Interaction method and device, equipment and storage medium

Abstract

The invention relates to an interaction method and device, equipment and a storage medium. The method comprises the steps of obtaining interaction intention information of an interaction target; obtaining interaction state information of the interaction target; generating interaction prompt information based on the interaction intention information and the interaction state information; based on the interaction intention information and the interaction prompt information, generating answer information; and providing the answer information to the interaction target. By means of the technical scheme, the answer information better conforming to the personalized features of the interaction target can be generated, the continuity of multiple rounds of interaction is enhanced, and therefore the interaction experience of the interaction target is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of information processing and artificial intelligence technology, and in particular to an interaction method, device, equipment and storage medium. Background Art

[0002] In related technologies, large models such as GPT (Generative Pre-Trained Transformer) are usually used to handle interactive tasks such as question-answering with users. The interactive results returned to users by this technical solution usually only depend on the actual intention represented by the user's current input information, and cannot generate answer information that can meet the user's personalized needs. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides an interaction method, device, equipment and storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, an interaction method is provided, comprising: obtaining interaction intention information of an interaction target; obtaining interaction status information of the interaction target; generating interaction prompt information based on the interaction intention information and the interaction status information; generating answer information based on the interaction intention information and the interaction prompt information; and providing the answer information to the interaction target.

[0005] In one implementation, the generating of the interaction prompt information based on the interaction intention information and the interaction status information includes: extracting information from the interaction status information based on the interaction intention information to obtain first related information; wherein the first related information is information in the interaction status information that is related to the interaction intention information; and generating the interaction prompt information based on the first related information.

[0006] In an optional implementation, the extracting information from the interaction status information based on the interaction intention information to obtain first relevant information includes: inputting the interaction intention information and the interaction status information into a pre-trained artificial intelligence (AI) model to obtain the first relevant information; and / or extracting information from the interaction status information in combination with the interaction intention information using preset information extraction rules to obtain the first relevant information.

[0007] In one implementation, generating answer information based on the interaction intention information and the interaction prompt information includes: generating input information based on the interaction intention information and the interaction prompt information; inputting the input information into a pre-trained generative pre-trained transformation (GPT) model to obtain the answer information.

[0008] In one implementation, the acquiring of the interaction intention information of the interaction target includes: acquiring input information of the interaction target; and performing semantic recognition on the input information to acquire the interaction intention information.

[0009] In one implementation, obtaining the interaction status information of the interaction target includes: obtaining historical interaction information of the interaction target; performing feature extraction on the historical interaction information to obtain the interaction status information of the interaction target; wherein the interaction status information includes at least one of the following: interaction feature information, background information, and knowledge information.

[0010] In one implementation, the method further includes: updating the interaction status information according to the interaction intention information and / or the answer information.

[0011] According to a second aspect of an embodiment of the present disclosure, an interaction device is provided, comprising: a first acquisition module for acquiring interaction intention information of an interaction target; a second acquisition module for acquiring interaction status information of the interaction target; a first processing module for generating interaction prompt information based on the interaction intention information and the interaction status information; a second processing module for generating answer information based on the interaction intention information and the interaction prompt information; and a third processing module for providing the answer information to the interaction target.

[0012] In one implementation, the first processing module is specifically used to: extract information from the interaction status information based on the interaction intention information to obtain first related information; wherein the first related information is information in the interaction status information that is related to the interaction intention information; and generate the interaction prompt information based on the first related information.

[0013] In an optional implementation, the first processing module is specifically used to: input the interaction intention information and the interaction status information into a pre-trained artificial intelligence AI model to obtain the first relevant information; and / or, use preset information extraction rules to extract information from the interaction status information in combination with the interaction intention information to obtain the first relevant information.

[0014] In one implementation, the second processing module is specifically used to: generate input information based on the interaction intention information and the interaction prompt information; input the input information into a pre-trained generative pre-trained transformation GPT model to obtain the answer information.

[0015] In one implementation, the first acquisition module is specifically used to: acquire input information of the interaction target; perform semantic recognition on the input information to acquire the interaction intention information.

[0016] In one implementation, the second acquisition module is specifically used to: acquire historical interaction information of the interaction target; perform feature extraction on the historical interaction information to acquire interaction status information of the interaction target; wherein the interaction status information includes at least one of the following: interaction feature information, background information, and knowledge information.

[0017] In one implementation, the device further includes: an updating module, configured to update the interaction status information according to the interaction intention information and / or the answer information.

[0018] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect above.

[0019] According to a fourth aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method as described in the first aspect above.

[0020] According to a fifth aspect of an embodiment of the present disclosure, the present disclosure provides a computer program product, including a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0021] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: based on the interaction intention information of the interaction target, the interaction prompt information representing the current interaction state of the interaction target can be obtained from the interaction state information of the interaction target, and answer information can be generated according to the interaction prompt information and the interaction prompt information. Answer information that is more in line with the personalized characteristics of the interaction target can be generated, and the coherence of multiple rounds of interaction can be enhanced to improve the interaction experience of the interaction target.

[0022] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0024] Figure 1 The present invention is a flowchart of an interaction method according to an exemplary embodiment.

[0025] Figure 2 The figure is a flow chart of another interaction method according to an exemplary embodiment.

[0026] Figure 3 is a flow chart of yet another interaction method according to an exemplary embodiment.

[0027] Figure 4 is a flow chart of yet another interaction method according to an exemplary embodiment.

[0028] Figure 5 is a flow chart of yet another interaction method according to an exemplary embodiment.

[0029] Figure 6 The figure is a flow chart showing an interaction scheme according to an exemplary embodiment.

[0030] Figure 7 It is a schematic diagram of an application scenario of an interaction method according to an exemplary embodiment.

[0031] Figure 8 It is a schematic diagram showing an interaction device according to an exemplary embodiment.

[0032] Fig. 9 is a schematic diagram of another interactive device according to an exemplary embodiment.

[0033] Fig.10 It is a block diagram of an electronic device for interaction according to an exemplary embodiment. DETAILED DESCRIPTION

[0034] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0035] In the description of the present disclosure, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The various numbers such as first, second, etc. involved in the present disclosure are only distinguished for the convenience of description, and are not used to limit the scope of the embodiments of the present disclosure, nor do they indicate the order of precedence.

[0036] Figure 1 FIG. 1 is a flow chart of an interaction method according to an exemplary embodiment. Figure 1As shown, the method may include but is not limited to the following steps.

[0037] Step S101: Acquire interaction intention information of an interaction target.

[0038] Among them, in the embodiments of the present disclosure, the above-mentioned interaction target may be a user who is using the method provided by the present disclosure to interact.

[0039] Specifically, the interaction intention information representing the real intention that the interaction target hopes to achieve through the interaction is obtained.

[0040] As an example, if the interaction target wants to learn English knowledge through interaction, the interaction intention information of the interaction target may be "learn English".

[0041] Step S102: Acquire the interaction status information of the interaction target.

[0042] Specifically, the interaction state information that can represent the state of the interaction target itself and the relevant features of the performed interaction process is obtained.

[0043] As an example, the interaction target may be a user who is interacting using the method provided by the present disclosure. The interaction status information may include but is not limited to the user's personal information, such as age, gender, and education level, and the characteristics of the user during the interaction, such as the user's knowledge level, hobbies, and preferred interaction methods.

[0044] Step S103: Generate interaction prompt information based on the interaction intention information and the interaction status information.

[0045] In the embodiments of the present disclosure, the above-mentioned interactive prompt information may include but is not limited to text information and image information.

[0046] For example, information related to the interaction intention of the interaction target is obtained from the interaction state information as the interaction prompt information, and the interaction prompt information can represent the personalized characteristics of the interaction target in the current interaction process.

[0047] As an example, take the interaction intention information as "learning English" as an example. Information related to learning English, such as education level, English knowledge level, favorite English movies, etc., can be obtained from the interaction status information.

[0048] Step S104: Generate answer information based on the interaction intention information and the interaction prompt information.

[0049] Specifically, in combination with the interaction prompt information, answer information with personalized features of the interaction target and capable of achieving the interaction intention of the interaction target is generated.

[0050] Step S105: providing answer information to the interaction target.

[0051] As an example, taking the answer information as text information, the answer information can be beautified and the beautified answer information can be provided to the interaction target.

[0052] As another example, taking the answer information as text information, corresponding multimedia information can be obtained according to the text information, and the multimedia information can be provided to the interaction target. For example, a video clip or picture containing the text information can be obtained.

[0053] In the embodiments of the present disclosure, multimedia information may include but is not limited to voice information, image information or video information.

[0054] By implementing the disclosed embodiments, based on the interaction intention information of the interaction target, the interaction prompt information representing the current interaction state of the interaction target can be obtained from the interaction state information of the interaction target, and answer information can be generated according to the interaction prompt information and the interaction prompt information. Answer information that is more in line with the personalized characteristics of the interaction target can be generated, and the coherence of multiple interactions can be enhanced to improve the interaction experience of the interaction target.

[0055] In one implementation, information related to the interaction intention of the interaction target can be obtained from the interaction state information to generate interaction prompt information based on the relevant information. Figure 2 , Figure 2 is a flowchart of another interactive method according to an exemplary embodiment. Figure 2 As shown, the method may include but is not limited to the following steps.

[0056] Step S201: Acquire interaction intention information of an interaction target.

[0057] In the embodiments of the present disclosure, step S201 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0058] Step S202: Acquire the interaction status information of the interaction target.

[0059] In the embodiments of the present disclosure, step S202 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0060] Step S203: extracting the interaction status information based on the interaction intention information to obtain first relevant information.

[0061] Among them, the first relevant information is the information related to the interaction intention information in the interaction status information.

[0062] Specifically, information extraction is performed on the interaction state information to obtain first relevant information related to the interaction intention of the interaction target in the interaction state information.

[0063] As an example, take the interaction intention information as learning English as an example. Then, information related to English learning in the interaction state information can be obtained, such as: the current English learning goal of the interaction target, the English movies that the interaction target likes, etc.

[0064] In an optional implementation, information extraction is performed on interaction status information based on interaction intention information to obtain first relevant information, including: inputting interaction intention information and interaction status information into a pre-trained AI (Artificial Intelligence) model to obtain first relevant information; and / or, using preset information extraction rules, combining interaction intention information with interaction status information to extract first relevant information.

[0065] Among them, in the embodiments of the present disclosure, the above-mentioned AI model may include but is not limited to a classification model and a regression model.

[0066] As an example, the interaction intention information and the interaction status information are input into a pre-trained AI model, so that the AI ​​model extracts the first relevant information related to the interaction intention information from the interaction status information.

[0067] As another example, information extraction is performed on the interaction state information based on a preset information extraction rule to extract first relevant information related to the interaction intention information from the interaction state information.

[0068] As another example, the interaction intention information and interaction status information are input into a pre-trained AI model, so that the AI ​​model obtains relevant information related to the interaction intention information from the interaction status information, and extracts information from the interaction status information based on pre-set information extraction rules to obtain relevant information related to the interaction intention information from the interaction status information, and the relevant information related to the interaction intention information obtained by the above two methods is used as the first relevant information.

[0069] It is understandable that the above interaction prompt information may include but is not limited to text information and multimedia information, such as a painting or a melody that the interaction target likes.

[0070] Step S204: Generate interactive prompt information based on the first relevant information.

[0071] As an example, a corresponding key prompt word is generated based on the first relevant information as the interaction prompt information.

[0072] As another example, corresponding multimedia information is obtained based on the first relevant information as interaction prompt information.

[0073] Step S205: Generate answer information based on the interaction intention information and the interaction prompt information.

[0074] In the embodiments of the present disclosure, step S205 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0075] Step S206: providing answer information to the interaction target.

[0076] In the embodiments of the present disclosure, step S206 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0077] By implementing the disclosed embodiments, information can be extracted from the interaction state information based on the interaction intention information, and the first relevant information related to the interaction intention of the interaction target in the interaction state information can be obtained, so as to generate interaction prompt information based on the first relevant information, and generate answer information according to the interaction prompt information and the interaction intention information. It is possible to generate answer information that is more in line with the personalized characteristics of the interaction target, enhance the coherence of multiple rounds of interaction, and improve the interaction experience of the interaction target.

[0078] In one implementation, the interaction intention information and the interaction prompt information may be combined to generate input information with personalized characteristics of the interaction target, so as to generate answer information based on the input information. As an example, see Figure 3 , Figure 3 is a flowchart of another interaction method according to an exemplary embodiment. Figure 3 As shown, the method may include but is not limited to the following steps.

[0079] Step S301: Acquire interaction intention information of an interaction target.

[0080] In the embodiments of the present disclosure, step S301 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0081] Step S302: Acquire the interaction status information of the interaction target.

[0082] In the embodiments of the present disclosure, step S302 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0083] Step S303: Generate interaction prompt information based on the interaction intention information and the interaction status information.

[0084] In the embodiments of the present disclosure, step S303 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0085] Step S304: Generate input information based on the interaction intention information and the interaction prompt information.

[0086] As an example, the interaction intention information is to learn English, the interaction prompt information includes that the English learning goal of the interaction target is to pass the CET-4 (College English Test Band 4) exam, and the movie that the interaction target likes is Movie A. The following input information can be generated based on the above interaction intention information and interaction prompt information: The interaction target is learning CET-4, he likes Movie A, please return English teaching sentences of the corresponding English level based on the relevant scenes of Movie A.

[0087] Step S305: Input the input information into a pre-trained GPT (Generative Pre-Trained Transformer) model to obtain answer information.

[0088] Specifically, the input information is input into a pre-trained GPT model to obtain the answer information generated by the GPT model based on the input information.

[0089] Step S306: providing answer information to the interaction target.

[0090] In the embodiments of the present disclosure, step S306 may be implemented in any of the ways in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0091] By implementing the disclosed embodiments, the interaction intention information and the interaction prompt information can be combined to generate input information with personalized characteristics of the interaction target, so as to generate answer information based on the input information. It is possible to generate answer information that is more in line with the personalized characteristics of the interaction target and improve the interaction experience of the interaction target.

[0092] In one implementation, the input information of the interaction target can be analyzed to obtain the interaction intention information of the interaction target. As an example, see Figure 4 , Figure 4 is a flowchart of another interaction method according to an exemplary embodiment. Figure 4 As shown, the method may include but is not limited to the following steps.

[0093] Step S401: Obtain input information of the interactive target.

[0094] As an example, the text information input by the interactive target is obtained.

[0095] As another example, voice information input by the interactive target is obtained, and voice recognition is performed on the voice information to obtain input text information.

[0096] Step S402: Perform semantic understanding processing on the input information to obtain interaction intention information.

[0097] For example, semantic understanding is performed on the input information to parse the language structure of the input information and identify keywords in the input information, thereby obtaining interaction intent information representing the goals that the input information is expected to achieve.

[0098] Step S403: Acquire the interaction status information of the interaction target.

[0099] In the embodiments of the present disclosure, step S403 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0100] Step S404: Generate interaction prompt information based on the interaction intention information and the interaction status information.

[0101] In the embodiments of the present disclosure, step S404 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0102] Step S405: Generate answer information based on the interaction intention information and the interaction prompt information.

[0103] In the embodiments of the present disclosure, step S405 can be implemented by any of the methods in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be repeated.

[0104] Step S406: providing answer information to the interaction target.

[0105] In the embodiments of the present disclosure, step S406 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0106] By implementing the disclosed embodiments, the input information of the interaction target can be semantically understood, thereby obtaining the interaction intention information of the interaction target, and obtaining corresponding answer information based on the interaction intention information. When the input information of the interaction target is large, the processing efficiency can be improved to shorten the interaction time and improve the interaction experience of the interaction target.

[0107] In one implementation, the interaction status information of the interaction target can be obtained through historical interaction information. For example, see Figure 5 , Figure 5 is a flowchart of another interaction method according to an exemplary embodiment. Figure 5 As shown, the method may include but is not limited to the following steps.

[0108] Step S501: Acquire interaction intention information of an interaction target.

[0109] In the embodiments of the present disclosure, step S501 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0110] Step S502: Acquire historical interaction information of the interaction target.

[0111] Specifically, historical interaction information of the interaction target in the completed interaction process is obtained.

[0112] Step S503: extract features from historical interaction information to obtain interaction status information of the interaction target.

[0113] Among them, in the embodiment of the present disclosure, the interaction state information includes at least one of the following: interaction feature information, background information and knowledge information.

[0114] Specifically, features related to the interaction target in the historical interaction information are extracted to obtain the interaction feature information, the background information of the interaction target and the knowledge information of the interaction target contained in the historical interaction information.

[0115] Among them, in the embodiment of the present disclosure, the interaction feature information is relevant information that can represent the interaction preference of the interaction target.

[0116] In the embodiment of the present disclosure, the background information of the interaction target may be related information representing the attributes of the interaction target itself.

[0117] As an example, taking the interaction target as a user, the background information may include but is not limited to the user's own attribute information such as gender and age.

[0118] In the embodiment of the present disclosure, the knowledge information may be interactive knowledge information related to the knowledge field to which the interactive content of the interactive target belongs.

[0119] As an example, taking the current interactive content of the interactive target as content in the field of learning, the above-mentioned knowledge information may include but is not limited to information such as the knowledge level, educational level and school attended by the interactive target.

[0120] In some embodiments of the present disclosure, before interacting with an interactive target, prompt information may be generated to prompt the interactive target to set its own background information.

[0121] As an example, before the interaction, the interaction target may be prompted through prompt information to set background information such as his / her age, gender, interests and hobbies.

[0122] In some embodiments of the present disclosure, before interacting with an interactive target, the interactive target may be prompted to set its own knowledge information according to the actual scenario.

[0123] As an example, in a learning interaction scenario, the interactive target may be prompted by prompt information to set learning-related knowledge information such as the current learning level and the school attended.

[0124] Step S504: Generate interaction prompt information based on the interaction intention information and the interaction status information.

[0125] In the embodiments of the present disclosure, step S504 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0126] Step S505: Generate answer information based on the interaction intention information and the interaction prompt information.

[0127] In the embodiments of the present disclosure, step S505 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0128] Step S506: providing answer information to the interaction target.

[0129] In the embodiments of the present disclosure, step S506 may be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0130] By implementing the disclosed embodiments, feature extraction can be performed on historical interaction information to obtain interaction status information of the interaction target, and answer information that is more in line with the personalized characteristics of the interaction target can be generated based on the interaction status information to improve the interaction experience of the interaction target.

[0131] In some embodiments of the present disclosure, the above method may further include: updating the interaction status information according to the interaction intention information and / or the answer information.

[0132] As an example, information that can represent the state of the interaction target itself and the interaction characteristics in the interaction intention information is obtained, and the above information is updated to the interaction state information.

[0133] As another example, the answer information obtained can represent information about the state of the interaction target itself and the interaction characteristics, and the above information is updated into the interaction state information.

[0134] As another example, information that can represent the state of the interaction target itself and the interaction characteristics in the interaction intention information and the answer information is obtained, and the above information is updated into the interaction state information.

[0135] In some embodiments of the present disclosure, the interaction status information may also be updated by acquiring other information.

[0136] As an example, when the interaction target carries a terminal device deployed with the interaction method of the embodiment of the present disclosure, the positioning information of the terminal device can be obtained after obtaining the consent of the interaction target, and the location information that appears multiple times in the positioning information can be updated to the interaction status information with the location information, or the related information represented by the location information (for example, a restaurant located at the location information) as the preferred location of the interaction target.

[0137] See also Figure 6 , Figure 6 FIG. 1 is a flow chart showing an interactive solution according to an exemplary embodiment. Figure 6 As shown, in this scheme, the input information of the interaction target can be analyzed for intent to obtain the current intent of the interaction target, and combined with the historical interaction information and background information of the interaction target, input information with personalized features of the interaction target is generated, and the input information is input into a pre-trained GPT model to obtain the output information of the GPT model as answer information, and the answer information is processed and returned to the interaction target.

[0138] See also Figure 7 , Figure 7 FIG. 1 is a schematic diagram of an application scenario of an interaction method according to an exemplary embodiment. Figure 7 As shown, the interaction method provided by the present disclosure can be applied to various scenarios including but not limited to: dialogue robots, virtual assistants and medical consultations. In practical applications, after obtaining the input information of the interaction target through relevant applications, the prompt state transition engine deployed with the interaction method provided by any embodiment of the present disclosure can obtain relevant information about the interaction intention with the interaction target from the database through a pre-trained AI model and a data processing system, and generate corresponding interaction prompt information (for example, prompt) based on the relevant information, and generate input information with personalized features of the interaction target based on the interaction prompt information and the interaction intention information, input the input information into the called GPT model to obtain the output result of the GPT model, and return the output result to the interaction target through the front-end application.

[0139] See also Figure 8, Figure 8 FIG. 1 is a schematic diagram of an interactive device according to an exemplary embodiment. Figure 8 As shown, the device 800 includes: a first acquisition module 801, used to acquire interaction intention information of an interaction target; a second acquisition module 802, used to acquire interaction status information of the interaction target; a first processing module 803, used to generate interaction prompt information based on interaction intention information and interaction status information; a second processing module 804, used to generate answer information based on interaction intention information and interaction prompt information; and a third processing module 805, used to provide answer information to the interaction target.

[0140] In one implementation, the first processing module 803 is specifically used to: extract information from the interaction status information based on the interaction intention information to obtain first related information; wherein the first related information is information in the interaction status information that is related to the interaction intention information; and generate interaction prompt information based on the first related information.

[0141] In an optional implementation, the first processing module 803 is specifically used to: input the interaction intention information and the interaction status information into a pre-trained artificial intelligence AI model to obtain first relevant information; and / or, use preset information extraction rules to extract information from the interaction status information in combination with the interaction intention information to obtain first relevant information.

[0142] In one implementation, the second processing module 804 is specifically used to: generate input information based on interaction intention information and interaction prompt information; input the input information into a pre-trained GPT model to obtain answer information.

[0143] In one implementation, the first acquisition module 801 is specifically used to: acquire input information of an interaction target; and perform semantic recognition on the input information to acquire interaction intention information.

[0144] In one implementation, the second acquisition module 802 is specifically used to: acquire historical interaction information of the interaction target; perform feature extraction on the historical interaction information to acquire interaction state information of the interaction target; wherein the interaction state information includes at least one of the following: interaction feature information, background information, and knowledge information.

[0145] In one implementation, the above device further includes: an update module. As an example, see Fig. 9 , Fig. 9 FIG. 1 is a schematic diagram of another interactive device according to an exemplary embodiment. Fig. 9 As shown, the device 900 further includes an updating module 906, which is used to update the interaction state information according to the interaction intention information and / or the answer information. Fig. 9 Modules 901 to 905 in Figure 8Modules 801 to 805 in the embodiment have the same structure and function.

[0146] Through the device of the embodiment of the present disclosure, based on the interaction intention information of the interaction target, the interaction prompt information representing the current interaction state of the interaction target can be obtained from the interaction state information of the interaction target, and the answer information can be generated according to the interaction prompt information and the interaction prompt information. It is possible to generate answer information that is more in line with the personalized characteristics of the interaction target, enhance the coherence of multiple interactions, and improve the interaction experience of the interaction target.

[0147] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0148] Fig.10 It is a block diagram of an electronic device for interaction according to an exemplary embodiment.

[0149] Reference Fig.10 , the electronic device 1000 may include one or more of the following components: a processing component 1002 , a memory 1004 , a power component 1006 , a multimedia component 1008 , an input / output (I / O) interface 1010 , and a communication component 1012 .

[0150] The processing component 1002 generally controls the overall operation of the electronic device 1000, such as operations associated with display, data communication, and recording operations. The processing component 1002 may include one or more processors 1020 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 1002 may include one or more modules to facilitate the interaction between the processing component 1002 and other components. For example, the processing component 1002 may include a multimedia module to facilitate the interaction between the multimedia component 1008 and the processing component 1002.

[0151] The memory 1004 is configured to store various types of data to support operations on the device 1000. Examples of such data include instructions for any application or method operating on the electronic device 1000, contact data, phone book data, messages, pictures, videos, etc. The memory 1004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0152] The power component 1006 provides power to the various components of the electronic device 1000. The power component 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 1000.

[0153] The multimedia component 1008 includes a screen that provides an output interface between the electronic device 1000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0154] The input / output interface 1010 provides an interface between the processing component 1002 and a peripheral interface module, which may be a keyboard, a click wheel, a button, etc.

[0155] The communication component 1012 is configured to facilitate wired or wireless communication between the electronic device 1000 and other devices. The electronic device 1000 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1012 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1012 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0156] In an exemplary embodiment, the electronic device 1000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0157] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1004 including instructions, and the instructions can be executed by the processor 1020 of the electronic device 1000 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0158] The present disclosure also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.

[0159] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0160] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. An interactive method, characterized in that: include: Obtaining interaction intention information of the interaction target; Acquiring interaction status information of the interaction target; Generate interaction prompt information based on the interaction intention information and the interaction state information; Generate answer information based on the interaction intention information and the interaction prompt information; The answer information is provided to the interaction target.

2. The method according to claim 1, characterized in that The generating the interaction prompt information based on the interaction intention information and the interaction state information includes: Extracting information from the interaction state information based on the interaction intention information to obtain first related information; wherein the first related information is information in the interaction state information that is related to the interaction intention information; The interaction prompt information is generated based on the first relevant information.

3. The method according to claim 2, characterized in that The extracting the interaction state information based on the interaction intention information to obtain first related information includes: Inputting the interaction intention information and the interaction status information into a pre-trained artificial intelligence (AI) model to obtain the first relevant information; and / or, The interaction state information is extracted by using a preset information extraction rule in combination with the interaction intention information to obtain the first relevant information.

4. The method according to claim 1, characterized in that The generating answer information based on the interaction intention information and the interaction prompt information includes: Generate input information based on the interaction intention information and the interaction prompt information; The input information is input into a pre-trained generative pre-trained transformation (GPT) model to obtain the answer information.

5. The method according to claim 1, characterized in that The acquiring the interaction intention information of the interaction target includes: Acquiring input information of the interactive target; Perform semantic recognition on the input information to obtain the interaction intention information.

6. The method according to claim 1, characterized in that The acquiring the interaction state information of the interaction target includes: Acquire historical interaction information of the interaction target; Feature extraction is performed on the historical interaction information to obtain interaction state information of the interaction target; wherein the interaction state information includes at least one of the following: interaction feature information, background information, and knowledge information.

7. The method according to claim 1, characterized in that The method further comprises: The interaction status information is updated according to the interaction intention information and / or the answer information.

8. An interactive device, characterized in that: include: A first acquisition module is used to acquire interaction intention information of an interaction target; A second acquisition module, used to acquire the interaction state information of the interaction target; A first processing module, configured to generate interaction prompt information based on the interaction intention information and the interaction state information; A second processing module, configured to generate answer information based on the interaction intention information and the interaction prompt information; The third processing module is used to provide the answer information to the interaction target.

9. An electronic device, characterized in that: The device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

Images