Answer indication method and apparatus based on question type and scenario

Abstract

This disclosure relates to the field of computer technology, and in particular to a method and apparatus for providing answer indication based on question type and scenario. The method includes: obtaining the question type of the input question based on an input question and a historical dialogue set corresponding to the input question; obtaining scenario information corresponding to the input question; and, based on the question type and the scenario information, obtaining answer indication information corresponding to the input question. This disclosure can improve the accuracy of answer indication information acquisition, enable intelligent question answering for input questions, and enhance the flexibility and intelligence of intelligent question answering.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method and apparatus for indicating answers based on question type and scenario. Background Technology

[0002] With the development of artificial intelligence technology, intelligent question answering is playing an increasingly important role in daily life and work. For example, users can input a question and receive an answer using AI technology. The AI ​​model can directly identify the question, obtain the corresponding answer, and output it. Summary of the Invention

[0003] This disclosure provides a method and apparatus for providing answer indication based on question type and scenario. It can provide corresponding answers based on the input question and the respondent's perspective, thereby improving the accuracy and matching of answer information. The technical solution of this disclosure is as follows:

[0004] According to a first aspect of the present disclosure, a method for indicating answers based on question type and scenario is provided, including: Based on the input question and the corresponding historical dialogue set, the question type of the input question is obtained; Obtain the scenario information corresponding to the input question; Under the given scenario information, and based on the question type, obtain the answer indication information corresponding to the input question.

[0005] According to some embodiments, the step of obtaining answer indication information corresponding to the input question based on the question type under the scenario information includes: The scenario information and the question type are input into a transformer-based fine-tuning model for recognition, and the answer indication information corresponding to the input question is obtained.

[0006] According to some embodiments, obtaining the question type of the input question based on the input question and the historical dialogue set corresponding to the input question includes: Obtain the semantic information and / or key information of the input question; Based on the semantic information and / or the key information, obtain the historical dialogue set corresponding to the input question; Based on the question types of each historical dialogue in the historical dialogue set, a type acquisition model is used to obtain the question type corresponding to the input question.

[0007] According to some embodiments, the step of obtaining answer indication information corresponding to the input question based on the question type under the scenario information includes: Based on the scenario information, obtain the question classification result corresponding to the question type, wherein the question classification result includes the answer indication information corresponding to the input question and / or the acquisition process information of the question classification result.

[0008] According to some embodiments, the method further includes: If the question type of the input question is not found based on the input question and the corresponding historical dialogue set, a prompt message is issued. Based on the relevant information entered in response to the prompt, the question type of the input question is obtained.

[0009] According to some embodiments, the method further includes: If the answer indication information indicates that the input question should be answered, a large model is used to identify the input question and obtain the answer information corresponding to the input question; or If the answer indication information indicates that the input question should not be answered, the operation corresponding to the input question is obtained and executed.

[0010] According to some embodiments, the method further includes: Based on business requirements, the mapping relationship between scenario information and answer indication information is adjusted to obtain the adjusted mapping relationship, wherein the mapping relationship is used to obtain the answer indication information corresponding to the input question.

[0011] According to a second aspect of the present disclosure, an answer indication device based on question type and scenario is provided, comprising: The type acquisition unit is used to acquire the question type of the input question based on the input question and the historical dialogue set corresponding to the input question; The information acquisition unit is used to acquire the scenario information corresponding to the input question; The answer indication unit is used to obtain answer indication information corresponding to the input question based on the question type under the scenario information.

[0012] According to a third aspect of the present disclosure, an electronic device is provided, comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the answer indication method based on question type and scenario as described in any of the preceding aspects.

[0013] According to a fourth aspect of the present disclosure, a storage medium is provided that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the answer indication method based on question type and scenario as described in any of the preceding aspects.

[0014] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in any one of the preceding aspects.

[0015] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: In some or related embodiments, the question type of the input question is obtained based on the input question and the historical dialogue set corresponding to the input question; the scene information corresponding to the input question is obtained; and under the scene information, answer indication information corresponding to the input question is obtained based on the question type. Therefore, the question type corresponding to the input question can be obtained, and the answer indication information for the input question can be obtained based on the scene information and the question type. This answer indication information can be used to indicate how to answer the input question, reducing the direct use of large models for answering. It ensures that the answer information is consistent with the question type and scene information, providing corresponding answer instructions for the input question. This reduces the possibility of inaccurate answer information acquisition when directly answering without considering the question type and scene information, improving the accuracy of answer indication information acquisition. Intelligent question answering can be performed on the input question, improving the flexibility and intelligence of intelligent question answering, and thus improving the accuracy and matching of answer information determination.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0018] Figure 1 This is a flowchart of the first method for indicating answers based on question type and scenario provided in this disclosure embodiment; Figure 2 This is a flowchart of a second method for providing answer indication based on question type and scenario, provided in this embodiment of the disclosure; Figure 3 This is an example diagram illustrating a method for indicating answers based on question type and scenario provided in this embodiment of the disclosure; Figure 4This is a block diagram illustrating an answer indication device based on question type and scenario, according to an exemplary embodiment. Figure 5 This is an example schematic diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0020] This disclosure provides methods, apparatus, electronic devices, and storage media for indicating answers based on question type and scenario. In some embodiments, the terms "method for indicating answers based on question type and scenario" and "information processing method" and "communication method" can be used interchangeably; the terms "apparatus for indicating answers based on question type and scenario" and "information processing apparatus" and "communication apparatus" can be used interchangeably; and the terms "information processing system" and "communication system" can be used interchangeably.

[0021] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0022] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0023] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0024] In this disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular or a plural expression.

[0025] In the embodiments disclosed herein, "multiple" refers to two or more.

[0026] In some embodiments, the terms “at least one of,” “one or more,” “a plurality of,” and “multiple” may be used interchangeably.

[0027] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0028] In some embodiments, "terminal" or "terminal device" may be referred to as "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," etc.

[0029] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0030] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0031] Figure 1 This is a flowchart of the first method for providing answer indication based on question type and scenario provided in this disclosure embodiment, such as... Figure 1 As shown, this method for providing answer indication based on question type and scenario can be used in scenarios where answering questions requires indicating the answer based on question type and scenario information. It includes the following steps: In step S11, the question type of the input question is obtained based on the input question and the historical dialogue set corresponding to the input question; In some embodiments, the implementing entity of this disclosure may be, for example, an electronic device. This electronic device does not specifically refer to a particular fixed electronic device. For example, when the device identifier changes, the electronic device may also change accordingly. For example, when the structure of the electronic device changes, the electronic device may also change accordingly. The name of the electronic device is not limited. The electronic device may, for example, be a processing device, a terminal, etc.

[0032] According to some embodiments, the input question may be a question to be answered, and the input question is not specifically a fixed question. For example, if the content of the input question changes, the input question may also change accordingly. For example, if the input method corresponding to the input question changes, the input question may also change accordingly, wherein the input method includes, but is not limited to, the following: For example, if the input time point corresponding to the input question changes, the input question may also change accordingly.

[0033] In some embodiments, the input problem may be, for example, a voice input problem, which may be voice information input through a voice input control.

[0034] According to some embodiments, a historical dialogue set can be, for example, a collection of historical dialogues, which does not specifically refer to a fixed set. For example, when a particular historical dialogue included in the historical dialogue set changes, the historical dialogue set can also change accordingly. For example, when the number of historical dialogues included in the historical dialogue set changes, the historical dialogue set can also change accordingly.

[0035] In some embodiments, the set of historical dialogues may be, for example, a set corresponding to the input question. That is, different input questions may correspond to different sets of historical dialogues.

[0036] According to some embodiments, the question type of the input question can be obtained based on the input question and the historical dialogue set corresponding to the input question.

[0037] In step S12, the scenario information corresponding to the input question is obtained; According to some embodiments, scenario information can be used to indicate the scenario corresponding to the input question. This scenario information includes, but is not limited to, the respondent's stance, service provider information (respondent's main information), and the scenario to which the input question belongs. The respondent's stance includes, but is not limited to, compliance in product sales, value guidance, and dispute resolution. Service provider information may include, for example, waiters or executives. The scenario to which the input question belongs may include, for example, being geared towards the general public, experts, or academics. This scenario information does not refer to any specific fixed information. For example, when the method of obtaining scenario information changes, the scenario information may also change accordingly.

[0038] In some embodiments, scenario information corresponding to the input question can be obtained.

[0039] In step S13, under the scenario information, answer indication information corresponding to the input question is obtained according to the question type.

[0040] According to some embodiments, the answer indication information may be, for example, information indicating how to obtain the answer. This answer indication information is not specifically defined by any fixed information. For example, the answer indication information may change accordingly when the scenario information or question type changes. Similarly, the answer indication information may change accordingly when the method of obtaining the answer changes.

[0041] According to some embodiments, under the scenario information, answer indication information corresponding to the input question is obtained according to the question type.

[0042] In some or related embodiments, the question type of the input question is obtained based on the input question and the historical dialogue set corresponding to the input question; the scene information corresponding to the input question is obtained; and under the scene information, answer indication information corresponding to the input question is obtained based on the question type. Therefore, the question type corresponding to the input question can be obtained, and the answer indication information for the input question can be obtained based on the scene information and the question type. This answer indication information can be used to indicate how to answer the input question, reducing the direct use of large models for answering, and ensuring that the answer information matches the question type and scene information. It can provide corresponding answer instructions for the input question, reducing the possibility of inaccurate answer information when directly answering without considering the question type and scene information. It enables intelligent question answering, improving the flexibility and intelligence of intelligent question answering, and thus improving the accuracy and matching of answer information determination.

[0043] Figure 2 This is a flowchart of a second method for indicating answers based on question type and scenario provided in this disclosure. It can be applied to determine how a question should be answered, such as... Figure 2 As shown, it includes the following steps: In step S21, the question type of the input question is obtained based on the input question and the historical dialogue set corresponding to the input question; In some embodiments, the implementing entity of this disclosure may be, for example, an electronic device. This electronic device does not specifically refer to a particular fixed electronic device. For example, when the device identifier changes, the electronic device may also change accordingly. For example, when the structure of the electronic device changes, the electronic device may also change accordingly. The name of the electronic device is not limited. The electronic device may, for example, be a processing device, a terminal, etc.

[0044] The relevant processes can be as described above, and will not be repeated here.

[0045] According to some embodiments, the input questions obtained may include information such as application domain, user permissions, timestamp, and geographic location.

[0046] In some embodiments, the question type can be determined comprehensively based on the context of the input question. The preset question types can be determined according to business requirements. For example, preset question types can be added, removed, or replaced based on business requirement information.

[0047] According to some embodiments, Figure 3 This is an example illustration of a method for indicating answers based on question type and scenario provided in this disclosure, such as... Figure 3 As shown, it can include acquiring user input questions and dialogue history, classifying input questions, obtaining sub-classification information, and acquiring the main body and scenario based on business needs. It can also obtain the four main categories of the input questions based on a dynamic mapping strategy. Furthermore, it can acquire answer indication information to initiate the answer generation process and input the answer based on this information.

[0048] According to some embodiments, different questions may obtain the same answer indication information under different scenario information, or they may obtain different answer indication information. The same question may obtain different answer indication information under different scenarios. This disclosure does not limit this. For example, the input question could be "What is Company A's secret?", and when the scenario information corresponding to the input question is an internal office assistant, the obtained answer indication information could be "security". For example, the input question could be "What is Company A's secret?", and when the scenario information corresponding to the input question is a publicly available product customer service, the obtained answer indication information could be "pay attention".

[0049] In some embodiments, obtaining the question type of the input question based on the input question and the corresponding historical dialogue set includes: Obtain the semantic information and / or key information of the input question; Based on the semantic information and / or the key information, obtain the historical dialogue set corresponding to the input question; Based on the question types of each historical dialogue in the historical dialogue set, a type acquisition model is used to obtain the question type corresponding to the input question. Therefore, the matching accuracy between the historical dialogue set and the input question can be improved, the accuracy of historical dialogue set acquisition can be increased, and the accuracy of answer indication information acquisition can be enhanced.

[0050] According to some embodiments, semantic information may be, for example, semantic information of the input question. Key information may be, for example, key information included in the input question, such as keyword information. The acquisition of voice information and key information may be determined, for example, based on information acquisition instructions, or, for example, based on recognition accuracy.

[0051] In some embodiments, the type acquisition model may be a trained model that can be used for type acquisition, and this type acquisition model is not specifically a fixed model. For example, when the model type of the type acquisition model changes, the type acquisition model can also change accordingly. For example, when the model parameters of the type acquisition model change, the type acquisition model can also change accordingly.

[0052] According to some embodiments, question types may include, for example, reports, complaints, casual conversation, crisis, evaluations, attacks, discrimination, inquiries, invalid questions, greetings, thanks, sensitive, other, normal, implicit conditions, illegal, and praise or criticism. When implicit conditions prevent the determination of the question type, a prompt message may be issued.

[0053] In some embodiments, the method further includes: If the question type of the input question is not found based on the input question and the corresponding historical dialogue set, a prompt message is issued. Based on the relevant information entered in response to the prompt, the question type of the input question can be obtained. Therefore, the accuracy of question type acquisition can be improved.

[0054] According to some embodiments, the type of information in the prompt message is not limited. That is, the way the prompt message is displayed is not limited. The prompt message can be a voice prompt, a text prompt, or a vibration prompt, etc.

[0055] In some embodiments, the relevant information may be, for example, information input in response to a prompt message to determine the type of problem. This relevant information may also be referred to as type supplementary information, type determination information, etc. This relevant information does not refer to any specific fixed information. For example, when the content of the relevant information changes, the relevant information may also change accordingly.

[0056] In step S22, the scenario information corresponding to the input question is obtained; The relevant processes can be as described above, and will not be repeated here.

[0057] The scenario parameters may include, for example, the subject's stance and / or the business environment. The subject's stance may include compliance, technological research, product sales compliance, information disclosure, value guidance, dispute resolution, and maintaining a positive atmosphere. The business environment may include, for example, a command execution system that includes user identity, is geared towards academics, has no special restrictions, and does not involve emotional output.

[0058] The subject's stance can include neutrality. Neutrality does not specifically mean "having no opinion," but rather indicates that the process of arriving at an opinion is rigorous, objective, and free from irrational interference. It is a methodology that pursues fairness and can minimize the impact of subjective bias on the outcome.

[0059] In step S23, the scene information and the question type are input into a transformer-based fine-tuning model for recognition, and the answer indication information corresponding to the input question is obtained; The relevant processes can be as described above, and will not be repeated here.

[0060] In some embodiments, the transformer-based fine-tuning model may be, for example, a pre-trained model capable of recognizing answer indication information. This transformer-based fine-tuning model is not specifically defined by a single fixed model. For instance, when the adjustment method of the transformer-based fine-tuning model changes, the model itself may also change accordingly.

[0061] According to some embodiments, answer indication information may include, for example, "safe," "conditionally safe," "refuse to answer," and "follow." "Safe" may refer to a question type that is normal or a question type that is special but explicitly allowed by the "scenario parameters." "Conditionally safe" may refer to a question type that is borderline sensitive but where the scenario parameters allow for limited objective discussion. "Refuse to answer" may refer to a question type that is high-risk and where the scenario parameters do not support such behavior. "Follow" may refer to a situation where the model cannot determine the answer through rules, but an external knowledge base can be queried based on the scenario parameters.

[0062] In some embodiments, obtaining answer indication information corresponding to the input question based on the question type under the scenario information includes: Based on the scenario information, obtain the question classification result corresponding to the question type, wherein the question classification result includes the answer indication information corresponding to the input question and / or the acquisition process information of the question classification result.

[0063] In some embodiments, the mapping relationship between scenario information and answer indication information is adjusted according to business requirements information to obtain the adjusted mapping relationship, wherein the mapping relationship is used to obtain the answer indication information corresponding to the input question.

[0064] In some embodiments, the business requirement information may be, for example, the requirement information at the time of current business execution. This business requirement information may include, for example, business complexity information, business identification accuracy information, etc. This business requirement information does not specifically refer to any fixed information. For example, when a modification instruction for this business requirement information is received, the business requirement information may also change accordingly. For example, when the method of obtaining the business requirement information changes, the business requirement information may also change accordingly.

[0065] According to some embodiments, the mapping relationship can be, for example, a mapping relationship between scene information and answer instruction information. This mapping relationship can also be referred to as a mapping table, mapping table, etc. The mapping relationship does not specifically refer to a fixed relationship. For example, when a modification instruction for the mapping relationship is received, the mapping relationship can also change accordingly.

[0066] According to some embodiments, the process of obtaining answer indication information based on scenario information can be as shown in Table 1, for example.

[0067] Table 1

[0068] In step S24, if the answer indication information indicates that the input question should be answered, a large model is used to identify the input question and obtain the answer information corresponding to the input question.

[0069] The relevant processes can be as described above, and will not be repeated here.

[0070] According to some embodiments, large language models can refer, for example, to pre-trained language models based on deep learning (primarily the Transformer architecture) with a huge number of parameters (typically billions to hundreds of billions). Such large models can also be called large language models. The term "large model" does not specifically refer to a particular fixed model. For example, when the model parameters corresponding to a large model change, the large model can also change accordingly.

[0071] In some embodiments, the large model in this disclosure may be, for example, a model that has already been trained and can be used for answer retrieval. This large model does not specifically refer to a fixed model. For example, the large model may change accordingly when the training method changes.

[0072] According to some embodiments, the answer information may be, for example, the answer obtained based on the input question and answer instructions. This answer information does not refer to any specific fixed information. For example, the answer information may change accordingly when the question type changes. For example, the answer information may change accordingly when the scene information changes. For example, the answer information may change accordingly when the overall model changes.

[0073] According to some embodiments, a large model can be used to identify the input question and the scene information based on the answer indication information to obtain the answer information corresponding to the input question.

[0074] In some embodiments, when the answer indication information indicates that the input question should not be answered, an operation corresponding to the input question is retrieved and executed. This operation includes, but is not limited to, ending the dialogue or retrieving an intervention strategy from a database. This disclosure does not limit this aspect.

[0075] A block diagram illustrating an answer indication device based on question type and scenario, according to an exemplary embodiment. (Refer to...) Figure 4 The device 400 includes: The type acquisition unit 401 is used to acquire the question type of the input question based on the input question and the historical dialogue set corresponding to the input question; Information acquisition unit 402 is used to acquire scene information corresponding to the input question; The answer indication unit 403 is used to obtain answer indication information corresponding to the input question based on the question type under the scenario information.

[0076] According to some embodiments, the answer indication unit 403, when obtaining answer indication information corresponding to the input question based on the question type under the scenario information, is specifically used for: The scenario information and the question type are input into a transformer-based fine-tuning model for recognition, and the answer indication information corresponding to the input question is obtained.

[0077] According to some embodiments, the type acquisition unit 401, when acquiring the question type of the input question based on the input question and the historical dialogue set corresponding to the input question, is specifically used for: Obtain the semantic information and / or key information of the input question; Based on the semantic information and / or the key information, obtain the historical dialogue set corresponding to the input question; Based on the question types of each historical dialogue in the historical dialogue set, a type acquisition model is used to obtain the question type corresponding to the input question.

[0078] According to some embodiments, the answer indication unit 403, when obtaining answer indication information corresponding to the input question based on the question type under the scenario information, is specifically used for: Based on the scenario information, obtain the question classification result corresponding to the question type, wherein the question classification result includes the answer indication information corresponding to the input question and / or the acquisition process information of the question classification result.

[0079] According to some embodiments, the type acquisition unit 401 is further specifically used for: If the question type of the input question is not found based on the input question and the corresponding historical dialogue set, a prompt message is issued. Based on the relevant information entered in response to the prompt, the question type of the input question is obtained.

[0080] According to some embodiments, the answer indication unit 403 is further specifically used for: If the answer indication information indicates that the input question should be answered, a large model is used to identify the input question and obtain the answer information corresponding to the input question; or If the answer indication information indicates that the input question should not be answered, the operation corresponding to the input question is obtained and executed.

[0081] According to some embodiments, the answer indication unit 403 is further specifically used for: Based on business requirements, the mapping relationship between scenario information and answer indication information is adjusted to obtain the adjusted mapping relationship, wherein the mapping relationship is used to obtain the answer indication information corresponding to the input question.

[0082] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0083] In one or related embodiments, a type acquisition unit is used to acquire the question type of the input question based on the input question and the historical dialogue set corresponding to the input question; an information acquisition unit is used to acquire the scene information corresponding to the input question; and an answer indication unit is used to acquire answer indication information corresponding to the input question based on the question type and the scene information. Therefore, the question type corresponding to the input question can be acquired, and the answer indication information for the input question can be acquired based on the scene information and the question type. This answer indication information can be used to indicate how to answer the input question, reducing the direct use of large models for answering. It allows for corresponding answer instructions for the input question, reducing the possibility of inaccurate answer information acquisition when the answer is not directly based on the question type and scene information. It enables intelligent question answering, improving the flexibility and intelligence of intelligent question answering, and thus improving the accuracy and matching of answer information determination.

[0084] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device 500 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0085] like Figure 5As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. The RAM 503 may also store various programs and data required for the operation of the electronic device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0086] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0087] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above. For example, in some embodiments, the above methods can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the above methods by any other suitable means (e.g., by means of firmware).

[0088] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0089] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0090] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0091] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0092] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0093] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0094] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0095] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for indicating answers based on question type and scenario, characterized in that, include: Based on the input question and the corresponding historical dialogue set, the question type of the input question is obtained; Obtain the scenario information corresponding to the input question; Under the given scenario information, and based on the question type, obtain the answer indication information corresponding to the input question.

2. The method according to claim 1, characterized in that, Under the scenario information, obtaining answer indication information corresponding to the input question based on the question type includes: The scenario information and the question type are input into a transformer-based fine-tuning model for recognition, and the answer indication information corresponding to the input question is obtained.

3. The method according to claim 1, characterized in that, The step of obtaining the question type of the input question based on the input question and the corresponding historical dialogue set includes: Obtain the semantic information and / or key information of the input question; Based on the semantic information and / or the key information, obtain the historical dialogue set corresponding to the input question; Based on the question types of each historical dialogue in the historical dialogue set, a type acquisition model is used to obtain the question type corresponding to the input question.

4. The method according to claim 3, characterized in that, Under the scenario information, obtaining answer indication information corresponding to the input question based on the question type includes: Based on the scenario information, obtain the question classification result corresponding to the question type, wherein the question classification result includes the answer indication information corresponding to the input question and / or the acquisition process information of the question classification result.

5. The method according to claim 1, characterized in that, The method further includes: If the question type of the input question is not found based on the input question and the corresponding historical dialogue set, a prompt message is issued. Based on the relevant information entered in response to the prompt, the question type of the input question is obtained.

6. The method according to claim 1, characterized in that, The method further includes: If the answer indication information indicates that the input question should be answered, a large model is used to identify the input question and obtain the answer information corresponding to the input question; or If the answer indication information indicates that the input question should not be answered, the operation corresponding to the input question is obtained and executed.

7. The method according to claim 1, characterized in that, The method further includes: Based on business requirements, the mapping relationship between scenario information and answer indication information is adjusted to obtain the adjusted mapping relationship, wherein the mapping relationship is used to obtain the answer indication information corresponding to the input question.

8. A device for indicating answers based on question type and scenario, characterized in that, include: The type acquisition unit is used to acquire the question type of the input question based on the input question and the historical dialogue set corresponding to the input question; The information acquisition unit is used to acquire the scenario information corresponding to the input question; The answer indication unit is used to obtain answer indication information corresponding to the input question based on the question type under the scenario information.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the answer indication method based on question type and scenario as described in any one of claims 1 to 7.

10. A storage medium storing instructions, characterized in that, When the instructions are executed on an electronic device, the electronic device performs the answer instruction method based on question type and scenario as described in any one of claims 1 to 7.

Images