Question generation method and device, electronic equipment and storage medium

Abstract

Embodiments of the invention disclose a question generation method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining target information of a target object in a target cooperation platform; and determining an object label of the target object according to the target information, and generating a target question according to the object label so as to display the target question in a question display interface in the target collaboration platform. Personalized question generation in enterprise questions and answers can be realized, question query and solving efficiency can be improved, and use experience is improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a question generating method, device, electronic device, and storage medium. Background Art

[0002] In the related technologies, the question-answering system applied to enterprises can help enterprise employees quickly solve work-related problems, which is conducive to reducing enterprise operating costs. At present, the enterprise question-answering system generates the same questions for all employees, and cannot realize personalized question generation, which affects the efficiency of question query and solution, and the user experience is poor. Summary of the invention

[0003] The embodiments of the present disclosure provide a question generation method, device, electronic device and storage medium, which can realize personalized question generation in enterprise question and answer, improve the efficiency of question query and solution, and enhance the user experience.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for generating a question, comprising:

[0005] Obtain target information of target objects in the target collaboration platform;

[0006] According to the target information, an object tag of the target object is determined, and a target question is generated according to the object tag, so as to display the target question in a question display interface in the target collaboration platform.

[0007] In a second aspect, the present disclosure also provides a question generating device, including:

[0008] An information acquisition module, used to acquire target information of a target object in a target collaboration platform;

[0009] The question generation module is used to determine the object tag of the target object according to the target information, and generate a target question according to the object tag to display the target question in the question display interface in the target collaboration platform.

[0010] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0011] one or more processors;

[0012] a storage device for storing one or more programs,

[0013] When the one or more programs are executed by the one or more processors, the one or more processors implement the question generating method as described in any one of the embodiments of the present disclosure.

[0014] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the question generating method as described in any one of the embodiments of the present disclosure.

[0015] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, characterized in that the computer program product comprises a computer program, and when the computer program is executed by a processor, the question generating method as described in any one of the embodiments of the present disclosure is implemented.

[0016] In the technical solution of the embodiment of the present disclosure, the target information of the target object in the target collaboration platform can be obtained; according to the target information, the object label of the target object is determined, and the target question is generated according to the object label, so as to display the target question in the question display interface of the target collaboration platform. Compared with the related art that generates the same questions for all employees, the embodiment of the present disclosure can abstractly summarize the target object according to the target information to obtain the object label, and then determine the personalized target question according to the object label, so as to realize the generation of personalized questions in the enterprise question and answer, improve the efficiency of question query and solution, and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0018] Figure 1 A flowchart of a method for generating questions provided by an embodiment of the present disclosure;

[0019] Figure 2 A schematic diagram of a question display interface in a question generation method provided in an embodiment of the present disclosure;

[0020] Figure 3 A schematic diagram of the structure of a question generating device provided by an embodiment of the present disclosure;

[0021] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0023] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0024] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "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". The relevant definitions of other terms will be given in the following description.

[0025] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0026] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0028] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0029] Figure 1 A flowchart of a question generation method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to the situation of question generation in an enterprise question-and-answer scenario. The method can be executed by a question generation device, which can be implemented in the form of software and / or hardware, and the device can be configured in an electronic device, for example, in a server of an enterprise collaboration platform.

[0030] like Figure 1 As shown, the question generation method provided in this embodiment may include:

[0031] S110: Acquire target information of a target object in a target collaboration platform.

[0032] In the disclosed embodiments, the target collaboration platform can be considered as an enterprise collaboration platform, which can provide multi-functional support for enterprise employees to work together. Exemplarily, the target collaboration platform can provide enterprise employees with functional support such as timely communication, scheduling, multimedia conferencing, collaborative documents, task flow and transaction approval. Among them, the target object in the target collaboration platform may include an account for logging into the target assistance platform. Among them, the target information of the target object may include information related to the account.

[0033] Wherein, obtaining the target information of the target object in the target collaboration platform may include: sending an information authorization request to the target object; and obtaining the target information of the target object in the target collaboration platform in response to receiving an authorization pass message sent by the target object.

[0034] By sending an information authorization request to the target object, the user corresponding to the target object can be clearly prompted that the operation of question generation in the question-and-answer service provided by the target collaboration platform will need to obtain and use information related to the target object. Thus, the user can independently choose whether to provide relevant information to the device that executes the technical solution of the present disclosure according to the prompt. Exemplarily, in some implementations, the method of sending an information authorization request to the target object can be, for example, a pop-up window, in which the information authorization request can be presented in text. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide relevant information, for the user to choose.

[0035] In the case of receiving the authorization approval message of the target object, it can be considered that the authorization of the user corresponding to the target object for obtaining and using the target information has been obtained, and then the target information can be obtained. It can be understood that the above notification and user authorization acquisition process are only illustrative, and other methods that meet relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0036] It can be considered that the target information involved in the embodiments of the present disclosure is information obtained after informing the target object and obtaining the target object's authorization, and the target information is authorized to be used for generating questions in the question-and-answer service provided for the target object in the target collaboration platform.

[0037] In some implementations, the target information may include information in at least one of the following dimensions: document dimension, conversation dimension, meeting dimension, basic data dimension, and device dimension, region dimension, and time dimension for logging into the target collaboration platform.

[0038] Among them, the target information of the document dimension may include the content of documents related to the target object, such as the content of documents browsed, edited, annotated, shared and shared by the target object; the target information of the conversation dimension may include messages of conversations related to the target object, such as single-person conversation messages and multi-person conversation messages of the target object; the target information of the meeting dimension may include information of meetings related to the target object, such as meeting records, meeting minutes and meeting attributes (such as meeting duration, meeting theme and meeting creator, etc.) of meetings participated by the target object; the target information of the basic data dimension may include the position and rank corresponding to the target object; the target information of the device dimension for logging into the target collaboration platform may include mobile terminals and computer terminals, the target information of the region dimension may include office areas in different regions of the enterprise, and the target information of the time dimension may include working days, holidays, mornings, afternoons and evenings, etc.

[0039] In these implementations, the target information of the document dimension, the conversation dimension, and the meeting dimension can help understand the target object's work content, the target information of the basic data dimension can help understand the target object's role in the company to which it belongs, and the equipment dimension, the region dimension, and the time dimension can help understand the target object's current office environment. In addition, the target information can also cover other dimensional information of the target object in the company to which it belongs, which are not exhaustive here.

[0040] In the embodiments of the present disclosure, different preset time intervals can be configured according to the change frequency of target information of different dimensions, so that the target information of the corresponding dimensions can be obtained at preset time intervals. In addition, the target information can be actively obtained through the corresponding interface in response to the change message of the target information of some dimensions. It is worth noting that the target information involved in the present disclosure should be obtained and used in an appropriate manner in accordance with relevant laws and regulations.

[0041] By obtaining the target information of the target object, the questions that the target object may search for can be attributed to improve the accuracy of predicting the target questions of the target object.

[0042] S120: Determine an object tag of the target object according to the target information, generate a target question according to the object tag, and display the target question in a question display interface in the target collaboration platform.

[0043] In the embodiment of the present disclosure, the object tag may be considered as a work-related tag of the target object and may be used to characterize the cause of the problem that the target object may search for.

[0044] In some implementations, the object label may include a label of at least one of the following dimensions: role dimension, industry background dimension, first skill dimension, and second skill dimension. In these implementations, the object label of the role dimension may include a label obtained by combining information of other dimensions based on the information of the basic data dimension, such as a project leader who often travels. The object label of the industry background dimension may include a label obtained by classifying the industry background according to the target information, such as ×× field in the Internet industry. The object label of the first skill dimension may be set according to the needs of the enterprise, for example, it may include but is not limited to core skills, technology trends, skill application fields, and field market dynamics. Among them, the object labels of the role dimension, industry background dimension, and first skill dimension can be considered as strong work-related labels. The object label of the second skill dimension may include labels of other skill dimensions that are further expanded on the basis of the first skill dimension of the target object. The second skill label can be considered as a label that is weakly work-related to the target object, but has a meaningful improvement on the work.

[0045] In the disclosed embodiments, the target information may be information in a textual modality; accordingly, the target information may be subjected to text understanding, abstraction, and summary through existing text understanding techniques (such as traditional text processing methods or machine learning models, etc.) to determine the object label of the target object. In some implementations, determining the object label of the target object according to the target information may include: determining the object label of the target object according to the target information through a preset generation model. In these implementations, the preset generation model may include a machine learning model with text understanding, abstraction, and summarization capabilities, which may be supervised and trained through sample target information and sample object labels so that the preset generation model has the ability to determine the object label based on the target information. Accordingly, the target information may be input into the preset generation model so that it outputs an object label, which may improve the processing efficiency of the target information.

[0046] In the embodiment of the present disclosure, the tag set to which the object tag belongs may contain hundreds or thousands of tags, and the object tag of the target object may include at least one of them. Among them, the target question can be generated based on at least one tag in the object tag. Exemplarily, the generation of the target question based on one object tag is given as follows: when the tag of the role dimension is "project leader", "how is the progress of the × project" can be determined as the target question. The generation of questions based on multiple tags is given as follows: when the object tag of the first skill dimension contains "× skill" and "× field", "how is the × skill applied in the × field" can be determined as the target question, etc. In this embodiment, the target question can be generated based on at least one object tag through the existing text-based text generation method. Since the object tag can characterize the reasons for the problem that the target object may search for, by generating the target question based on the object tag, personalized question generation can be achieved, the accuracy of question generation can be improved, and thus the user experience can be improved. Among them, after the target object logs in to the target collaboration platform, the target question generated based on the target information of the target object can be displayed through the question display interface in the target collaboration platform. In some implementations, the question display interface may include, but is not limited to, a conversation interface of an intelligent assistant provided by the target collaboration platform, an information search interface or a document interface provided by the target collaboration platform. By setting up a variety of question generation interfaces and increasing the number of question search entries, users can quickly query questions in different business scenarios, which can further improve the user experience.

[0047] For example, Figure 2 A schematic diagram of a question display interface in a question generation method provided by an embodiment of the present disclosure. Figure 2 After the target object logs in to the target collaboration platform, it can access the "Knowledge Question and Answer" function interface (which can be considered as an information search interface). The question display interface can obtain at least one target question generated by the question generation device deployed on the server, and can display the question in a preset manner (such as Figure 2 At least one target question is displayed by flattening question cards 210).

[0048] In some optional implementations, the question generation method may further include: generating a target answer to the target question based on the target information, so that when the question display interface receives a query instruction for the target question, the corresponding target answer is displayed.

[0049] After generating the target question of the target object, the question generating device can also generate the target answer according to the target information of the target object. Figure 2, the question display interface can not only display the target question, but also display at least part of the target answer content simultaneously. Among them, the query instruction can be generated by triggering the target question displayed in the interface, and then the content of the target answer corresponding to the target question can be fully displayed. In addition, if Figure 2 As shown, the target question in the question display interface can also serve as a reference for question examples. The query control 220 in the question display interface can receive questions input by the user, and generate and display corresponding target answers based on the target information of the target object.

[0050] In these optional implementations, a target answer corresponding to the target question can be further generated based on the target information, so that the question display interface can complete the question query by triggering the target question, which is conducive to improving the efficiency of question query and resolution and further improving the user experience.

[0051] In the technical solution of the embodiment of the present disclosure, the target information of the target object in the target collaboration platform is obtained; based on the target information, the object tag of the target object is determined, and the target question is generated based on the object tag, so as to display the target question in the question display interface in the target collaboration platform. Compared with the related art that generates the same questions for all employees, the embodiment of the present disclosure can abstractly summarize the target object according to the target information to obtain the object tag, and then determine the personalized target question according to the object tag, so as to realize the generation of personalized questions in the enterprise Q&A, improve the efficiency of question query and solution, and improve the user experience.

[0052] The various optional schemes in the question generation method provided in the embodiment of the present disclosure and the above embodiment can be combined. The question generation method provided in the present embodiment describes in detail the process of generating target questions based on object tags. In the embodiment of the present disclosure, the target question can be generated by a preset language model, a preset template, a preset label-question correspondence, and a method of matching questions or similar users based on object tags, which can realize flexible and diverse generation of target questions, improve the richness and accuracy of question generation, and improve user experience.

[0053] In the question generation method provided in this embodiment, generating a target question based on an object label may include at least one of the following: generating a target question based on an object label through a preset language model; generating a target question based on an object label and a preset template containing a placeholder identifier; generating a target question based on an object label and a preset label-question correspondence; obtaining first historical question data that matches the object label, and generating a target question based on the first historical question data; determining similar objects of the target object from a target collaboration platform based on the object label, and generating a target question based on second historical question data of the similar objects.

[0054] The preset language model may include a large language model (LLM). The preset language model may be constructed by further fine-tuning based on sample object labels and sample target questions on the basis of the existing language model pre-built based on a massive corpus. Furthermore, the object label may be input into the preset language model, and the target question may be generated according to at least one label in the object label through the preset language model.

[0055] Among them, the preset template may include question templates pre-set for different dimensional tags, and the preset template may include at least one placeholder. Among them, according to the dimension of the object tag, a target template matching at least one tag in the object tag can be determined from the preset template, and at least one tag can replace the placeholder in the target template to obtain the target question. Exemplarily, in the case where at least one tag includes "× field", "What new technologies are there in the field of [placeholder] recently" can be used as the target template, and "× field" can replace "[placeholder]" to obtain the target question "What new technologies are there in the field of × recently".

[0056] Among them, corresponding questions can be pre-set for the tags in the tag set, and the correspondence between the tags and the corresponding questions (i.e., the tag-question correspondence) can be stored in a preset manner (such as a table, etc.). Furthermore, the question corresponding to at least one tag in the object tag can be searched from the preset tag-question correspondence to obtain the target question. Among them, generating the target question based on the preset tag-question correspondence can be used as a fallback cold start strategy for question generation.

[0057] After the target question is queried, a corresponding relationship between it and the corresponding object tag can be established. After obtaining the object tag of the target object, the target question (i.e., the first historical question data) of the historical query corresponding to at least one tag in the object tag can be obtained first; then the first historical questions can be sorted according to the query popularity (such as the total number of queries or the number of queries within a preset time period, etc.); finally, the first preset number of first historical questions in the sorting can be used as the target question.

[0058] Among them, the similarity of the object labels of each target object in the target collaboration platform can also be determined based on the existing label similarity calculation method, and the similar objects of each target object can be determined according to the similarity. Among them, the similar objects can include at least one. Furthermore, the target question can be generated according to the target question of the historical query of the similar object (i.e., the second historical question data). For example, the second historical question data can be directly used as the target question, and the target question that the target object has historically queried in the second historical question data can be filtered to obtain the target question, etc., which are not exhaustive here.

[0059] In the disclosed embodiment, target questions can be generated by using a preset language model, a preset template, a preset label-question correspondence, and a method of matching questions or similar users based on object labels. This allows for flexible and diverse generation of target questions, improves the richness and accuracy of question generation, and improves user experience.

[0060] In some optional implementations, generating a target question based on object tags through a preset language model may include: obtaining at least one target tag from the object tags, and determining a keyword based on the target tag; generating prompt words based on the keyword and a preset question type library; and generating a target question based on the prompt words through a preset language model.

[0061] Among them, one target tag can be used as a subject word, or a combination of at least two target tags can be used as a subject word. Among them, the preset question type library can include examples of questions with better questioning methods, and the preset question type library can be used to guide the preset language model to perform in-context learning to generate target questions with better questioning methods. Among them, prompt words can be generated according to the subject words and the question type library by means of prompt engineering. By inputting prompt words into the preset language model, the preset language model can output higher quality target questions.

[0062] In these optional implementations, by generating prompt words based on one target tag, generation of target questions involving the privacy of the target object can be avoided; by generating prompt words based on at least two target tags, the accuracy of the target question can be improved.

[0063] In some optional implementations, after generating a target question according to the prompt word, it may also include: performing quality classification on the target question through a preset classification model; wherein the result of the quality classification displayed in the question display interface belongs to the target question of the target classification.

[0064] In these optional implementations, a preset classification model can be pre-built based on sample target questions and corresponding quality classification truth values. Among them, the quality classification can include quality pass and quality fail. Among them, the classification of quality fail may include, for example, but not limited to sensitive classes and semantically unclear classes. Among them, the target classification may include quality pass classification. The preset classification model can be used to check the quality of the target questions, and publicly acceptable, clear and meaningful high-quality questions can be displayed as target questions on the question display interface to improve the user experience.

[0065] The technical solution of the disclosed embodiment describes in detail the process of generating target questions based on object tags. In the disclosed embodiment, the target questions can be generated by preset language models, preset templates, preset label-question correspondences, and matching questions or similar users based on object tags, which can achieve flexible and diverse generation of target questions, improve the richness and accuracy of question generation, and improve user experience. The question generation method provided in the disclosed embodiment and the question generation method provided in the above embodiment belong to the same disclosed concept. The technical details not described in detail in the present embodiment can be referred to the above embodiment, and the same technical features have the same beneficial effects in the present embodiment and the above embodiment.

[0066] Figure 3 The following is a schematic diagram of a question generation device provided in an embodiment of the present disclosure. The question generation device provided in this embodiment is suitable for question generation in an enterprise question-answering scenario.

[0067] like Figure 3 As shown, the question generating device provided by the embodiment of the present disclosure may include:

[0068] The information acquisition module 310 is used to acquire target information of a target object in a target collaboration platform;

[0069] The question generation module 320 is used to determine the object label of the target object according to the target information, and generate a target question according to the object label to display the target question in the question display interface in the target collaboration platform.

[0070] In some optional implementations, the question generation module may be used to perform at least one of the following:

[0071] Generate target questions based on object labels through a preset language model;

[0072] Generate target questions based on object labels and preset templates containing placeholders;

[0073] Generate the target question based on the object label and the preset label-question correspondence;

[0074] Acquire first historical question data matching the object label, and generate a target question based on the first historical question data;

[0075] According to the object label, similar objects of the target object are determined from the target collaboration platform, and a target question is generated according to the second historical question data of the similar objects.

[0076] In some optional implementations, the question generation module may be used to:

[0077] Obtain at least one target tag from the object tags, and determine a topic word according to the target tag;

[0078] Generate prompt words based on subject words and preset question type library;

[0079] Generate target questions based on prompt words through the preset language model.

[0080] In some optional implementations, the question generation module may also be used to:

[0081] The target problem is quality-classified by a preset classification model; wherein the quality classification results displayed in the problem display interface belong to the target problem of the target classification.

[0082] In some optional implementations, the information acquisition module may be used to:

[0083] Send an information authorization request to the target object;

[0084] In response to receiving the authorization pass message sent by the target object, the target information of the target object in the target collaboration platform is acquired.

[0085] In some optional implementations, the target information includes information in at least one of the following dimensions: document dimension, conversation dimension, meeting dimension, basic data dimension, and device dimension, region dimension, and time dimension for logging into the target collaboration platform.

[0086] In some optional implementations, the object label includes a label of at least one of the following dimensions: a role dimension, an industry background dimension, a first skill dimension, and a second skill dimension.

[0087] In some optional implementations, the tag determination module may be used to:

[0088] By presetting the generative model, the object label of the target object is determined according to the target information.

[0089] In some optional implementations, the question generating device may further include:

[0090] The answer generation module is used to generate a target answer to a target question based on the target information, so as to display the corresponding target answer when a query instruction of the target question is received on the question display interface.

[0091] In some optional implementations, the question display interface includes a conversation interface of an intelligent assistant provided by the target collaboration platform, an information search interface or a document interface provided by the target collaboration platform.

[0092] The question generating device provided in the embodiments of the present disclosure can execute the question generating method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0093] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0094] Reference below Figure 4 , which shows an electronic device (eg, Figure 4 The terminal device in the embodiment of the present disclosure may include but is 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), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0095] like Figure 4 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 to a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0096] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0097] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the problem generation method of the embodiment of the present disclosure are executed.

[0098] The electronic device provided in the embodiment of the present disclosure and the question generating method provided in the above embodiment belong to the same disclosed concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0099] The embodiments of the present disclosure provide a storage medium of computer executable instructions. When the computer executable instructions are executed by a computer processor, they can be used to execute the question generating method provided by the above embodiments.

[0100] It should be noted that the storage medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM) or a flash memory (FLASH), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing executable instructions, which may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable executable instruction. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit executable instructions for use by or in conjunction with an instruction execution system, apparatus, or device. The executable instructions contained on the storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0101] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text 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"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0102] The storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0103] The storage medium carries one or more executable instructions. When the one or more executable instructions are executed by the electronic device, the electronic device:

[0104] Obtain target information of a target object in a target collaboration platform; determine an object label of the target object according to the target information, generate a target question according to the object label, and display the target question in a question display interface in the target collaboration platform.

[0105] Executable instructions for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The executable instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0106] An embodiment of the present disclosure further provides a computer program product, including a computer program, which, when executed by a processor, can implement a question generating method as provided in any embodiment of the present disclosure.

[0107] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code for the disclosed operation, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0108] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0109] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the names of the units and modules do not, in some cases, limit the units and modules themselves.

[0110] 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: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), etc.

[0111] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] According to one or more embodiments of the present disclosure, a question generation method is provided, the method comprising:

[0113] Obtain target information of target objects in the target collaboration platform;

[0114] According to the target information, an object tag of the target object is determined, and a target question is generated according to the object tag, so as to display the target question in a question display interface in the target collaboration platform.

[0115] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0116] In some optional implementations, generating a target question according to the object tag includes at least one of the following:

[0117] Generate the target question according to the object label by using a preset language model;

[0118] Generate the target question according to the object label and a preset template including a placeholder identifier;

[0119] Generate the target question according to the object label and the preset label-question correspondence relationship;

[0120] Acquire first historical question data matching the object tag, and generate the target question according to the first historical question data;

[0121] According to the object tag, similar objects of the target object are determined from the target collaboration platform, and the target question is generated according to the second historical question data of the similar objects.

[0122] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0123] In some optional implementations, generating the target question according to the object label by using a preset language model includes:

[0124] Acquire at least one target tag from the object tags, and determine a keyword according to the target tag;

[0125] Generate prompt words according to the subject words and the preset question type library;

[0126] The target question is generated according to the prompt word through the preset language model.

[0127] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0128] In some optional implementations, after generating the target question according to the prompt word, the method further includes:

[0129] The target problem is quality-classified by a preset classification model; wherein the result of the quality classification displayed in the problem display interface belongs to the target problem of the target classification.

[0130] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0131] In some optional implementations, the step of obtaining target information of a target object in a target collaboration platform includes:

[0132] Sending an information authorization request to the target object;

[0133] In response to receiving the authorization pass message sent by the target object, the target information of the target object in the target collaboration platform is acquired.

[0134] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0135] In some optional implementations, the target information includes information of at least one of the following dimensions: document dimension, conversation dimension, meeting dimension, basic data dimension, and device dimension, region dimension, and time dimension for logging into the target collaboration platform.

[0136] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0137] In some optional implementations, the object label includes a label of at least one of the following dimensions: a role dimension, an industry background dimension, a first skill dimension, and a second skill dimension.

[0138] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0139] In some optional implementations, determining the object tag of the target object according to the target information includes:

[0140] By presetting the generation model, the object label of the target object is determined according to the target information.

[0141] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0142] In some optional implementations, the method further includes:

[0143] A target answer to the target question is generated according to the target information, so that when the question display interface receives a query instruction for the target question, the corresponding target answer is displayed.

[0144] According to one or more embodiments of the present disclosure, a question generation method is provided, further comprising:

[0145] In some optional implementations, the question display interface includes a conversation interface of an intelligent assistant provided by the target collaboration platform, an information search interface or a document interface provided by the target collaboration platform.

[0146] According to one or more embodiments of the present disclosure, a question generating device is provided, the device comprising:

[0147] An information acquisition module, used to acquire target information of a target object in a target collaboration platform;

[0148] The question generation module is used to determine the object tag of the target object according to the target information, and generate a target question according to the object tag to display the target question in the question display interface in the target collaboration platform.

[0149] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0150] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0151] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for generating a question, characterized in that: include: Obtain target information of target objects in the target collaboration platform; According to the target information, an object tag of the target object is determined, and a target question is generated according to the object tag, so as to display the target question in a question display interface in the target collaboration platform.

2. The method according to claim 1, characterized in that Generating a target question according to the object label includes at least one of the following: Generate the target question according to the object label by using a preset language model; Generate the target question according to the object label and a preset template including a placeholder identifier; Generate the target question according to the object label and the preset label-question correspondence relationship; Acquire first historical question data matching the object tag, and generate the target question according to the first historical question data; According to the object tag, similar objects of the target object are determined from the target collaboration platform, and the target question is generated according to the second historical question data of the similar objects.

3. The method according to claim 2, characterized in that The generating the target question according to the object label by using a preset language model includes: Acquire at least one target tag from the object tags, and determine a keyword according to the target tag; Generate prompt words according to the subject words and the preset question type library; The target question is generated according to the prompt word through the preset language model.

4. The method according to claim 3, characterized in that After generating the target question according to the prompt word, the method further includes: The target problem is quality-classified by a preset classification model; wherein the result of the quality classification displayed in the problem display interface belongs to the target problem of the target classification.

5. The method according to claim 1, characterized in that The step of obtaining target information of a target object in a target collaboration platform includes: Sending an information authorization request to the target object; In response to receiving the authorization pass message sent by the target object, the target information of the target object in the target collaboration platform is acquired.

6. The method according to claim 1, characterized in that The target information includes information of at least one of the following dimensions: document dimension, conversation dimension, meeting dimension, basic data dimension, and device dimension, region dimension, and time dimension for logging into the target collaboration platform.

7. The method according to claim 1, characterized in that The object label includes a label of at least one of the following dimensions: a role dimension, an industry background dimension, a first skill dimension, and a second skill dimension.

8. The method according to claim 1, characterized in that The step of determining the object label of the target object according to the target information includes: By presetting the generation model, the object label of the target object is determined according to the target information.

9. The method according to claim 1, characterized in that: Also includes: A target answer to the target question is generated according to the target information, so that when the question display interface receives a query instruction for the target question, the corresponding target answer is displayed.

10. The method according to claim 1, characterized in that The question display interface includes a conversation interface of an intelligent assistant provided by the target collaboration platform, an information search interface or a document interface provided by the target collaboration platform.

11. A question generating device, characterized in that: include: An information acquisition module, used to acquire target information of a target object in a target collaboration platform; The question generation module is used to determine the object tag of the target object according to the target information, and generate a target question according to the object tag to display the target question in the question display interface in the target collaboration platform.

12. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the question generating method as described in any one of claims 1 to 10.

13. A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to perform the question generation method according to any one of claims 1 to 10 when executed by a computer processor.

14. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the question generating method according to any one of claims 1 to 10.

Images