Interactive method and apparatus, electronic device, storage medium and program product

Abstract

The present disclosure relates to the technical field of computers, and relates to an interactive method and apparatus, an electronic device, a storage medium and a program product. The interactive method in the present disclosure comprises: in response to a user inputting health-related interactive information, determining the type of the interactive information; on the basis of the type of the interactive information and attribute information of the user, acquiring target media content for responding to the interactive information, wherein the target media content comprises at least one of an image and a video; generating response text for the interactive information; and displaying the target media content and the response text.

Description

Interaction method, device, electronic device, storage medium and program product TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to an interaction method, device, electronic device, storage medium and program product. BACKGROUND

[0002] With the development of Artificial Intelligence (AI) technology, an intelligent agent can interact with a user more naturally and smoothly.

[0003] At present, some intelligent agents can generate a reply according to a health-related question input by a user, guide the user to exercise or answer a health-related question of the user.

[0004] SUMMARY

[0005] This summary is provided to introduce a selection of concepts, which are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it used to limit the scope of the claimed subject matter's scope.

[0006] According to some embodiments of the present disclosure, an interaction method is provided, including: in response to a user inputting health-related interaction information, determining a type of the interaction information; based on the type of the interaction information and attribute information of the user, obtaining target media content for replying to the interaction information, wherein the target media content includes at least one of an image and a video; generating reply text of the interaction information; and displaying the target media content and the reply text.

[0007] According to other embodiments of the present disclosure, an interaction device is provided, including: a determination module configured to, in response to a user inputting health-related interaction information, determine a type of the interaction information; an obtaining module configured to, based on the type of the interaction information and attribute information of the user, obtain target media content for replying to the interaction information, wherein the target media content includes at least one of an image and a video; a generation module configured to generate reply text of the interaction information; and a display module configured to display the target media content and the reply text.

[0008] According to still other embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor, configured to store instructions, when the instructions are executed by the processor, causing the processor to execute the interaction method of any one of the embodiments of the present disclosure.

[0009] According to still another embodiment of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, which when executed by a processor, performs the interaction method of any one of the embodiments of the present disclosure.

[0010] According to yet another embodiment of the present disclosure, a computer program product is provided, comprising instructions, which when executed by a processor, implement the interaction method of any one of the embodiments of the present disclosure.

[0011] According to still another embodiment of the present disclosure, a computer program is provided, comprising instructions, which when executed by a processor, implement the interaction method of any one of the embodiments of the present disclosure.

[0012] Other features, aspects, and advantages of the present disclosure will become apparent from the following detailed description of the exemplary embodiments of the present disclosure with reference made to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0013] The preferred embodiments of the present disclosure will be described below with reference to the accompanying drawings. The accompanying drawings are used to provide further understanding of the present disclosure, and together with the specific description below, form a part of the description of the present disclosure, and are used to explain the present disclosure. It should be understood that the accompanying drawings below only relate to some embodiments of the present disclosure, and do not limit the present disclosure. In the drawings:

[0014] FIG. 1 shows a flowchart of an interaction method according to some embodiments of the present disclosure;

[0015] FIG. 2 shows a schematic diagram of an information interaction interface according to some embodiments of the present disclosure;

[0016] FIG. 3 shows a schematic diagram of an information interaction interface according to some other embodiments of the present disclosure;

[0017] FIG. 4 shows a schematic diagram of a system architecture according to some embodiments of the present disclosure;

[0018] FIG. 5 shows a flowchart of an interaction method according to some other embodiments of the present disclosure;

[0019] FIG. 6 shows a schematic diagram of a processing method of different types of interaction information according to some embodiments of the present disclosure;

[0020] FIG. 7 shows a schematic diagram of an interaction device according to some embodiments of the present disclosure;

[0021] FIG. 8 shows a schematic diagram of an electronic device according to some embodiments of the present disclosure;

[0022] FIG. 9 shows a schematic diagram of a computer system according to some embodiments of the present disclosure.

[0023] It should be understood that the dimensions of the various parts shown in the drawings are not necessarily to scale. Identical or similar components are identified throughout the various figures with identical or similar reference numerals. Therefore, when a component is identified in one figure, it can not be further discussed in subsequent figures. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some of the embodiments of the present disclosure, but not all the embodiments. The description of the embodiments below is actually only illustrative, and should not be construed as any limitation on the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms, and should not be construed as being limited to the embodiments set forth herein.

[0025] It should be understood that the various steps recited in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit performing the steps shown. The scope of the present disclosure is not limited in this respect. Unless specifically stated otherwise, the relative arrangement of components and steps set forth in these embodiments, numerical expressions, and numerical values should be interpreted as merely exemplary, not limiting the scope of the present disclosure.

[0026] The term "comprise" and variations thereof used in the present disclosure means an open term that includes at least the recited elements / features, but does not exclude other elements / features. In addition, the term "include" and variations thereof used in the present disclosure means an open term that includes at least the recited elements / features, but does not exclude other elements / features. Therefore, include and comprise are synonymous. The term "based on" means "at least partially based on".

[0027] Throughout the specification, the term "one embodiment", "some embodiments", or "embodiments" means that the specific feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments". Moreover, the appearance of the phrase "in one embodiment", "in some embodiments", or "in embodiments" at various places in the specification does not necessarily all refer to the same embodiment, but can refer to different embodiments.

[0028] It should be noted that the terms "first", "second", and the like in the present disclosure are merely intended to distinguish different devices, modules, or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules, or units. Unless otherwise specified, the terms "first", "second", and the like are not intended to imply a given order or any other manner of given order in time, space, ranking, or any other manner.

[0029] It should be noted that the terms "one", "multiple" in the present disclosure are illustrative rather than limiting, and those skilled in the art should understand that unless otherwise explicitly specified in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0031] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described in some embodiments. In addition, in one or more embodiments, specific features, structures, or characteristics can be combined by any suitable manner from the present disclosure which is clear to those skilled in the art.

[0032] Currently, an agent can generate a reply text in combination with the context for a question raised by a user. Health-related questions are usually associated with the personal situation of the user. For example, for the exercise needs of a certain part, different users adopt different actions and exercise intensities. Therefore, if only the question raised by the user is replied to, the accuracy is low. Based on the above idea, the present disclosure proposes an interaction method, which will be described below in combination with some embodiments.

[0033] FIG. 1 is a flowchart of some embodiments of the interaction method of the present disclosure. As shown in FIG. 1, the method of this embodiment includes steps S102-S108.

[0034] In step S102, the type of the interaction information is determined in response to the user inputting health-related interaction information. The health-related interaction information includes exercise health-related interaction information. For example, the exercise health-related interaction information includes interaction information related to exercise and fitness, interaction information related to health knowledge involved in exercise and fitness, etc., without being limited to the examples. The health-related interaction information can also include other health-related interaction information, etc., without being limited to the examples.

[0035] In some embodiments, the information interaction interface is displayed, and the health-related interaction information is displayed in the information interaction interface in response to a user input.

[0036] The type of interaction information is used to reflect the key content of the interaction information. In some embodiments, the type of interaction information includes a first type related to a sports action, a second type related to a fitness plan, or a third type related to health knowledge other than the sports action and the fitness plan. The type of interaction information can be divided according to needs, not limited to the examples shown.

[0037] In step S104, target media content for replying to the interaction information is obtained based on the type of the interaction information and the attribute information of the user.

[0038] It should be noted that the acquisition and application of the attribute information of the user comply with the relevant legal regulations, and the user needs to be informed and obtain the consent or authorization of the user. When applicable, the attribute information of the user is subjected to de-identification and / or anonymization and / or encryption technical processing. The attribute information of the user includes the attribute information of the user related to sports, fitness and / or health. For example, the attribute information of the user includes the height, weight and information related to sports of the user, etc. For example, the information related to sports includes sports goals, sports frequency, sports preferences, target parts for exercise, injured parts, etc., not limited to the examples shown.

[0039] For example, the target media content includes at least one of an image and a video. The image includes at least one of a static image and a dynamic image. The target media content can include at least one image and / or at least one video. The target media content for replying to the interaction information and matching the attribute information of the user can be searched in the media content library according to the type of the health-related interaction information input by the user and the attribute information of the user.

[0040] In step S106, a reply text of the interaction information is generated.

[0041] The order of obtaining the target media content and generating the reply text can not be sequential. A target model can be used to generate the reply text according to the interaction information. For example, the target model is a LLM (Large Language Model) or other generative model, a multi-modal model, etc. machine learning model, not limited to the examples shown.

[0042] In step S108, the target media content and the reply text are displayed.

[0043] The target media content and the reply text can be displayed in an information interaction interface, or can be displayed in various forms of interfaces such as a floating layer and a window, and are not limited to the examples shown. The target media content and the reply text can be displayed in the form of a card.

[0044] The method of the above embodiments, in response to the user inputting health-related interaction information, acquires target media content for replying to the interaction information and matching the attribute information of the user according to the interaction information and the attribute information of the user, and generates a reply text according to the interaction information, and displays the target media content and the reply text. Since the attribute information of the user is referred to, the target media content acquired can more accurately reply to the interaction information, personalized target media content can be provided for different users, and the interaction experience of the user is improved. In addition, for the interaction information input by the user, various forms of reply content such as images, videos, and texts can be provided, the richness and effectiveness of the reply content are improved, and the interaction experience of the user is further improved.

[0045] The specific way of acquiring the target media content will be described below in combination with some embodiments.

[0046] In some embodiments, the target model is used to rewrite the interaction information according to the attribute information to generate search information; and the target media content is acquired by searching in a media content library according to the search information.

[0047] The target model can automatically rewrite the interaction information to generate search information. The search information generated can include key information in the interaction information and part or all of the attribute information, and the target media content searched in the media content library based on the search information can be used to reply to the interaction information and match the attribute information of the user.

[0048] The interaction information can be one or more, and the intention of the user can be identified in combination with multiple pieces of interaction information input by the user, key information of the multiple pieces of interaction information is determined, the interaction information is rewritten according to the attribute information and the key information to generate search information.

[0049] In some embodiments, the content of the interaction information is parsed by using the target model to determine the type of the interaction information, wherein the types of the interaction information are different, and the rewriting methods are different.

[0050] The type of the interaction information can reflect the main content of the interaction information, the target model can be used to parse the interaction information to determine the type of the interaction information, and then different rewriting methods are used to rewrite different types of interaction information, so that the search information generated is more accurate, and the target media content obtained is also more accurate. The type of the interaction information can be set according to actual conditions, and is not limited to the examples shown.

[0051] The following describes some embodiments of how to generate search information, taking three types of interaction information as examples, i.e., related to a movement action, related to a fitness plan, and related to health knowledge other than the movement action and the fitness plan.

[0052] In some embodiments, in response to the type of the interaction information being the first type related to the movement action, a first keyword corresponding to the movement action is extracted from the interaction information; and the search information is generated according to a combination of the first keyword and the attribute information.

[0053] For example, the interaction information is “how to do dumbbell bench press”, and “dumbbell bench press” can be extracted as the first keyword from the interaction information. Then, the attribute information of the user can be combined with the first keyword to obtain the search information. For example, the search information is “young, male, dumbbell bench press”.

[0054] The attribute information combined with the first keyword can be part of the attribute information of the user, and the target model can determine the attribute information combined with the first keyword according to the first keyword, and then obtain the search information. For some movement actions, the attribute information of the user can have little effect, in which case the target model can also determine that the first keyword is directly used as the search information without being combined with the attribute information.

[0055] Since the same movement action can be different for different groups of people and action details, using the combination of the first keyword and the attribute information to generate the search information is more accurate, so that the target media content obtained is more accurate in reply to the interaction information.

[0056] In some embodiments, in response to the type of the interaction information being the second type related to the fitness plan, a second keyword corresponding to the fitness plan is extracted from the interaction information; and the search information is generated by combining the second keyword and the identifier of the user in the attribute information.

[0057] The user can input the interaction information to obtain a fitness plan that has been formulated. For example, the interaction information is “what is my weekly fitness plan” or “what is my leg exercise plan”, etc. For example, “weekly fitness plan” and “leg exercise plan” in the interaction information can be extracted as the second keyword. The identifier of the user can be used to find the fitness plan corresponding to the user in the media content library, and thus the search information is generated by combining the second keyword and the identifier of the user.

[0058] By extracting the second keyword and combining it with the identifier of the user to generate the search information, the user's fitness plan can be searched more accurately and quickly, and the accuracy and efficiency of the reply are improved.

[0059] In some embodiments, in response to the type of the interaction information being the third type related to health knowledge other than exercise actions and fitness plans, target attribute information is selected from the attribute information according to semantic information of the interaction information; the target attribute information is fused with the interaction information to generate search information.

[0060] For example, the interaction information is “I want to exercise my chest muscles”, and the attribute information of the user includes: male, young, and exercise preference: like exercising at home. Since the age has little effect on the exercise of chest muscles, the target model selects “male” and “like exercising at home” as target attribute information according to the semantic information of the interaction information. The target attribute information is fused with the interaction information to obtain “male wants to exercise chest muscles at home” as search information. The interaction information can also be “Can I drink a beverage to lose weight?” and “What can I eat to make my muscles grow faster?” and other questions raised by users according to their own needs.

[0061] For some interaction information related to health knowledge other than exercise actions and fitness plans, the attribute information of the user can have little or no effect on the search results, and the target model can determine to directly use the interaction information or key information in the interaction information as search information, and the target attribute information is empty.

[0062] For some interaction information, it can contain both keywords of exercise actions or fitness plans and keywords related to health knowledge other than exercise actions and fitness plans, for example, the interaction information is “What should I do if my knees hurt after doing deep squats?”. The target model can understand that the search information needs to include keywords of exercise actions or fitness plans and keywords related to health knowledge other than exercise actions and fitness plans through analysis of the interaction information. Therefore, this type of interaction information can be classified as the third type related to health knowledge other than exercise actions and fitness plans, and the rewriting method of the third type of interaction information is used for rewriting.

[0063] The method of the above embodiments can automatically select target attributes to be fused with the interaction information for the third type of interaction information related to health knowledge other than exercise actions and fitness plans, and fuse the interaction information with the target attributes to generate search information in natural language, which can improve the accuracy of the search information and further improve the accuracy of the target media content obtained.

[0064] In some embodiments, the attribute information of the user, the interaction information, and the prompt information (Prompt) are input into the target model, and the target model is used to rewrite the interaction information according to the attribute information and the prompt information to generate search information.

[0065] The prompt information includes description information of a role of the target model, a task, a rewriting example, and the like. The description information of the task is used to instruct the target model to extract key information from the interaction information, generate search information in combination with attribute information, and the rewriting example can include rewriting examples of multiple interaction information. The description information of the task can also instruct the target model to distinguish different types of interaction information, and generate specific manners of search information for different types of interaction information.

[0066] The media content library can include multiple sub-databases, and for different types of interaction information, the target media content can be obtained in different sub-databases, which will be described in combination with some embodiments.

[0067] In some embodiments, according to the type of the interaction information, a target sub-database is determined from the multiple sub-databases; and according to the search information, a search is performed in the target sub-database.

[0068] Dividing the media content library into multiple sub-databases, and determining a corresponding target sub-database for different types of interaction information to perform a search, can improve the efficiency of the search.

[0069] In some embodiments, in response to the type of the interaction information being a first type related to a motion action, a first sub-database storing images of the motion action and a second sub-database storing videos in the multiple sub-databases are determined as the target sub-databases.

[0070] For example, the first sub-database includes multiple images of motion actions, and each image in the first sub-database corresponds to description information of a motion action. The description information includes at least one of a name of the action, a type of the action, an exercise part corresponding to the action, required equipment, a key point of the action, a motion location, and information of each group of actions. For example, the type of the action includes aerobic, anaerobic, and the like, the exercise part corresponding to the action includes back, legs, whole body, and the like, the required equipment includes dumbbells, jump rope, and no equipment, and the motion location includes outdoor, gym, and home. Generally, the action is trained in groups, and for example, the information of each group of actions includes the number of actions, the interval between groups, and the energy consumption value. The description information of the motion action can include other information, which is not limited to the examples. The description information of the motion action can also include an identifier of a video corresponding to the motion action, a link, and the like, and through the identifier, the content in the video corresponding to the motion action, the link, and the like can be obtained. For example, the description information of the motion action includes an identifier of a video corresponding to the motion action in the second sub-database.

[0071] The images stored in the first sub-database can be dynamic images, which can more accurately show the movement actions. The first sub-database specially storing images of various movement actions is constructed, and when the user consults a question related to the movement action, more professional and accurate reply information can be provided to the user to guide the user to perform the movement.

[0072] The second sub-database stores a plurality of videos. The videos can be videos related to health or sports health, or can include other types of videos. Each video can be stored in correspondence with its description information. For example, the description information of each video includes the name, abstract, etc. of the video. The description information of the video can be the description information input by the user who publishes the video, or can be generated by using a target model according to the content of the video.

[0073] In the case where the interaction information is related to the movement action, searching the target media content from the first sub-database storing the images of the movement actions and the second sub-database storing the videos can improve the content richness, interest and professionalism of the generated reply, and more easily attract the user, improve the interest and experience of the user.

[0074] In some embodiments, in response to the type of the interaction information being a second type related to the fitness plan, a third sub-database storing the fitness plan in the plurality of sub-databases is determined as the target sub-database.

[0075] For the second type of interaction information related to the fitness plan, the search can be directly performed in the third sub-database storing the fitness plan, improving the accuracy and efficiency of the search.

[0076] In some embodiments, in response to the type of the interaction information being a third type related to health knowledge other than the movement action and the fitness plan, the second sub-database storing the videos in the plurality of sub-databases is determined as the target sub-database.

[0077] For the third type of interaction information, since it does not match the movement action and the fitness plan, the search can be directly performed in the second sub-database storing the videos, improving the efficiency of the search.

[0078] The second sub-database can only store videos related to health (or sports health), or can store other types of videos other than the health-related videos. In some embodiments, in response to the second sub-database including other types of videos other than the health-related videos, a third keyword representing health or fitness is added to the search information before the search, to obtain adjusted search information; and the search is performed in the target sub-database according to the adjusted search information.

[0079] For example, the interaction information is "how to do box jumping", "box jumping" can be used as the name of a sports action or a game action, and searching according to the search information generated based on "box jumping" can obtain inaccurate videos. Therefore, a third keyword for indicating health or fitness is added before the search information, for example, "health and fitness" is directly added before the search information, to obtain adjusted search information. "Fitness action" or "sports action" or the like can also be added as the third keyword, and is not limited to the examples shown.

[0080] By adjusting the search information, the accuracy of searching videos in the target sub-database can be improved, and the target media content obtained is more accurate.

[0081] How to search the target media content will be described below in combination with some embodiments.

[0082] In some embodiments, the search information is keyword-matched with the description information of the sports action corresponding to each image to obtain one or more first images and the keyword matching degrees of the one or more first images; the semantic information of the search information is semantically matched with the description information of the sports action corresponding to each image to obtain one or more second images and the semantic similarities of the one or more second images; and the target media content is determined according to the keyword matching degrees of the one or more first images and the semantic similarities of the one or more second images.

[0083] For example, the first image with the highest keyword matching degree can be selected as the target media content according to the keyword matching degrees of the one or more first images, and / or the second image with the highest semantic similarity can be selected as the target media content according to the semantic similarities of the one or more second images. For another example, the first image with a keyword matching degree higher than a first threshold value can be selected as the target media content according to the keyword matching degrees of the one or more first images, and / or the second image with a semantic similarity higher than a second threshold value can be selected as the target media content according to the semantic similarities of the one or more second images.

[0084] For another example, the keyword matching degrees of the one or more first images are all higher than a third threshold value, and the semantic similarities of the one or more second images are all higher than a fourth threshold value, the images that are overlapped in the first images and the second images are determined as third images, if there are multiple third images, the keyword matching degrees and the semantic similarities of the multiple third images are weighted and summed to obtain a comprehensive matching degree, the third image with the comprehensive matching degree higher than a matching degree threshold value is selected as the target media content, or the third image with the highest comprehensive matching degree is selected as the target media content.

[0085] The target media content is determined based on the keyword matching degree and the semantic similarity, so that the target media content is more matched with the search information, and more accurate target media content is obtained.

[0086] The description information of each video is included in the second sub-database, and the video can be searched by using a similar method as searching the image, which is not described herein again. The content of each video can be understood by using the target model, and the search information is matched with the content of the video to obtain the target media content.

[0087] The fitness plans of each user are stored in the third sub-database, and one or more fitness plans corresponding to the user can be searched according to the identification of the user, and then the second keyword is matched with the one or more fitness plans to obtain the target media content.

[0088] The interactive information input by the user can also be the fourth type of interactive information irrelevant to health (or sports health). Whether the interactive information input by the user is irrelevant to health (or sports health) can be automatically determined by the target model. In response to the interactive information being the fourth type of interactive information, the second sub-database in which the videos are stored in the plurality of sub-databases can be determined as the target sub-database. The interactive information is understood by using the target model to obtain the theme information of the interactive information, the theme information is matched with the videos in the target sub-database to obtain the target media content. The target model can determine whether the attribute information of the user needs to be combined, and in the case where the attribute information of the user needs to be combined, the target attribute information is determined, the search information is generated according to the theme information and the target attribute information, the target sub-database is searched according to the search information, and the target media content is obtained.

[0089] How to generate the reply text will be described below in combination with some embodiments.

[0090] In some embodiments, the reply text is generated according to the target media content and the interactive information.

[0091] The target media content can be summarized by using the target model to obtain the summary information, and the reply text is generated according to the summary information and the interactive information. For example, the summary information can be obtained according to the description information corresponding to the target media content and / or the target media content itself. In response to the target media content being an image, the summary information can be obtained according to the description information corresponding to the target media content, and in response to the target media content being a video, the target media content and the description information corresponding to the target media content are summarized to generate the summary information. For example, the interactive information is “how to do dumbbell bench press”, and the reply text can be generated according to the action points and other information of the image, the description information of the video and the explanation content of the dumbbell bench press in the video. The interactive information can be one or more, and the current interactive information and one or more previous interactive information can be combined, that is, the context is combined to generate the reply text.

[0092] According to the target media content and the interaction information, the reply text can be generated to be more accurate and more matched with the target media content, and the reply information formed by combining various media contents such as text, image and video is more rich, vivid and interesting, and the user experience is improved.

[0093] In some embodiments, the reply text is generated according to the interaction information and the attribute information of the user.

[0094] For example, the interaction information is “how to do dumbbell bench press”, and the reply text is generated by combining the attribute information of the user and the target model, so that the reply text is more accurate and personalized for different users.

[0095] The generated reply text can also include guiding information corresponding to the target media content, for example, the guiding information is “the following video will show you the correct execution method of dumbbell bench press…”.

[0096] In some embodiments, the reply text is generated according to the target media content, the attribute information of the user and the interaction information.

[0097] By combining the target media content, the interaction information and the attribute information of the user, the accuracy of the reply text can be further improved, and specific details can be referred to the foregoing embodiments, which will not be described here.

[0098] In the following, some embodiments are described to show how to display the target media content and the reply text.

[0099] In some embodiments, in response to the type of the interaction information being a first type related to a motion action, the target media content includes an image and one or more videos related to the motion action.

[0100] The reply text, the image and the one or more videos related to the motion action can be displayed in the information interaction interface. The reply text, the image and the one or more videos related to the motion action can also be displayed in a new interface, and the display form is not limited.

[0101] For example, as shown in FIG. 2, the information interaction interface is shown, the user inputs the interaction information, and the interaction information 201 is displayed in the information interaction interface. The reply text 202, the image 203 and the video 204 related to the motion action are displayed. The video 204 can be multiple, and part of the videos can be displayed first, and in response to the switching operation of the user, the switched video is displayed. For example, the user can switch the currently displayed video by left and right sliding. The reply text can include the action description of dumbbell Romanian hard pull, the guiding information including the image and the video, etc.

[0102] In some embodiments, in response to the type of the interaction information being a second type related to a fitness plan, the target media content includes a plurality of images corresponding to the fitness plan, wherein the plurality of images corresponding to the fitness plan are dynamic images.

[0103] The target media content can further include description information of the fitness plan, for example, each of the plurality of images corresponding to the fitness plan further corresponds to action description information, interval between actions, exercise duration, energy consumption, etc. The action description information includes, for example, name of the action, number of sets, exercise part, etc.

[0104] As shown in FIG. 3, for the user input interaction information 301, the generated reply text 302 can be displayed, the fitness plan 303 can be displayed as the target media content, including a plurality of images 304, and the description information 305 of the fitness plan.

[0105] In the case where the fitness plan includes a plurality of levels of information, the highest level of fitness plan information can be displayed, and in response to the user's operation, the lower level of fitness plan information can be displayed. For example, the interaction information is "my weekly fitness plan", and the overview information of the fitness plan for each day in a week can be displayed, and in response to the user's operation, the specific fitness plan information for a day can be displayed.

[0106] In some embodiments, in response to the type of the interaction information being a third type related to health knowledge other than sports action and fitness plan, the target media content includes one or more videos related to the health knowledge.

[0107] The video can be a plurality of videos, and part of the plurality of videos can be displayed first, and in response to the user's switching operation, the switched video can be displayed, and details are not described again.

[0108] Some embodiments of the overall architecture of the interaction method of the present disclosure are described below in conjunction with FIG. 4.

[0109] As shown in FIG. 4, the intelligent agent system includes an intelligent agent engine, a Workflow, a knowledge base, a health server, a display UI, and the like. The intelligent agent engine is configured to receive interactive information of a user, identify an intention of the user, rewrite the interactive information, and the like, and further trigger different works in the Workflow. The Workflow mainly includes a unit for obtaining attribute information of the user, a unit for querying a fitness plan, and a unit for knowledge Q&A. The querying of the fitness plan and the knowledge Q&A both belong to units for generating reply information. The unit for querying the fitness plan can query the health server to generate a fitness plan, and the unit for knowledge Q&A can obtain target media content from the knowledge base. The knowledge base mainly includes a motion library and a health knowledge base. The motion library includes images of motion actions, and the health knowledge base includes information such as videos. The health server provides business modules and underlying infrastructure. The business modules can obtain attribute information of the user, generate a fitness plan, and provide business services such as knowledge Q&A. The underlying infrastructure provides functions such as database query, file operation, and search engine. Finally, the Workflow generates reply text and target multimedia content, which are displayed through the display UI, and can be displayed in the form of a reply card.

[0110] The flowchart of some embodiments of the interactive method of the present disclosure is described below in combination with FIG. 5.

[0111] FIG. 5 is a flowchart of some embodiments of the interactive method of the present disclosure. As shown in FIG. 5, the method of the embodiment includes steps S501-S508.

[0112] In step S501, the intelligent agent receives interactive information sent by a user.

[0113] The intelligent agent can also be referred to as an intelligent agent engine, i.e., the intelligent agent engine shown in FIG. 4.

[0114] In step S502, the intelligent agent obtains attribute information of the user from a variable storage database storing the attribute information of the user.

[0115] In step S503, the intelligent agent rewrites the interactive information according to the type of the interactive information and the attribute information of the user, and generates search information.

[0116] In step S504, the intelligent agent sends the search information to a Workflow engine.

[0117] For example, in response to the type of the interaction information being a first type related to a motion action, the agent invokes the query interface of the workflow engine, and takes the first keyword corresponding to the motion action and the attribute information of the user as parameters, and takes the value (e.g., true) representing the action query as the value of the action query flag. In response to the type of the interaction information being a third type related to health knowledge other than the motion action and the fitness plan, the agent invokes the query interface of the workflow engine, and takes the search information as a parameter, and takes the value (e.g., false) representing the non-action query as the value of the action query flag.

[0118] In step S505, the workflow engine queries the action library for the image related to the motion action.

[0119] The action library is the first sub-database in the foregoing embodiments, and the video library is the second sub-database in the foregoing embodiments.

[0120] In step S506, the workflow engine queries the video library for the video.

[0121] Steps S505 and S506 are optional steps.

[0122] In step S507, the workflow engine returns the target media content to the agent.

[0123] In step S508, the agent generates reply information.

[0124] The reply information, for example, includes the reply text and the target media content.

[0125] For different types of interaction information, the way of obtaining the target media content is different, and some embodiments of the method of obtaining the target media content described in the foregoing embodiments are summarized as follows in combination with FIG. 6.

[0126] As shown in FIG. 6, the interactive information is divided into a first type related to the exercise action, a second type related to the fitness plan, a third type related to the health knowledge other than the exercise action and the fitness plan, and a fourth type unrelated to the health knowledge. For the interactive information of the first type, the first keyword related to the exercise action needs to be extracted during rewriting, and the attribute information of the user also needs to be combined. In addition, a third keyword needs to be added before searching the information, and the action library and the video library are searched respectively to finally generate the card. For the interactive information of the second type, different types of fitness plans such as the weekly plan and the daily plan can be searched to generate the corresponding fitness plan card. For the interactive information of the third type, the attribute information also needs to be combined during rewriting, and the third keyword needs to be added before searching the information, and the video library is searched to finally generate the card. For the interactive information of the fourth type, the reply information can be directly generated, or the corresponding video can be searched as described in the foregoing embodiment. The specific process can be referred to the foregoing embodiment, which will not be described here. The searching, obtaining the weekly plan, obtaining the daily plan, and the like can be executed by the Workflow.

[0127] The present disclosure also provides an interactive device, which is described below in combination with FIG. 7.

[0128] FIG. 7 is a structural diagram of some embodiments of the interactive device of the present disclosure. As shown in FIG. 7, the interactive device 70 of the embodiment includes a determination module 710, an acquisition module 720, a generation module 730, and a display module 740.

[0129] The determination module 710 is configured to determine the type of the interactive information in response to the user inputting the health-related interactive information.

[0130] The acquisition module 720 is configured to acquire target media content for replying to the interactive information based on the type of the interactive information and the attribute information of the user, wherein the target media content includes at least one of an image and a video.

[0131] The generation module 730 is configured to generate the reply text of the interactive information.

[0132] The display module 740 is configured to display the target media content and the reply text.

[0133] In some embodiments, the acquisition module 720 is configured to rewrite the interactive information according to the type of the interactive information and the attribute information by using a target model, generate search information, search in the media content library according to the search information, and acquire the target media content.

[0134] In some embodiments, the acquisition module 720 is configured to parse the content of the interactive information by using a target model, and determine the type of the interactive information, wherein the types of the interactive information are different, and the rewriting manners are different.

[0135] In some embodiments, the obtaining module 720 is configured to, in response to the type of the interaction information being a first type related to a sports action, extract a first keyword corresponding to the sports action from the interaction information; and generate the search information according to a combination of the first keyword and the attribute information.

[0136] In some embodiments, the obtaining module 720 is configured to, in response to the type of the interaction information being a second type related to a fitness plan, extract a second keyword corresponding to the fitness plan from the interaction information; and take the identity of the user in the attribute information and the second keyword as the search information.

[0137] In some embodiments, the obtaining module 720 is configured to, in response to the type of the interaction information being a third type related to health knowledge other than the sports action and the fitness plan, select target attribute information from the attribute information according to semantic information of the interaction information; and fuse the target attribute information with the interaction information to generate the search information.

[0138] In some embodiments, the media content library includes a plurality of sub-databases, and the obtaining module 720 is configured to determine a target sub-database from the plurality of sub-databases according to the type of the interaction information; and search in the target sub-database according to the search information.

[0139] In some embodiments, the obtaining module 720 is configured to, in response to the type of the interaction information being a first type related to a sports action, determine a first sub-database storing images of sports actions and a second sub-database storing videos in the plurality of sub-databases as the target sub-databases.

[0140] In some embodiments, the obtaining module 720 is configured to, in response to the type of the interaction information being a second type related to a fitness plan, determine a third sub-database storing fitness plans in the plurality of sub-databases as the target sub-database.

[0141] In some embodiments, the obtaining module 720 is configured to, in response to the type of the interaction information being a third type related to health knowledge other than the sports action and the fitness plan, determine the second sub-database storing videos in the plurality of sub-databases as the target sub-database.

[0142] In some embodiments, the obtaining module 720 is configured to, in response to the second sub-database including videos of other types than health-related videos, add a third keyword representing health or fitness to the search information to obtain adjusted search information; and search in the target sub-database according to the adjusted search information.

[0143] In some embodiments, the media content library includes a first sub-database storing images of sports actions, each image in the first sub-database corresponds to description information of a sports action, the obtaining module 720 is configured to perform keyword matching between the search information and the description information of the sports action corresponding to each image to obtain one or more first images and keyword matching degrees corresponding to the one or more first images; perform semantic matching between semantic information of the search information and the description information of the sports action corresponding to each image to obtain one or more second images and semantic similarities corresponding to the one or more second images; and determine the target media content according to the keyword matching degrees corresponding to the one or more first images and the semantic similarities corresponding to the one or more second images.

[0144] In some embodiments, the generating module 730 is configured to generate the reply text according to the target media content and the interaction information.

[0145] In some embodiments, in response to the type of the interaction information being a first type related to sports actions, the target media content includes sports action related images and one or more videos, wherein the sports action related images are dynamic images; and / or in response to the type of the interaction information being a second type related to fitness plans, the target media content includes a plurality of images corresponding to the fitness plans, wherein the plurality of images corresponding to the fitness plans are dynamic images; and / or in response to the type of the interaction information being a third type related to health knowledge other than sports actions and fitness plans, the target media content includes one or more videos related to the health knowledge.

[0146] It should be noted that each unit (module) described above is only a logical division according to the specific function implemented by it, and is not used to limit the specific implementation manner, for example, it can be implemented in software, hardware or a combination of software and hardware. In actual implementation, each unit described above can be implemented as an independent physical entity, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, each unit described above is indicated by a dashed line in the drawings, indicating that these units can not actually exist, and the operations / functions implemented by them can be implemented by the processing circuit itself.

[0147] Further, although not shown, the device can also include a memory that can store various information generated by the device, the various units included in the device in operation, programs and data for operation, data to be transmitted by the communication unit, and the like. The memory can be a volatile memory and / or a non-volatile memory. For example, the memory can include, but is not limited to, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a read only memory (ROM), a flash memory. Of course, the memory can also be located outside the device. Alternatively, although not shown, the device can also include a communication unit that can be used to communicate with other devices. In one example, the communication unit can be implemented in an appropriate manner known in the art, for example, including a communication component such as an antenna array and / or a radio frequency link, various types of interfaces, communication units, and the like. Here will not be described in detail. In addition, the device can also include other components not shown, such as radio frequency links, baseband processing units, network interfaces, processors, controllers, and the like. Here will not be described in detail.

[0148] Some embodiments of the present disclosure also provide an electronic device. FIG. 8 shows a block diagram of some embodiments of the electronic device of the present disclosure. For example, in some embodiments, the electronic device 80 can be various types of devices, for example, can include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. For example, the electronic device 80 can include a display panel for displaying data and / or execution results utilized in the scheme according to the present disclosure. For example, the display panel can be various shapes, such as a rectangular panel, an oval panel, or a polygonal panel, and the like. In addition, the display panel can not only be a flat panel, but also a curved panel, or even a spherical panel.

[0149] As shown in FIG. 8, the electronic device 80 of this embodiment includes a memory 81 and a processor 82 coupled to the memory 81. It should be noted that the components of the electronic device 80 shown in FIG. 8 are only exemplary and are not limiting, and the electronic device 80 can also have other components according to actual application needs. The processor 82 can control other components in the electronic device 80 to perform the desired functions.

[0150] In some embodiments, the memory 81 is configured to store one or more computer readable instructions. When the processor 82 executes the computer readable instructions, the computer readable instructions are executed by the processor 82 to implement the method according to any of the above embodiments. For specific implementation of each step of the method and related explanations, please refer to the above embodiments, and the repeated parts will not be described here.

[0151] For example, the processor 82 and the memory 81 can communicate with each other directly or indirectly. For example, the processor 82 and the memory 81 can communicate with each other through a network. The network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 82 and the memory 81 can also communicate with each other through a system bus, and the present disclosure does not limit this.

[0152] For example, the processor 82 can be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), a network processing unit (NP), etc.; and can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component. The central processing unit (CPU) can be an X86 or ARM architecture, etc. For example, the memory 81 can include any combination of various forms of computer-readable storage media, such as a volatile memory and / or a non-volatile memory. The memory 81 may, for example, include a system memory, which stores, for example, an operating system, an application program, a boot loader, a database, and other programs, etc. Various application programs and various data, etc. can also be stored in the storage medium.

[0153] In addition, according to some embodiments of the present disclosure, various operations / processes according to the present disclosure, in the case of being implemented by software and / or firmware, can install programs constituting the software from a storage medium or a network to a computer system having a dedicated hardware structure, such as the computer system (or electronic device) 90 shown in FIG. 9, which is capable of performing various functions when various programs are installed. FIG. 9 is a block diagram showing an example structure of a computer system that can be employed according to embodiments of the present disclosure.

[0154] In FIG. 9, a central processing unit (CPU) 901 executes various processes in accordance with a program stored in a read only memory (ROM) 902 or a program loaded from a storage section 908 to a random access memory (RAM) 903. In the RAM 903, data required when the CPU 901 executes various processes and the like is also stored as necessary. The central processing unit is merely exemplary, and can be other types of processors, such as the various processors described above. The ROM 902, the RAM 903, and the storage section 908 can be various forms of computer readable storage media, as described below. Note that, although the ROM 902, the RAM 903, and the storage section 908 are shown separately in FIG. 9, one or more of them can be combined or located in the same or different memory or storage modules.

[0155] The CPU 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output interface 905 is also connected to the bus 904.

[0156] The following components are connected to the input / output interface 905: an input section 906, such as a touch panel, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, and the like; an output section 907, including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, and the like; a storage section 908, including a hard disk, a magnetic tape, and the like; and a communication section 909, including a network interface card, such as a LAN card, a modem, and the like. The communication section 909 allows communication processing to be performed via a network, such as the Internet. It is readily understood that, although the various devices or modules in the computer system 90 are shown in FIG. 9 as communicating through the bus 904, they can also communicate through a network or other means, where the network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network.

[0157] A drive 910 is also connected to the input / output interface 905 as necessary. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like, is attached to the drive 910 as necessary, so that a computer program read therefrom is installed in the storage section 908 as necessary.

[0158] In the case where the above-described series of processes are implemented by software, the program constituting the software can be installed from a network, such as the Internet, or a storage medium, such as the removable medium 911.

[0159] According to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the CPU 901, the above-described functions defined in the methods of the embodiments of the present disclosure are executed.

[0160] It should be noted that, in the context of the present disclosure, a computer readable medium can be a tangible medium which can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable medium can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable program code is carried. Such a propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wire, cable, RF (radio frequency), or any suitable combination thereof.

[0161] The above computer readable medium can be included in the above electronic device; or can exist separately, without being assembled into the electronic device.

[0162] In some embodiments, a computer program including instructions which, when executed by a processor, causes the processor to carry out the method according to any of the embodiments described above is also provided. For example, the instructions can be embodied in a computer program code.

[0163] In an embodiment of the disclosure, the computer program code for carrying out operations of the disclosure can be written in one or more programming languages or combinations thereof including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0164] The flow diagrams and the block diagrams in the drawings are illustrations of possible architectures, functions, and operations for systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0165] The modules, components or units described in the embodiments of the present disclosure can be implemented by software or by hardware. In some cases, the name of the module, component or unit does not constitute a limitation on the module, component or unit itself.

[0166] The functionality described herein above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, example hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), etc.

[0167] According to some embodiments of the present disclosure, an interaction method is provided, including: in response to a user inputting health-related interaction information, determining a type of the interaction information; based on the type of the interaction information and attribute information of the user, obtaining target media content for replying to the interaction information, wherein the target media content includes at least one of an image and a video; generating reply text of the interaction information; and displaying the target media content and the reply text.

[0168] In some embodiments, based on the type of the interaction information and the attribute information of the user, obtaining the target media content for replying to the interaction information includes: using a target model, rewriting the interaction information according to the type of the interaction information and the attribute information, to generate search information; and searching in a media content library according to the search information to obtain the target media content.

[0169] In some embodiments, determining the type of the interaction information includes: using a target model to parse the content of the interaction information, to determine the type of the interaction information, wherein the types of the interaction information are different, and the rewriting manners are different.

[0170] In some embodiments, rewriting the interaction information according to the type of the interaction information and the attribute information to generate search information includes: in response to the type of the interaction information being a first type related to a sports action, extracting a first keyword corresponding to the sports action from the interaction information; and generating the search information according to a combination of the first keyword and the attribute information.

[0171] In some embodiments, rewriting the interaction information according to the type of the interaction information and the attribute information to generate search information includes: in response to the type of the interaction information being a second type related to a fitness plan, extracting a second keyword corresponding to the fitness plan from the interaction information; and taking the identity of the user in the attribute information and the second keyword as the search information.

[0172] In some embodiments, rewriting the interaction information according to the type of the interaction information and the attribute information to generate search information includes: in response to the type of the interaction information being a third type related to health knowledge other than sports actions and fitness plans, selecting target attribute information from the attribute information according to semantic information of the interaction information; and fusing the target attribute information with the interaction information to generate the search information.

[0173] In some embodiments, the media content library comprises a plurality of sub-databases, and searching in the media content library according to the search information comprises: determining a target sub-database from the plurality of sub-databases according to the type of the interaction information; and searching in the target sub-database according to the search information.

[0174] In some embodiments, determining the target sub-database from the plurality of sub-databases according to the type of the interaction information comprises: in response to the type of the interaction information being a first type related to a sports action, determining a first sub-database storing images of the sports action and a second sub-database storing videos from the plurality of sub-databases as the target sub-database.

[0175] In some embodiments, determining the target sub-database from the plurality of sub-databases according to the type of the interaction information comprises: in response to the type of the interaction information being a second type related to a fitness plan, determining a third sub-database storing the fitness plan from the plurality of sub-databases as the target sub-database.

[0176] In some embodiments, determining the target sub-database from the plurality of sub-databases according to the type of the interaction information comprises: in response to the type of the interaction information being a third type related to health knowledge other than the sports action and the fitness plan, determining the second sub-database storing the videos from the plurality of sub-databases as the target sub-database.

[0177] In some embodiments, searching in the target sub-database according to the search information comprises: in response to the second sub-database including videos of other types than health-related videos, adding a third keyword representing health or fitness to the search information to obtain adjusted search information before the searching; and searching in the target sub-database according to the adjusted search information.

[0178] In some embodiments, the media content library comprises a first sub-database storing images of sports actions, each image in the first sub-database corresponding to description information of a sports action, and searching in the media content library according to the search information to obtain target media content comprises: performing keyword matching between the search information and the description information of the sports action corresponding to each image to obtain one or more first images and a keyword matching degree corresponding to the one or more first images; performing semantic matching between semantic information of the search information and the description information of the sports action corresponding to each image to obtain one or more second images and a semantic similarity corresponding to the one or more second images; and determining the target media content according to the keyword matching degree corresponding to the one or more first images and the semantic similarity corresponding to the one or more second images.

[0179] In some embodiments, generating the reply text of the interaction information comprises: generating the reply text according to the target media content and the interaction information.

[0180] In some embodiments, in response to the type of the interaction information being a first type related to a sports action, the target media content comprises sports action related images and one or more videos, wherein the sports action related images are dynamic images; and / or in response to the type of the interaction information being a second type related to a fitness plan, the target media content comprises a plurality of images corresponding to the fitness plan, wherein the plurality of images corresponding to the fitness plan are dynamic images; and / or in response to the type of the interaction information being a third type related to health knowledge other than the sports action and the fitness plan, the target media content comprises one or more videos related to the health knowledge.

[0181] According to some other embodiments of the present disclosure, an interaction device is provided, comprising: a determination module configured to determine a type of interaction information in response to a user inputting the health related interaction information; an acquisition module configured to acquire target media content for replying to the interaction information based on the type of the interaction information and attribute information of the user, wherein the target media content comprises at least one of an image and a video; a generation module configured to generate a reply text of the interaction information; and a display module configured to display the target media content and the reply text.

[0182] According to some other embodiments of the present disclosure, an electronic device is provided, comprising: a processor; and a memory coupled to the processor, configured to store instructions, which when executed by the processor, cause the processor to perform the interaction method of any one of the embodiments of the present disclosure.

[0183] According to some other embodiments of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, which when executed by a processor, performs the interaction method of any one of the embodiments of the present disclosure.

[0184] According to some other embodiments of the present disclosure, a computer program product is provided, comprising: instructions, which when executed by a processor, implement the interaction method of any one of the embodiments of the present disclosure.

[0185] According to some other embodiments of the present disclosure, a computer program is provided, comprising: instructions, which when executed by a processor, implement the interaction method of any one of the embodiments of the present disclosure.

[0186] The above description is merely some embodiments of the present disclosure and a description of the principles of the applied technology. It should be understood by those skilled in the art that the disclosure scope involved in the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combinations of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the above features are replaced with each other to form technical solutions with similar functions disclosed in the present disclosure (but not limited to).

[0187] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

[0188] In addition, while operations are depicted in a particular, chronological sequence, this should not be understood as requiring such order unless otherwise specifically indicated, and one or more activities can occur in different orders or concurrently with each other. Similarly, while several specific implementation details are included herein, they should not be taken as limitations of the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination.

[0189] While certain embodiments of the disclosure have been described herein, other embodiments will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. Therefore, the disclosure is not limited to these embodiments, but instead has a scope as defined by the appended claims. In addition, various modifications can be made in detail to the embodiments of the present disclosure without changing the overall scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. An interaction method, comprising: determining a type of health-related interaction information in response to a user inputting the interaction information; obtaining target media content for replying to the interaction information based on the type of the interaction information and attribute information of the user, wherein the target media content comprises at least one of an image and a video; generating reply text of the interaction information; displaying the target media content and the reply text.

2. The interaction method of claim 1, wherein, The obtaining of the target media content for replying to the interaction information based on the type of the interaction information and the attribute information of the user comprises: rewriting the interaction information according to the type of the interaction information and the attribute information by using a target model to generate search information; searching in a media content library according to the search information to obtain the target media content.

3. The interaction method of claim 2, wherein, The determination of the type of the interaction information comprises: analyzing content of the interaction information by using the target model to determine the type of the interaction information, wherein the type of the interaction information is different and the rewriting manner is different.

4. The interaction method of claim 3, wherein, The rewriting of the interaction information according to the type of the interaction information and the attribute information to generate the search information comprises: extracting a first keyword corresponding to a motion action from the interaction information in response to the type of the interaction information being a first type related to the motion action; generating the search information according to a combination of the first keyword and the attribute information.

5. The interaction method according to claim 3 or 4, wherein, The rewriting of the interaction information according to the type of the interaction information and the attribute information to generate the search information comprises: extracting a second keyword corresponding to a fitness plan from the interaction information in response to the type of the interaction information being a second type related to the fitness plan; taking an identifier of the user in the attribute information and the second keyword as the search information.

6. The interaction method according to any of claims 3-5, wherein, The rewriting of the interaction information according to the type of the interaction information and the attribute information to generate the search information comprises: selecting target attribute information from the attribute information according to semantic information of the interaction information in response to the type of the interaction information being a third type related to health knowledge other than the motion action and the fitness plan; fusing the target attribute information and the interaction information to generate the search information.

7. The interaction method according to any of claims 2-6, wherein, The media content library comprises a plurality of sub-databases, and the searching in the media content library according to the search information comprises: determining a target sub-database from the plurality of sub-databases according to the type of the interaction information; searching in the target sub-database according to the search information.

8. The interaction method of claim 7, wherein, The determination of the target sub-database from the plurality of sub-databases according to the type of the interaction information comprises: determining a first sub-database storing images of motion actions and a second sub-database storing videos in the plurality of sub-databases as the target sub-database in response to the type of the interaction information being the first type related to the motion action.

9. The interaction method according to claim 7 or 8, wherein, The determination of the target sub-database from the plurality of sub-databases according to the type of the interaction information comprises: In response to the type of the interaction information being a second type related to a fitness plan, a third sub-database storing a fitness plan in the plurality of sub-databases is determined as the target sub-database.

10. The interaction method according to any of claims 7-9, wherein, The determining the target sub-database from the plurality of sub-databases according to the type of the interaction information comprises: In response to the type of the interaction information being a third type related to health knowledge other than the exercise action and the fitness plan, a second sub-database storing a video in the plurality of sub-databases is determined as the target sub-database.

11. The interaction method of claim 8 or 10, wherein, The searching in the target sub-database according to the search information comprises: In response to the second sub-database including other types of videos other than health-related videos, a third keyword representing health or fitness is added before the search information to obtain adjusted search information; The searching in the target sub-database according to the adjusted search information.

12. The interaction method according to any of claims 4-11, wherein, The media content library comprises a first sub-database storing images of exercise actions, each image in the first sub-database corresponds to description information of an exercise action, and the searching in the media content library according to the search information to obtain the target media content comprises: performing keyword matching between the search information and the description information of the exercise action corresponding to each image to obtain one or more first images and a keyword matching degree corresponding to the one or more first images; performing semantic matching between semantic information of the search information and the description information of the exercise action corresponding to each image to obtain one or more second images and a semantic similarity corresponding to the one or more second images; and determining the target media content according to the keyword matching degree corresponding to the one or more first images and the semantic similarity corresponding to the one or more second images.

13. The interaction method according to any of claims 1-12, wherein, The generating the reply text of the interaction information comprises: generating the reply text according to the target media content and the interaction information.

14. The interaction method according to any one of claims 1-13, wherein: in response to the type of the interaction information being a first type related to an exercise action, the target media content comprises an image related to the exercise action and one or more videos, wherein the image related to the exercise action is a dynamic image; and / or in response to the type of the interaction information being a second type related to a fitness plan, the target media content comprises a plurality of images corresponding to the fitness plan, wherein the plurality of images corresponding to the fitness plan are dynamic images; and / or in response to the type of the interaction information being a third type related to health knowledge other than the exercise action and the fitness plan, the target media content comprises one or more videos related to the health knowledge.

15. An image generation apparatus, comprising: a determination module configured to determine a type of interaction information input by a user in response to the user inputting health-related interaction information; an acquisition module configured to acquire target media content for replying to the interaction information based on the type of the interaction information and attribute information of the user, wherein the target media content comprises at least one of an image and a video. a generating module configured to generate a reply text of the interaction information; a displaying module configured to display the target media content and the reply text. 16.An electronic device, comprising: a processor; and a memory coupled to the processor for storing instructions, which when executed by the processor, cause the processor to perform the interaction method of any one of claims 1-14.

17. A computer readable storage medium having stored thereon a computer program, wherein, The program, when executed by the processor, implements the interaction method of any one of claims 1-14.

18. A computer program product, comprising: instructions, which when executed by the processor, implement the interaction method of any one of claims 1-14.

Images