Interaction method and device, equipment and storage medium

Abstract

The invention provides an interaction method and device, equipment and a storage medium, and relates to the technical field of data processing and image processing, in particular to the technical field of artificial intelligence, large models and the like. According to the specific implementation scheme, in response to a first control operation, a first intention feature of the first control operation is obtained, and the first intention feature is at least used for indicating the intelligent digital person to adjust an image feature; based on a target triggering instruction indicated by the first intention characteristic, adjusting an image characteristic of the intelligent digital person so as to display the adjusted intelligent digital person; and outputting first response information corresponding to the first intention feature.

Description

Technical Field

[0001] The present disclosure relates to the technical fields of data processing and image processing, and in particular to technical fields such as artificial intelligence and large models. Background Art

[0002] At present, many e-commerce platforms have launched virtual fitting models in order to occupy a technological high ground in the field of e-commerce. However, although these models have made certain breakthroughs in technology, they have brought certain difficulties in understanding and application. Therefore, to achieve the ideal effect of virtual fitting, it still requires a lot of time and practice to explore and improve. Summary of the invention

[0003] The present disclosure provides an interaction method, apparatus, device and storage medium.

[0004] According to one aspect of the present disclosure, there is provided an interaction method, comprising:

[0005] In response to a first control operation, obtaining a first intention feature of the first control operation, wherein the first intention feature is at least used to instruct the intelligent digital human to adjust an image feature;

[0006] Based on the target trigger instruction indicated by the first intention feature, adjusting the image features of the intelligent digital human to display the adjusted intelligent digital human; and

[0007] Output first response information corresponding to the first intention feature.

[0008] According to another aspect of the present disclosure, there is provided an interaction device, comprising:

[0009] A processing unit is used to obtain a first intention feature of the first control operation in response to the first control operation, wherein the first intention feature is at least used to instruct the intelligent digital human to adjust the image feature; based on the target trigger instruction indicated by the first intention feature, adjust the image feature of the intelligent digital human to obtain an adjusted intelligent digital human; and

[0010] The output unit is used to display the adjusted intelligent digital human and output first response information corresponding to the first intention feature.

[0011] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] 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 execute any method in the embodiments of the present disclosure.

[0015] According to another aspect 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 any method according to the embodiments of the present disclosure.

[0016] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements any method according to the embodiments of the present disclosure when executed by a processor.

[0017] In this way, the disclosed solution can adjust the image characteristics of the intelligent digital human according to the intention characteristics of the target object, and simultaneously output response information corresponding to the intention characteristics, thereby achieving multi-dimensional interaction with the target object, thereby enriching the user experience while improving the user experience.

[0018] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0020] Figure 1 This is a schematic diagram of the implementation process of the interaction method according to an embodiment of the present application. Figure 1 ;

[0021] Figure 2 This is a schematic diagram of the implementation process of the interaction method according to an embodiment of the present application. Figure 2 ;

[0022] Figure 3(a) to Figure 3(e) This is a schematic diagram of an interactive scene of an intelligent digital human according to an embodiment of the present application. Figure 1 ;

[0023] Figure 4 is a schematic flowchart 3 of an interaction method according to an embodiment of the present application;

[0024] Figure 5(a) to Figure 5(d) This is a schematic diagram of an interactive scene of an intelligent digital human according to an embodiment of the present application. Figure 2 ;

[0025] Figure 6 This is a schematic diagram of a comparison scenario of commodity feature information of the same commodity object according to an embodiment of the present application;

[0026] FIG. 7( a ) and FIG. 7( b ) are flowcharts of an interaction method according to an embodiment of the present application in a specific embodiment;

[0027] Figure 8 is a schematic diagram of the structure of an interactive device according to an embodiment of the present application;

[0028] Fig. 9 It is a block diagram of an electronic device used to implement the interactive method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0030] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may 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 term "at least one" in this article means any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C. The terms "first" and "second" in this article refer to multiple similar technical terms and distinguish them. They do not mean to limit the order or to limit them to only two. For example, the first feature and the second feature refer to two types / two features. The first feature can be one or more, and the second feature can also be one or more.

[0031] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the specific embodiments below. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0032] The disclosed solution provides a specific solution that can change the image characteristics of intelligent digital people in real time, such as changing clothes in real time, and can display the three-dimensional effect of clothing after trying on in multiple dimensions. Moreover, the solution can use the carrier of intelligent digital people (such as super-realistic digital people) to carry out intelligent dialogue, intelligent recommendations (such as clothing matching recommendations) while changing the image characteristics, and even display the product feature information of the same product object from different recommendation platforms, thus enriching the user experience while improving the user experience.

[0033] Specifically, Figure 1 This is a schematic flow chart of an interactive method according to an embodiment of the present application. Figure 1 The method may be optionally applied to electronic devices, such as personal computers, servers, server clusters, and other electronic devices.

[0034] Further, the method includes at least part of the following contents. Figure 1 As shown, including:

[0035] Step S101: In response to a first control operation, obtaining a first intention feature of the first control operation.

[0036] Here, the first intention feature is at least used to instruct the intelligent digital human to adjust the image feature. For example, in one example, the image feature includes but is not limited to at least one of the following: facial features (such as expression, action and makeup, etc.), hairstyle features (such as hair color, hairstyle, etc.), clothing, etc.

[0037] Further, in one example, the first control operation may specifically be a voice control operation or a text control operation.

[0038] Here, it should be noted that the intelligent digital human described in the disclosed solution can be specifically a 3-dimensional (Dimension, D) intelligent digital human, that is, specifically a 3D intelligent digital human.

[0039] Step S102: Based on the target trigger instruction indicated by the first intention feature, the image feature of the intelligent digital human is adjusted to display the adjusted intelligent digital human.

[0040] Step S103: outputting first response information corresponding to the first intention feature.

[0041] For example, in one example, the intelligent digital human may be specifically used to output first response information corresponding to the first intention feature. Alternatively, the intelligent digital human with an adjusted image may be specifically used to output first response information corresponding to the first intention feature.

[0042] Furthermore, in one example, the first response information can be specifically outputted by voice through the intelligent digital human. For example, after obtaining the first response information, the first response information can be converted into response voice data, and then the intelligent digital human can be used for voice playback. Furthermore, in order to further improve the user experience and the display effect, the mouth movements of the intelligent digital human can be rendered based on the response voice data and displayed synchronously with the voice broadcast.

[0043] It should be noted that the first response information can also be displayed through text content. For example, a text display box is set in at least part of the area other than the intelligent digital human in the display page. At this time, the text content of the first response information can be displayed in the text display box.

[0044] In this way, the disclosed solution can adjust the image characteristics of the intelligent digital human according to the intention characteristics of the target object, and simultaneously output response information corresponding to the intention characteristics, thereby achieving multi-dimensional interaction with the target object, thereby enriching the user experience while improving the user experience.

[0045] For example, in the scenario of trying on clothes by an intelligent digital human, the disclosed solution can effectively change clothes through an intelligent digital human according to the needs of the target object (i.e., the intention characteristics), and then intuitively display the trying-on effect of clothing (including clothes and accessories) on the intelligent digital human. This process does not require the target object to try on the clothes in person, which effectively saves the target object's time and energy. Moreover, through the intelligent digital human changing clothes and interacting with the target object, it can also effectively reduce the target object's feeling of jumping out during the browsing process, so that the target object can obtain a more immersive browsing experience, thereby further effectively improving the user experience.

[0046] In a specific example, when displaying the adjusted intelligent digital human, the adjusted intelligent digital human can be triggered to rotate around a preset axis for multi-dimensional display; or, when displaying the adjusted intelligent digital human, in response to a display operation (for example, in response to a touch operation of a display button (for example, which can be a virtual button) set on the display interface), the adjusted intelligent digital human can be triggered to rotate around a preset axis for multi-dimensional display. In this way, the overall effect of the adjusted image characteristics can be further displayed, thereby further improving the browsing experience.

[0047] Here, in one example, the multi-dimensional display can be specifically a 360-degree full-scale display. For example, in one example, while displaying the adjusted intelligent digital human, the intelligent digital human can also automatically rotate 360 ​​degrees around a preset axis to display 360 degrees, so that the effect of the adjusted intelligent digital human image can be viewed from all angles, thereby effectively improving the user experience.

[0048] Or, in another example, when displaying the adjusted intelligent digital human, a 360-degree display instruction of the target object is obtained. At this time, based on the 360-degree display instruction, the intelligent digital human is triggered to automatically rotate 360 ​​degrees around a preset axis.

[0049] In this way, the disclosed solution can realize the observation of the details of the image of the intelligent digital person from multiple angles, further improving the browsing experience. Moreover, multi-dimensional, such as 360-degree display, can also enhance the immersion and interactive experience of the target object, thereby significantly improving the realism of the user experience.

[0050] In a specific example of the disclosed solution, the first intention feature may be obtained in the following manner; specifically, the above-mentioned obtaining the first intention feature of the first control operation in response to the first control operation (for example, step S101) specifically includes:

[0051] In response to a first control operation, an operation feature of the first control operation (eg, text data corresponding to the first control operation) is input into a second model to obtain a first intention feature of the first control operation.

[0052] For example, when the first control operation is a voice control operation, the voice data corresponding to the voice control operation can be converted into text data, and the text data of the voice control operation can be input into the second model to obtain the first intention feature of the voice control operation.

[0053] Alternatively, when the first control operation is a text control operation, the text data corresponding to the text control operation may be directly input into the second model to obtain the first intention feature of the text control operation.

[0054] That is to say, in this example, the second model can be used to understand the intent, and then quickly infer the first intention feature of the first control operation.

[0055] Here, the second model may specifically be a large language model (also referred to as a large model), or it may also be other natural language processing models with content reasoning capabilities, and the present disclosure does not impose any specific restrictions on this.

[0056] In this way, the disclosed solution can use the model to deeply understand the control operations input by the target object, so as to accurately locate the needs of the target object, and then facilitate subsequent operations based on the understood needs, thus laying the foundation for improving user experience.

[0057] Further, in a specific example, in response to the first control operation, inputting the operation characteristics of the first control operation into the second model to obtain the first intention characteristics of the first control operation specifically includes:

[0058] In response to a first control operation including voice data, converting the first control operation into target text data;

[0059] The target text data is input into a second model to obtain a first intention feature of the first control operation.

[0060] For example, in one example, the target object inputs a piece of voice data to control the intelligent digital human to adjust the image features. At this time, the voice data input by the target object (that is, the voice data corresponding to the voice control operation, also called control voice data) can be converted into target text data using speech-to-text technology, and then the obtained target text data is input into the large language model for intent understanding to obtain the target object's intent features (that is, the first intent features).

[0061] Here, the speech-to-text technology in this example may specifically be a recognition technology based on an acoustic model, or may also be a recognition technology based on a language model, and the present disclosure does not impose any restrictions on this.

[0062] In this way, the disclosed solution can effectively respond to control voice data and convert the control voice data into text, and then use the large model to perform deep understanding and complex reasoning to obtain intent features. In this way, the efficiency and accuracy of information processing are significantly improved, and a deep understanding of user needs is achieved, thereby laying the foundation for providing more accurate feedback in the future.

[0063] Figure 2 This is a schematic flow chart of an interactive method according to an embodiment of the present application. Figure 2 The method can be optionally applied to electronic devices, such as personal computers, servers, server clusters, and other electronic devices. It can be understood that the above Figure 1 The relevant contents of the method shown can also be applied to this example, and the relevant contents will not be described in detail in this example.

[0064] Further, the method includes at least part of the following contents. Figure 2 As shown, including:

[0065] Step S201: In response to a first control operation, obtaining a first intention feature of the first control operation.

[0066] Here, the first intention feature is at least used to instruct the intelligent digital human to adjust the image feature.

[0067] It should be noted that the relevant content about the first intention feature can be referred to the above example and will not be repeated here.

[0068] Step S202: Based on the target trigger instruction indicated by the first intention feature, the image feature of the intelligent digital human is adjusted to display the adjusted intelligent digital human.

[0069] Step S203: generating a target prompt word based on the first intention feature of the first control operation and a preset prompt word template.

[0070] For instance, in one example, the preset prompt word template includes preset examples (e.g., question-answer pairs, etc.). At this time, based on the first intention feature and the preset examples of the preset prompt word template, a target prompt word matching the first intention feature (e.g., including question-answer pairs that meet the requirements) can be obtained. In this way, the target prompt word can be used to effectively guide the first model to perform reasoning, thereby obtaining the first response information that meets expectations.

[0071] Step S204: inputting the target prompt word into the first model to obtain first response information.

[0072] Here, the first model may specifically be a large language model (also referred to as a large model), or it may also be other natural language processing models with content reasoning capabilities, and the present disclosure does not impose any specific restrictions on this.

[0073] Step S205: output first response information corresponding to the first intention feature.

[0074] For example, the intelligent digital human may be specifically used to output the first response information corresponding to the first intention feature. Alternatively, the intelligent digital human with an adjusted image may be specifically used to output the first response information corresponding to the first intention feature. For specific examples, please refer to the above description, which will not be repeated here.

[0075] Here, it should be noted that some of the above steps can be executed simultaneously, or the execution order can be swapped. For example, step S202 and steps S203 to S205 can be executed simultaneously, or steps S203 to S205 can be executed first, and then step S202, etc. The present disclosure does not limit this.

[0076] Step S206: Obtain first reply information for the first response information.

[0077] Step S207: at least input the first reply information into the first model to obtain second response information for the first reply information.

[0078] Step S208: output the second response information to perform intelligent question and answer.

[0079] For example, the second response information may be output by using an intelligent digital human being. Alternatively, the second response information may be output by using an intelligent digital human being whose image has been adjusted.

[0080] Furthermore, in one example, the second response information can be specifically outputted by voice through the intelligent digital human. For example, after obtaining the second response information, the second response information can be first converted into response voice data, and then the intelligent digital human can be used for voice playback. Furthermore, in order to further improve the user experience and the display effect, the mouth movements of the intelligent digital human can also be rendered based on the response voice data and displayed synchronously with the voice broadcast.

[0081] It should be noted that the second response information can also be displayed through text content. For example, a text display box is set in at least part of the area other than the intelligent digital human in the display page. At this time, the text content of the second response information can be displayed in the text display box.

[0082] That is to say, in one example, in the process of adjusting the image characteristics of the intelligent digital human according to the target trigger instruction indicated by the first intention feature, intelligent question and answer can also be performed. For example, an intelligent question and answer instruction can be generated in response to the first intention feature, and according to the intelligent question and answer instruction, a target prompt word is generated based on the first intention feature and a preset prompt word template, and a large language model service is called to use the target prompt word to obtain the first response information. Furthermore, the first response information can be converted into audio data using a text-to-speech service, and then the intelligent digital human can be used for voice broadcasting.

[0083] Furthermore, in another example, before using the intelligent digital human for voice broadcasting, the mouth movements of the intelligent digital human can be rendered in real time based on the text data of the first response information, so that the mouth movements can match the text content and then be displayed synchronously with the voice broadcast.

[0084] Furthermore, in one example, the target object can also respond to the content of the intelligent digital human's voice broadcast, and then generate second response information for the response content based on the target object's response content (that is, the first response information), and then output the second response information, thereby realizing intelligent question and answer.

[0085] For example, in one example, after being awakened, the intelligent digital human can output initial response information. For example, as shown in FIG3(a), the target object triggers the image adjustment function of the intelligent digital human, or after logging into the application (or platform, etc.) for adjusting the intelligent digital human, the intelligent digital human outputs response information such as "self-introduction" and "guided content" to the target object, thereby guiding the target object to input control operations (such as entering text, voice, and other control operations in a text box).

[0086] It should be noted that the disclosed solution can adapt to a variety of control operations (such as text, voice or video, etc.), such as text input operations in silent environments, or more intelligent voice interaction operations, etc., thereby meeting the needs of different users and improving the user experience.

[0087] Furthermore, in one example, the disclosed solution also provides other interactive functions during the dialogue between the target object and the intelligent digital human. For example, as shown in FIG3(b), a function bar button (e.g., a "+" button) is set to expand the function bar. In addition to displaying the real-time dialogue function, the function bar also includes functions such as uploading pictures, sharing functions, and one-key adjustment. In this way, "communication and interaction" with the intelligent digital human can be effectively achieved, so that the intelligent digital human can quickly and accurately understand user needs, and then provide feedback more timely and realistically, so as to further enhance the user experience.

[0088] Furthermore, in one example, in order to further enhance the user's sense of control, a control button for intelligent question and answer can also be set. For example, as shown in FIG3(c), in response to the target object's operation on the conversation start and stop button, the current conversation with the intelligent digital person can be started or ended.

[0089] Furthermore, in one example, as shown in FIG3(d), the disclosed solution can also display the content of the conversation in real time in the form of subtitles when the target object is conversing with the intelligent digital human; in addition, as shown in FIG3(e), the disclosed solution can also view the chat conversation record with the intelligent digital human through the function of "expanding the input box", thereby further improving the user experience.

[0090] In this way, the disclosed solution uses the method of intelligent question and answer to adjust the intelligent digital human, thus achieving the "communication and interaction" between the target object and the intelligent digital human, thereby further enriching the user experience and at the same time further improving the user experience.

[0091] Figure 4 3 is a schematic flow chart of an interactive method according to an embodiment of the present application. The method can be optionally applied to electronic devices, such as personal computers, servers, server clusters and other electronic devices. It can be understood that the above Figure 1 to Figure 3(e) The relevant contents of the method shown can also be applied to this example, and the relevant contents will not be described in detail in this example.

[0092] Further, the method includes at least part of the following contents. Figure 4 As shown, including:

[0093] Step S401: In response to a first control operation, obtaining a first intention feature of the first control operation.

[0094] Here, the first intention feature is at least used to instruct the intelligent digital human to adjust the image feature. For the relevant content of this part, please refer to the above example, and no further details will be given here.

[0095] Step S402: Based on the target trigger instruction indicated by the first intention feature, display at least two first product objects recommended by the first intention feature.

[0096] Step S403: responding to a second control operation, where the second control operation is used to select a target commodity object from at least two first commodity objects.

[0097] Step S404: using the target commodity object, adjusting the image characteristics of the intelligent digital human to display the intelligent digital human with the adjusted image characteristics.

[0098] Step S405: output first response information corresponding to the first intention feature.

[0099] It should be noted that after obtaining the first intention feature of the first control operation, the corresponding target trigger instruction can be executed according to the intention content indicated by the first intention feature. For example, if the intention content indicated by the first intention feature is used to indicate the recommendation of at least two first commodity objects (such as recommending a full set of clothing), a target trigger instruction for indicating the recommended commodity objects can be generated. At this time, according to the target trigger instruction, the at least two first commodity objects indicated for recommendation can be displayed for the target object to select; further, in response to the second control operation of the target object (that is, the selection operation), the target commodity object is determined, and then the image characteristics of the intelligent digital human are adjusted using the target commodity object, and the adjusted intelligent digital human is displayed.

[0100] For example, taking the first intention feature being used to indicate recommended clothing, first, as shown in FIG5(a), according to the recommendation instruction indicated by the first intention feature, multiple recommended clothing are displayed on the display interface, such as a display page containing multiple recommended clothing (for example, including tops and bottoms) pops up in the right sidebar of the display interface; secondly, after the target object selects clothing such as tops of style 1 and bottoms of style 1 from the displayed clothing, the target object changes clothes to obtain the smart digital human after changing clothes as shown in FIG5(b); finally, the smart digital human after changing clothes can also be used to output the first response information.

[0101] Here, for the relevant instructions on the intelligent digital human outputting the first response information, please refer to the above example and will not be repeated here.

[0102] Here, it should be noted that, in this example, after executing the target trigger instruction, a prompt message indicating that the recommendation is ready can be displayed, as shown in FIG5(c), where a "clothing button" is displayed. In this way, by clicking the clothing button, multiple recommended clothing items can be displayed.

[0103] Furthermore, in one example, as shown in FIG5(a), the disclosed solution can also set buttons such as clothing collection function, search function, sliding function, etc. on the display page according to actual needs, so as to meet the different needs of users.

[0104] In this way, the disclosed solution can recommend commodity objects that meet the needs of the target object according to the intention characteristics, and then adjust the image characteristics of the intelligent digital human according to the target commodity object selected by the target object, so as to intuitively display the effect of the target commodity object on the intelligent digital human, enrich the interactivity, and at the same time, ensure that the target object can have a comprehensive understanding of the commodity object, thus greatly enriching the user experience and greatly improving the user experience.

[0105] It should be noted that, in one example, the first intention feature can also directly instruct the intelligent digital human to change designated clothing. At this time, a change instruction can be directly generated, and based on the change instruction, the clothing to be changed can be determined, and then the clothing can be used to adjust the image characteristics of the intelligent digital human, and the adjusted intelligent digital human can be displayed. This process can achieve the adjustment of image characteristics without recommendation.

[0106] Alternatively, in another example, the first intention feature may also instruct the intelligent digital human to adjust body movements. In this case, a body adjustment instruction may be generated based on the first intention feature, and the body movement to be displayed may be determined based on the body adjustment instruction to display the adjusted intelligent digital human.

[0107] It should be noted that the above is only a specific exemplary description of the first intention feature. In actual applications, there may be other intention features, and the present disclosure does not limit this.

[0108] Furthermore, in a specific example, after the target object selects the target product object from the displayed multiple product objects, other product objects associated with the target product object may be further displayed, for example, specifically including:

[0109] In response to the recognition operation on the target product object, other second product objects associated with the description information of the target product object are displayed.

[0110] For example, in one example, the target object clicks the identification button corresponding to the target product object on the display page to display other product objects (i.e., the second product object) associated with the description information of the target product object; for example, continuing to take Figure 5(a) as an example, when using the top of style 1 to adjust the clothing of the intelligent digital human and displaying the adjusted intelligent digital human, as shown in Figure 5(d), the target object can also click the identification button corresponding to the top of style 1. At this time, other styles of tops associated with the description information of the top of style 1 can be displayed in the style display area, thereby realizing the recommendation of similar product objects, thereby further improving the user experience.

[0111] In this way, the disclosed solution utilizes the recognition function for the target commodity object to obtain more information about the commodity object, thereby increasing the user's selection range for the commodity object, thereby helping the user to quickly find a satisfactory commodity object, thereby further improving the user experience.

[0112] Furthermore, in a specific example, after the target object selects the target product object from the displayed multiple product objects, the product feature information for the target product object is displayed, for example, it may specifically include:

[0113] In response to a product comparison operation on the target product object, at least two product feature information corresponding to the target product object are displayed.

[0114] Here, the commodity characteristic information includes at least one of the following: price, sales volume, etc. Further, different commodity characteristic information comes from different recommendation sites (here, site may specifically refer to a network site). For example, for the same commodity object, the commodity price of the same commodity object on different recommendation sites may be different. In this case, the disclosed solution can be used to intuitively display the commodity characteristic information of the same commodity object on different recommendation sites, thereby further improving the user experience.

[0115] For example, as shown in FIG5(d), after the target object clicks the product comparison button for the top of style 1 (not shown), multiple product feature information of the top of style 1 on multiple recommendation sites can be displayed, for example, Figure 6 As shown, the price (such as price 1) and sales volume (such as sales volume 1) of the top of style 1 on website 1 are displayed, and the price (such as price 2) and sales volume (such as sales volume 2) of the top of style 1 on website 2 are displayed; in this way, the product feature information of the same product object on different recommendation sites is compared and displayed, which facilitates users to make decisions quickly and accurately, thereby further improving the user experience.

[0116] In this way, the disclosed solution can utilize the comparison function of the product feature information of the product object to display the product feature information of the same product object under different recommendation sites to the target object, so that users can quickly find the product objects they need based on the differences. Moreover, by comparing the product feature information of the product objects, users can make more accurate decisions, thereby further improving the user experience.

[0117] The following is a further detailed description of the disclosed solution in conjunction with a specific example. In this example, as shown in FIG. 7( a ) and FIG. 7( b ), the implementation steps of the disclosed solution may specifically include:

[0118] Step S701: Obtain the control operation input by the target object, and input the acquired control operation into the large language model (corresponding to the second model described above) to understand the intention and obtain the intention feature of the target object (corresponding to the first intention feature described above).

[0119] Here, in one example, the control operation may be specifically an input operation, such as inputting a piece of text content, or the control operation may also be a voice operation, such as inputting a piece of control voice data through a microphone. At this time, a speech-to-text service may be called, and a request instruction for understanding the user's intention may be generated to request the large model to obtain the intention features of the target object; further, the control voice data representing the control operation may be converted into target text data, and the large language model service may be called to input the target text data into the large language model to obtain the intention features of the target object.

[0120] Step S702: Generate a corresponding trigger instruction according to the intention characteristics of the target object.

[0121] For example, in one example, if the intention feature of the target object is used to instruct an intelligent digital human (eg, a 3D intelligent digital human) to change designated clothing, a specific change instruction may be generated and the process proceeds to step S703.

[0122] Alternatively, in another example, if the intended feature of the target object is used to indicate the recommendation of at least two clothing items (eg, a full set of clothing items, etc.), a recommendation instruction is generated and the process proceeds to step S704.

[0123] Alternatively, in another example, if the intention feature of the target object is used to instruct the intelligent digital human to adjust the body movement, a body adjustment instruction is generated to trigger the body movement of the intelligent digital human, and the process proceeds to step S707.

[0124] It should be pointed out that in actual applications, different functions can be scheduled through central control scheduling, so as to achieve functions such as intelligent clothing recommendations, intelligent question and answer, intelligent digital human clothing changing, and intelligent digital human driving limbs, lips and other movements.

[0125] Step S703: Determine the target clothing to be replaced according to the replacement instruction indicated by the intention feature of the target object; and proceed to step S706.

[0126] Step S704: according to the recommendation instruction indicated by the intention feature of the target object, call the clothing recommendation service to display at least two recommended clothing items to realize intelligent clothing recommendation; and proceed to step S705.

[0127] Step S705: In response to the target object's selection operation on the displayed clothing, determine the target clothing to be replaced; and proceed to step S706.

[0128] Step S706: Using the target clothing, adjust the image features of the intelligent digital human to obtain the adjusted intelligent digital human, and display the adjusted intelligent digital human. Go to step S708.

[0129] For example, the target clothing is rendered onto the intelligent digital human to obtain the rendered intelligent digital human, and then the rendered intelligent digital human is displayed.

[0130] It should be noted that in this example, the intelligent digital human can also be displayed in 360 degrees. For example, while displaying the rendered intelligent digital human, the intelligent digital human can also automatically rotate 360 ​​degrees around the preset axis for a 360-degree display. This makes it easier to browse the effects of clothing changes in more dimensions, thereby effectively improving the user experience.

[0131] Alternatively, in one example, when displaying the rendered intelligent digital human, a 360-degree display instruction of the target object is obtained. At this time, based on the 360-degree display instruction, the intelligent digital human is triggered to automatically rotate 360 ​​degrees around a preset axis.

[0132] Step S707: According to the limb adjustment instructions indicated by the intention characteristics of the target object, the target action characteristics that the intelligent digital human needs to display are determined, and the process proceeds to step S708.

[0133] Step S708: Generate intelligent question-answering instructions based on the intention characteristics of the target object; and proceed to step S709.

[0134] Step S709: calling the large language model service to infer the intention features of the target object and obtain the response content for responding to the target object. Going to step S710.

[0135] Step S710: Using the text-to-speech service, the response content used to respond to the target object is converted into response voice data, and the intelligent digital human is used for voice broadcasting. At the same time, the lip movements of the intelligent digital human are rendered in real time based on the response voice data and displayed synchronously with the voice broadcast.

[0136] Step S711: according to the target action features to be displayed (such as body movements, lip movements), the actions displayed by the intelligent digital human are adjusted, and the adjusted intelligent digital human is displayed in real time.

[0137] In this way, the disclosed solution can adjust the clothing or actions of the intelligent digital human according to the different intentions of the user, and display the adjusted (such as changing clothes) intelligent digital human, while voice broadcast is used to reply to the user's response content. In this way, the disclosed solution presents different clothing matching effects to the user through multi-dimensional interaction between the user and the intelligent digital human, and uses the intelligent digital human as a carrier, thereby enhancing the user's immersive experience.

[0138] The disclosed solution provides an interactive device, such as Figure 8 As shown, including:

[0139] The processing unit 801 is used to obtain a first intention feature of the first control operation in response to the first control operation, wherein the first intention feature is at least used to instruct the intelligent digital human to adjust the image feature; based on the target trigger instruction indicated by the first intention feature, adjust the image feature of the intelligent digital human to obtain the adjusted intelligent digital human; and

[0140] The output unit 802 is used to display the adjusted intelligent digital human and output the first response information corresponding to the first intention feature.

[0141] In a specific example of the disclosed solution, the processing unit is further used for:

[0142] In the case of displaying the adjusted intelligent digital human, triggering the adjusted intelligent digital human to rotate around a preset axis for multi-dimensional display;

[0143] Alternatively, in the case of displaying the adjusted intelligent digital human, in response to the display operation, the adjusted intelligent digital human is triggered to rotate around a preset axis for multi-dimensional display.

[0144] In a specific example of the disclosed solution, the processing unit is further used for:

[0145] generating a target prompt word based on the first intention feature of the first control operation and a preset prompt word template;

[0146] The target prompt word is input into the first model to obtain the first response information.

[0147] In a specific example of the present disclosure,

[0148] The processing unit is further configured to obtain first reply information for the first response information; at least input the first reply information into the first model to obtain second response information for the first reply information; and

[0149] The output unit is further used to output the second response information for intelligent question and answering.

[0150] In a specific example of the present disclosure,

[0151] The processing unit is specifically configured to obtain, based on the target trigger instruction, at least two first commodity objects recommended as indicated by the first intention feature;

[0152] The output unit is specifically configured to display at least two first commodity objects recommended by the first intention feature;

[0153] The processing unit is further specifically used to respond to a second control operation, wherein the second control operation is used to select a target commodity object from at least two first commodity objects; and use the target commodity object to adjust the image characteristics of the intelligent digital human to obtain an intelligent digital human with adjusted image characteristics.

[0154] In a specific example of the present disclosure,

[0155] The processing unit is further configured to respond to an identification operation on the target commodity object;

[0156] The output unit is further configured to display other second commodity objects associated with the description information of the target commodity object.

[0157] In a specific example of the present disclosure,

[0158] The processing unit is further configured to respond to a product comparison operation for the target product object;

[0159] The output unit is further used to display at least two commodity feature information corresponding to the target commodity object, wherein different commodity feature information comes from different recommendation sites.

[0160] In a specific example of the disclosed solution, the processing unit is specifically used to:

[0161] In response to a first control operation, an operation characteristic of the first control operation is input into a second model to obtain a first intention characteristic of the first control operation.

[0162] In a specific example of the present disclosure,

[0163] The processing unit is specifically configured to convert the first control operation into target text data in response to the first control operation including the voice data;

[0164] The target text data is input into a second model to obtain a first intention feature of the first control operation.

[0165] For the description of the specific functions and examples of each unit of the device in the embodiment of the present disclosure, reference can be made to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0166] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0167] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0168] Fig. 9 A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0169] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0170] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0171] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as interactive methods. For example, in some embodiments, the interactive method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the interactive method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the interactive method in any other appropriate manner (e.g., by means of firmware).

[0172] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0173] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0174] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0175] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0176] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0177] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0178] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0179] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An interactive method, comprising: In response to a first control operation, obtaining a first intention feature of the first control operation, wherein the first intention feature is at least used to instruct the intelligent digital human to adjust an image feature; Based on the target trigger instruction indicated by the first intention feature, adjusting the image features of the intelligent digital human to display the adjusted intelligent digital human; and Output first response information corresponding to the first intention feature.

2. The method according to claim 1, wherein: In the case of displaying the adjusted intelligent digital human, triggering the adjusted intelligent digital human to rotate around a preset axis for multi-dimensional display; Alternatively, in the case of displaying the adjusted intelligent digital human, in response to the display operation, the adjusted intelligent digital human is triggered to rotate around a preset axis for multi-dimensional display.

3. The method according to claim 1, further comprising: generating a target prompt word based on the first intention feature of the first control operation and a preset prompt word template; The target prompt word is input into the first model to obtain the first response information.

4. The method according to claim 3, further comprising: Obtaining first reply information for the first response information; at least inputting the first reply information into the first model to obtain second response information to the first reply information; as well as The second response information is output to perform intelligent question and answer.

5. The method according to any one of claims 1 to 4, wherein: The target triggering instruction indicated by the first intention feature is used to adjust the image feature of the intelligent digital human to display the adjusted intelligent digital human, including: Based on the target trigger instruction, display at least two first commodity objects recommended by the first intention feature; In response to a second control operation, the second control operation is used to select a target commodity object from at least two first commodity objects; The target commodity object is used to adjust the image characteristics of the intelligent digital human, so as to display the intelligent digital human with the adjusted image characteristics.

6. The method according to claim 5, further comprising: In response to the recognition operation on the target product object, other second product objects associated with the description information of the target product object are displayed.

7. The method according to claim 5, further comprising: In response to a product comparison operation for the target product object, at least two product feature information corresponding to the target product object are displayed, wherein different product feature information comes from different recommendation sites.

8. The method according to any one of claims 1 to 4, wherein: The acquiring, in response to the first control operation, a first intention feature of the first control operation includes: In response to a first control operation, an operation characteristic of the first control operation is input into a second model to obtain a first intention characteristic of the first control operation.

9. The method according to claim 8, wherein: In response to the first control operation, inputting the operation characteristic of the first control operation into the second model to obtain the first intention characteristic of the first control operation includes: In response to a first control operation including voice data, converting the first control operation into target text data; The target text data is input into a second model to obtain a first intention feature of the first control operation.

10. An interactive device, comprising: A processing unit is used to obtain a first intention feature of the first control operation in response to the first control operation, wherein the first intention feature is at least used to instruct the intelligent digital human to adjust the image feature; based on the target trigger instruction indicated by the first intention feature, adjust the image feature of the intelligent digital human to obtain an adjusted intelligent digital human; and The output unit is used to display the adjusted intelligent digital human and output first response information corresponding to the first intention feature.

11. The interactive device according to claim 10, wherein: The processing unit is further used for: In the case of displaying the adjusted intelligent digital human, triggering the adjusted intelligent digital human to rotate around a preset axis for multi-dimensional display; Alternatively, in the case of displaying the adjusted intelligent digital human, in response to the display operation, the adjusted intelligent digital human is triggered to rotate around a preset axis for multi-dimensional display.

12. The interactive device according to claim 10, wherein: The processing unit is further used for: generating a target prompt word based on the first intention feature of the first control operation and a preset prompt word template; The target prompt word is input into the first model to obtain the first response information.

13. The interactive device according to claim 12, wherein: The processing unit is further configured to obtain first reply information for the first response information; at least input the first reply information into the first model to obtain second response information for the first reply information; and The output unit is further used to output the second response information for intelligent question and answering.

14. The interactive device according to any one of claims 10 to 13, wherein: The processing unit is specifically configured to obtain, based on the target trigger instruction, at least two first commodity objects recommended as indicated by the first intention feature; The output unit is specifically configured to display at least two first commodity objects recommended by the first intention feature; The processing unit is further specifically used to respond to a second control operation, wherein the second control operation is used to select a target commodity object from at least two first commodity objects; and use the target commodity object to adjust the image characteristics of the intelligent digital human to obtain an intelligent digital human with adjusted image characteristics.

15. The interactive device according to claim 14, wherein: The processing unit is further configured to respond to an identification operation on the target commodity object; The output unit is further configured to display other second commodity objects associated with the description information of the target commodity object.

16. The interactive device according to claim 14, wherein: The processing unit is further configured to respond to a product comparison operation for the target product object; The output unit is further used to display at least two commodity feature information corresponding to the target commodity object, wherein different commodity feature information comes from different recommendation sites.

17. The interactive device according to any one of claims 10 to 13, wherein: The processing unit is specifically used for: In response to a first control operation, an operation characteristic of the first control operation is input into a second model to obtain a first intention characteristic of the first control operation.

18. The interactive device according to claim 17, wherein: The processing unit is specifically configured to convert the first control operation into target text data in response to the first control operation including the voice data; The target text data is input into a second model to obtain a first intention feature of the first control operation.

19. An electronic device comprising: at least one processor; as well as 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 9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

21. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images