Data processing method, device and equipment, computer readable storage medium and product

Abstract

The invention provides a data processing method, device and equipment, a computer readable storage medium and a product, and relates to the field of artificial intelligence, in particular to the field of computer vision. The specific implementation scheme is as follows: displaying a session interface associated with a preset virtual object, wherein the virtual object is a virtual image capable of calling a preset network model for data processing; displaying a plurality of preset data processing controls in the session interface; in response to a trigger operation of a user for any data processing control, determining a text instruction associated with the data processing control, and obtaining material content determined by the user; and sending the text instruction and the material content to a session interface, so that the virtual object performs data processing on the text instruction and the material content based on a preset network model after obtaining the text instruction and the material content. Therefore, the user can interact with the virtual object more conveniently, the display content of the session interface is enriched, and the data processing efficiency can be improved.

Description

Technical Field

[0001] The present disclosure relates to computer vision in artificial intelligence, and more particularly to a data processing method, apparatus, device, computer-readable storage medium, and product. Background Art

[0002] In the related art, many application software provide users with virtual objects with artificial intelligence data processing capabilities. Users can issue data processing instructions to virtual objects through interactive operations with virtual objects, so that virtual objects can use artificial intelligence capabilities to perform data processing operations.

[0003] Currently, interaction with virtual objects is generally achieved through a graphical user interface. Summary of the invention

[0004] The present disclosure provides a data processing method, apparatus, device, computer-readable storage medium and product for interacting with a virtual object through a language user interface to achieve data processing.

[0005] According to a first aspect of the present disclosure, there is provided a data processing method, comprising:

[0006] Displaying a conversation interface associated with a preset virtual object, wherein the virtual object is a virtual image capable of invoking a preset network model for data processing;

[0007] Displaying a plurality of preset data processing controls in the conversation interface;

[0008] In response to a trigger operation of a user on any data processing control, determining a text instruction associated with the data processing control, and acquiring material content determined by the user;

[0009] The text instruction and the material content are sent to the conversation interface, so that after the virtual object obtains the text instruction and the material content, it performs data processing on the text instruction and the material content based on a preset network model.

[0010] According to a second aspect of the present disclosure, there is provided a data processing method, comprising:

[0011] Acquire a data processing request sent by a terminal device, wherein the data processing request includes a text instruction and material content, and the text instruction and the material content are determined based on the data processing method described in the first aspect;

[0012] Calling a preset network model to perform data processing on the text instructions and material content to obtain a processing result;

[0013] The processing result is sent to the conversation interface in a conversational manner.

[0014] According to a third aspect of the present disclosure, there is provided a data processing device, comprising:

[0015] A conversation module, used to display a conversation interface associated with a preset virtual object, wherein the virtual object is a virtual image capable of invoking a preset network model for data processing;

[0016] A display module, used to display a plurality of preset data processing controls in the conversation interface;

[0017] A determination module, configured to determine, in response to a trigger operation of a user on any data processing control, a text instruction associated with the data processing control, and obtain material content determined by the user;

[0018] The sending module is used to send the text instruction and the material content to the conversation interface, so that after the virtual object obtains the text instruction and the material content, it performs data processing on the text instruction and the material content based on a preset network model.

[0019] According to a fourth aspect of the present disclosure, there is provided a data processing device, comprising:

[0020] A transmission module, used to obtain a data processing request sent by a terminal device, wherein the data processing request includes a text instruction and material content, and the text instruction and the material content are determined based on the data processing device according to the third aspect;

[0021] A calling module is used to call a preset network model to perform data processing on the text instructions and material content to obtain a processing result;

[0022] The interactive module is used to send the processing result to the conversation interface in the form of a conversation.

[0023] According to a fifth aspect of the present disclosure, there is provided an electronic device, including:

[0024] at least one processor; and

[0025] a memory communicatively connected to the at least one processor; wherein,

[0026] 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 described in the first aspect or the second aspect.

[0027] According to a sixth 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 the method described in the first aspect or the second aspect.

[0028] According to the seventh aspect of the present disclosure, a computer program product is provided, comprising: a computer program, wherein the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the electronic device executes the method described in the first aspect or the second aspect.

[0029] The technology disclosed in the present invention solves the technical problem that the operation is complicated and the data processing efficiency is low due to the interaction between the graphical user interface and the virtual object to perform data processing operations.

[0030] 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

[0031] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0032] Figure 1 A flowchart of a data processing method provided by an embodiment of the present disclosure;

[0033] Figure 2 A schematic diagram of interface interaction provided by an embodiment of the present disclosure;

[0034] Figure 3 A flowchart of a data processing method provided by another embodiment of the present disclosure;

[0035] Figure 4 A schematic diagram of a display interface provided in an embodiment of the present disclosure;

[0036] Figure 5 A flowchart of a data processing method provided by another embodiment of the present disclosure;

[0037] Figure 6 A flowchart of a data processing method provided by another embodiment of the present disclosure;

[0038] Figure 7 A schematic diagram of the structure of a data processing device provided in an embodiment of the present disclosure;

[0039] Figure 8 A schematic diagram of the structure of a data processing device provided in an embodiment of the present disclosure;

[0040] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0041] 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 and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0042] The present disclosure provides a data processing method, device, equipment, computer-readable storage medium and product, which are applied to the field of computer vision in the field of artificial intelligence to achieve more flexible interaction with virtual objects and realize data processing effects based on a preset network model.

[0043] In the related art, many application software provide users with virtual objects with artificial intelligence data processing capabilities. Users can issue data processing instructions to virtual objects through interactive operations with virtual objects, so that virtual objects can use artificial intelligence capabilities to perform data processing operations.

[0044] Currently, the interaction with virtual objects is generally achieved through a graphical user interface. However, the above method is often complicated to operate, and the graphical user interface is limited by the display space and is difficult to present complex information or options, which may not meet the actual needs of users.

[0045] In the process of solving the above technical problems, the inventors discovered through research that in order to facilitate users to more flexibly call virtual objects for data processing operations, the graphical user interface can be converted into a language user interface.

[0046] The mapping relationship between the data processing control and the text instruction can be preset. In response to the user's triggering operation on any data processing control, the text instruction associated with the data processing control is determined, and the material content determined by the user is obtained. The text instruction and the material content are sent to the conversation interface in a conversational manner.

[0047] It should be noted that the head model in this embodiment is not a head model for a specific user and cannot reflect the personal information of a specific user. It should be noted that the two-dimensional face image in this embodiment comes from a public data set.

[0048] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure 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.

[0049] In order to enable readers to more deeply understand the implementation principle of the present disclosure, the following Figure 1-Figure 9 The embodiments of the present disclosure are further refined.

[0050] Figure 1 A flow chart of a data processing method provided by an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the method includes:

[0051] Step 101: display a conversation interface associated with a preset virtual object, where the virtual object is a virtual image that can call a preset network model to perform data processing.

[0052] The execution subject of this embodiment is a data processing device. The data processing device can be coupled to a preset client in the terminal device. The client can be an application client for cloud storage and data processing of user-related files.

[0053] In this embodiment, in order to facilitate users to perform data processing operations more quickly and flexibly, virtual objects can be pre-set in the client. The virtual object can be a virtual image that can call a preset network model to perform data processing. The user can determine the current material content to be processed and the current data processing operation through interaction with the virtual object, so the virtual object can call the preset network model to perform corresponding data processing operations on the material content determined by the user.

[0054] Optionally, the user can enter a conversation interface associated with the virtual object and implement interactive operations with the virtual object in the conversation interface. The user can interact with the virtual object by voice, text, or by triggering a preset control, and the present disclosure does not limit this.

[0055] Step 102: Display a plurality of preset data processing controls in the conversation interface.

[0056] In this embodiment, all data processing functions associated with the virtual object may be predetermined, and data processing controls associated with each data processing function may be created.

[0057] Among them, the virtual object can realize data processing operations on audio and video material content, and the data processing operations include but are not limited to video courseware function, video to text function, audio meeting minutes function, audio to text function, etc.

[0058] In addition, the virtual object can perform data processing operations on data processing types. For example, for students, they need to process courseware, course videos, teaching videos, etc. to generate PPT, documents and other content. For working people, they need to process meeting minutes and video content generated during work to generate text-type meeting minutes, PPT and other content.

[0059] Optionally, after entering the conversation interface, in order to facilitate the user's understanding of the functions currently achievable by the virtual object, a plurality of preset data processing controls may be displayed in the conversation interface.

[0060] Step 103: In response to a trigger operation of a user on any data processing control, a text instruction associated with the data processing control is determined, and material content determined by the user is acquired.

[0061] In this embodiment, the user can call any data processing function to perform data processing operations.

[0062] In order to facilitate the interaction between the user and the virtual object and enable the user to more intuitively understand the current interaction status and data processing status, a text instruction associated with each data processing control can be set.

[0063] Therefore, in response to a user's triggering operation on any data processing control, the text instruction associated with the data processing control can be determined according to a preset mapping relationship between the data processing control and the text instruction.

[0064] In addition, in response to a trigger operation of a user on any data processing control, the material content determined by the user for the data processing function associated with the data processing control may also be obtained.

[0065] For example, a user can generate a PPT based on a video of a conference record. In response to the user's data processing control associated with the video-to-text function, the text instruction associated with the data processing control and the video of the conference record are sent in the conversation interface in a conversational manner, so that the virtual object can call the corresponding network model to perform data processing operations to generate a PPT corresponding to the conference record.

[0066] Step 104: Send the text instruction and the material content to the conversation interface, so that after the virtual object obtains the text instruction and the material content, it performs data processing on the text instruction and the material content based on a preset network model.

[0067] In this implementation, after the text instructions and material contents associated with the data processing controls are respectively determined, the text instructions and the material contents may be sent to the conversation interface in a conversational manner.

[0068] Therefore, the virtual object can obtain the text instruction and the material content in the conversation interface. Therefore, the text instruction and the material content can be processed based on the preset network model.

[0069] The data processing method provided in this embodiment displays multiple data processing controls in the conversation interface associated with the virtual object, so that the user can more quickly and intuitively understand the functions that can be realized by the virtual object. In addition, by responding to the user's trigger operation on any data processing control, the text instruction associated with the data processing control is determined, and the material content determined by the user is obtained. The text instruction and the material content are sent to the conversation interface, so that the interaction with the virtual object can be realized more conveniently in the form of a conversation, and the data processing operation can be realized. Therefore, the user can more flexibly call the virtual object to perform data processing operations, thereby improving the user experience.

[0070] Further, based on any of the above embodiments, after step 104, the method further includes:

[0071] The processing result generated after the virtual object calls the network model to perform data processing on the text instruction and the material content is obtained.

[0072] The processing result is displayed in a conversational manner in a display area associated with the virtual object in the conversation interface.

[0073] In this embodiment, the virtual object can obtain the text instruction and the material content in the conversation interface, and thus the network model can be called to perform data processing on the text instruction and the material content.

[0074] In addition, in order to facilitate users to view and call processing results more intuitively, after the network model performs data processing to generate processing results, the processing results sent by the virtual object can also be obtained. In the display area associated with the virtual object in the conversation interface, the processing results are displayed in a conversational manner.

[0075] Figure 2 A schematic diagram of the interface interaction provided by the embodiment of the present disclosure, such as Figure 2 As shown, multiple preset data processing controls 22 can be displayed in the conversation interface 21. In response to the user's triggering operation on any data processing control 22, the text instruction 23 associated with the data processing control 22 is determined, and the material content determined by the user is obtained. The text instruction 23 and the material content 24 are sent to the conversation interface 21. The conversion from the graphical user interface to the language user interface is realized.

[0076] Furthermore, after acquiring the text instruction and the material content, the virtual object performs data processing on the text instruction and the material content based on the preset network model to obtain the processing result 25. In the display area associated with the virtual object in the conversation interface 21, the processing result 25 is displayed in a conversational manner.

[0077] The data processing method provided in this embodiment obtains the processing result generated by the virtual object calling the network model to process the text instruction and the material content. In the display area associated with the virtual object in the conversation interface, the processing result is displayed in a conversational manner, so that the user can more intuitively view the processing result in the conversation interface. The display content in the conversation interface is enriched, and the user experience in the data processing process is improved.

[0078] Figure 3 A flowchart of a data processing method provided by another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 3 As shown, step 103 includes:

[0079] Step 301: In response to the user's triggering operation on any data processing control, a preset material determination interface is displayed.

[0080] Step 302: Display all the materials to be selected in the preset storage path in the material determination interface.

[0081] Step 303: In response to the selection operation triggered by the user, the candidate material currently selected by the user is determined as the material content.

[0082] In this embodiment, after multiple data processing controls are displayed in the conversation interface, the user can trigger any data processing control according to actual needs. In response to the trigger operation, a preset material determination interface can be displayed, so that the user can determine the material content in the material determination interface.

[0083] Optionally, all the materials to be selected in the preset storage path can be displayed in the material determination interface, wherein the preset storage path includes a local storage path and a cloud storage path.

[0084] The user can select from all candidate materials according to actual needs. In response to the selection operation triggered by the user, the candidate material currently selected by the user is determined as the material content.

[0085] Figure 4 A schematic diagram of a display interface provided by an embodiment of the present disclosure, such as Figure 4As shown, after entering the material determination interface 41 based on the user's triggering operation on the data processing control, all the candidate resources 42 in the local storage path of the terminal device can be displayed by default in the material determination interface 41. In addition, the material determination interface 41 also includes a preset type switching control 43, and the user can view the candidate materials in different storage paths by triggering the type switching control 43.

[0086] The data processing method provided in this embodiment displays a preset material determination interface in response to a user's triggering operation on any data processing control, and displays all the materials to be selected in the preset storage path in the material determination interface. Thus, the user can more conveniently select material content in the material determination interface according to actual needs.

[0087] Further, based on any of the above embodiments, step 302 includes:

[0088] All the selected materials corresponding to the local storage path are displayed in the material determination interface, and a preset path switching control is displayed in the material determination interface.

[0089] In response to the user's triggering operation on the path switching control, all the materials to be selected in the cloud storage path are switched and displayed in the material determination interface.

[0090] In this embodiment, in response to the user triggering an operation on any data processing control, after entering the material determination interface, all the candidate materials corresponding to the local storage path can be displayed in the material determination interface by default for the user to select.

[0091] In order to enable the user to more flexibly implement the material content selection operation, a preset path switching control may also be displayed in the material determination interface.

[0092] The user can switch to display all the selected materials in different storage paths by triggering the path switching control. Therefore, in response to the user's triggering operation on the path switching control, all the selected materials in the cloud storage path are switched to display in the material determination interface.

[0093] The path switching control may include a local sub-control and a cloud sub-control. The user may implement the path switching operation by triggering the local sub-control or the cloud sub-control. Alternatively, in response to the user's triggering operation, a switching list may be displayed, in which the triggering controls associated with the local storage path and the cloud storage path are displayed. The path switching is implemented based on the user's selection operation. The present disclosure does not limit this.

[0094] The data processing method provided in this embodiment displays a preset path switching control in the material determination interface, so that the user can flexibly switch to selected material content in different storage paths for viewing, thereby making the material content selected by the user more in line with the user's personalized needs.

[0095] Further, based on any of the above embodiments, step 302 includes:

[0096] A plurality of material contents whose material types are video type and / or audio type are determined from all the material contents stored in the preset storage path, and the plurality of material contents are determined as all the materials to be selected.

[0097] Display all the materials to be selected.

[0098] In this embodiment, the virtual object may be a virtual image that only performs data processing on audio and video materials.

[0099] Therefore, in order to facilitate the user to select the material content more quickly and accurately, multiple material contents of video type and / or audio type can be determined from all the material contents stored in the preset storage path, and the multiple material contents are determined as all the materials to be selected. All the materials to be selected are displayed.

[0100] The data processing method provided in this embodiment determines that multiple material contents of video type and / or audio type are displayed from all material contents stored in a preset storage path, so that users can browse the audio and video type material contents more intuitively and quickly select the material contents.

[0101] Further, based on any of the above embodiments, step 103 includes:

[0102] A preset mapping relationship list is obtained, wherein the mapping relationship list includes mapping relationships associated with identification information of multiple data processing controls and preset text instructions.

[0103] The target identification information of the data processing control triggered by the user is determined, and the preset text instruction matching the target identification information in the mapping relationship list is determined as the text instruction associated with the data processing control.

[0104] In this embodiment, in order to quickly determine the text instruction based on the user's triggering operation on the data processing control, a mapping relationship list can be pre-constructed, wherein the mapping relationship list includes mapping relationships associated with identification information of multiple data processing controls and preset text instructions.

[0105] Therefore, in response to the triggering operation on the data processing control, the target identification information of the data processing control triggered by the user can be determined, and the preset text instruction matching the target identification information in the mapping relationship list can be determined as the text instruction associated with the data processing control.

[0106] The data processing method provided in this embodiment pre-sets a mapping relationship list, so that when a user triggers a data processing instruction, the associated text instruction can be determined based on the mapping relationship list, and then the text instruction can be sent to the virtual object in a conversational manner. The virtual object performs a data processing operation based on the text instruction. Thus, the user can implement a conversation operation with the virtual object through a simple trigger operation.

[0107] Figure 5 A flowchart of a data processing method provided by another embodiment of the present disclosure is shown in FIG. Figure 5 As shown, the method includes:

[0108] Step 501: Acquire a data processing request sent by a terminal device, wherein the data processing request includes a text instruction and material content, and the text instruction and the material content are determined based on the data processing method described in any of the above embodiments.

[0109] Step 502: Call a preset network model to perform data processing on the text instructions and material content to obtain a processing result.

[0110] Step 503: Send the processing result to the conversation interface in a conversational manner.

[0111] The execution subject of this embodiment is a data processing device. The data processing device can be coupled to a server associated with a virtual object, and can be connected to a terminal device for communication. Therefore, after obtaining the text instructions and material content sent by the terminal device, the network model can be called to perform data processing operations.

[0112] In this embodiment, the user can trigger the data processing control in the conversation interface associated with the virtual object in the terminal device. Based on the trigger operation, the text instruction corresponding to the data processing control can be sent in the conversation interface. The user can also determine the material content based on the trigger operation, and send the text instruction and the material content to the conversation interface.

[0113] Accordingly, the virtual object can obtain the data processing request sent by the terminal device, which includes text instructions and material content, and call the preset network model to perform data processing on the text instructions and material content to obtain the processing result.

[0114] Furthermore, in order to facilitate the user to view and call the processing results, the processing results can also be sent to the conversation interface in the form of a conversation.

[0115] The data processing method provided in this embodiment processes the text instruction and the material content through a preset network model after obtaining the data processing request sent by the terminal device to obtain the processing result. The processing result is sent to the conversation interface in the form of a conversation, so that the virtual object can interact with the user in the form of a conversation. This makes it easier for the user to call the virtual object for data processing.

[0116] Figure 6 A flowchart of a data processing method provided by another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 6 As shown, step 502 includes:

[0117] Step 601: Determine the data processing type associated with the data processing request.

[0118] Step 602: Use a target network model that matches the data processing type to perform data processing on the text instructions and material content to obtain a processing result.

[0119] In this embodiment, in order to improve the data processing accuracy for the material content, a plurality of different network models may be preset, and different network models are used to perform data processing on data processing requests of different data processing types.

[0120] The data processing types include, but are not limited to, processing types for meeting records and work videos, processing types for course videos and courseware videos, and processing types for life-related videos, such as food tutorial videos and handicraft videos.

[0121] Therefore, the data processing type associated with the data processing request can be determined, and the target network model matching the data processing type is used to perform data processing on the text instruction and the material content to obtain a processing result.

[0122] The data processing method provided in this embodiment pre-trains different network models for different data processing types, so that based on the data processing type associated with the data processing request, the target network model matching the data processing type can be used to process text instructions and material content to obtain processing results, thereby improving processing accuracy.

[0123] Further, based on any of the above embodiments, step 601 includes:

[0124] A content recognition operation is performed on the material content to determine a content type associated with the material content.

[0125] The data processing type is determined based on the content type and a preset first type mapping relationship, wherein the first type mapping relationship includes mapping relationships between multiple content types and data processing types.

[0126] In this embodiment, after obtaining the material content determined by the user, a content recognition operation can be performed on the material content to determine the content type associated with the material content. The content type includes but is not limited to the conference record type, courseware type, etc. Any content recognition algorithm can be used to implement the content recognition operation on the material content, and the present disclosure does not limit this.

[0127] In addition, a first type mapping relationship between multiple content types and data processing types can be preset. For the conference record type, its associated data processing type can be a conference record processing type generated based on the conference record, a PPT generation type, etc. For the courseware type, its associated data processing type can be a type such as a courseware text summary based on a courseware video, etc.

[0128] Therefore, after identifying the content type associated with the material content, the data processing type may be determined based on the content type and a preset type mapping relationship.

[0129] The data processing method provided in this embodiment can determine the data processing type based on the content type and a preset type mapping relationship by performing content recognition operations on the material content, and then can use a target network model that matches the data processing type to perform data processing on text instructions and material content to obtain processing results, thereby improving processing accuracy.

[0130] Further, based on any of the above embodiments, the data processing request is initiated by the user in the conversation interface associated with the virtual object by triggering a preset data processing control, and the conversation interface is displayed after the user performs a trigger operation on the trigger control associated with the preset recommended content. Step 601 includes:

[0131] Determine a recommended content type associated with the recommended content, wherein the recommended content types associated with recommended content recommended to different types of users are different.

[0132] The data processing type is determined based on the recommended content type and a preset second type mapping relationship, wherein the second type mapping relationship includes a plurality of mapping relationships between recommended content types and data processing types.

[0133] In this embodiment, in order to facilitate the user's calling operation on the virtual object, recommended content matching the user group can also be generated in advance for different user groups. The recommended content can be video media content, graphic media content, audio media content, etc., which is not limited by the present disclosure. The user group includes but is not limited to the student group, the working group, etc.

[0134] Furthermore, after the recommended content is pushed to the user, an associated anchor point may be included in the recommended content. The user may enter the conversation interface with the virtual object by triggering the associated anchor point, and trigger the data processing control in the conversation interface.

[0135] Therefore, since the content types associated with the recommended content recommended to different types of users are different, the content type associated with the recommended content can be determined.

[0136] In addition, a second type of mapping relationship between multiple content types and data processing types can be preset. Among them, for the recommended content type pushed to the student group, the associated data processing type can be a courseware processing type. For the recommended content type pushed to the working group, the associated data processing type can be a meeting record processing type, a PPT generation type, etc.

[0137] Therefore, after determining the content type associated with the recommended content, the data processing type may be determined based on the content type and a preset type mapping relationship.

[0138] The data processing method provided in this embodiment can determine the data processing type based on the content type and a preset type mapping relationship by determining the content type associated with the recommended content, and then can use a target network model that matches the data processing type to perform data processing on text instructions and material content to obtain processing results, thereby improving processing accuracy.

[0139] Figure 7 A schematic diagram of the structure of a data processing device provided in an embodiment of the present disclosure, such as Figure 7As shown, the device includes: a conversation module 71, a display module 72, a determination module 73 and a sending module 74. The conversation module 71 is used to display a conversation interface associated with a preset virtual object, and the virtual object is a virtual image that can call a preset network model to perform data processing. The display module 72 is used to display a plurality of preset data processing controls in the conversation interface. The determination module 73 is used to determine the text instruction associated with the data processing control in response to a user's trigger operation on any data processing control, and to obtain the material content determined by the user. The sending module 74 is used to send the text instruction and the material content to the conversation interface, so that the virtual object performs data processing on the text instruction and the material content based on the preset network model after obtaining the text instruction and the material content.

[0140] Further, based on any of the above embodiments, the device further includes: an acquisition module, used to acquire a processing result generated after the virtual object calls the network model to perform data processing on the text instruction and the material content. A display module, used to display the processing result in a conversational manner in a display area associated with the virtual object in the conversation interface.

[0141] Further, based on any of the above embodiments, the determination module includes: a display unit, configured to display a preset material determination interface in response to a trigger operation of the user on any data processing control; a processing unit, configured to display all the materials to be selected in the preset storage path in the material determination interface; and a selection unit, configured to determine the material to be selected currently selected by the user as the material content in response to a selection operation triggered by the user.

[0142] Further, based on any of the above embodiments, the preset storage path includes a local storage path and a cloud storage path.

[0143] Further, based on any of the above embodiments, the processing unit includes: a display subunit, configured to display all the selected materials corresponding to the local storage path in the material determination interface, and to display a preset path switching control in the material determination interface. A switching subunit, configured to switch and display all the selected materials in the cloud storage path in the material determination interface in response to the user's triggering operation on the path switching control.

[0144] Further, based on any of the above embodiments, the processing unit includes: a determination subunit, configured to determine a plurality of material contents whose material types are video types and / or audio types from all the material contents stored in the preset storage path, and determine the plurality of material contents as all the materials to be selected. A display subunit, configured to display all the materials to be selected.

[0145] Further, based on any of the above embodiments, the determination module includes: an acquisition unit, used to acquire a preset mapping relationship list, wherein the mapping relationship list includes mapping relationships between identification information of multiple data processing controls and preset text instructions. A determination unit, used to determine the target identification information of the data processing control triggered by the user, and determine the preset text instruction in the mapping relationship list that matches the target identification information as the text instruction associated with the data processing control.

[0146] Figure 8 A schematic diagram of the structure of a data processing device provided in an embodiment of the present disclosure, such as Figure 8 As shown, the device includes: a transmission module 81, a calling module 82 and an interaction module 83. The transmission module 81 is used to obtain a data processing request sent by a terminal device, wherein the data processing request includes a text instruction and material content, and the text instruction and the material content are determined based on the data processing device described in any of the above embodiments. The calling module 82 is used to call a preset network model to perform data processing on the text instruction and the material content to obtain a processing result. The interaction module 83 is used to send the processing result to the session interface in a conversational manner.

[0147] Further, based on any of the above embodiments, the calling module includes: a type determination unit, configured to determine a data processing type associated with the data processing request; and a data processing unit, configured to perform data processing on the text instruction and the material content using a target network model matching the data processing type to obtain a processing result.

[0148] Further, based on any of the above embodiments, the type determination unit includes: an identification subunit, configured to perform a content identification operation on the material content to determine the content type associated with the material content; a mapping subunit, configured to determine the data processing type based on the content type and a preset first type mapping relationship, wherein the first type mapping relationship includes a mapping relationship between multiple content types and data processing types.

[0149] Further, based on any of the above embodiments, the data processing request is initiated by the user in the conversation interface associated with the virtual object by triggering a preset data processing control, and the conversation interface is displayed after the user performs a trigger operation on the preset trigger control associated with the recommended content. The determination of the data processing type associated with the data processing request includes: an identification subunit, which is used to determine the content type associated with the recommended content, wherein the content types associated with the recommended content recommended to different types of users are different. A mapping subunit, which is used to determine the data processing type based on the recommended content type and a preset second type mapping relationship, wherein the second type mapping relationship includes a plurality of mapping relationships between recommended content types and data processing types.

[0150] 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.

[0151] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, including:

[0152] at least one processor; and

[0153] a memory communicatively connected to the at least one processor; wherein,

[0154] 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 so that the at least one processor can execute the method described in any one of the above embodiments.

[0155] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the method described in any one of the above embodiments.

[0156] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0157] Fig. 9A schematic diagram of an electronic device provided for an embodiment of the present disclosure. The electronic device 900 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, 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 claimed herein.

[0158] like Fig. 9 As shown, the device 9000 includes a computing unit 9001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 9002 or a computer program loaded from a storage unit 9008 into a random access memory (RAM) 9003. In the RAM 9003, various programs and data required for the operation of the device 9000 can also be stored. The computing unit 9001, the ROM 9002, and the RAM 9003 are connected to each other via a bus 9004. An input / output (I / O) interface 9005 is also connected to the bus 9004.

[0159] A number of components in the device 9000 are connected to the I / O interface 9005, including: an input unit 9006, such as a keyboard, a mouse, etc.; an output unit 9007, such as various types of displays, speakers, etc.; a storage unit 9008, such as a disk, an optical disk, etc.; and a communication unit 9009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 9009 allows the device 9000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0160] The computing unit 9001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 9001 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 9001 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 9008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 9000 via ROM 9002 and / or communication unit 9009. When the computer program is loaded into RAM 9003 and executed by the computing unit 9001, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 9001 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0161] 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), complex 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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 between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0167] 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.

[0168] 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 spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A data processing method, comprising: Displaying a conversation interface associated with a preset virtual object, wherein the virtual object is a virtual image capable of invoking a preset network model for data processing; Displaying a plurality of preset data processing controls in the conversation interface; In response to a trigger operation of a user on any data processing control, determining a text instruction associated with the data processing control, and acquiring material content determined by the user; The text instruction and the material content are sent to the conversation interface, so that after the virtual object obtains the text instruction and the material content, it performs data processing on the text instruction and the material content based on a preset network model.

2. The method according to claim 1, after sending the text instruction and the material content to the conversation interface, further comprising: Obtaining a processing result generated after the virtual object calls the network model to perform data processing on the text instruction and the material content; The processing result is displayed in a conversational manner in a display area associated with the virtual object in the conversation interface.

3. The method according to claim 1, wherein: The obtaining of the material content determined by the user includes: In response to a trigger operation of the user on any data processing control, displaying a preset material determination interface; Displaying all the materials to be selected in the preset storage path in the material determination interface; In response to the selection operation triggered by the user, the to-be-selected material currently selected by the user is determined as the material content.

4. The method according to claim 3, wherein: The preset storage path includes a local storage path and a cloud storage path.

5. The method according to claim 4, wherein: The display of all the materials to be selected in the preset storage path in the material determination interface includes: Displaying all the to-be-selected materials corresponding to the local storage path in the material determination interface, and displaying a preset path switching control in the material determination interface; In response to the user's triggering operation on the path switching control, all the materials to be selected in the cloud storage path are switched and displayed in the material determination interface.

6. The method according to claim 4, wherein: The display of all the materials to be selected in the preset storage path in the material determination interface includes: Determining a plurality of material contents whose material types are video type and / or audio type from all the material contents stored in the preset storage path, and determining the plurality of material contents as all the materials to be selected; Display all the materials to be selected.

7. The method according to any one of claims 1 to 6, wherein: The determining of the text instruction associated with the data processing control includes: Obtaining a preset mapping relationship list, wherein the mapping relationship list includes mapping relationships associated with identification information of multiple data processing controls and preset text instructions; The target identification information of the data processing control triggered by the user is determined, and the preset text instruction matching the target identification information in the mapping relationship list is determined as the text instruction associated with the data processing control.

8. A data processing method, comprising: Obtaining a data processing request sent by a terminal device, wherein the data processing request includes a text instruction and material content, and the text instruction and the material content are determined based on the data processing method according to any one of claims 1 to 7; Calling a preset network model to perform data processing on the text instructions and material content to obtain a processing result; The processing result is sent to the conversation interface in a conversational manner.

9. The method according to claim 8, wherein: The calling of a preset network model to perform data processing on the text instruction and the material content to obtain a processing result includes: determining a data processing type associated with the data processing request; The target network model matching the data processing type is used to perform data processing on the text instructions and material content to obtain processing results.

10. The method according to claim 9, wherein: The determining the data processing type associated with the data processing request includes: Performing a content recognition operation on the material content to determine the content type associated with the material content; The data processing type is determined based on the content type and a preset first type mapping relationship, wherein the first type mapping relationship includes mapping relationships between multiple content types and data processing types.

11. The method according to claim 9, wherein: The data processing request is initiated by the user in the conversation interface associated with the virtual object by triggering a preset data processing control, and the conversation interface is displayed after the user performs a trigger operation on a preset trigger control associated with the recommended content; The determining the data processing type associated with the data processing request includes: Determining a content type associated with the recommended content, wherein the content types associated with the recommended content recommended to different types of users are different; The data processing type is determined based on the recommended content type and a preset second type mapping relationship, wherein the second type mapping relationship includes a plurality of mapping relationships between recommended content types and data processing types.

12. A data processing device, comprising: A conversation module, used to display a conversation interface associated with a preset virtual object, wherein the virtual object is a virtual image capable of invoking a preset network model for data processing; A display module, used to display a plurality of preset data processing controls in the conversation interface; A determination module, configured to determine, in response to a trigger operation of a user on any data processing control, a text instruction associated with the data processing control, and obtain material content determined by the user; The sending module is used to send the text instruction and the material content to the conversation interface, so that after the virtual object obtains the text instruction and the material content, it performs data processing on the text instruction and the material content based on a preset network model.

13. The device according to claim 12, further comprising: An acquisition module, used for acquiring a processing result generated after the virtual object calls the network model to perform data processing on the text instruction and the material content; A display module is used to display the processing result in a conversational manner in a display area associated with the virtual object in the conversation interface.

14. The device according to claim 12, wherein: The determination module comprises: A display unit, configured to display a preset material determination interface in response to a trigger operation of the user on any data processing control; A processing unit, used for displaying all the materials to be selected in the preset storage path in the material determination interface; The selection unit is configured to determine the candidate material currently selected by the user as the material content in response to the selection operation triggered by the user.

15. The device according to claim 14, wherein: The preset storage path includes a local storage path and a cloud storage path.

16. The device according to claim 15, wherein: The processing unit comprises: A display subunit, used to display all the to-be-selected materials corresponding to the local storage path in the material determination interface, and to display a preset path switching control in the material determination interface; The switching subunit is used to switch and display all the selected materials in the cloud storage path in the material determination interface in response to the user's triggering operation on the path switching control.

17. The device according to claim 15, wherein: The processing unit comprises: In the determination subunit, it is used to determine a plurality of material contents of video type and / or audio type from all the material contents stored in the preset storage path, and determine the plurality of material contents as all the materials to be selected; The display subunit is used to display all the materials to be selected.

18. The device according to any one of claims 12 to 17, wherein: The determination module comprises: An acquiring unit, configured to acquire a preset mapping relationship list, wherein the mapping relationship list includes mapping relationships between identification information of a plurality of data processing controls and preset text instructions; A determination unit is used to determine the target identification information of the data processing control triggered by the user, and determine the preset text instruction matching the target identification information in the mapping relationship list as the text instruction associated with the data processing control.

19. A data processing device, comprising: A transmission module, used for acquiring a data processing request sent by a terminal device, wherein the data processing request includes a text instruction and material content, and the text instruction and the material content are determined based on the data processing device according to any one of claims 12 to 18; A calling module is used to call a preset network model to perform data processing on the text instructions and material content to obtain a processing result; The interactive module is used to send the processing result to the conversation interface in the form of a conversation.

20. The device according to claim 19, wherein The calling module includes: a type determination unit, configured to determine a data processing type associated with the data processing request; The data processing unit is used to perform data processing on the text instructions and material content using a target network model that matches the data processing type to obtain a processing result.

21. The device according to claim 20, wherein: The type determination unit comprises: An identification subunit, configured to perform a content identification operation on the material content to determine a content type associated with the material content; A mapping subunit is used to determine the data processing type based on the content type and a preset first type mapping relationship, wherein the first type mapping relationship includes mapping relationships between multiple content types and data processing types.

22. The device according to claim 20, wherein: The data processing request is initiated by the user in the conversation interface associated with the virtual object by triggering a preset data processing control, and the conversation interface is displayed after the user performs a trigger operation on a preset trigger control associated with the recommended content; The determining the data processing type associated with the data processing request includes: an identification subunit, configured to determine a content type associated with the recommended content, wherein the content types associated with the recommended content recommended to different types of users are different; A mapping subunit is used to determine the data processing type based on the recommended content type and a preset second type mapping relationship, wherein the second type mapping relationship includes a plurality of mapping relationships between recommended content types and data processing types.

23. 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 of any one of claims 1-7 or 8-11.

24. 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 1-7 or 8-11.

25. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7 or 8 to 11.

Images