terminal, a PC side, a server, or the like.

As shown in fig. 1, the method includes:

s110, displaying the fusion page.

The fused page may be considered as a page for problem fusion. The fusion page comprises a target question display area, a to-be-fused question display area and an answer display area, wherein a target question is displayed in the target question display area, a to-be-fused question to be fused with the target question is displayed in the to-be-fused question display area, and an answer corresponding to the target question is displayed in the answer display area.

The target question display area may be regarded as an area in which the target question is displayed. The question to be fused display area may be regarded as an area in which the question to be fused is displayed. The answer display area may be regarded as an area in which an answer is displayed.

The target question displayed in the target question display area may be one. The number of questions to be fused displayed in the question display area may be at least one. The answer displayed in the answer display area may be an answer to the target question.

The target problem may be a standard problem, among others. Such as a question in a standard format or in a standard question-asking manner. The target problem can be automatically recommended by the system where the problem fusion method is located, or can be selected by a user. The problem to be fused may be regarded as a problem to be fused with the target problem. The problem to be fused may be a problem that is repeated with the target problem, or may be a similar problem to the target problem.

The dataset is the basis for model training, which contains a large amount of sample data for model learning and understanding. A high quality data set may help the model learn more knowledge and patterns, thereby improving accuracy of the answers. The dataset includes a series of questions and answers corresponding thereto, referred to as question-answer pairs.

Reliability of a question-answer model refers to the ability of the model to give consistent, accurate, and trusted answers under different circumstances. The consistency of the question-answer model is that for the same or similar inputs, the model should give consistent answers, avoiding random or unstable results. Question-answering model an artificial intelligence technique for processing and answering questions posed by natural language. The question-answering model is based on machine learning and natural language processing techniques, by training a large number of question-answering pairs, learns how to understand questions and generates corresponding answers.

The number of users using the system can be multiple, different users can enter answer pairs through the system, so the system can have repeated problems, different people can have different description modes aiming at the same problem, and similar problems can exist in the system. Similar problems can be considered to be similar problems that are semantically identical to standard problems, but in a different expression. The repetition problem may be exactly or almost the same.

In order to improve reliability and consistency of the question-answer model, the method and the device can fuse the to-be-fused problem with the target problem. The questions to be fused may include, among other things, duplicate questions that duplicate the target question and similar questions that are similar to the target question. The answers to the repeated questions should be the same and the answers to the similar questions may be different.

The method and the device can take the problem which should have the same answer with the target problem as the problem to be fused with the target problem, and enable the description of the normalized answer through fusing the problem to be fused.

And S120, responding to the adjustment operation of the answers in the answer display area, and displaying the adjusted answers in the answer display area.

The adjustment operation may be an operation of adjusting the answer. The manner of operation of the adjustment operation is not limited here. If the control is clicked, a corresponding answer is generated as an adjusted answer after the control is triggered. And adjusting the answers, for example, by editing the answers in the answer display area.

After the adjustment operation is obtained in the present disclosure, the adjusted answer may be displayed in the answer display area, so as to be convenient for the user to view.

And S130, responding to the triggering operation of the fusion control in the fusion page, and displaying a fusion result for question-answer model training.

The fusion control may be a control that triggers fusion of the questions to be fused. The triggering operation is not limited, and may be a clicking operation on the fusion control. And the fusion result indicates that the answer of the to-be-fused question and the target question is a target answer, and the target answer is an answer determined based on the adjusted answer.

The fusion result indicates that the to-be-fused question and the target question are fused, and the two answers are fused into the target answer. The target answer may be an answer trained by a question-answer model. The question-answer model may be an answer that is determined based on the adjusted answer. If the adjusted answer is directly used as the target answer. And as a target answer after the color is moistened on the basis of the adjusted answer.

The embodiment does not limit the page displaying the fusion result, and can be a page representing the completion of fusion or an updated problem summary page for selecting the target problem. A plurality of questions are displayed in the question summary page, which may include all of the questions used to train the question-answering model. Among the multiple questions may be the target questions for which fusion results have been obtained.

According to the technical scheme, through displaying a fusion page, the fusion page comprises a target question display area, a to-be-fused question display area and an answer display area, a target question is displayed in the target question display area, a to-be-fused question to be fused with the target question is displayed in the to-be-fused question display area, and an answer corresponding to the target question is displayed in the answer display area; responding to the adjustment operation of the answers in the answer display area, and displaying the adjusted answers in the answer display area; and responding to the triggering operation of the fusion control in the fusion page, displaying a fusion result for training the question-answer model, wherein the fusion result indicates that the questions to be fused and the answers of the target questions are target answers, and the target answers are answers determined based on the adjusted answers, so that the problem that different answers are output according to different question methods of the same question is solved.

On the basis of the above embodiments, modified embodiments of the above embodiments are proposed, and it is to be noted here that only the differences from the above embodiments are described in the modified embodiments for the sake of brevity of description.

In one embodiment, the displaying the adjusted answer in the answer display area in response to the adjustment operation of the answer in the answer display area includes:

And responding to the triggering operation of the target control in the answer display area, and displaying the answer corresponding to the target control as an adjusted answer in the answer display area.

The target control may be a control for switching answers. The triggering operation of the target control is not limited, and may be, for example, clicking on the target control. The answer display area can display a plurality of controls, the control clicked by the user can be a target control, different controls correspond to different answers, and different answer generation modes are different. After the target control is clicked, the answer corresponding to the target control can be displayed in the answer display area as the adjusted answer. If the target control is a control with the function of regenerating the answer, after the target control is triggered, the answer of the target question can be regenerated, and the regenerated answer is used as the adjusted answer.

Fig. 2 is a flowchart of another method for question fusion according to an embodiment of the present disclosure, where the operation of answer adjustment is refined, and the method for question fusion includes the following operations:

s210, displaying the fusion page.

S220, responding to an answer checking operation of the target to-be-fused questions in the to-be-fused questions, and displaying the answers of the target to-be-fused questions.

The target to-be-fused problem can be the to-be-fused problem for answer viewing in the to-be-fused problem. The answer viewing operation may be regarded as an operation of making an answer view. Each question to be fused has a corresponding answer. The operation can acquire the answer checking operation of the target to-be-fused problem in the to-be-fused problems, and display the answer of the target to-be-fused problem. And checking the answers of the target questions to be fused in the fusion page.

And the answer adjusting operation is an operation of adjusting the answer in the answer display area by referring to the answer of the target to-be-fused question.

The answer in the auxiliary answer display area is conveniently adjusted by displaying the answers of the target questions to be fused. The user can adjust the answer of the target question by referring to the answer of the target question to be fused. The adjustment operation can also be automatically realized, and the answer of the target question is optimized by referring to the answer of the target question to be fused.

S230, responding to the adjustment operation of the answers in the answer display area, and displaying the adjusted answers in the answer display area.

S240, responding to the triggering operation of the fusion control in the fusion page, and displaying a fusion result for question-answer model training.

When the answer in the answer display area is adjusted, the adjusted answer quality can be better by displaying the answer of the target to-be-fused question and assisting the adjustment of the answer in the answer display area.

In one embodiment, before responding to the triggering operation of the fusion control in the fusion page, the method further comprises the following steps:

responding to the triggering operation of the adding control in the to-be-fused problem display area, and displaying an adding page;

and responding to the adding operation of the problem to be added in the adding page, and displaying the problem to be added to the problem display area to be fused.

The add control may be considered a control that triggers the addition of a question to be fused. The add page may be a page that implements the addition of the question to be fused. The question to be added may be regarded as a question selected as a newly added question to be added. Also known as questions to be added to the question to be fused display area. After the problem to be added is added to the problem to be fused display area, the problem to be fused can be used as the problem to be fused and fused with the target problem.

The adding operation may be regarded as an operation to effect addition of the question to be added. After the adding operation is triggered, the to-be-added problem can be added to the to-be-fused problem display area.

Fig. 3 is an interface schematic diagram of a fusion page provided by an embodiment of the present disclosure, and fig. 4 is an interface schematic diagram of an add page provided by an embodiment of the present disclosure, referring to fig. 3, the fusion page includes a target question display area 1, a question to be fused display area 2, and an answer display area 3. After the addition control 21 in the fusion question display area 2 is triggered, an addition page may be displayed, see fig. 4, which includes the candidate area 4 and the selected area 5. The candidate area 4 includes a question to be selected, the question to be selected can be displayed in the selected area 5 as a question to be added after being selected, and the adding operation of the question to be added can be considered to be completed after the confirmation control 6 is triggered in the adding page. And further, the to-be-added problem can be added to the to-be-fused problem display area.

The default display in the answer display area is the best answer, and the user can display a specific answer in the answer by clicking to view the answer. The user clicks the original answer control, so that the answer of the target question can be displayed, and the user clicks the regeneration control, so that the answer generated by the artificial intelligence technology can be displayed. The optimum criteria are not limited herein.

Clicking the fusion control by the user can integrate the target questions and all answers of the questions to be fused into one answer, wherein the answer is an answer in the input box.

In one embodiment, the method for fusing pages provided by the present disclosure further includes:

displaying a page to be classified, wherein the page to be classified is displayed with a plurality of question-answer pairs to be solved;

responding to the processing operation of the target to-be-solved question-answer pair in the to-be-solved question-answer pair, and displaying a processing page;

and responding to the input operation of the generation reason of the target to-be-solved question-answer pair in the processing page, and displaying a processing result page.

The page to be classified can be regarded as a page for classifying reasons of the question-answer pair to be solved. The question-answer pair to be solved may be regarded as a question-answer pair with a problem to be solved. If the answer in the question-answer pair to be solved is not in line with expectations. The manner in which the page to be classified displays the plurality of question-answer pairs to be solved is not limited, for example, the question-answer pairs to be solved can be displayed in a form of a table. The problems displayed on the pages to be classified can be characterized by different table entries to judge whether the reason classification is carried out. If the reason classification has been performed on the question-answer pair to be solved, the state can be changed to processed.

The target question-answer pair may be considered to be the currently processed question to be solved in the question-answer pair. The processing operation may be an operation that triggers a processing objective to solve a problem, such as an operation of clicking a processing control.

The processing page may be regarded as a page for which the cause of the target problem to be solved is filled out. The target to-be-solved question-answer pair generation cause may be regarded as the target to-be-solved question-answer pair generation cause. The input operation may be considered as an operation for the cause of the output generation, and the specific operation mode of the input operation is not limited, and may be selected or filled. The processing result page may be regarded as a page of the processing result of the target to-be-solved question-answer pair.

Fig. 5 is a schematic page diagram of a page to be classified according to an embodiment of the present disclosure, referring to fig. 5, an operation in which the manual processing control 7 is triggered in the page to be classified may be regarded as a processing operation on a target answer pair, where a problem in the target answer pair may be "how much the database links are too many" in the first row in the table. The content of each item in the page to be classified is not limited, and may include a question and answer pair to be solved, which is composed of a question and an answer. The method may further include a number of entries of similar questions similar to the question, and may further include entries of a reason classification corresponding to the question to be solved, the reason classification may indicate a reason for the question to be solved. A status entry may also be included, the status indicating whether the pending question-answer pair was used by the question-answer model training. A creation schedule item may also be included, and the creation time may indicate a time at which the corresponding problem pair to be solved was created. And may include an operation list, and operations may include various operations, such as manual processing of the control 7.

In one embodiment, the processing page displays the target to-be-solved question-answer pair, or the processing page displays the target to-be-solved question-answer pair and a question-answer pair repeated with the target to-be-solved question-answer pair.

Only the target to-be-solved question-answer pair can be displayed in the processing page, and the target to-be-solved question-answer pair and the question-answer pair repeated with the target to-be-solved question-answer pair can be displayed. Question-answer pairs that repeat with the target to-be-solved question-answer pair may be question-repeat. If the question pair which is repeated with the question in the target question-answer pair belongs to the answer pair.

The embodiment can display the content corresponding to the control through selecting different controls.

Fig. 6 is a schematic diagram of a processing page provided by an embodiment of the present disclosure, and referring to fig. 6, the processing page includes a control corresponding to only a current problem and a control corresponding to the current problem and all repeated problems. Only the control corresponding to the current problem is selected, and only the target problem to be solved can be displayed in the processing page. After the controls corresponding to all the repeated questions are selected, the target to-be-processed question-answer pairs and the question-answer pairs repeated with the target to-be-solved question-answer pairs can be displayed in the processing page. In fig. 6, the controls corresponding to all the repeated questions are selected, and the target to-be-processed question-answer pair and the repeated question-answer pair with the target to-be-solved question-answer pair are displayed. Each target to-be-solved question-answer pair displayed on the processing page can display similar problems similar to the target to-be-solved question-answer pair through a drop-down option.

The filling of the cause of the generation can be implemented in the processing page, for example by clicking or filling in. After the reason is input, the reason can be used as a target to-be-solved question-answer pair and a question-answer pair repeated with the target to-be-solved question-answer pair. The input of the reasons for each question and answer is realized by processing one input of the page.

In one embodiment, the problem fusion method further comprises:

responding to the association operation of the target to-be-solved question-answer pair in the to-be-solved question-answer pair, and displaying an association page;

and setting a question-answer pair associated with the to-be-solved question-answer pair in the associated page.

The association operation may be regarded as an operation of performing problem association. The associated page may be considered as a page for problem association. The embodiment can set the question-answer pair associated with the question-answer pair to be solved in the associated page. Through the association of the question-answer pairs, when the question-answer model is used for answering the target to be solved, the questions of the question-answer pairs associated with the question-answer pairs to be solved can be displayed to the user for the user to select whether to input the questions of the associated question-answer pairs so as to present the answers of the associated question-answer pairs. I.e. to implement a recommendation of the associated problem.

The display content of the associated page is not limited herein, and for example, selection of a data set, selection of a question similar to the selected question, and editing and display of an answer may be implemented.

In one embodiment, the displaying the fused page includes:

displaying a question summary page, wherein at least one question is displayed in the question summary page;

And responding to the fusion operation of the target problem in the at least one problem, and displaying a fusion page.

The question summary page may be considered a page of question summary in question pairs for use in training a question-answer model. The questions displayed on the question summary page can be used for question and answer model training.

The fusing operation of the target problem may be an operation of fusing the problem to be fused corresponding to the target problem. The operation manner of the fusion operation is not limited, and may be, for example, a click operation on the corresponding control.

And realizing fusion operation in the problem summary page by clicking a fusion control, and displaying the fusion page.

Fig. 7 is an interface schematic diagram of a question summary page provided in an embodiment of the present disclosure, referring to fig. 7, in which included questions may be shown in a table manner, and entries included in the question summary page are not limited, and may include standard questions, quality scores, number of duplicate questions, source, enabled status, creator, last update time, question status, and operation. After the fusion control in the fusion page is triggered, the number of repeated questions in the question summary page can be updated to 0. And setting ash of a fusion control of the corresponding target problem in the problem summary page, and changing the problem state into processed.

All questions in the question-answer pair for question-answer model training can be displayed as standard questions. The quality score may be a score value after quality scoring of question-answer pairs. The number of repeat questions may be the number of repeat questions that repeat with the standard questions. The source may be a source of question-answer pairs. The enablement state can characterize whether the corresponding question-answer pair is used for question-answer model training. In the case that the enabling state is enabled, the corresponding question-answer pair can be used for question-answer model training. The creator may be a user who creates a question-answer pair. The last update time may be the time of the question-answer pair last update. The question state may be a state that characterizes whether the question is handled, and if so, a fused state. The operation may be to operate on the standard questions, the content of the operation may be to edit the standard questions, ignore the standard questions, and fuse the standard questions. After the fusion control 8 is triggered, a fusion page may be displayed.

Wherein the quality scoring may be scoring the quality of the corresponding question-answer pair by selecting a question state and a question source.

In one embodiment, the problem fusion method further comprises:

responding to the deleting operation of the problem to be deleted in the at least one problem, and displaying a deleting confirmation page;

Responding to the triggering operation of the multi-selection control in the deletion confirmation page, and displaying the to-be-deleted problem and the problem repeated with the to-be-deleted problem;

And deleting the to-be-deleted problem and the problem repeated with the to-be-deleted problem in response to the triggering operation of the deletion control in the deletion confirmation page.

The questions to be deleted may be pages to be deleted in at least one question in the question summary page. The delete operation may be considered as an operation that triggers the deletion of the question to be deleted, and the manner of operation is not limited herein, such as an operation of clicking the delete control. The deletion confirmation page may be a page for which deletion confirmation of the question to be deleted is performed.

The multiple-choice control may be a control for displaying a plurality of questions, such as displaying a question to be deleted and a question repeated with the question to be deleted, and each question may present a corresponding similar question by means of a drop-down.

The confirmation deleting control can be considered as a control for confirming the deletion of the problem to be deleted, and after the confirmation deleting control is triggered, the problem to be deleted and the problem repeated with the problem to be deleted can be deleted, so that the problem deleting efficiency is improved.

Fig. 8 is an interface schematic diagram of a deletion confirmation page provided by an embodiment of the present disclosure, and referring to fig. 8, the multi-selection control may be a control corresponding to a current problem and all repeated problems, where the current problem in fig. 8 may be a problem to be deleted. The questions to be deleted and the questions to be repeated with the questions to be deleted may be deleted after the deletion confirmation control 9 is triggered. The questions repeated with the questions to be deleted may also be selected by selecting whether the deletion confirmation page is deleted together by way of selection. And when only the control corresponding to the current problem is selected, the problem to be deleted can be displayed in the deletion confirmation page, and after the deletion confirmation control is triggered, the problem to be deleted can be deleted only.

The question summary page may also include an enable control and a disable control, the enable control may jump to an enable confirmation page after being triggered. The disable control can be adjusted to disable the confirmation page after being penalized. The interface schematic of enabling the confirmation page and disabling the confirmation control may be similar to that of fig. 8, e.g., may display only the current question that is enabled, or may display both the current question that is enabled and all questions that are repeated with the current question.

The repeated question page may be displayed after the repeated question control is triggered in the question summary page, and the displayed content of the repeated question page may be similar to that shown in fig. 8, which is not limited herein, so long as the repeated questions repeated with the target question can be displayed.

The question fusion method provided by the disclosure can improve the quality of question-answer pairs used for training a question-answer model. The repeat problem and the similar problem in the application can be automatically screened out by the model. By quality checking the question-answer pairs, the number of repeated questions is presented, and the user can fuse the repeated questions. When the repeated problems are fused, a fused page can be displayed in a drawer mode, and the target problem and the problem to be fused are displayed. And displaying the target questions, the questions to be fused and the answers through the fusion page, wherein the user can check the answers of each question, and the answers of all the questions to be fused are fused by taking the answers of the target questions as the reference. The answer to the target question may be an answer that has been rendered by artificial intelligence techniques. The user may view the original answer or regenerate the answer through artificial intelligence techniques. The answer first displayed by the fusion page may be the best answer to recommend. May be an artificial intelligence technology recommendation. The problems to be fused can be recommended through an algorithm, omission can occur, so that the problems to be added can be added through the operation of an adding control by a user, and the repeated problems are all selected. The problems to be fused can be divided into two types, one is automatically identified by the system, and the other is newly added by a user manually through adding a control.

Fig. 9 is a schematic structural diagram of a problem fusion device according to an embodiment of the present disclosure, as shown in fig. 9, where the device includes:

The first display module 910 is configured to display a fusion page, where the fusion page includes a target question display area, a question display area to be fused, and an answer display area, a target question is displayed in the target question display area, a question to be fused with the target question is displayed in the question display area to be fused, and an answer corresponding to the target question is displayed in the answer display area;

A second display module 920, configured to display an adjusted answer in the answer display area in response to an adjustment operation on the answer in the answer display area;

and the third display module 930 is configured to respond to a triggering operation of the fusion control in the fusion page, and display a fusion result for training the question-answer model, where the fusion result indicates that the answer of the question to be fused and the target question is a target answer, and the target answer is an answer determined based on the adjusted answer.

According to the technical scheme provided by the embodiment of the disclosure, the problem that different answers are output by different question methods aiming at the same problem is solved, and the to-be-fused problem and the target problem are fused, so that the answers of the to-be-fused problem and the target problem are unified into the target answer, and the reliability of the question-answer model is improved when the question-answer model is trained based on the target problem, the to-be-fused problem and the target answer.

In one embodiment, the second display module 920 is specifically configured to:

In one embodiment, the question fusion device further includes a fourth display module, configured to, before displaying the adjusted answer in the answer display area in response to the adjustment operation of the answer in the answer display area, display the answer of the target question to be fused in response to the answer check operation of the target question to be fused in the question to be fused, where the adjustment operation is an operation of adjusting the answer in the answer display area with reference to the answer of the target question to be fused.

In one embodiment, the question fusion device further includes a fifth display module, configured to display an add page in response to a trigger operation of an add control in the question display area to be fused before a fusion result for question-answer model training is displayed in response to a trigger operation of a fusion control in the fusion page;

In one embodiment, the problem fusion apparatus further includes a sixth display module specifically configured to:

In one embodiment, the problem fusion apparatus further includes a seventh display module configured to:

In one embodiment, the first display module is specifically configured to:

In one embodiment, the problem fusion apparatus further includes an eighth display module for:

The problem fusion device provided by the embodiment of the disclosure can execute the problem fusion method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

It should be noted that each unit and module included in the above apparatus are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for convenience of distinguishing from each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. Referring now to fig. 10, a schematic diagram of an electronic device (e.g., a terminal device or server in fig. 10) 500 suitable for use in implementing embodiments of the present disclosure is shown.

The electronic device 500 includes:

One or more processing devices 501;

storage 508, for storing one or more programs,

The one or more programs, when executed by the one or more processing devices 501, cause the one or more processing devices 501 to implement the problem fusion method as provided by the present disclosure.

The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 10 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.

As shown in fig. 10, the electronic device 500 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 501, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An edit/output (I/O) interface 505 is also connected to bus 504.

In general, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 508 including, for example, magnetic tape, hard disk, etc.; and communication means 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 10 shows an electronic device 500 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or from the storage means 508, or from the ROM 502. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 501.

The electronic device provided by the embodiment of the present disclosure and the problem fusion method provided by the foregoing embodiment belong to the same inventive concept, and technical details not described in detail in the present embodiment may be referred to the foregoing embodiment, and the present embodiment has the same beneficial effects as the foregoing embodiment.

The embodiment of the present disclosure provides a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the problem fusion method provided by the above embodiment.

It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two.

The computer storage medium may be a storage medium of computer executable instructions, which when executed by a computer processor, are for performing a method as provided by the present disclosure.

The computer readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to:

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules or units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The name of a module or unit is not limited to the unit itself in some cases, and for example, the first display module may also be described as a "fused page display module".

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, there is provided a problem fusion method [ example 1], comprising: displaying a fusion page, wherein the fusion page comprises a target question display area, a to-be-fused question display area and an answer display area, the target question display area is internally provided with a target question, the to-be-fused question display area is internally provided with a to-be-fused question to be fused with the target question, and the answer display area is internally provided with an answer corresponding to the target question;

According to one or more embodiments of the present disclosure, there is provided the method of example 1 [ example 2 ], the displaying, in the answer display area, the adjusted answer in response to an adjustment operation of the answer in the answer display area, including:

According to one or more embodiments of the present disclosure, there is provided the method of example 1, further comprising, in response to an adjustment operation of an answer in the answer display area, displaying the adjusted answer in the answer display area:

And responding to an answer checking operation of a target to-be-fused problem in the to-be-fused problems, displaying an answer of the target to-be-fused problem, wherein the adjusting operation is an operation of adjusting the answer in the answer display area by referring to the answer of the target to-be-fused problem.

According to one or more embodiments of the present disclosure, the method of example 1 is provided [ example 4 ], before displaying the fusion result for question-answer model training in response to a triggering operation of the fusion control in the fusion page, further comprising:

According to one or more embodiments of the present disclosure, there is provided the method of example 1 [ example 5 ], further comprising:

According to one or more embodiments of the present disclosure, the method of example 5 is provided [ example 6 ], the processing page displaying the target to-be-solved question-answer pair or the processing page displaying the target to-be-solved question-answer pair and a question-answer pair repeated with the target to-be-solved question-answer pair.

According to one or more embodiments of the present disclosure, there is provided the method of example 1 [ example 7 ], further comprising:

According to one or more embodiments of the present disclosure, there is provided the method of example 1, the displaying a fused page, comprising:

According to one or more embodiments of the present disclosure, there is provided the method of example 8 [ example 9 ], further comprising:

According to one or more embodiments of the present disclosure, there is provided a problem fusion apparatus [ example 10 ], comprising:

According to one or more embodiments of the present disclosure, there is provided an electronic device [ example 11 ], the electronic device comprising:

one or more processing devices;

Storage means for storing one or more programs,

When the one or more programs are executed by the one or more processing devices, the one or more processing devices are caused to implement the problem fusion method of any of examples 1-9.

According to one or more embodiments of the present disclosure, there is provided a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing the problem fusion method as described in any one of examples 1-9.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are example forms of implementing the claims.

Claims

1. A method of problem fusion, comprising:

2. The method of claim 1, wherein the displaying the adjusted answer in the answer display area in response to the adjusting operation of the answer in the answer display area comprises:

3. The method of claim 1, further comprising, prior to displaying the adjusted answer in the answer display area in response to the adjustment operation of the answer in the answer display area:

4. The method of claim 1, further comprising, prior to displaying the fusion result for question-answering model training in response to a triggering operation of a fusion control in the fusion page:

5. The method as recited in claim 1, further comprising:

6. The method of claim 5, wherein the processing page displays the target to-be-solved question-answer pair or the processing page displays the target to-be-solved question-answer pair and a question-answer pair repeated with the target to-be-solved question-answer pair.

7. The method as recited in claim 1, further comprising:

8. The method of claim 1, wherein displaying the fused page comprises:

9. The method as recited in claim 8, further comprising:

10. A problem fusion device, comprising:

11. An electronic device, the electronic device comprising:

one or more processing devices;

Storage means for storing one or more programs,

The one or more programs, when executed by the one or more processing devices, cause the one or more processing devices to implement the problem fusion method of any of claims 1-9.

12. A storage medium containing computer executable instructions for performing the problem fusion method of any of claims 1-9 when executed by a computer processor.