Information generation method and apparatus, device, storage medium and program product

Abstract

Provided in the present disclosure are an information generation method and apparatus, a device, a storage medium and a program product, which can be applied to the technical fields of computers, natural language processing and information generation. The information generation method comprises: on the basis of a preset verification rule, displaying a collapsible answer corresponding to a received question statement, the collapsible answer comprising M collapsible option identifiers, and M being a positive integer; on the basis of a triggered target collapsible option identifier among the M collapsible option identifiers, generating initial response information; and using an answer generation tool to process the initial response information, so as to obtain response information corresponding to the question statement.

Description

Information generation method and device, equipment, storage medium and program product

[0001] The present application claims priority to Chinese Patent Application No. 202410726034.2, filed on June 5, 2024, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present disclosure relates to the field of computer technology, natural language processing technology and information generation technology, and more particularly, to an information generation method, device, equipment, storage medium and program product. BACKGROUND

[0003] With the development of natural language processing technology, natural language processing technology can be applied to information generation.

[0004] Information generation can refer to a process of obtaining response information corresponding to a received question sentence in response to the received question sentence. The question sentence can include text, voice and video, etc. The response information can be generated by using a response tool.

[0005] In the process of implementing the present disclosure, the inventors have found that the related art at least has the following problems: for a received question sentence, in the case that the obtained response information is ambiguous response information, it is often necessary to continue information generation. In the case of responding again to the received question sentence, since the generation process of the response information usually involves multiple different response tools, each response tool will generate information for the question sentence, and the information generation processes of multiple response tools can interfere or conflict with each other, which can cause confusion and errors in information transmission in the information generation process, thereby resulting in low efficiency of information generation and low matching degree of the response information and the question sentence. SUMMARY

[0006] The present disclosure provides an information generation method, device, equipment, storage medium and program product.

[0007] According to one aspect of the present disclosure, an information generation method is provided, comprising: according to a preset verification rule, displaying a folded answer corresponding to a received question sentence, wherein the folded answer comprises M folded option identifiers, and M is a positive integer; generating initial response information according to a target folded option identifier triggered in the M folded option identifiers; and processing the initial response information by using an answer generation tool to obtain response information corresponding to the question sentence.

[0008] According to an embodiment of the present disclosure, the preset checking rule includes a question type checking rule and an answer type checking rule, the question type checking rule is used to determine a question type of the question statement, and the question type includes a historical question statement or a new question statement; and the answer type checking rule is used to determine an answer type of the answer statement, and the answer type includes a folded answer statement or a general answer statement.

[0009] According to an embodiment of the present disclosure, the preset checking rule includes a question type checking rule and an answer type checking rule, the question type checking rule is used to determine a question type of the question statement, and the question type includes a historical question statement or a new question statement; and the answer type checking rule is used to determine an answer type of the answer statement, and the answer type includes a folded answer statement or a general answer statement.

[0010] According to an embodiment of the present disclosure, the preset checking rule includes a question type checking rule and an answer type checking rule, the question type checking rule is used to determine a question type of the question statement, and the question type includes a historical question statement or a new question statement; and the answer type checking rule is used to determine an answer type of the answer statement, and the answer type includes a folded answer statement or a general answer statement.

[0011] According to an embodiment of the present disclosure, the preset checking rule includes a question type checking rule and an answer type checking rule, the question type checking rule is used to determine a question type of the question statement, and the question type includes a historical question statement or a new question statement; and the answer type checking rule is used to determine an answer type of the answer statement, and the answer type includes a folded answer statement or a general answer statement.

[0012] According to an embodiment of the present disclosure, the preset checking rule includes a question type checking rule and an answer type checking rule, the question type checking rule is used to determine a question type of the question statement, and the question type includes a historical question statement or a new question statement; and the answer type checking rule is used to determine an answer type of the answer statement, and the answer type includes a folded answer statement or a general answer statement.

[0013] According to an embodiment of the present disclosure, the preset checking rule includes a question type checking rule and an answer type checking rule, the question type checking rule is used to determine a question type of the question statement, and the question type includes a historical question statement or a new question statement; and the answer type checking rule is used to determine an answer type of the answer statement, and the answer type includes a folded answer statement or a general answer statement.

[0014] According to an embodiment of the present disclosure, the folded answer has state information; and generating the initial response information corresponding to the (p+1)th sub-folded option identifier comprises: in response to the state information including the (p+1)th sub-folded option identifier, invoking, by using the context management tool, the initial response information corresponding to the (p+1)th sub-folded option identifier; and in response to the state information not including the (p+1)th sub-folded option identifier, generating, by using the answer generation tool, the initial response information.

[0015] According to an embodiment of the present disclosure, the method further comprises, before displaying the folded answer corresponding to the received question sentence according to the preset checking rule: normalizing the received initial question sentence to obtain the question sentence based on a preset input rule; and processing the initial response information to obtain the response information by using the answer generation tool, comprising: normalizing the obtained initial response information to obtain the response information based on a preset output rule.

[0016] According to an embodiment of the present disclosure, the method further comprises, after processing the initial response information to obtain the response information by using the answer generation tool: determining a target database corresponding to a question intention of the question sentence according to the question sentence; and storing the question sentence, the folded answer identifier, the target folded option identifier and the response information in the target database in association.

[0017] According to another aspect of the present disclosure, an information generation apparatus is provided, comprising: a display module configured to display a folded answer corresponding to a received question sentence according to a preset checking rule, wherein the folded answer comprises M folded option identifiers, M being a positive integer; a generation module configured to generate initial response information according to a target folded option identifier triggered in the M folded option identifiers; and a processing module configured to process the initial response information by using an answer generation tool to obtain response information corresponding to the question sentence.

[0018] According to another aspect of the present disclosure, an electronic device is provided, comprising: one or more processors; a memory configured to store one or more instructions, wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement the method as described above.

[0019] According to another aspect of the present disclosure, a computer readable storage medium is provided, having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the method as described above.

[0020] According to another aspect of the present disclosure, a computer program product is provided, comprising computer executable instructions for implementing the method as described above when executed by a processor. BRIEF DESCRIPTION OF DRAWINGS

[0021] The above and other objects, features and advantages of the present disclosure will be more clearly understood from the following description taken in conjunction with the accompanying drawings, in which:

[0022] FIG. 1 schematically illustrates a system architecture to which an information generation method according to an embodiment of the present disclosure can be applied;

[0023] FIG. 2 schematically illustrates a flowchart of an information generation method according to an embodiment of the present disclosure;

[0024] FIG. 3 exemplarily illustrates an exemplary schematic diagram of an information generation method according to an embodiment of the present disclosure;

[0025] FIG. 4 exemplarily illustrates an exemplary schematic diagram of an information generation process according to an embodiment of the present disclosure;

[0026] FIG. 5 schematically illustrates a structural block diagram of an information generation apparatus according to an embodiment of the present disclosure;

[0027] FIG. 6 schematically illustrates a block diagram of an electronic device suitable for implementing an information generation method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood, however, that the description which follows is merely exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description of the embodiments of the present disclosure, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it would be apparent to one skilled in the art that the present disclosure can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring the concepts of the present disclosure.

[0029] The terms used herein are merely used to describe specific embodiments and are not intended to limit the present disclosure. The terms "include", "comprise", and the like used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0030] All terms used herein, including technical and scientific terms, have the same meanings as those generally understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the present description, and should not be interpreted in an idealized or excessively formal manner.

[0031] In the case of using expressions similar to "at least one of A, B, and C, etc.", it will be understood that the meaning is that "only one of A, B, or C is required to be used in a given instance." In addition, the expression "and / or" includes combinations thereof, for example, A and / or B, in which A and B are valid.

[0032] In embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) comply with relevant laws and regulations, are used for legal purposes, and do not violate public order and good customs. In particular, necessary measures have been taken to prevent illegal access to user personal information data, to maintain user personal information security and network security.

[0033] In embodiments of the present disclosure, the authorization or consent of the user is obtained before the user's personal information is acquired or collected.

[0034] For example, after collecting the question statement, desensitization can be performed on your information by using a de-identification or anonymization processing method to protect your information security.

[0035] With the development of natural language processing technology, natural language processing technology can be applied to information generation.

[0036] Information generation can refer to a process of obtaining response information corresponding to a question statement in response to the received question statement. The question statement can include text, voice, and video, etc. The response information can be generated by using a response tool.

[0037] In the process of implementing the present concept, the inventors have found that the related art has at least the following problems: For a received question statement, in the case that the obtained response information is indefinite response information, it is often necessary to continue information generation. In the case of again responding to the received question statement, since the response information generation process usually involves multiple different response tools, each response tool will generate information for the question statement, and the information generation processes of multiple response tools can interfere or conflict with each other, which can cause confusion and errors in information transmission in the information generation process, thereby resulting in low efficiency of information generation and low matching degree and accuracy of the response information to the question statement.

[0038] To at least partially solve the technical problems existing in the related art, the present disclosure provides an information generation method and device, which can be applied to the fields of computer technology, natural language processing (NLP) and information generation. The information generation method comprises: according to a preset verification rule, displaying a collapsed answer corresponding to a received question sentence, wherein the collapsed answer comprises M collapsed option identifiers, and M is a positive integer; generating initial response information according to a target collapsed option identifier triggered in the M collapsed option identifiers; and processing the initial response information by using an answer generation tool to obtain response information corresponding to the question sentence.

[0039] FIG. 1 schematically shows a system architecture to which the information generation method according to an embodiment of the present disclosure can be applied. It should be noted that FIG. 1 only shows an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure cannot be applied to other devices, systems, environments or scenarios.

[0040] As shown in FIG. 1, the system architecture 100 according to the embodiment can include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0041] A user can use at least one of the first terminal device 101, the second terminal device 102 and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102 and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0042] The first terminal device 101, the second terminal device 102 and the third terminal device 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smartphones, tablet computers, laptop computers and desktop computers, etc.

[0043] The server 105 can be a server that provides various services, such as a background management server that provides support for a website browsed by a user using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (as an example only). The background management server can perform analysis and the like on received user requests and the like, and feed back the processing results (such as a webpage, information, or data, or the like, obtained or generated in accordance with the user request) to the terminal device.

[0044] It should be noted that the information generation method provided by the embodiments of the present disclosure can generally be executed by the server 105. Accordingly, the information generation apparatus provided by the embodiments of the present disclosure can generally be arranged in the server 105. The information generation method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Accordingly, the information generation apparatus provided by the embodiments of the present disclosure can also be arranged in a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0045] Alternatively, the information generation method provided by the embodiments of the present disclosure can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or by another terminal device different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the information generation apparatus provided by the embodiments of the present disclosure can also be arranged in the first terminal device 101, the second terminal device 102, or the third terminal device 103, or in another terminal device different from the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0046] It should be understood that the number of terminal devices, networks, and servers in FIG. 1 is merely illustrative. Any number of terminal devices, networks, and servers can be provided as needed.

[0047] It should be noted that the serial numbers of the various operations in the following method are merely used to represent the operations for description, and should not be regarded as representing the execution sequence of the various operations. The method does not need to be executed in the order shown unless explicitly indicated.

[0048] According to one embodiment of the present disclosure, the explicit answer information can be understood as the answer information that can directly answer the user's question or provide the required information, and the non-explicit answer information can be understood as the answer information that cannot directly answer the user's question or provide the required information, and the user can need to make further selection or clarification to obtain the explicit answer information. The non-explicit answer information can include multi-option form answer information or suggestion form answer information.

[0049] According to an embodiment of the present disclosure, the explicit answer information can belong to a general answer, and the multi-option answer form answer information can belong to a folded answer.

[0050] According to an embodiment of the present disclosure, the folded answer refers to the obtained answer information containing some folded options, and the user can select the folded option that meets his / her needs / intentions according to the folded options contained in the folded answer, and enter the next round of information generation based on the selected folded option.

[0051] FIG. 2 schematically shows a flowchart of an information generation method according to an embodiment of the present disclosure.

[0052] As shown in FIG. 2, the information generation method 200 provided by the embodiment of the present disclosure includes operations S210-S230.

[0053] In operation S210, according to a preset checking rule, a folded answer corresponding to the received question sentence is displayed. The folded answer includes M folded option identifiers, and M is a positive integer.

[0054] In operation S220, according to a target folded option identifier triggered in the M folded option identifiers, an initial answer information is generated.

[0055] In operation S230, the initial answer information is processed by an answer generation tool to obtain answer information corresponding to the question sentence.

[0056] According to an embodiment of the present disclosure, in response to the need for information generation, the question sentence can be obtained from an information source. Illustratively, the information source can include a user, and the question sentence can include content input by the user or an identifier related to the question sentence input by the user. As an example, the content of the question sentence can include text, image and / or voice, and the identifier related to the question sentence can include a folded option identifier.

[0057] According to an embodiment of the present disclosure, the folded answer includes a folded option, and the folded option identifier is used to represent the folded option.

[0058] According to an embodiment of the present disclosure, the preset checking rule can be configured according to actual business requirements, which is not limited herein. For example, the preset checking rule can be set to directly display the folded answer corresponding to the received question statement according to the question statement. After displaying the folded answer, the user can select the folded option that best meets the demand or intention from the multiple candidate folded options, and trigger the target folded option identifier.

[0059] According to an embodiment of the present disclosure, the initial response information can be generated according to the target folded option identifier. The initial response information can be processed by using the answer generation tool to obtain the response information corresponding to the question statement.

[0060] According to an embodiment of the present disclosure, the initial response information can be understood as the answer statement corresponding to the question statement generated according to the target folded option identifier, and the response information can be understood as the result obtained after processing the initial response information by using the answer generation tool. In one example, the foregoing response information can include explicit response information.

[0061] According to an embodiment of the present disclosure, the data structure of the generated initial response information can include at least one of a one-dimensional array, a two-dimensional array, a key-value pair, an object, and a graph.

[0062] According to an embodiment of the present disclosure, the processing of the initial response information by the answer generation tool can include processing the data structure of the initial response information into a preset data structure to obtain the response information. According to another embodiment of the present disclosure, the processing of the initial response information by the answer generation tool can also include storing information / data related to the initial response information to a target database to obtain the response information, which is not limited herein.

[0063] According to an embodiment of the present disclosure, the answer generation tool can include a software development kit (SDK), which is a collection of tools, libraries, and documents for software development, and can provide developers with some convenient tools and resources to make it easier to develop applications for specific platforms, frameworks, or technologies.

[0064] According to an embodiment of the present disclosure, the answer generation tool can be designed for a specific operating system, programming language, hardware platform, or development framework. As an example, the answer generation tool can include at least one of the following: Android SDK and iOS SDK for mobile application development, JavaScript SDK for Web development, and TensorFlow and PyTorch for machine learning, which is not limited herein.

[0065] According to an embodiment of the present disclosure, by checking the question sentence according to the preset checking rule, the folded answer corresponding to the question sentence can be directly displayed, and the target folding option identifier is triggered on the basis of the folded answer, and then the response information corresponding to the question sentence is obtained according to the target folding option identifier. In response to receiving the historical question sentence again, since the response information is generated based on the folded answer corresponding to the historical question sentence, the information generation process of the plurality of response tools for the historical question sentence is not triggered, which can effectively avoid the mutual interference or conflict between the information generation processes of the plurality of response tools, thereby at least partially overcoming the technical problems of information transmission confusion and information transmission error in the related art, and helping to improve the matching degree of the response information and the question sentence. On this basis, directly displaying the folded answer corresponding to the question sentence is also helpful to improve the generation efficiency of the response information, and helps to reduce the data transmission amount and data operation amount in the information generation process. In addition, the answer generation tool can be used to process the initial response information to obtain the response information, which can facilitate the management, maintenance and subsequent expansion of the system.

[0066] The information generation method 200 according to an embodiment of the present disclosure will be further described below with reference to FIGS. 3 and 4.

[0067] According to an embodiment of the present disclosure, the preset checking rule includes a question type checking rule and an answer type checking rule. The question type checking rule is used to determine the question type of the question sentence, and the question type includes a historical question sentence or a new question sentence. The answer type checking rule is used to determine the answer type of the answer sentence, and the answer type includes a folded answer sentence or a general answer sentence.

[0068] According to an embodiment of the present disclosure, the historical question sentence can be understood as a question sentence that has been subjected to information generation before. The new question sentence can be understood as a question sentence that has not been subjected to information generation before. The historical response information can be understood as the response information corresponding to the historical question sentence. The historical answer sentence can be understood as the answer sentence corresponding to the historical response information and / or the historical question sentence.

[0069] According to an embodiment of the present disclosure, the answer sentence corresponds to the response information and / or the question sentence, and the answer type can be understood as the answer type of the answer sentence of the response information corresponding to the question sentence. The folded answer sentence can be understood as the answer type of the answer sentence of the response information corresponding to the question sentence belonging to the folded answer. The general answer sentence can be understood as the answer type of the answer sentence of the response information corresponding to the question sentence belonging to the general answer.

[0070] As an example, the above question type and / or answer type can be determined according to the content of the question statement, which can include text, image, voice, and / or the like. As another example, the above question type and / or answer type can also be determined according to the identification related to the question statement, which can include a folding option identification. A person skilled in the art can set a reasonable preset verification rule according to actual needs or scenarios, which is not limited herein.

[0071] For example, it can be determined whether there is a response information corresponding to the question statement in the historical record of response information in the selected interval based on the content of the question statement or the question intention expressed by the folding option identification. If yes, the question type of the question statement is a historical question statement; if no, the question type of the question statement is a new question statement. In response to the question type of the question statement belonging to the historical question statement, it is determined whether the answer type of the historical answer statement corresponding to the historical question statement belongs to the folding answer. If yes, the answer type of the historical answer statement is a folding answer statement; if no, the answer type of the historical answer statement is a general answer statement.

[0072] According to an embodiment of the present disclosure, the question intention can be understood as the purpose, requirement or intention of the question statement expressed or implied by the question statement. The question intention can be determined by text understanding, entity recognition, keyword matching or contact context, which is not limited herein.

[0073] According to an embodiment of the present disclosure, in response to the content of the question statement including text, a deep learning model based on a transformer can be used to perform text understanding processing on the question statement to determine the question intention, and then display the folding answer corresponding to the question statement according to the question intention.

[0074] According to another embodiment of the present disclosure, in response to the question statement including a folding option identification, the folding option identification can be identified to determine the question intention, and then the folding answer corresponding to the question statement is displayed according to the question intention.

[0075] According to an embodiment of the present disclosure, operation S210 can include, in response to the question statement belonging to the historical question statement, determining a historical answer identification according to the question intention of the question statement; and in response to the type of the answer statement corresponding to the historical answer identification belonging to the folding answer statement, displaying the folding answer corresponding to the historical answer identification.

[0076] According to an embodiment of the present disclosure, the historical answer identifier can be used to represent the historical response information and / or the historical answer sentence. In response to the question sentence belonging to the historical question sentence, the historical response information corresponding to the question sentence can be determined according to the question intention of the question sentence, so that the historical answer identifier can be determined according to the historical response information corresponding to the question sentence.

[0077] According to an embodiment of the present disclosure, in response to the type of the answer sentence corresponding to the historical answer identifier belonging to the folded answer sentence, the folded answer corresponding to the historical answer identifier can be directly displayed. Since the displayed folded answer corresponds to the historical answer identifier, and the historical answer identifier is determined according to the question intention of the question sentence, the displayed folded answer corresponds to the question sentence. On this basis, information generation can be performed based on the folded answer corresponding to the question sentence, without triggering multiple response tools to perform information generation for the historical question sentence, thereby effectively avoiding possible mutual interference or conflict between the information generation processes of multiple response tools, so that the technical problems of information transmission confusion and information transmission error in the related art can be at least partially overcome, which helps to improve the matching degree of the response information and the question sentence. In addition, directly displaying the folded answer corresponding to the question sentence is also conducive to improving the generation efficiency of the response information, and helps to reduce the data transmission amount and data operation amount in the information generation process.

[0078] According to an embodiment of the present disclosure, the response tool can be used to generate the answer sentence.

[0079] According to an embodiment of the present disclosure, the response tool can include at least one of a deep learning model based on a convolutional neural network, a deep learning model based on a recurrent neural network, a deep learning model based on a generative adversarial network, and a deep learning model based on a transformer, without limitation.

[0080] According to an embodiment of the present disclosure, the information generation method 200 can further include: in response to the question sentence belonging to a new question sentence, determining a plurality of candidate answer identifiers corresponding to the question sentence; using a scheduling tool to determine a target answer identifier in the plurality of candidate answer identifiers; and in response to the answer sentence corresponding to the target answer identifier belonging to a folded answer sentence, displaying a folded answer corresponding to the target answer identifier.

[0081] According to an embodiment of the present disclosure, the information generation method involves a plurality of different response tools, and the plurality of response tools can generate a plurality of different answer sentences corresponding to the new question sentence. The candidate answer sentence can be understood as the answer sentence corresponding to the response tool, and the target answer sentence can be understood as the answer sentence corresponding to the question sentence determined by the scheduling tool in the plurality of candidate answer sentences. The candidate answer identifier can be used to represent the candidate answer sentence, and the target answer identifier can be used to represent the target answer sentence.

[0082] According to one example embodiment of the present disclosure, four different response tools can be involved in the information generation process, including a response tool 1, a response tool 2, a response tool 3 and a response tool 4. The four response tools can generate four different answer statements, including a candidate answer statement 1, a candidate answer statement 2, a candidate answer statement 3 and a candidate answer statement 4, corresponding to the added question statement. A scheduling tool can be used to determine a target answer statement from the above four candidate answer statements, thereby determining a target answer identifier.

[0083] According to an embodiment of the present disclosure, the scheduling tool can determine the target answer identifier from the multiple candidate answer identifiers based on a scheduling rule.

[0084] According to one embodiment of the present disclosure, the scheduling rule can include determining the target answer according to the priority or weight preset by the response tool, determining the target answer according to the matching degree of the candidate answer with the question statement and / or the context information, determining the target answer according to the confidence or confidence score of the candidate answer, or determining the target answer by comprehensively processing the multiple candidate answers. Those skilled in the art can select a reasonable scheduling rule according to actual needs or application scenarios, which is not limited herein.

[0085] According to an embodiment of the present disclosure, the scheduling tool can select the target answer identifier from the multiple candidate answer identifiers, thereby determining the target answer identifier for subsequent information generation. In response to the answer statement corresponding to the target answer identifier being a folded answer statement, the folded answer corresponding to the target answer identifier can be displayed.

[0086] According to an embodiment of the present disclosure, the scheduling tool can select the candidate answer statement with higher matching degree with the question statement according to the preset evaluation standard, user preference, context information, etc., and exclude unsuitable or conflicting candidate answer statements, thereby facilitating to improve the matching degree of the response information with the question statement. On this basis, it can also help to improve the overall performance of the system and the satisfaction of the user.

[0087] According to an embodiment of the present disclosure, the scheduling tool can include at least one of a deep learning model based on a convolutional neural network, a deep learning model based on a recurrent neural network, a deep learning model based on a generative adversarial network and a deep learning model based on a transformer, which is not limited herein.

[0088] According to one embodiment of the present disclosure, the target answer statement can include any one of the multiple candidate answer statements, for example, the target answer statement can be the candidate answer statement 2. According to another embodiment of the present disclosure, the target answer statement can also be obtained by comprehensively processing the multiple candidate answer statements.

[0089] According to an embodiment of the present disclosure, the information generation method 200 can further include the following operation.

[0090] In response to the answer sentence corresponding to the historical answer identifier or the answer sentence corresponding to the target answer identifier being a general answer sentence, the general answer sentence is determined as the response information corresponding to the question sentence.

[0091] According to an embodiment of the present disclosure, by responding to the answer sentence corresponding to the historical answer identifier or the answer sentence corresponding to the target answer identifier being a general answer sentence, directly determining the general answer sentence as the response information corresponding to the received question sentence, the generation efficiency of the response information can be improved.

[0092] According to an embodiment of the present disclosure, the folded answer can include P levels of sub-folded answers, each of which includes Q sub-folded option identifiers, and P and Q are positive integers. Operation S220 can include repeatedly performing the following operations until the initial response information is obtained: displaying a (p+1) level of sub-folded answers corresponding to a pth sub-folded option identifier according to a Qth sub-folded option identifier of the Q sub-folded option identifiers of the pth level of sub-folded answers being triggered; and generating initial response information corresponding to a (p+1)th sub-folded option identifier according to a (p+1)th sub-folded option identifier of the Q sub-folded option identifiers of the (p+1) level of sub-folded answers being triggered.

[0093] According to an embodiment of the present disclosure, the pth sub-folded answer can be understood as a sub-folded answer corresponding to the pth level, and the pth sub-folded option can include any one of the Q sub-folded option identifiers of the pth sub-folded answer. The pth sub-folded option identifier of the Q sub-folded option identifiers of the pth level being triggered can be understood as determining a target sub-folded option identifier from the Q candidate pth sub-folded option identifiers.

[0094] As an example, the folded answer can include 3 levels of sub-folded answers, each of which can include a plurality of sub-folded options. For example, the 1st level of sub-folded answers can include 3 1st sub-folded options, the 2nd level of sub-folded answers can include 2 2nd sub-folded options, and the 3rd level of sub-folded answers can include 4 3rd sub-folded options.

[0095] According to one example embodiment of the present disclosure, operation S220 can include repeatedly performing the following operations until the initial response information is obtained: identifying any one first sub-folding option identifier that is triggered from the three first-level sub-folding option identifiers, presenting a second-level sub-folding answer corresponding to the first sub-folding option identifier; and generating initial response information corresponding to any one second sub-folding option identifier that is triggered from the two second-level sub-folding option identifiers of the second-level sub-folding answer.

[0096] According to an embodiment of the present disclosure, the response information corresponding to the initial response information can include explicit response information. By repeatedly performing the presentation of the multi-level sub-folding answer and the triggering of the multi-level sub-folding option until the initial response information is obtained, the problem intent can be more comprehensively and accurately determined, thereby improving the accuracy of the interaction. On this basis, the obtained response information can be able to directly answer the user's question or provide the required information, which is conducive to improving the matching degree of the response information and the question sentence, thereby helping to improve the accuracy of information generation and user satisfaction.

[0097] According to an embodiment of the present disclosure, each sub-folding option identifier corresponds to a source identifier. The information generation method 200 can further include the following operations.

[0098] Before presenting the (p+1)-th level sub-folding answer corresponding to the p-th sub-folding option identifier: using the answer generation tool, calling a response tool corresponding to the source identifier of the p-th sub-folding option identifier; and using the response tool, generating the (p+1)-th level sub-folding answer.

[0099] According to an embodiment of the present disclosure, the source identifier can represent a response tool corresponding to the sub-folding option. As an example, the source identifiers corresponding to the Q sub-folding option identifiers of the p-th level sub-folding answer can include one or more, which is not limited herein.

[0100] According to an embodiment of the present disclosure, according to the p-th sub-folding option identifier that is triggered from the Q sub-folding option identifiers of the p-th level, the answer generation tool can be used to call a response tool corresponding to the source identifier of the p-th sub-folding option identifier, and then the response tool can be used to generate the (p+1)-th level sub-folding answer, and finally the (p+1)-th level sub-folding answer corresponding to the p-th sub-folding option identifier is presented.

[0101] According to an embodiment of the present disclosure, calling a response tool corresponding to the source identifier of the p-th sub-folding option identifier can ensure the consistency between the p-th sub-folding option identifier and the (p+1)-th level sub-folding answer, thereby facilitating the coherence of the context content to generate the (p+1)-th level sub-folding answer that is more consistent with the p-th sub-folding option identifier.

[0102] According to an embodiment of the present disclosure, the folded answer has state information. Generating the initial answer information corresponding to the (p+1)-th sub-folded option identifier comprises: in response to the state information including the (p+1)-th sub-folded option identifier, invoking, by the context management tool, the initial answer information corresponding to the (p+1)-th sub-folded option identifier; and in response to the state information not including the (p+1)-th sub-folded option identifier, generating, by the answer generation tool, the initial answer information.

[0103] According to an embodiment of the present disclosure, the state information can be used to represent a trigger path of a target folded option identifier and / or a target sub-folded option identifier corresponding to the folded answer. The trigger path of the target folded option identifier and / or the target sub-folded option identifier can be understood as a trigger result of the target folded option identifier and / or a display result of the multiple hierarchical sub-folded options and a trigger result of the multiple hierarchical sub-folded option identifiers in the information generation process.

[0104] For example only, the folded answer can include 2 levels of sub-folded answers. The 1st level sub-folded answer can include 3 1st sub-folded options, i.e., sub-folded option 1.1, sub-folded option 1.2 and sub-folded option 1.3. In the 1st level sub-folded answer, the sub-folded option 1.2 can be triggered to display the 2nd level sub-folded answer corresponding to the sub-folded option 1.2. The 2nd level sub-folded answer can include 2 2nd sub-folded options, i.e., sub-folded option 2.1 and sub-folded option 2.2. In the 2nd level sub-folded answer, the sub-folded option 2.1 can be triggered to generate the initial answer information corresponding to the sub-folded option 2.2. The state information of the folded answer can be used to represent the trigger path from the 1st level sub-folded answer to the sub-folded option 1.2, from the sub-folded option 1.2 to the 2nd level sub-folded answer, from the 2nd level sub-folded answer to the sub-folded option 2.1, and finally from the sub-folded option 2.1 to the initial answer information.

[0105] According to an embodiment of the present disclosure, the context management tool can be used to generate and / or store the state information related to the folded answer, and the context management tool can also be used to invoke the initial answer information corresponding to the target folded option identifier and / or the target sub-folded option identifier according to the state information. Through such a setting, the context management tool can be used to maintain the state information of the folded answer corresponding to the question statement, so as to accurately restore the trigger path of the target folded identifier and / or the target sub-folded option identifier of the folded answer, and thereby realize context management.

[0106] According to one embodiment of the present disclosure, in response to the question type of the question sentence belonging to the historical question sentence and the answer type of the question sentence belonging to the folded answer sentence, the context management tool can determine the state information of the folded answer according to the historical answer identifier, so that the folded answer corresponding to the question sentence can be correctly displayed by using the state information, thereby keeping the consistency of the response information in the case of multiple information generation for the same question intention, and helping to improve the matching degree of the response information and the question sentence and the satisfaction of the user.

[0107] According to an embodiment of the present disclosure, the context management tool can include at least one of a SQL or NoSQL based database, a recurrent neural network based deep learning model, and a buffer memory, without limitation.

[0108] According to an embodiment of the present disclosure, the information generation method 200 can further include the following operations.

[0109] Before operation S210, the received initial question sentence can be normalized based on a preset input rule to obtain the question sentence, and operation S230 can include normalizing the obtained initial response information based on a preset output rule to obtain the response information.

[0110] As an example, the initial question sentence can include content input by a user.

[0111] According to an embodiment of the present disclosure, the normalization of the initial question sentence based on the preset input rule can include processing the data structure of the initial question sentence into a first preset data structure to obtain the question sentence. The first preset data structure is preferably a unified general data structure to adapt to initial question sentences of different data structures. By way of example, the first preset data structure can be selected as an object and / or a map.

[0112] According to an embodiment of the present disclosure, the normalization of the initial response information based on the preset output rule can include processing the data structure of the initial response information into a second preset data structure to obtain the response information. The second preset data structure is preferably a unified general data structure to adapt to initial response information of different data structures. By way of example, the second preset data structure can be selected as an object and / or a map.

[0113] According to an embodiment of the present disclosure, an object is a data structure for storing key-value pairs. A map is another data structure for storing key-value pairs, and the keys can be of any data type. In some possible embodiments, objects and maps can be combined / nested with each other to provide a more flexible and versatile data structure. Such an arrangement can facilitate unified data management and maintenance of all received initial question information and / or generated initial answer information, which in turn facilitates subsequent possible system expansion and the like. A person skilled in the art can reasonably select the first preset data format and / or the second preset data format according to actual needs and application scenarios, which is not limited herein.

[0114] According to an embodiment of the present disclosure, the information generation method 200 can further include the following operations.

[0115] After operation S230: determining, according to the question sentence, a target database corresponding to a question intention of the question sentence; and storing the question sentence, the folded answer identifier, the target folded option identifier, and the answer information in the target database in association.

[0116] According to an embodiment of the present disclosure, the folded answer identifier can be used to represent the folded answer sentence.

[0117] According to an embodiment of the present disclosure, the target database can be used to store the question sentence and the folded answer identifier, the target folded option identifier, and the answer information related to the question sentence in association according to the question intention. Through such an arrangement, the target database can store and maintain the history record of the answer information according to the question intention, and can cooperate with the context management tool to associate the question sentence and the answer information corresponding to the question sentence with the context content and state information, thereby facilitating data maintenance and management.

[0118] According to an embodiment of the present disclosure, in response to the question type of the question sentence belonging to the historical question sentence and the answer type of the question sentence belonging to the folded answer sentence, the corresponding target database can be determined according to the question intention of the question sentence, and the question sentence and the folded answer identifier, the target folded option identifier, and the answer information related to the question sentence stored in the target database can be checked according to the preset checking rule, to determine the question type of the question sentence and the answer type of the answer sentence corresponding to the question sentence, thereby determining the historical answer identifier and displaying the folded answer corresponding to the historical answer identifier.

[0119] According to an embodiment of the present disclosure, the target database can include at least one of a database based on SQL or NoSQL or a buffer memory and a deep learning model based on a recurrent neural network, which is not limited herein.

[0120] FIG. 3 illustrates an exemplary schematic diagram of an information generation method according to an embodiment of the present disclosure.

[0121] As shown in FIG. 3, based on a preset input rule, the received initial question sentence is normalized by using an answer generation tool 301 to obtain a question sentence. On this basis, the question intent can be determined according to the received question sentence. The corresponding target database 302 can be determined according to the question intent, and the question type of the question sentence can be determined in combination with a preset verification rule.

[0122] In response to the question type of the question sentence belonging to a historical question sentence, the historical answer identifier corresponding to the historical question sentence can be determined by using the target database 302, and the historical answer identifier corresponds to the historical question sentence and its historical answer information and / or historical answer sentence. According to the historical answer identifier, the type of the answer sentence corresponding to the historical answer identifier can be determined by using the target database 302.

[0123] In response to the type of the answer sentence corresponding to the historical answer identifier belonging to a folded answer sentence, the folded answer corresponding to the historical answer identifier can be directly displayed. In response to the type of the answer sentence corresponding to the historical answer identifier belonging to a general answer sentence, the general answer sentence can be determined as the answer information corresponding to the historical question sentence.

[0124] The folded answer can include M folded option identifiers, and M is a positive integer. According to the triggered target folded option identifier in the M folded option identifiers, the answer generation tool 302 is used to call the answer tool 303_1 corresponding to the source identifier of the target folded option identifier, and the answer tool 303_1 is used to generate the answer sentence corresponding to the target folded option identifier. In response to the answer type of the answer sentence corresponding to the target folded option identifier belonging to a general answer sentence, the initial answer information can be generated according to the general answer sentence by using the answer generation tool 302. The folded answer can include P levels of sub-folded answers, and each sub-folded answer includes Q sub-folded option identifiers, and P and Q are positive integers. In response to the answer type of the answer sentence corresponding to the target folded option identifier belonging to a folded answer sentence, the sub-folded answer corresponding to the target folded option identifier can be displayed.

[0125] According to the p-th sub-folding option identifier triggered in the Q sub-folding option identifiers of the p-th level (i.e., the target sub-folding option identifier), the answer generation tool 301 can be used to call the answer tool 303_1 corresponding to the source identifier of the p-th sub-folding option identifier, and generate an answer sentence corresponding to the p-th sub-folding option identifier by using the answer tool 303_1. In response to the answer type of the answer sentence corresponding to the p-th sub-folding option identifier belonging to a folding answer sentence, the answer sentence can be determined as a sub-folding answer of the (p+1)-th level, and the sub-folding answer of the (p+1)-th level is displayed.

[0126] According to the (p+1)-th sub-folding option identifier triggered in the Q sub-folding option identifiers of the (p+1)-th level (i.e., the target sub-folding option identifier), the answer tool 303_1 corresponding to the (p+1)-th sub-folding option identifier can be called, and an answer sentence corresponding to the (p+1)-th sub-folding option identifier can be generated by using the answer tool 303. Until the answer type of the answer sentence corresponding to the (p+1)-th sub-folding option identifier belongs to a general answer sentence, the initial answer information can be generated by using the answer generation tool 301 according to the general answer sentence.

[0127] The folding answer has state information. In response to the state information of the folding answer including the (p+1)-th sub-folding option identifier, the initial answer information corresponding to the (p+1)-th sub-folding option identifier can be called by using the context management tool 304. In response to the state information of the folding answer not including the (p+1)-th sub-folding option identifier, the initial answer information can be generated by using the answer generation tool 301.

[0128] On this basis, the obtained initial answer information can be standardized by using the answer generation tool 301 based on a preset output rule to obtain the answer information. After obtaining the answer information corresponding to the question sentence, the target database 302 corresponding to the question intention of the question sentence can be determined according to the question sentence; and the question sentence, the folding answer identifier, the target folding option identifier, and the answer information are stored in the target database 302.

[0129] In response to the question type of the question sentence belonging to a newly added question sentence, the answer tool 303 can be used to generate a plurality of candidate answers corresponding to the question sentence. The target answer identifier can be determined in the plurality of candidate answer identifiers by using the scheduling tool 305. As an example, the candidate answer identifier generated by the answer tool 303_2 can be determined as the target answer identifier by using the scheduling tool 305.

[0130] In response to the answer statement corresponding to the target answer identifier being a folded answer statement, a folded answer corresponding to the target answer identifier can be displayed. In response to the type of the answer statement corresponding to the target answer identifier being a general answer statement, the general answer statement can be determined as the response information corresponding to the above-mentioned newly-added question statement.

[0131] FIG. 4 exemplarily shows an exemplary schematic diagram of an information generation process according to an embodiment of the present disclosure.

[0132] As shown in FIG. 4, based on a preset input rule, the received initial question statement 401 is normalized to obtain a question statement 402. According to a question type checking rule, it is determined whether the question statement 402 has been subjected to information generation before. If yes, the question type of the question statement 402 belongs to a historical question statement 403_1; if no, the question type of the question statement 402 belongs to a newly-added question statement 403_2.

[0133] In response to the question type of the question statement 402 belonging to the historical question statement 403_1, a historical answer identifier 404 of a historical answer statement corresponding to the historical question statement 403_1 can be determined according to the question intent of the historical question statement 403_1. According to an answer type checking rule, it is determined whether the historical answer statement corresponding to the historical answer identifier 404 is a folded answer. If yes, the answer type of the historical answer statement belongs to a folded answer statement 405_1; if no, the answer type of the historical answer statement belongs to a general answer statement 405_2.

[0134] In response to the question type of the question statement 402 belonging to the newly-added question statement 403_2, a plurality of candidate answer identifiers 406 corresponding to the newly-added question statement 403_2 can be determined, and a target answer identifier 407 can be determined from the plurality of candidate answer identifiers 406 by using a scheduling tool.

[0135] In response to the answer statement corresponding to the target answer identifier 407 being the folded answer statement 405_1, a folded answer corresponding to the target answer identifier 407 can be displayed.

[0136] In response to the answer statement corresponding to the historical answer identifier 404 or the answer statement corresponding to the target answer identifier 407 being the general answer statement 405_2, the general answer statement 405_2 can be determined as the response information 410 corresponding to the question statement 402.

[0137] The folded answer can include P levels of sub-folded answers, each of which includes Q sub-folded option identifiers, and P and Q are positive integers. The following operations can be repeatedly performed until the initial response information is obtained: according to a pthsub-folded option identifier triggered from Q sub-folded option identifiers of a pthlevel, a (p+1) thlevel sub-folded answer corresponding to the pthsub-folded option identifier is displayed; and according to a (p+1) thsub-folded option identifier triggered from Q sub-folded option identifiers of the (p+1) thlevel sub-folded answer, initial response information corresponding to the (p+1) thsub-folded option identifier is generated.

[0138] In response to the answer sentence corresponding to the target folded option identifier belonging to the general answer sentence 405_2, the initial response information 409 can be determined according to the general answer sentence 405_2.

[0139] On this basis, the initial response information 409 obtained can be normalized according to a preset output rule to obtain response information 410.

[0140] After obtaining the response information 410: according to the question sentence, a target database 411 corresponding to a question intention of the question sentence can be determined; and the question sentence 402, the folded answer identifier 412, the target folded option identifier 408, and the response information 410 are stored in association in the target database 411.

[0141] The above is only an exemplary embodiment, but is not limited thereto, and other information generation methods known in the art can also be included as long as information generation can be achieved.

[0142] FIG. 5 schematically shows a block diagram of an information generation apparatus according to an embodiment of the present disclosure.

[0143] As shown in FIG. 5, the information generation apparatus 500 can include a display module 510, a generation module 520, and a processing module 530.

[0144] The display module 510 is configured to display a folded answer corresponding to a received question sentence according to a preset verification rule, wherein the folded answer includes M folded option identifiers, and M is a positive integer.

[0145] The generation module 520 is configured to generate initial response information according to a target folded option identifier triggered from the M folded option identifiers.

[0146] The processing module 530 is configured to process the initial response information by using an answer generation tool to obtain response information corresponding to the question sentence.

[0147] According to an embodiment of the present disclosure, the display module 510 can include a question type verification module, an answer type verification module, a historical answer identifier determination module, and a display sub-module.

[0148] The question type verification module is configured to determine a question type of the question statement, and the question type includes a historical question statement or a new question statement.

[0149] The answer type verification module is configured to determine an answer type of the answer statement, and the answer type includes a folded answer statement or a general answer statement.

[0150] The historical answer identifier determination module is configured to, in response to the question statement belonging to the historical question statement, determine a historical answer identifier according to a question intention of the question statement.

[0151] The display submodule is configured to, in response to the answer statement corresponding to the historical answer identifier belonging to the folded answer statement, display a folded answer corresponding to the historical answer identifier, and in response to the answer statement corresponding to the target answer identifier belonging to the folded answer statement, display a folded answer corresponding to the target answer identifier.

[0152] According to an embodiment of the present disclosure, the generation module 520 can include a response submodule, a scheduling submodule, and a sub-folded answer submodule.

[0153] The response submodule is configured to, in response to the question statement belonging to the new question statement, determine a plurality of candidate answer identifiers corresponding to the question statement.

[0154] The scheduling submodule is configured to determine a target answer identifier from the plurality of candidate answer identifiers by using a scheduling tool.

[0155] The sub-folded answer submodule is configured to repeatedly perform the following operations until initial response information is obtained: display a sub-folded answer of a (p+1)th level corresponding to a pth sub-folded option identifier from Q sub-folded option identifiers of the pth level that is triggered according to the pth sub-folded option identifier; and generate initial response information corresponding to a (p+1)th sub-folded option identifier according to a (p+1)th sub-folded option identifier from Q sub-folded option identifiers of the (p+1)th level that is triggered according to the sub-folded answer of the (p+1)th level.

[0156] According to an embodiment of the present disclosure, the sub-folded answer submodule can further include a calling unit and a generating unit.

[0157] The calling unit is configured to, before displaying the sub-folded answer of the (p+1)th level corresponding to the pth sub-folded option identifier: call a response tool corresponding to a source identifier of the pth sub-folded option identifier by using an answer generation tool.

[0158] The generating unit is configured to generate the sub-folded answer of the (p+1)th level by using the response tool.

[0159] According to an embodiment of the present disclosure, the information generation apparatus 500 can further include a general answer module.

[0160] The general answer module is configured to determine the answer statement as the response information corresponding to the question statement, in response to the answer statement corresponding to the historical answer identifier or the answer statement corresponding to the target answer identifier being a general answer statement.

[0161] According to an embodiment of the present disclosure, the generation module 520 can further include a state information module.

[0162] The state information module is configured to: in response to the state information including the (p+1)th sub-folding option identifier, invoke the initial response information corresponding to the (p+1)th sub-folding option identifier by using the context management tool; and in response to the state information not including the (p+1)th sub-folding option identifier, generate the initial response information by using the answer generation tool.

[0163] According to an embodiment of the present disclosure, the processing module 530 can include an input specification sub-module and an output specification sub-module.

[0164] The input specification sub-module is configured to, before displaying the folding answer corresponding to the received question statement according to a preset checking rule: perform specification processing on the received initial question statement based on a preset input rule to obtain the question statement.

[0165] The output specification sub-module is configured to perform specification processing on the obtained initial response information based on a preset output rule to obtain the response information.

[0166] According to an embodiment of the present disclosure, the information generation apparatus 500 can further include a target database module.

[0167] The target database module is configured to, after processing the initial response information by using the answer generation tool to obtain the response information: determine, according to the question statement, a target database corresponding to a question intention of the question statement; and store the question statement, the folding answer identifier, the target folding option identifier and the response information in association to the target database.

[0168] Any of the modules, sub-modules, units, sub-units, or at least part of any of them according to embodiments of the present disclosure can be implemented in one module. Any of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure can be split into multiple modules. Any of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure can be implemented at least in part as a hardware circuit, for example, a field-programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application-specific integrated circuit (ASIC), or any other reasonable way of hardware or firmware by integrating or packaging circuits, or in any one of software, hardware, and firmware, or in a proper combination of any of them. Alternatively, any of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure can be implemented at least in part as computer program modules, which can perform corresponding functions when the computer program modules are run.

[0169] For example, any of the modules 510, 520, and 530 can be combined in one module / unit / sub-unit, or any of them can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of the modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units, and implemented in one module / unit / sub-unit. According to embodiments of the present disclosure, at least one of the modules 510, 520, and 530 can be implemented at least in part as a hardware circuit, for example, a field-programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application-specific integrated circuit (ASIC), or any other reasonable way of hardware or firmware by integrating or packaging circuits, or in any one of software, hardware, and firmware, or in a proper combination of any of them. Alternatively, at least one of the modules 510, 520, and 530 can be implemented at least in part as computer program modules, which can perform corresponding functions when the computer program modules are run.

[0170] It should be noted that the information generation device part in embodiments of the present disclosure corresponds to the information generation method part in embodiments of the present disclosure, and the description of the information generation device part is specifically referred to the information generation method part, which will not be repeated here.

[0171] FIG. 6 schematically illustrates a block diagram of an electronic device suitable for implementing the information generation method according to an embodiment of the present disclosure. The electronic device shown in FIG. 6 is merely an example and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.

[0172] As shown in FIG. 6, the computer electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 909 into a random access memory (RAM) 603. The processor 601 can include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor, and / or a related chipset, and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), and so on. The processor 601 can also include an on-board memory for cache use. The processor 601 can include a single processing unit or a plurality of processing units for performing different actions of the method processes according to the embodiments of the present disclosure.

[0173] In the RAM 603, various programs and data required for the operation of the electronic device 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The processor 601 performs various operations of the method processes according to the embodiments of the present disclosure by executing the programs in the ROM 602 and / or the RAM 603. It is to be noted that the programs can also be stored in one or more memories other than the ROM 602 and the RAM 603. The processor 601 can also perform various operations of the method processes according to the embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0174] According to an embodiment of the present disclosure, the electronic device 600 can further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 can further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, and so on; an output portion 607 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), and so on, and a speaker, and so on; a storage portion 608 including a hard disk, and so on; and a communication portion 609 including a network interface card such as a LAN card, a modem, and so on. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as necessary. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and so on is mounted on the drive 610 as necessary, so that a computer program read out therefrom is installed in the storage portion 608 as necessary.

[0175] According to an embodiment of the present disclosure, the method flow according to the embodiments of the present disclosure can be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product comprising a computer program carrying out the program codes for executing the method shown in the flow chart. In such embodiments, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from the detachable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system / apparatus according to the embodiments of the present disclosure are executed. According to an embodiment of the present disclosure, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0176] The present disclosure also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments, or exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which when executed, implement the method according to the embodiments of the present disclosure.

[0177] According to an embodiment of the present disclosure, the computer readable storage medium can be a non-volatile computer readable storage medium. For example, it can include but not limited to portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any appropriate combination thereof. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0178] For example, according to an embodiment of the present disclosure, the computer readable storage medium can include one or more memories other than the ROM 602 and / or the RAM 603 and / or the ROM 602 and the RAM 603 described above.

[0179] The embodiments of the present disclosure also include a computer program product comprising a computer program containing program codes for executing the method provided by the embodiments of the present disclosure, which program codes are used to make the electronic device implement the information generation method provided by the embodiments of the present disclosure when the computer program product is running on the electronic device.

[0180] When the computer program is executed by the processor 601, the above-mentioned functions defined in the system / apparatus according to the embodiments of the present disclosure are executed. According to an embodiment of the present disclosure, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0181] In one embodiment, the computer program can be embodied on a tangible memory device, such as a magnetic storage device, an optical storage device, etc. In another embodiment, the computer program can be transmitted in a signal over a network, distributed across networks, downloaded and installed, and / or installed from a removable memory media 611. The computer program comprising the program code can be transmitted using any suitable network medium, including, but not limited to wireless, wired, etc., or any suitable combination of the foregoing.

[0182] According to an embodiment of the disclosure, program code for execution by a computer program can be written in any combination of one or more programming languages, and can specifically be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, Java, C++, python, “C”, or similar programming languages. Program code can execute entirely on a user’s computing device, partly on a user device, partly on a remote computing device, or entirely on a remote computing device or server. In the latter scenario, the remote computing device can be connected to the user’s computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0183] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features recited in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not expressly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0184] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. An information generation method, comprising: displaying a collapsed answer corresponding to a received question statement according to a preset checking rule, wherein the collapsed answer comprises M collapsed option identifiers, M being a positive integer; generating initial response information according to a target collapsed option identifier triggered from the M collapsed option identifiers; and processing the initial response information by using an answer generation tool to obtain response information corresponding to the question statement.

2. The method of claim 1, wherein, the preset checking rule comprises a question type checking rule and an answer type checking rule, the question type checking rule is used to determine a question type of the question statement, and the question type comprises a historical question statement or a new question statement; and the answer type checking rule is used to determine an answer type of an answer statement, and the answer type comprises a collapsed answer statement or a general answer statement.

3. The method of claim 2, wherein, the displaying of the collapsed answer corresponding to the received question statement according to the preset checking rule comprises: in response to the question statement belonging to the historical question statement, determining a historical answer identifier according to a question intention of the question statement; and in response to an answer statement corresponding to the historical answer identifier belonging to the collapsed answer statement, displaying a collapsed answer corresponding to the historical answer identifier.

4. The method of claim 3, further comprising: in response to the question statement belonging to the new question statement, determining a plurality of candidate answer identifiers corresponding to the question statement; determining a target answer identifier from the plurality of candidate answer identifiers by using a scheduling tool; and in response to an answer statement corresponding to the target answer identifier belonging to the collapsed answer statement, displaying a collapsed answer corresponding to the target answer identifier.

5. The method of claim 3, further comprising: in response to an answer statement corresponding to the historical answer identifier or an answer statement corresponding to the target answer identifier belonging to the general answer statement, determining the answer statement as response information corresponding to the question statement. the collapsed answer comprises P levels of sub-collapsed answers, each of the sub-collapsed answers comprises Q sub-collapsed option identifiers, and P and Q are positive integers; 6. The method of any one of claims 1 to 5, wherein, the generating of the initial response information according to the target collapsed option identifier triggered from the M collapsed option identifiers comprises: repeatedly performing the following operations until the initial response information is obtained: displaying a (p+1)th level of sub-collapsed answer corresponding to a pth sub-collapsed option identifier triggered from Q sub-collapsed option identifiers of a pth level according to the pth sub-collapsed option identifier; and generating initial response information corresponding to a (p+1)th sub-collapsed option identifier triggered from Q sub-collapsed option identifiers of the (p+1)th level of sub-collapsed answer according to the (p+1)th sub-collapsed option identifier. each of the sub-collapsed option identifiers corresponds to a source identifier; the method further comprises, before the displaying of the (p+1)th level of sub-collapsed answer corresponding to the pth sub-collapsed option identifier:

7. The method of claim 6, wherein, calling a response tool corresponding to the source identifier of the pth sub-collapsed option identifier by using the answer generation tool; and ​ ​ The response tool is used to generate the (p+1)th level sub-folded answer.

8. The method of claim 7, wherein, The folded answer has state information; The generating includes: In response to the state information including the (p+1)th sub-folded option identifier, the context management tool is used to call initial response information corresponding to the (p+1)th sub-folded option identifier; and In response to the state information not including the (p+1)th sub-folded option identifier, the answer generation tool is used to generate the initial response information.

9. The method of any one of claims 1 to 5, further comprising, before the displaying the folded answer corresponding to the received question statement according to the preset checking rule: normalizing the received initial question statement based on a preset input rule to obtain the question statement; and The processing of the initial response information by the answer generation tool to obtain the response information includes: normalizing the obtained initial response information based on a preset output rule to obtain the response information.

10. The method of any one of claims 1 to 5, further comprising, after the processing of the initial response information by the answer generation tool to obtain the response information: determining a target database corresponding to a question intent of the question statement according to the question statement; and storing the question statement, the folded answer identifier, the target folded option identifier, and the response information in association to the target database.

11. An information generation apparatus, comprising: a display module configured to display a folded answer corresponding to a received question statement according to a preset checking rule, wherein the folded answer includes M folded option identifiers, M being a positive integer; a generation module configured to generate initial response information according to a target folded option identifier triggered from the M folded option identifiers; and a processing module configured to process the initial response information by an answer generation tool to obtain response information corresponding to the question statement.

12. An electronic device, comprising: one or more processors; a memory configured to store one or more instructions, wherein when the one or more instructions are executed by the one or more processors, the one or more processors are caused to implement the method of any one of claims 1 to 10.

13. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the method of any one of claims 1 to 10.

14. A computer program product, comprising computer executable instructions that, when executed, are configured to implement the method of any one of claims 1 to 10.

Images