Methods, apparatus, electronic devices, and storage media for generating questions based on content.

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for generating questions based on content. [Solution] A method for generating questions based on content includes the steps of: obtaining information sources corresponding to a target user; generating a target question based on the information sources; and displaying the target question in response to an operation that triggers viewing of the target question, wherein the information sources corresponding to the target user include documents accessed by the target user's affiliated users, and the number of affiliated users is one or more. This disclosure ensures that the target question is on an issue of interest to the target user and improves the efficiency of resolving the question.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and particularly to a method, apparatus, electronic device, and storage medium for generating questions based on content.

Background Art

[0002] With the development of artificial intelligence technology, users can interact with artificial intelligence (AI) programs. For example, a user can submit a question to an AI program, and the AI can detect an answer from an information database based on the question. Current AI depends on active questions from users, and the efficiency of problem-solving is low.

Summary of the Invention

Means for Solving the Problems

[0003] The present disclosure provides a method, apparatus, electronic device, and storage medium for generating questions based on content.

[0004] The present disclosure uses the following technical solutions. In some embodiments, the present disclosure obtains an information source corresponding to a target user, and generates a target question based on the information source, and displays the target question in response to an operation that triggers viewing of the target question, and the information source corresponding to the target user includes documents accessed by associated users of the target user, and the number of the associated users is one or more. Provide a method for generating questions based on content

[0005] In some embodiments, the present disclosure obtains an information source corresponding to a target user, and a obtaining unit that generates a target question based on the information source, and The system includes a control unit that displays the target question in response to an operation that triggers viewing of the target question, The information source corresponding to the target user includes documents accessed by the target user's affiliated users, and the number of affiliated users may be one or more. We provide a device that generates questions based on content.

[0006] In some embodiments, the present disclosure provides an electronic device comprising at least one memory and at least one processor. Memory is for storing program code, and the processor is for calling the program code stored in the memory and executing the above method.

[0007] In some embodiments, the present disclosure provides a computer-readable storage medium. The computer-readable storage medium is for storing program code, and when the program code is executed by a processor, it causes the processor to implement the above method.

[0008] The method for generating questions based on content according to the embodiments of this disclosure uses documents accessed by the linked user as the source of information, ensuring that the target questions are of interest to the target user, avoiding the problem of generating invalid target questions that would hinder the target user and reduce efficiency, and by generating target questions relevant to the target user, it is possible to make it easier for the target user to submit questions and improve processing efficiency. [Brief explanation of the drawing]

[0009] The above and other features, advantages and aspects of each embodiment of this disclosure will become clearer with reference to the drawings and the specific embodiments described below. Throughout the drawings, identical or similar reference numerals represent identical or similar elements. The drawings are illustrative and should be understood to mean that elements and components are not necessarily depicted in proportion.

[0010] [Figure 1] Figure 1 is a flowchart of a method for generating questions based on content according to an embodiment of the present disclosure. [Figure 2] Figure 2 is a schematic diagram showing the display of a target question in a search box according to an embodiment of the present disclosure. [Figure 3] Figure 3 is a schematic diagram of the configuration of an electronic device according to an embodiment of the present disclosure. [Modes for carrying out the invention]

[0011] It is understood that, before using the technical solutions disclosed in each embodiment of this disclosure, it is necessary to inform the user in an appropriate manner, in accordance with applicable laws and regulations, about the types of personal information related to this disclosure, the scope of use, usage scenarios, etc., and to obtain the user's grant.

[0012] For example, in response to receiving an active request from the user, prompt information is sent to the user to clearly indicate that the operation requested to be performed requires the acquisition and use of the user's personal information. This allows the user to choose whether or not to provide personal information to software or hardware such as electronic devices, application programs, servers, or storage media that perform the operation of the technical solution of this disclosure, depending on the information provided.

[0013] As a non-restrictive and selectable implementation, the method of sending information to the user in response to receiving an active request from the user may be, for example, a pop-up window, in which the information may be displayed in text format. The pop-up window may also include a selection control that allows the user to choose whether to "agree" or "disagree" to providing personal information to the electronic device.

[0014] The notification and user permission process described above are illustrative and do not limit the implementation of this disclosure. It should be understood that other methods that comply with applicable laws and regulations may also be applicable to implementations of this disclosure.

[0015] It is understood that the data relating to this technical solution (including, but not limited to, the data itself, the acquisition of the data, or the use of the data) must comply with applicable laws, regulations, and related provisions.

[0016] The embodiments of this disclosure will be described in more detail below with reference to the drawings. Although several embodiments of this disclosure are shown in the drawings, this disclosure can be realized in various forms and should not be construed as being limited to the embodiments described herein. Rather, these embodiments should be understood as being provided for a more thorough and complete understanding of this disclosure. The drawings and embodiments of this disclosure are for illustrative purposes only and should not be used to limit the scope of protection of this disclosure.

[0017] Each step described in the embodiments of the method of this disclosure should be understood to be performed sequentially and / or in parallel. Furthermore, embodiments of the method may include additional steps and / or omit the performance of the disclosed steps. The scope of this disclosure is not limited in this respect.

[0018] As used herein, the term "comprising" and variations thereof are open-ended inclusion, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" represents "at least one embodiment", the term "another embodiment" represents "at least one another embodiment", and the term "some embodiments" represents "at least some embodiments". Definitions for other terms are provided in the following description.

[0019] Note that the concepts such as "first", "second", etc. mentioned in this disclosure are for distinguishing different devices, modules or units, and are not for limiting the order or mutual dependency of the functions executed by these devices, modules or units.

[0020] Note that the modifier "one" in this disclosure is illustrative rather than limiting, and those skilled in the art can understand that it should be understood as "one or more" unless otherwise specified in the context.

[0021] The names of messages or information that interact between multiple devices in the embodiments of this disclosure are not intended to limit the scope of these messages or information, and are only used for the purpose of explanation.

[0022] Hereinafter, with reference to the drawings, the technical solutions provided by the embodiments of this disclosure will be described in detail.

[0023] In a client such as a conversation software, a user can send information such as a question, and a chatbot can answer the question sent by the user. When no information is sent from the user, the input box or search box of the conversation may display questions that the user may want to ask. If these questions are irrelevant to the user, there may be a decline in the user experience.

[0024] In particular, if conversational software is internal to an organization, the generated questions should be relevant to the user's work; if the generated questions are irrelevant to the user's work, the user's work efficiency may be affected. In some technologies, the source of the generated questions is documentation, especially documentation that the user has access to. However, if the question generation method is not appropriate, documents of no interest to the user are likely to become the source of the generated questions, leading to reduced effectiveness.

[0025] As shown in Figure 1, Figure 1 is a flowchart of a method for generating questions based on content according to an embodiment of the present disclosure, and includes the following steps:

[0026] S11. Obtain information sources corresponding to the target user and generate target questions based on said information sources.

[0027] In some embodiments, the methods relating to this disclosure may be used on electronic devices such as terminals, including mobile phones, computers, and servers. More specifically, the methods relating to this disclosure may be used on clients such as artificial intelligence programs. In some embodiments, each user has a corresponding information source, and each information source corresponding to a user is independent. The content in the information source is used to generate a target question. The information source corresponding to the target user includes documents accessed by the target user's affiliated users. The number of affiliated users may be one or more. In some embodiments, the target user may be any single user, for example, the current user. The target user has affiliated users. Affected users may be users participating in the same matter; for example, if user A and user B are participating in the same matter, they become each other's affiliated users. More specifically, in some embodiments, the same matter in which they are participating must be in an incomplete and normal running state. This is because if the same matter in which two users are jointly participating has already been completed, it indicates that the relevance between the two users is low, and if the same matter in which both users are participating is in a normal running state, it indicates that the documents viewed by the users are highly relevant. In other words, documents viewed by collaborating users are likely to be related to matters in which they are jointly participating, and therefore are likely to be of interest to the target user. When generating target questions based on information sources, target questions may also be generated based on the document content of documents accessed by collaborating users. There may be multiple target questions, and one or more target questions may be generated from a single document. Target questions may be, for example, questions that the user is suggested to ask, and may be questions generated in response to document content. For example, if the document content describes how to implement a certain function, the target question may be a question about how to implement that function.

[0028] S12, In response to an operation that triggers viewing of the target question, the target question is displayed.

[0029] In some embodiments, the scenarios in which the target question is displayed in response to an action that triggers viewing the target question vary. For example, the target question may be displayed in a conversation with a chatbot in an instant messaging client after the user triggers a conversation with the chatbot by clicking or other means. Alternatively, the target page may be displayed on a search page after the user triggers a search box by clicking or other means. In some embodiments, the trigger for viewing the target question may be when the target user logs into a client that performs the method of this disclosure. In this case, the target question may be displayed in the search box in the client (e.g., the top part of Figure 3), the conversation input box with the chatbot (the chatbot may be an artificial intelligence program), or the area surrounding the input box (for example, in Figure 3, the target question is "What is the progress of the XX project?"). In some embodiments, there may be multiple target questions. In this case, multiple target questions may be displayed one by one, or only one question may be displayed at a time.

[0030] Related technologies, when generating questions, generate questions based only on the content of documents the user has permission to access. This can easily lead to situations where documents the user has permission to access but is not interested in become sources of information, reducing efficiency. In some embodiments of this disclosure, target questions are generated and displayed to the target user based on the target user's sources of information, which include documents accessed by the target user's affiliated users. This disclosure considers the relationship between the target user and the affiliated user, and because of this relationship, the content that the target user and the affiliated user are interested in is likely to be the same. Therefore, by generating target questions using documents accessed by the affiliated user as sources of information, it is possible to ensure that the target questions are of interest to the target user and to avoid the problem of generating invalid target questions that would hinder the target user and reduce efficiency. The target user can send the target question to the chatbot to obtain an answer by triggering the target question with a click or other means, or they can copy the target question to find the answer. In either method, providing target questions is advantageous in improving the efficiency of the target user.

[0031] In some embodiments of this disclosure, displaying the target question in response to an action that triggers viewing the target question includes, in response to the action that triggers viewing the target question, jumping to a page where the user interacts with a chatbot and displaying the target question on that page, or displaying the target question in a predetermined area of ​​the current interface in response to the action that triggers viewing the target question. In some embodiments, the action that triggers viewing the target question may be clicking a control, opening software, or activating a window. In some embodiments, the current page does not have to be the page where the user interacts with a chatbot; after detecting the action that triggers viewing the target question, the user may open the page where the user interacts with a chatbot and then display the target question there. In some embodiments, after the action that triggers viewing the target question is performed, the target question may be displayed in a predetermined area of ​​the current interface without leaving the current interface. For example, the target question may be displayed in the current interface around the location where the target user performs the action that triggers viewing the target question.

[0032] In some embodiments of this disclosure, the documents accessed by the linked user in the information source are documents accessed by the linked user of the target user, but not by the target user. In some embodiments, the documents accessed by the linked user in the information source do not include documents accessed by the target user; that is, documents accessed by both the linked user and the target user are not added to the information source. This is because target questions are generated based on the information source, specifically based on the document content of the documents. The target user already knows the content of the documents they have accessed and does not need to know the content of those documents again. Target questions generated based on documents accessed by the target user are unlikely to contain the content the target user wants to know. Therefore, documents accessed by the linked user that the target user has also accessed should be removed from the information source.

[0033] In some embodiments of the present disclosure, generating a target question based on the information source includes obtaining candidate documents from documents accessed by a target affiliate user, wherein the target affiliate user is a first predetermined number of affiliate users with the closest relationship to the target user; determining a second predetermined number of target documents with the highest number of accesses from the candidate documents based on the number of accesses to the candidate documents; and generating the target question based on the target documents.

[0034] In some embodiments, when generating target questions based on information sources, first, a predetermined number (e.g., 3) of collaborating users with the highest level of closeness to the target user are determined as target collaborating users. Closeness may represent the degree of relevance of the collaborating relationship between the target user and the collaborating users, with higher closeness indicating a higher degree of relevance in the collaborating relationship between them. The method for calculating closeness may be based on the number of matters currently being jointly participated in, the length of time spent jointly participating in those matters, and the relevance of the content each user is responsible for, with higher closeness indicating more jointly participated matters, longer joint participation times, and higher relevance of the content each user is responsible for. Of course, any other known method may be used to calculate closeness. Then, some documents are selected as candidate documents from the documents accessed by the target collaborating users, and from these candidate documents, a predetermined number (e.g., 5) of candidate documents with the highest number of accesses are selected as target documents, and then, based on the content of the target documents, target questions are generated. The total number of times a candidate document has been accessed is the sum of the number of times each user has accessed that candidate document. In other words, each time a user accesses a candidate document, 1 is added to its access count. In this embodiment, the closeness between the collaborating user and the target user is taken into consideration, and the documents accessed by the collaborating user with the highest level of closeness are selected to maximize the likelihood that the target question will be of interest to the target user. At the same time, the number of times a document has been accessed is also considered, and documents with a high number of accesses are more likely to be shared documents rather than the collaborating user's own private documents. This ensures that the target document is a work-related document rather than a personal one.

[0035] In some embodiments of the present disclosure, obtaining candidate documents from documents accessed by target linked users includes obtaining the most recently accessed documents of each of the target linked users, wherein the most recently accessed documents of any of the target linked users are a third predetermined number of documents recently accessed by that target linked user, and each of the most recently accessed documents of each target linked user is designated as a candidate document.

[0036] In some embodiments, linked users typically access a large number of documents, and it is natural that many of these documents contain content that is of no interest to the target user. Considering the linked relationship between the target user and the linked user, it is likely that documents recently accessed by the linked user are likely to contain content of interest to the target user. Therefore, for each target linked user, a third predetermined number (e.g., 5) of documents recently accessed by that target linked user are extracted as their most recently accessed documents, and these most recently accessed documents for each target linked user are designated as candidate documents. As an example, if the first predetermined number is 3 and the third predetermined number is 5, first, the three linked users with the highest level of closeness are determined as target linked users, and then, for each target linked user, the 5 documents they most recently accessed are obtained as their most recently accessed documents, resulting in a total of 15 documents as candidate documents.

[0037] In some embodiments of the present disclosure, after obtaining candidate documents from the documents accessed by the target linked user, and before determining a second predetermined number of target documents from the candidate documents based on the number of times the candidate documents have been accessed, the further includes removing documents from the candidate documents that match predetermined filtering rules, the predetermined filtering rules include one or more of the following: the document title contains predetermined words; the document content contains predetermined words; and the target user has accessed the document.

[0038] In some embodiments, after obtaining candidate documents, it is necessary to filter the documents and remove those that match the filtering rules before ranking them by access count. Specifically, documents containing certain keywords (predetermined words) may be removed. These predetermined words include words indicating confidential content and / or words indicating routine matters. If there are words indicating confidential content (e.g., top secret, internal confidential, business secret), it indicates that the document is relatively sensitive. On the other hand, if there are words indicating routine matters (e.g., morning meeting, weekly meeting), it indicates that the target user is not interested in the document and should therefore be removed. If the target user has already accessed the document, the target user already knows the document's content and does not need to understand it further, so the document that the target user has accessed should be removed.

[0039] In some embodiments of the present disclosure, after generating the target questions based on the target document, in response that the number of target questions generated based on the content of the target document has not reached a fourth predetermined number, the present invention further includes continuing to generate target questions sequentially based on candidate documents that are not selected as target documents, in descending order of the number of accesses of the candidate documents, until the total number of target questions reaches the fourth predetermined number.

[0040] In some embodiments, one or more target questions may be generated based on a single document. When target questions are displayed to a target user, the user may wish to view more than one target question, meaning the user may request to swap out a different target question. Therefore, the number of target questions needs to reach a fourth predetermined number (e.g., 10 or 20). If the number of target questions generated based on the target document does not reach the fourth predetermined number, the system continues to generate target questions by preferentially using the remaining documents among the candidate documents. When continuing to generate target questions, the system prioritizes selecting candidate documents with high access counts. This ensures that there are enough target questions relevant to the target user.

[0041] In some embodiments of this disclosure, the information source further includes related documents to the document accessed by the target user. In some embodiments, since the document accessed by the target user is a document of interest, its related documents are also likely to be of interest. Related documents to the document accessed by the target user may be, for example, documents cited, mentioned, or other documents by the same author in the document accessed by the target user.

[0042] In some embodiments of this disclosure, An acquisition unit that acquires information sources corresponding to the target user and generates target questions based on the said information sources, The system includes a control unit that displays the target question in response to an operation that triggers viewing of the target question, The information source corresponding to the target user includes documents accessed by the target user's affiliated users, and the number of affiliated users may be one or more. We provide a device that generates questions based on content.

[0043] In some embodiments, displaying the target question in response to an operation that triggers viewing the target question may involve jumping to a page where one can converse with a chatbot, and displaying the target question on the chatbot conversation page, or This includes displaying the target question within a predetermined area of ​​the current interface in response to an operation that triggers viewing of the target question.

[0044] In some embodiments, generating a target question based on the information source is: The process involves obtaining candidate documents from documents accessed by target linked users, wherein the target linked users are a predetermined number of linked users with the closest relationship to the target users. Based on the number of accesses to the aforementioned candidate documents, a second predetermined number of target documents with the highest number of accesses are determined from the candidate documents. This includes generating the target question based on the target document, The number of accesses to the aforementioned candidate document is the sum of the number of accesses to that candidate document by each user.

[0045] In some embodiments, candidate documents are obtained from documents accessed by the target linked user. Obtaining the most recently accessed documents of each of the target linked users, wherein the most recently accessed documents of any of the target linked users are a third predetermined number of documents that the target linked user has recently accessed. This includes setting the most recently accessed document of each target linked user as the candidate document.

[0046] In some embodiments, after obtaining candidate documents from documents accessed by the target linked user, and before determining a second predetermined number of target documents from the candidate documents based on the number of times the candidate documents have been accessed, the acquisition unit is further used to remove documents from the candidate documents that match predetermined filtering rules, the predetermined filtering rules include one or more of the following: the document title contains predetermined words, the document content contains predetermined words, and the target user has accessed the document.

[0047] In some embodiments, the predetermined words include words indicating confidential content and / or words indicating routine matters.

[0048] In some embodiments, the control unit is further used to continue generating target questions based on the target document, and in response to the fact that the number of target questions generated based on the content of the target document has not reached a fourth predetermined number, in descending order of the number of accesses of the candidate documents, until the total number of target questions reaches the fourth predetermined number.

[0049] In some embodiments, the information source further includes related documents to the documents accessed by the target user.

[0050] In some embodiments, the documents accessed by the linked user in the information source are documents accessed by the linked user of the target user, but not by the target user.

[0051] Since the embodiments of the apparatus essentially correspond to the embodiments of the method, relevant sections should be referred to in the description of the embodiments of the method. The embodiments of the apparatus described above are illustrative only, and modules described as separate modules may or may not be separate. Some or all of these modules may be selected as needed to achieve the objectives of the embodiment. Those skilled in the art will be able to understand and implement the present invention without requiring any creative effort.

[0052] The methods and apparatus of this disclosure have been described above based on the examples and applications. Furthermore, this disclosure provides electronic devices and computer-readable storage media. These electronic devices and computer-readable storage media will be described below.

[0053] Next, refer to Figure 3. Figure 3 shows a schematic diagram of the configuration of an electronic device (e.g., terminal device or server) 800 suitable for implementing an embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include, but is not limited to, mobile devices such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. The electronic device shown in the figure is merely an example and does not impose any limitations on the functionality and scope of use of the embodiment of the present disclosure.

[0054] The electronic device 800 may include a processing unit (e.g., a central processing unit, graphics processor, etc.) 801, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. The RAM 803 also stores various programs and data necessary for the operation of the electronic device 800. The processing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0055] Typically, input devices 806, including, for example, a touchscreen, touch panel, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc., output devices 807, including, for example, a liquid crystal display (LCD), speaker, vibrator, etc., storage devices 808, including, for example, magnetic tape, hard disk, etc., and communication devices 809 may be connected to the I / O interface 805. The communication devices 809 enable the electronic device 800 to exchange data with other devices via wireless or wired communication. In the figure, an electronic device 800 equipped with various devices is shown, but it should be understood that it is not required to implement or include all of the devices shown. Alternatively, it is possible to implement or include more or fewer devices.

[0056] In particular, according to embodiments of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product which includes a computer program mounted on a computer-readable medium. The computer program includes program code for performing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When executed by a processing unit 801, the computer program performs the functions limited to the methods of embodiments of the present disclosure.

[0057] The computer-readable medium in this disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specifically, the computer-readable storage medium may include, but is not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, the program may be used in or in combination with an instruction execution system, apparatus, or device. In this disclosure, the computer-readable signal medium may contain a data signal propagated in the baseband or as part of a carrier wave, which contains computer-readable program code. The data signals propagated in this manner may take many forms and may include, but are not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may be any computer-readable medium other than a computer-readable storage medium, and such computer-readable medium may transmit, propagate, or transmit programs used in or in combination with instruction execution systems, apparatus, or devices. The program code contained in the computer-readable medium may be transmitted by any suitable medium, including, but are not limited to, electric wires, optical cables, RF (radio frequency), or any suitable combination thereof.

[0058] In some embodiments, the client and server may communicate using any known or future-to-be-developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with digital data communications (e.g., communication networks) in any form or medium. Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), and any known or future-to-be-developed networks.

[0059] The computer-readable medium described above may be included in the electronic device described above, or it may exist independently without being attached to the electronic device.

[0060] The computer-readable medium described above stores one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is made to perform the method of the present disclosure described above.

[0061] Computer program code for performing the operations disclosed herein may be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, for example, object-oriented programming languages ​​such as Java, Smalltalk, and C++, and general procedural programming languages ​​such as the "C" language or similar programming languages. The program code may run entirely on the user's computer, partially on the user's computer, as a standalone 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 may be connected to the user's computer via any network, including a local area network (LAN) or wide area network (WAN), or it may be connected to an external computer (for example, via the Internet provided by an Internet service provider).

[0062] The flowcharts and block diagrams in the drawings illustrate the implementable system architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code. The module, program segment, or part of code contains one or more executable instructions for implementing a given logical function. It should also be noted that in some alternative implementations, the functions represented in a block may be implemented in a different order than those shown in the drawings. For example, two consecutively shown blocks may actually be executed in parallel, or they may be executed in reverse order depending on the function. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs a given function or operation, or by a combination of dedicated hardware and computer instructions.

[0063] The units described in the embodiments of this disclosure may be implemented in software or in hardware. Hereinafter, the names of the units are not limited in any case to the modules themselves.

[0064] The functions described herein may be performed, at least in part, by one or more hardware logic components. For example, in non-limiting examples, exemplary categories of hardware logic components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on chips (SOCs), and complex programmable logic devices (CPLDs).

[0065] In the context of this disclosure, a machine-readable medium may be a tangible medium that contains or stores a program used in or in combination with an instruction execution system, device, or apparatus. 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, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or apparatus, or any suitable combination thereof. More specifically, machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0066] According to one or more embodiments of this disclosure, Obtain information sources corresponding to the target user, and generate target questions based on said information sources, The process includes displaying the target question in response to an operation that triggers viewing of the target question, The information source corresponding to the target user includes documents accessed by the target user's affiliated users, and the number of affiliated users may be one or more. A method for generating questions based on content is provided.

[0067] According to one or more embodiments of the present disclosure, displaying the target question in response to an operation that triggers viewing the target question is: In response to an action that triggers viewing of the target question, the user is redirected to a page where they can converse with the chatbot, and the target question is displayed on the page where they converse with the chatbot, or In response to an operation that triggers viewing of the target question, the system includes displaying the target question within a predetermined area of ​​the current interface. A method for generating questions based on content is provided.

[0068] According to one or more embodiments of this disclosure, generating a target question based on the said information source is: The process involves obtaining candidate documents from documents accessed by target linked users, wherein the target linked users are a predetermined number of linked users with the closest relationship to the target users. Based on the number of accesses to the aforementioned candidate documents, a second predetermined number of target documents with the highest number of accesses are determined from the candidate documents. This includes generating the target question based on the target document, The number of accesses to the aforementioned candidate document is the sum of the number of accesses to that candidate document by each user. A method for generating questions based on content is provided.

[0069] According to one or more embodiments of this disclosure, obtaining candidate documents from documents accessed by the target linked user is: Obtaining the most recently accessed documents of each of the target linked users, wherein the most recently accessed documents of any of the target linked users are a third predetermined number of documents that the target linked user has recently accessed. This includes setting the most recently accessed document of each target linked user as the candidate document, A method for generating questions based on content is provided.

[0070] According to one or more embodiments of the present disclosure, after obtaining candidate documents from the documents accessed by the target linked user, and before determining a second predetermined number of target documents from the candidate documents based on the number of times the candidate documents have been accessed, The process further includes removing documents from the candidate documents that match predetermined filtering rules, The aforementioned predetermined filtering rule includes one or more of the following: the document title contains a predetermined word; the document content contains a predetermined word; and the target user has previously accessed the document. A method for generating questions based on content is provided.

[0071] According to one or more embodiments of the present disclosure, a method is provided for generating questions based on content, wherein the predetermined words include words indicating confidential content and / or words indicating routine matters.

[0072] According to one or more embodiments of the present disclosure, after generating the target question based on the target document, In response to the fact that the number of target problems generated based on the content of the target document has not reached a fourth predetermined number, the method further includes continuing to generate target problems sequentially based on candidate documents that are not selected as target documents, in descending order of the number of accesses of the candidate documents, until the total number of target problems reaches the fourth predetermined number. A method for generating questions based on content is provided.

[0073] According to one or more embodiments of the present disclosure, the information source further includes related documents of the documents accessed by the target user. A method for generating questions based on content is provided.

[0074] According to one or more embodiments of this disclosure, the documents accessed by the linked user in the information source are documents accessed by the linked user of the target user, and not accessed by the target user. A method for generating questions based on content is provided.

[0075] According to one or more embodiments of this disclosure, an apparatus for generating questions based on content is provided. The apparatus is An acquisition unit that acquires information sources corresponding to the target user and generates target questions based on the said information sources, The system includes a control unit that displays the target question in response to an operation that triggers viewing of the target question, The information source corresponding to the target user includes documents accessed by the target user's affiliated users, and the number of affiliated users may be one or more.

[0076] According to one or more embodiments of this disclosure, an electronic device is provided. The electronic device is, At least one memory, Equipped with at least one processor, The at least one memory is for storing program code, and the at least one processor is for calling the program code stored in the at least one memory to perform the method described in any one of the above items.

[0077] According to one or more embodiments of the present disclosure, a computer-readable storage medium is provided for storing program code, which, when executed by a processor, causes the processor to implement the above method.

[0078] The above description is merely a description of preferred embodiments and applicable technical principles of the present disclosure. Those skilled in the art will understand that the scope of the present disclosure is not limited to technical solutions formed by specific combinations of the above technical features, but should also include other technical solutions formed by arbitrarily combining the above technical features or their equivalents without departing from the disclosed idea. For example, technical solutions formed by substituting the above features with technical features having similar functions disclosed in this disclosure (not limited to those disclosed herein) are also included in the scope of the present disclosure.

[0079] Furthermore, although each operation has been described in a specific order, this should not be understood as requiring that they be performed in a specific order or sequence. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although the foregoing description includes various specific implementation details, these should not be interpreted as limiting the scope of this disclosure. Some features described in the context of individual embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable subcombination in multiple embodiments.

[0080] While the present invention has been described using language specific to structural features and / or methodological logic, it should be understood that the themes defined in the attached claims are not necessarily limited to the specific features or behaviors described above. Rather, the aforementioned features and behaviors are merely illustrative forms for carrying out the claims.

Claims

1. A method for generating questions based on content, Obtain information sources corresponding to the target user, and generate target questions based on said information sources, The process includes displaying the target question in response to an operation that triggers viewing of the target question, The information source corresponding to the target user includes documents accessed by the target user's affiliated users, and the number of affiliated users may be one or more. A method characterized by the following:

2. Displaying the target question in response to an operation that triggers viewing of the target question means that In response to an action that triggers viewing of the target question, the user is redirected to a page where they can converse with the chatbot, and the target question is displayed on the page where they converse with the chatbot, or This includes displaying the target question within a predetermined area of ​​the current interface in response to an operation that triggers viewing of the target question, The method according to feature 1.

3. Generating target questions based on the aforementioned information sources is, The process involves obtaining candidate documents from documents accessed by target linked users, wherein the target linked users are a predetermined number of linked users with the closest relationship to the target users. Based on the number of accesses to the aforementioned candidate documents, a second predetermined number of target documents with the highest number of accesses are determined from the candidate documents. This includes generating the target question based on the target document, The number of accesses to the aforementioned candidate document is the sum of the number of accesses to that candidate document by each user. The method according to feature 1.

4. Obtaining candidate documents from documents accessed by the aforementioned target linked user is: Obtaining the most recently accessed documents of each of the target linked users, wherein the most recently accessed documents of any of the target linked users are a third predetermined number of documents that the target linked user has recently accessed. This includes setting the most recently accessed document of each target linked user as the candidate document, The method according to feature 3.

5. After obtaining candidate documents from the documents accessed by the target linked user, and before determining a second predetermined number of target documents from the candidate documents based on the number of times the candidate documents have been accessed, The process further includes removing documents from the candidate documents that match predetermined filtering rules, The aforementioned predetermined filtering rules include one or more of the following: the document title contains a predetermined word; the document content contains a predetermined word; and the target user has previously accessed the document. The method according to feature 3.

6. The aforementioned specified words include words indicating confidential content and / or words indicating routine matters. The method according to specification 5.

7. After generating the target question based on the target document, In response to the fact that the number of target problems generated based on the content of the target document has not reached a fourth predetermined number, the system further includes continuing to generate target problems sequentially based on candidate documents that are not selected as target documents, in descending order of the number of accesses of the candidate documents, until the total number of target problems reaches the fourth predetermined number. The method according to feature 3.

8. The information source further includes related documents of the document accessed by the target user, The method according to feature 1.

9. In the aforementioned information source, the documents accessed by the linked user are documents accessed by the linked user of the target user, but not by the target user. The method according to feature 1.

10. A device that generates questions based on content, An acquisition unit that acquires information sources corresponding to the target user and generates target questions based on the said information sources, The system includes a control unit that displays the target question in response to an operation that triggers viewing of the target question, The information source corresponding to the target user includes documents accessed by the target user's affiliated users, and the number of affiliated users may be one or more. A device characterized by the following features.

11. At least one memory, Equipped with at least one processor, The aforementioned at least one memory is for storing program code, The at least one processor is for calling program code stored in the memory to perform the method according to any one of claims 1 to 9. electronic equipment.

12. A computer-readable storage medium for storing program code, A computer-readable storage medium wherein, when the program code is executed by the processor, the processor implements the method according to any one of claims 1 to 9.

Images