Text processing interface display method and device and text processing method and device

Abstract

The invention relates to a text processing interface display method and device and a text processing method and device.The text processing interface display method and device comprise the steps that a first interface is displayed, and the first interface comprises a first display area and a voice assistant control used for calling a second interface; first quotation content and an input method keyboard are displayed in the first display area; in response to monitoring that the voice assistant control is touched, the second interface is displayed, the second interface comprises a second display area, and one or more text operation suggestion controls are displayed in the second display area. According to the method, the expression requirement of the user can be better met, the user is helped to express the intention more intelligently and conveniently, and the input efficiency is improved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence technology and computer technology, and in particular to a method and device for displaying a text processing interface and a method and device for text processing. Background Art

[0002] In the related technologies, input methods all rely on user input and lack a deep understanding and recognition of the user input content. For example, if an ambiguous or vague word is entered, the input method may not be able to provide accurate matching results, so it takes more time to correct and adjust, which reduces the user's input efficiency. In the current information age, people's information needs are becoming increasingly complex and diverse. How to better meet the user's expression needs, help users express their intentions more intelligently and conveniently, and improve input efficiency has become one of the important research directions. Summary of the invention

[0003] The present application provides a method and device for displaying a text processing interface and a method and device for processing text, so as to at least solve the problem of better meeting the expression needs of users, enabling users to express their intentions more intelligently and conveniently, and improving input efficiency. The technical solution of the present application is as follows:

[0004] According to a first aspect of an embodiment of the present application, a method for displaying a text processing interface is provided, comprising:

[0005] Displaying a first interface, wherein the first interface includes a first display area and a voice assistant control for calling a second interface, and the first quotation content and an input method keyboard are displayed in the first display area;

[0006] In response to detecting that the voice assistant control is touched, the second interface is displayed, wherein the second interface includes a second display area, and the second display area displays one or more text operation suggestion controls.

[0007] According to a second aspect of an embodiment of the present application, a text processing method is provided, comprising:

[0008] In response to receiving a request instruction sent by the application, obtaining application information, interface information and first quotation content of the application;

[0009] Determine and display multiple text operation suggestions based on application information, interface information, and first cited content;

[0010] Monitor whether the first citation content is updated and whether any text operation suggestion is triggered;

[0011] Based on at least one of the monitored second citation content and the target text operation suggestion, the language model is called to generate a text processing result, the second citation content is the updated first citation content, and the target text operation suggestion is the triggered text operation suggestion.

[0012] According to a third aspect of an embodiment of the present application, a display device for a text processing interface is provided, including:

[0013] A first display module, used to display a first interface, wherein the first interface includes a first display area and a voice assistant control for calling a second interface, and the first quotation content and an input method keyboard are displayed in the first display area;

[0014] The second display module is used to display the second interface in response to detecting that the voice assistant control is touched, wherein the second interface includes a second display area, and the second display area displays one or more text operation suggestion controls.

[0015] According to a fourth aspect of an embodiment of the present application, there is provided a text processing device, including:

[0016] An acquisition module, configured to acquire application information, interface information and first citation content of the application in response to receiving a request instruction sent by the application;

[0017] A determination module, used to determine and display multiple text operation suggestions based on application information, interface information and the first cited content;

[0018] A monitoring module, used to monitor whether the first citation content is updated and whether any text operation suggestion is triggered;

[0019] The text processing module is used to call the language model to generate a text processing result based on at least one of the monitored second citation content and the target text operation suggestion, where the second citation content is the updated first citation content and the target text operation suggestion is the triggered text operation suggestion.

[0020] According to the fifth aspect of the embodiments of the present application, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement a display method of a text processing interface as in the first aspect of the embodiments of the present application or a text processing method as in the second aspect of the embodiments.

[0021] According to the sixth aspect of the embodiments of the present application, a non-transitory computer-readable storage medium storing computer instructions is proposed, wherein the computer instructions are used to implement the display method of the text processing interface as described in the first aspect embodiment of the present application or the text processing method of the second aspect embodiment.

[0022] According to the seventh aspect of the embodiments of the present application, a computer program product is proposed, including a computer program, which, when executed by a processor, implements the display method of the text processing interface as described in the first aspect embodiment of the present application or the text processing method as described in the second aspect embodiment.

[0023] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0024] In an embodiment of the present application, multiple text operation suggestions are determined and displayed based on application information, interface information and the first cited content; relevant content can be intelligently recommended to better meet the user's expression needs, monitor whether the first cited content is updated and whether any text operation suggestion is triggered; based on the monitored second cited content and at least one of the target text operation suggestions, a language model is called to generate a text processing result, which can help users express their intentions more intelligently and conveniently and improve input efficiency.

[0025] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0027] Figure 1 is a schematic diagram of an exemplary implementation of a method for displaying a text processing interface shown in the present application;

[0028] FIG2( a) is a schematic diagram of a first interface shown in the present application;

[0029] FIG2( b ) is a schematic diagram of a second interface shown in the present application;

[0030] FIG2( c ) is a schematic diagram of a second interface shown in the present application;

[0031] FIG2( d ) is a schematic diagram of a second interface shown in the present application;

[0032] FIG2( e ) is a schematic diagram of a first interface shown in the present application;

[0033] FIG3( a) is a schematic diagram of a first interface shown in the present application;

[0034] FIG3( b ) is a schematic diagram of a second interface shown in the present application;

[0035] FIG3( c ) is a schematic diagram of a second interface shown in the present application;

[0036] FIG3( d ) is a schematic diagram of a second interface shown in the present application;

[0037] FIG3( e) is a schematic diagram of a first interface shown in the present application;

[0038] FIG4( a) is a schematic diagram of a first interface shown in the present application;

[0039] FIG4( b ) is a schematic diagram of a second interface shown in the present application;

[0040] FIG4( c ) is a schematic diagram of a second interface shown in the present application;

[0041] FIG4( d ) is a schematic diagram of a second interface shown in the present application;

[0042] FIG4( e) is a schematic diagram of a first interface shown in the present application;

[0043] Figure 5 is a schematic diagram of an exemplary implementation of a text processing method shown in the present application;

[0044] Figure 6 is a schematic diagram of an exemplary implementation of a text processing method shown in the present application;

[0045] Figure 7 is a schematic diagram of an exemplary implementation of a text processing method shown in the present application;

[0046] Figure 8 is a schematic diagram of an exemplary implementation of a text processing method shown in the present application;

[0047] Fig. 9 is a schematic diagram of a display device of a text processing interface shown in the present application;

[0048] Fig.10 is a schematic diagram of a text processing device shown in the present application;

[0049] Fig.11 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0050] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0052] Figure 1 is a schematic diagram of an exemplary implementation of a method for displaying a text processing interface shown in the present application, such as Figure 1 As shown, the display method of the text processing interface includes the following steps:

[0053] S101, displaying a first interface, wherein the first interface includes a first display area and a voice assistant control for calling a second interface, and a first quotation content and an input method keyboard are displayed in the first display area.

[0054] In some embodiments, the first display area displays the first citation content and the input method keyboard, the first citation content is the citation content currently being edited by the input method, optionally, the first citation content can be in the form of text, optionally, the first citation content can also be blank citation content that has not yet been edited.

[0055] In some embodiments, the first interface corresponding to the current input method is displayed as shown in Figure 2(a), wherein the first display area 201 is used to display the current input method keyboard 202 and the voice assistant control 203, and the first quotation content 204 of the first display area 201 is blank quotation content, that is, the current input method has not input any quotation content.

[0056] S102, in response to detecting that the voice assistant control is touched, displaying a second interface, wherein the second interface includes a second display area, and the second display area displays one or more text operation suggestion controls.

[0057] For example, if a click operation or a double-click operation on the voice assistant control is detected, it is determined that the voice assistant control is touched, and the second interface is displayed.

[0058] In some embodiments, if the voice assistant control 203 shown in Figure 2(a) is touched, a second interface is displayed as shown in Figure 2(b), and the second interface includes a second display area 205, wherein the second display area displays multiple text operation suggestion controls 206, and the second interface also includes an input method keyboard 207.

[0059] In some implementations, in response to monitoring a preset first operation on a text operation suggestion control, a text processing result corresponding to the text operation suggestion control is displayed in a second display area of ​​the second interface.

[0060] Optionally, in response to detecting that any text operation suggestion control is touched, such as detecting a click operation or a double-click operation on any text operation suggestion control, it is determined that a preset first operation for the text operation suggestion control is detected, and the text processing result corresponding to the text operation suggestion control is displayed in a second display area of ​​the second interface.

[0061] In some implementations, the second interface further includes: an input method keyboard, and the method further includes: in response to monitoring a preset second operation for the input method keyboard, further displaying a text processing result corresponding to the preset second operation in the second display area.

[0062] In some embodiments, as shown in FIG. 2(b), the second display area is also used to display the current input method keyboard. As shown in FIG. 2(c), in response to detecting that the current input method keyboard is triggered and the second quotation content is input, the second quotation content 208 is displayed in the second display area, and it is determined that a preset second operation on the second interface is monitored. As shown in FIG. 2(d), the text processing result 209 and the insert original text control 210 for returning to the first interface are displayed in the second display area.

[0063] In some embodiments, the second interface further includes: replacing the original text control and / or inserting the original text control, in response to monitoring the triggering operation of replacing the original text control, displaying the first interface and displaying the text processing result in the first display area, that is, replacing the first quotation content with the text processing result, and displaying the text processing result only in the first display area;

[0064] In response to monitoring a trigger operation of inserting the original text control, displaying the first interface, and displaying the first citation content and the text processing result in the first display area, that is, inserting the text processing result into the first citation content, and displaying the first citation content and the text processing result in the first display area;

[0065] In some embodiments, in response to the word count of the first citation content being greater than a preset first word count threshold, the first citation content is displayed in the second display area of ​​the second interface. Optionally, the first word count threshold may be 0, that is, if the first citation content is not blank content, the first citation content is displayed in the second display area of ​​the second interface. If the first citation content is blank content, the first citation content is not displayed in the second display area of ​​the second interface.

[0066] In some embodiments, before the replace original text control or insert original text control is detected to be triggered, if a sliding operation on the target text in the text processing result is detected, the target text is marked and displayed with a preset color, and when the second request control is detected to be triggered, the target text is used as the text processing result displayed in the first interface. For another example, the target text can be copied after a long press operation or a double-click operation is detected, and then the first interface is displayed after the return control is detected to be triggered, and the target text is pasted at the cursor position after a long press operation or a double-click operation is detected at the cursor position, that is, the target text is brought from the second interface to the first interface and displayed at the cursor position.

[0067] For example, it is detected that the insert original text control 210 in FIG. 2( d ) is triggered, and the first interface is displayed as shown in FIG. 2( e ), and the text processing result 211 is displayed in the first display area.

[0068] In some embodiments, the first interface corresponding to the current input method is displayed as shown in FIG3(a), wherein the first display area is used to display the current input method keyboard 301, the first interface also displays the voice assistant control 302, and the first quotation content 304 of the first display area 303 is a quotation content with text. If the voice assistant control 302 shown in FIG3(a) is touched, the second interface is displayed as shown in FIG3(b), the second interface includes a second display area 305, the second display area 305 includes the first quotation content 306, a plurality of text operation suggestion controls 307, and the second interface also includes an input method keyboard 308, as shown in FIG3(c), in response to detecting that the current input method keyboard is touched and the second quotation content is input, the second quotation content 309 is displayed in the second display area, and it is determined that the preset second operation on the second interface is monitored, as shown in FIG3(d), the text processing result 310 and the insert original text control 311 for returning to the first interface are displayed in the second display area. It is detected that the insert original text control 311 in FIG. 3( d ) is triggered, and the first interface is displayed as shown in FIG. 3( e ), where the first citation content and the text processing result 312 are displayed in the first display area.

[0069] As shown in FIG. 4 , in some embodiments, the first interface corresponding to the current input method is shown in FIG. 4 (a), wherein the first display area is used to display the current input method keyboard 401, the first interface also displays the voice assistant control 402, and the first quotation content 404 of the first display area 403 is a quotation content with text. If a sliding operation is detected on the target quotation content in the first quotation content shown in FIG. 4 (a), the target quotation content is marked and displayed with a preset color, and if the voice assistant control 402 shown in FIG. 4 (a) is touched, the second interface is displayed as shown in FIG. 4 (b), and the second interface includes a second display area 405 and an input method keyboard 406, wherein the second display area 405 includes a plurality of text operation suggestion controls 407, and the second display area 405 is also used to display the target quotation content 408. As shown in FIG4(c), in response to detecting that any text operation suggestion control 409 is touched, the text operation suggestion 410 corresponding to the text operation suggestion control is displayed in the second display area, and it is determined that the preset operation on the second interface is detected, as shown in FIG4(d), the text processing result 411 and the replace original text control 412 for returning to the first interface are displayed in the second display area. It is detected that the replace original text control in FIG4(d) is triggered, and the first interface is displayed as shown in FIG4(e), and the text processing result 413 is displayed in the first display area.

[0070] The embodiments of the present application can better meet the user's expression needs, help the user express his or her intentions more intelligently and conveniently, improve input efficiency, add text writing capabilities in high-frequency input scenarios, use the global advantages of the input method, and quickly connect with the scenarios of each application program itself, helping users to input faster and more intelligently and express better.

[0071] Figure 5 is a schematic diagram of an exemplary implementation of a text processing method shown in the present application, such as Figure 5 As shown, the text processing method comprises the following steps:

[0072] S501, in response to receiving a request instruction sent by an application, obtaining application information, interface information and first quotation content of the application.

[0073] The embodiments of the present application can be applied to multiple business scenarios. For example, it can be applied to users' prediction of possible text generation behaviors in six major scenarios, such as media copywriting, life sharing, document creation, content analysis, office documents, and travel planning.

[0074] In some embodiments, the executing entity of the embodiments of the present application may be a server. When the control of the application is triggered, the application sends a request instruction to the server. After the server receives the request instruction sent by the application, it obtains the application information, interface information and first quotation content of the application through the system interface.

[0075] In other implementations, the execution subject of the present application may also be other systems or electronic devices with computing and analysis functions, and the embodiments of the present application are not limited to this.

[0076] In some implementations, the application information includes a target application identifier, and the interface information includes a target interface identifier. Optionally, the first quoted content may be in the form of text and / or image.

[0077] The first citation content is the citation content being edited in the current input method dialog box. Optionally, the first citation content may be blank citation content, that is, the current input method has not input citation content.

[0078] S502, determining and displaying a plurality of text operation suggestions based on the application information, the interface information and the first cited content.

[0079] In some implementations, when the first citation content is blank citation content, one or more text operation suggestions are determined from preset text operation suggestions based on the application information and the interface information and displayed.

[0080] In some implementations, when the first citation content is citation content having text, multiple text operation suggestions are determined from preset text operation suggestions and displayed based on the application information, the interface information, and the first citation content.

[0081] For example, the text operation suggestions may be multiple ones of "please generate an inspiring motivational copy", "generate a commonly used comment template", "recommend some good novels", "write a holiday greeting message", and "write a travel plan for a certain place".

[0082] S503, monitoring whether the first cited content is updated and whether any text operation suggestion is triggered.

[0083] For example, it is possible to determine through the system interface whether the current first citation content is updated, and in response to monitoring that the first citation content is updated, obtain the updated first citation content as the second citation content.

[0084] In some implementations, the text operation suggestion is displayed as a control. If the control corresponding to the text operation suggestion is triggered, it is determined that the text operation suggestion is triggered, and the triggered text operation suggestion is obtained as the target text operation suggestion.

[0085] S504, based on the monitored second citation content and at least one of the target text operation suggestions, call the language model to generate a text processing result, the second citation content is the updated first citation content, and the target text operation suggestion is the triggered text operation suggestion.

[0086] The language model has multiple text processing modules, corresponding to the different text processing capabilities of the language model.

[0087] In some embodiments, semantic analysis is performed on at least one of the monitored second citation content and the target text operation suggestion to obtain the user intent, and the first text processing module of the language model is called to answer according to the user intent to generate a text processing result.

[0088] In some implementations, when the first citation content is a citation content with text, the monitored second citation content and at least one of the target text operation suggestions are spliced ​​with the first citation content to obtain the target context, and the language model is called based on the target context to perform text processing to generate a text processing result. Optionally, the text processing method can be one or more of text polishing processing, text summarization processing, and text expansion processing.

[0089] Optionally, the language model may be a preset generative pre-trained language model (Generative Pre-trained Transformer, GPT). In other implementations, the language model may also be other language models with text processing capabilities, which is not limited in the embodiments of the present application.

[0090] In an embodiment of the present application, multiple text operation suggestions are determined and displayed based on application information, interface information and the first cited content; relevant content can be intelligently recommended to better meet the user's expression needs, monitor whether the first cited content is updated and whether any text operation suggestion is triggered; based on the monitored second cited content and at least one of the target text operation suggestions, a language model is called to generate a text processing result, which can help users express their intentions more intelligently and conveniently and improve input efficiency.

[0091] Figure 6 is a schematic diagram of an exemplary implementation of a text processing method shown in the present application, such as Figure 6 As shown, the text processing method comprises the following steps:

[0092] S601, in response to receiving a request instruction sent by an application, obtaining application information, interface information and first quotation content of the application.

[0093] The application information includes a target application identifier, and the interface information includes a target interface identifier.

[0094] For the introduction of step S601, please refer to the relevant content in the above embodiment, which will not be repeated here.

[0095] S602, identifying the first quotation content and obtaining the number of quotation words.

[0096] In some implementations, when the first citation content includes text and an image, or when the first citation content includes text, character recognition is performed on the first citation content to obtain the number of citation characters.

[0097] In some implementations, when the first citation content includes an image, or the first citation content is blank, the first citation content is identified and the number of citation words is determined to be 0, that is, it is considered that there is no citation content.

[0098] S603, in response to the number of quoted words being less than a preset first word count threshold, determining a plurality of text operation suggestions according to the application information and the interface information and displaying them.

[0099] In some implementations, the first word count threshold is 0, that is, when the first quotation content includes an image, or the first quotation content is blank, multiple text operation suggestions are determined and displayed based on the application information and the interface information.

[0100] Optionally, obtain a first association relationship between the application identifier, the interface identifier, and the text operation suggestion, retrieve the first association relationship with the target application identifier as the first index and the target interface identifier as the second index, obtain multiple text operation suggestions corresponding to the target application identifier and the target interface identifier, and display the multiple text operation suggestions corresponding to the target application identifier and the target interface identifier in the form of controls.

[0101] Optionally, in some embodiments, the first association relationship is retrieved with the target application identifier as the first index and the target interface identifier as the second index, and no text operation suggestions corresponding to the target application identifier and the target interface identifier are retrieved, the preset first text operation suggestions are displayed as multiple text operation suggestions corresponding to the target application identifier and the target interface identifier.

[0102] S604, monitoring whether the first cited content is updated and whether any text operation suggestion is triggered.

[0103] For the introduction of step S604, please refer to the relevant content in the above embodiment, which will not be repeated here.

[0104] S605: Perform semantic analysis based on the monitored second cited content and at least one of the target text operation suggestions to obtain user intention.

[0105] In some implementations, only the second citation content is monitored, and semantic analysis is performed based on the second citation content to obtain the user intent.

[0106] In some implementations, only the target text operation suggestions are monitored, and semantic analysis is performed based on the target text operation suggestions to obtain the user intention.

[0107] In some implementations, the target text operation suggestion and the second cited content are monitored simultaneously, and semantic analysis is performed based on the target text operation suggestion and the second cited content to obtain the user intention.

[0108] S606: Call the first text processing module of the language model to answer according to the user's intention and generate a text processing result.

[0109] Optionally, the first text processing module has general text writing capabilities and can answer according to user intentions and generate text processing results.

[0110] In other implementations, the user intent can also be distributed to the vertical skills corresponding to the language model to generate text processing results. The vertical skills refer to the expertise and understanding ability in a specific field or topic.

[0111] In an embodiment of the present application, semantic analysis is performed based on the monitored second quoted content and at least one of the target text operation suggestions to obtain the user's intention, and the first text processing module of the language model is called to answer according to the user's intention to generate a text processing result, and the system input method and the dialogue capability of the language model are integrated. In high-frequency input scenarios, new artificial intelligence (AI) capabilities such as text writing capabilities are added, and the global advantages of the input method are utilized to quickly connect with the scenarios of each application program, helping users to input faster and smarter and express better.

[0112] Figure 7 is a schematic diagram of an exemplary implementation of a text processing method shown in the present application, such as Figure 7 As shown, the text processing method comprises the following steps:

[0113] S701, in response to receiving a request instruction sent by an application, obtaining application information, interface information and first quotation content of the application.

[0114] The application information includes a target application identifier, and the interface information includes a target interface identifier.

[0115] S702, identifying the first quotation content and obtaining the number of quotation words.

[0116] For the introduction of step S701 to step S702, reference may be made to the relevant contents in the above embodiment, which will not be repeated here.

[0117] S703, in response to the number of quoted words being greater than or equal to a first word count threshold, determining and displaying a plurality of text operation suggestions based on the application information, the interface information, and the number of quoted words.

[0118] In some embodiments, the first word count threshold is 0, that is, when the first citation content includes text and images, or when the first citation content includes text, multiple text operation suggestions are determined and displayed based on the application information, interface information, and the number of citation words.

[0119] In an embodiment of the present application, a second association relationship among the application identifier, the interface identifier, the quotation word count range, and the text operation suggestion is obtained, the target quotation word count range where the quotation word count is located is determined, the second association relationship is searched with the target application identifier as the third index, the target interface identifier as the fourth index, and the target quotation word count range as the fifth index, and multiple text operation suggestions corresponding to the target application identifier, the target interface identifier, and the target quotation word count range are obtained, and then the multiple text operation suggestions corresponding to the target application identifier, the target interface identifier, and the target quotation word count range are displayed in the form of controls.

[0120] Optionally, in some embodiments, the second association relationship is retrieved with the target application identifier as the third index, the target interface identifier as the fourth index, and the target quoted word range as the fifth index, and no text operation suggestions corresponding to the target application identifier, the target interface identifier, and the target quoted word range are retrieved, the preset second text operation suggestions are displayed as the text operation suggestions corresponding to the target application identifier, the target interface identifier, and the target quoted word range.

[0121] S704, monitoring whether the first cited content is updated and whether any text operation suggestion is triggered.

[0122] For the introduction of step S704, please refer to the relevant content in the above embodiment, which will not be repeated here.

[0123] S705: Concatenate the monitored second citation content and at least one of the target text operation suggestions with the first citation content to obtain a target context.

[0124] In some implementations, only the second citation content is monitored, and the second citation content is spliced ​​with the first citation content to obtain the target context.

[0125] In some implementations, only the target text operation suggestion is monitored, and the target text operation suggestion and the first cited content are spliced ​​to obtain the target context.

[0126] In some implementations, the target text operation suggestion and the second citation content are monitored simultaneously, and the target text operation suggestion, the second citation content, and the first citation content are spliced ​​to obtain the target context.

[0127] S706, calling a language model based on the target context to generate a text processing result.

[0128] Optionally, the second text processing module has general text expansion and text polishing capabilities. In response to the number of quoted words being less than a preset second word count threshold, the second text processing module of the language model is called to perform text expansion and text polishing on the target context to generate a text processing result.

[0129] Optionally, the third text processing module has general text summarization and text polishing capabilities, and in response to the number of quoted words being greater than or equal to a second word count threshold, calls the third text processing module of the language model to perform text summarization and text polishing on the target context to generate a text processing result.

[0130] In an embodiment of the present application, the monitored second citation content and at least one of the target text operation suggestions are spliced ​​with the first citation content to obtain the target context, and the language model is called based on the target context to generate a text processing result. The system input method is integrated with the text expansion, summarization, and polishing capabilities of the language model. The global advantages of the input method are utilized in high-frequency input scenarios to quickly connect with the scenarios of each application program itself, helping users to input faster and smarter and express better.

[0131] Figure 8 is a schematic diagram of an exemplary implementation of a text processing method shown in the present application, such as Figure 8 As shown, the text processing method comprises the following steps:

[0132] S801, in response to receiving a request instruction sent by an application, obtaining application information, interface information and first quotation content of the application.

[0133] S802, determining and displaying a plurality of text operation suggestions based on the application information, the interface information and the first cited content.

[0134] S803, monitoring whether the first cited content is updated and whether any text operation suggestion is triggered.

[0135] S804, based on the monitored second citation content and at least one of the target text operation suggestions, call the language model to generate a text processing result, the second citation content is the updated first citation content, and the target text operation suggestion is the triggered text operation suggestion.

[0136] For the introduction of steps S801 to S804, reference may be made to the relevant contents in the above embodiments, which will not be repeated here.

[0137] S805: Display the text processing result.

[0138] The text processing results are displayed in the form of controls.

[0139] S806 , in response to the text processing result being triggered, updating the text processing result to the first citation content to generate target citation content.

[0140] In some implementations, in response to a control containing a text processing result being triggered, the text processing result is updated to the first citation content to generate a target citation content.

[0141] In some implementations, in response to a text processing result being triggered, one or more selected characters in the text processing result are obtained and updated to the first citation content to generate the target citation content.

[0142] S807, continue to determine multiple text operation suggestions for display based on the application information, interface information and target citation content, and perform subsequent steps of obtaining text processing results to update the target citation content.

[0143] In the embodiment of the present application, the citation content and the text operation suggestion can also be associated according to the multi-round effect. In the multi-round session, the server splices the multi-round citation content and the text operation suggestion as the target context assembly request language model, and continuously updates the target citation content.

[0144] The first citation content in step S801 can be understood as the first citation content of the first round, and the target citation content in step S806 can be understood as the first citation content of the second round. That is to say, the target citation content in step S806 is used as the first citation content of the second round, and steps S802 to S806 are continued to be executed to continuously update the target citation content.

[0145] In an embodiment of the present application, in response to the text processing result being triggered, the text processing result is updated to the first citation content to generate the target citation content, which can further meet the user's expression needs, continue to determine multiple text operation suggestions for display based on the application information, interface information and target citation content, and execute subsequent steps to obtain the text processing results to update the target citation content. The accuracy of text input can be further improved based on multiple rounds of text processing, helping users to express their intentions more intelligently and conveniently, thereby improving input efficiency.

[0146] Fig. 9 is a schematic diagram of a display device of a text processing interface shown in the present application, such as Fig. 9 As shown, the display device 900 of the text processing interface includes:

[0147] A first display module 910 is used to display a first interface, wherein the first interface includes a first display area and a voice assistant control for calling a second interface, and the first quotation content and an input method keyboard are displayed in the first display area;

[0148] The second display module 920 is used to display a second interface in response to detecting that the voice assistant control is touched, wherein the second interface includes a second display area, and the second display area displays one or more text operation suggestion controls.

[0149] In some embodiments, the second display module 920 is further used for:

[0150] In response to monitoring a preset first operation on the text operation suggestion control, a text processing result corresponding to the text operation suggestion control is displayed in a second display area of ​​the second interface.

[0151] In some implementations, the second interface further includes: an input method keyboard, a second display module 920, and is further used for:

[0152] In response to monitoring a preset second operation on the input method keyboard, a text processing result corresponding to the preset second operation is also displayed in the second display area.

[0153] In some embodiments, the second display module 920 is further used for:

[0154] One or more of the first citation content, the text operation suggestion corresponding to the touched text operation suggestion control, and the second citation content corresponding to the preset second operation are displayed in the second display area.

[0155] In some implementations, the second interface further includes: replacing the original text control, inserting the original text control, and the second display module 920 is further used to:

[0156] In response to monitoring the triggering operation of replacing the original text control, displaying the first interface and displaying the text processing result in the first display area; or,

[0157] In response to monitoring a triggering operation of inserting the original text control, a first interface is displayed, and the first citation content and the text processing result are displayed in a first display area.

[0158] In some embodiments, the second display module 920 is further used for:

[0159] In response to the word count of the first citation content being greater than a preset first word count threshold, the first citation content is displayed in a second display area of ​​the second interface.

[0160] The embodiments of the present application can better meet the user's expression needs, help the user express his or her intentions more intelligently and conveniently, improve input efficiency, add text writing capabilities in high-frequency input scenarios, use the global advantages of the input method, and quickly connect with the scenarios of each application program itself, helping users to input faster and more intelligently and express better.

[0161] Fig.10 is a schematic diagram of a text processing device shown in the present application, such as Fig.10 As shown, the text processing device 1000 includes:

[0162] The acquisition module 1010 is used to acquire application information, interface information and first quotation content of the application in response to receiving a request instruction sent by the application;

[0163] A determination module 1020, configured to determine and display a plurality of text operation suggestions based on the application information, the interface information and the first quoted content;

[0164] A monitoring module 1030 is used to monitor whether the first cited content is updated and whether any text operation suggestion is triggered;

[0165] The text processing module 1040 is used to call the language model to generate a text processing result based on at least one of the monitored second citation content and the target text operation suggestion, where the second citation content is the updated first citation content and the target text operation suggestion is the triggered text operation suggestion.

[0166] In some implementations, the determination module 1020 is further configured to:

[0167] Identify the first citation content and obtain the number of citation words;

[0168] In response to the number of words in the quotation being less than a preset first word count threshold, determining and displaying a plurality of text operation suggestions based on the application information and the interface information;

[0169] In response to the number of quoted words being greater than or equal to a first word count threshold, a plurality of text operation suggestions are determined and displayed based on the application information, the interface information, and the number of quoted words.

[0170] In some implementations, the application information includes a target application identifier, and the interface information includes a target interface identifier.

[0171] In some implementations, the determination module 1020 is further configured to:

[0172] Obtaining a first association relationship between the application identifier, the interface identifier, and the text operation suggestion;

[0173] The first association relationship is searched using the target application identifier as a first index and the target interface identifier as a second index to obtain a plurality of text operation suggestions corresponding to the target application identifier and the target interface identifier;

[0174] Multiple text operation suggestions corresponding to the target application identifier and the target interface identifier are displayed.

[0175] In some implementations, the text processing module 1040 is further configured to:

[0176] Performing semantic analysis based on the monitored second citation content and at least one of the target text operation suggestions to obtain the user intention;

[0177] The first text processing module of the language model is called according to the user's intention to answer and generate a text processing result.

[0178] In some implementations, the determination module 1020 is further configured to:

[0179] Obtaining a second association relationship between the application identifier, the interface identifier, the quoted word count range, and the text operation suggestion;

[0180] Determine the target quotation word number range within which the quotation word number falls;

[0181] The second association relationship is searched using the target application identifier as a third index, the target interface identifier as a fourth index, and the target quoted word count range as a fifth index to obtain a plurality of text operation suggestions corresponding to the target application identifier, the target interface identifier, and the target quoted word count range;

[0182] Multiple text operation suggestions corresponding to the target application identifier, target interface identifier, and target quoted word count range are displayed.

[0183] In some implementations, the text processing module 1040 is further configured to:

[0184] The monitored second citation content and at least one of the target text operation suggestions are spliced ​​with the first citation content to obtain the target context;

[0185] The language model is called based on the target context to generate text processing results.

[0186] In some implementations, the text processing module 1040 is further configured to:

[0187] In response to the number of words in the quotation being less than a preset second word count threshold, calling a second text processing module of the language model to perform text expansion and text polishing on the target context to generate a text processing result; or

[0188] In response to the number of words in the quotation being greater than or equal to the second word count threshold, calling a third text processing module of the language model to perform text summarization and text polishing on the target context to generate a text processing result;

[0189] The first word count threshold is smaller than the second word count threshold.

[0190] In some implementations, the text processing module 1040 is further configured to:

[0191] Display the text processing results;

[0192] In response to the text processing result being triggered, the text processing result is updated to the first citation content to generate the target citation content.

[0193] In some implementations, the text processing module 1040 is further configured to:

[0194] Continue to determine multiple text operation suggestions for display based on the application information, interface information, and target citation content, and perform subsequent steps of obtaining text processing results to update the target citation content.

[0195] In an embodiment of the present application, multiple text operation suggestions are determined and displayed based on application information, interface information and the first cited content; relevant content can be intelligently recommended to better meet the user's expression needs, monitor whether the first cited content is updated and whether any text operation suggestion is triggered; based on the monitored second cited content and at least one of the target text operation suggestions, a language model is called to generate a text processing result, which can help users express their intentions more intelligently and conveniently and improve input efficiency.

[0196] Fig.11 is a block diagram of an electronic device 1100 according to an exemplary embodiment.

[0197] like Fig.11 As shown, the electronic device 1100 includes:

[0198] The memory 1101 and the processor 1102, a bus 1103 connecting different components (including the memory 1101 and the processor 1102), the memory 1101 stores a computer program, and when the processor 1102 executes the program, the display method or text processing method of the text processing interface of the embodiment of the present application is implemented.

[0199] Bus 1103 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0200] The electronic device 1100 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by the electronic device 1100, including volatile and non-volatile media, removable and non-removable media.

[0201] The memory 1101 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1104 and / or cache memory 1105. The electronic device 1100 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 1106 may be used to read and write non-removable, non-volatile magnetic media ( Fig.11 not shown, usually called a "hard drive"). Although Fig.11 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to bus 1103 via one or more data medium interfaces. Memory 1101 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of each embodiment of the present application.

[0202] A program / utility 1108 having a set (at least one) of program modules 1107 may be stored, for example, in the memory 1101, such program modules 1107 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 1107 generally perform the functions and / or methods of the embodiments described herein.

[0203] The electronic device 1100 may also communicate with one or more external devices 1109 (e.g., keyboard, pointing device, display 1110, etc.), one or more devices that enable a user to interact with the electronic device 1100, and / or any device that enables the electronic device 1100 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 1111. Furthermore, the electronic device 1100 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 1112. Fig.11 As shown, the network adapter 1112 communicates with other modules of the electronic device 1100 via the bus 1103. It should be understood that although Fig.11 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0204] The processor 1102 executes the programs stored in the memory 1101 to perform various functional applications and data processing.

[0205] It should be noted that the implementation process and technical principles of the electronic device of this embodiment refer to the aforementioned explanation of the text processing method of the embodiment of the present application, and will not be repeated here.

[0206] In order to implement the above embodiment, the embodiment of the present application also proposes a non-transient computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to implement the display method of the text processing interface or the text processing method as shown in the above embodiment. Optionally, the non-transient computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0207] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0208] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0209] This application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, this application is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, risks can be minimized by limiting data collection and deleting data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of users.

[0210] In order to implement the above embodiments, the embodiments of the present application also propose a computer program product, including a computer program, which, when executed by a processor, implements the display method of the text processing interface or the text processing method as shown in the above embodiments.

[0211] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0212] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for displaying a text processing interface, characterized in that: include: Displaying a first interface, wherein the first interface includes a first display area and a voice assistant control for calling a second interface, and the first quotation content and an input method keyboard are displayed in the first display area; In response to detecting that the voice assistant control is touched, the second interface is displayed, wherein the second interface includes a second display area, and the second display area displays one or more text operation suggestion controls.

2. The method according to claim 1, characterized in that The method further comprises: In response to monitoring a preset first operation for the text operation suggestion control, a text processing result corresponding to the text operation suggestion control is displayed in the second display area of ​​the second interface.

3. The method according to claim 1, characterized in that The second interface further includes: the input method keyboard, and the method further includes: In response to monitoring a preset second operation on the input method keyboard, a text processing result corresponding to the preset second operation is also displayed in the second display area.

4. The method according to claim 2 or 3, characterized in that: The method further comprises: The text operation suggestion corresponding to the touched text operation suggestion control or the second quoted content corresponding to the preset second operation is displayed in the second display area.

5. The method according to claim 2 or 3, characterized in that: The second interface further includes: replacing the original text control and / or inserting the original text control, and the method further includes: In response to monitoring the triggering operation of the replace original text control, displaying the first interface and displaying the text processing result in the first display area; or, In response to monitoring a triggering operation on the insert original text control, the first interface is displayed, and the first citation content and the text processing result are displayed in the first display area.

6. The method according to claim 1, characterized in that The method further comprises: In response to the word count of the first citation content being greater than a preset first word count threshold, the first citation content is displayed in a second display area of ​​the second interface.

7. A text processing method, characterized in that: include: In response to receiving a request instruction sent by an application, obtaining application information, interface information and first quotation content of the application; Determine and display a plurality of text operation suggestions based on the application information, the interface information and the first quoted content; Monitoring whether the first citation content is updated and whether any of the text operation suggestions is triggered; Based on at least one of the monitored second citation content and the target text operation suggestion, the language model is called to generate a text processing result, wherein the second citation content is the updated first citation content, and the target text operation suggestion is the triggered text operation suggestion.

8. The method according to claim 7, characterized in that The determining and displaying a plurality of text operation suggestions according to the application information, the interface information and the first quoted content includes: Identify the first citation content and obtain the number of citation words; In response to the number of words in the quotation being less than a preset first word count threshold, determining and displaying the plurality of text operation suggestions according to the application information and the interface information; In response to the number of quoted words being greater than or equal to the first word count threshold, the plurality of text operation suggestions are determined and displayed based on the application information, the interface information, and the number of quoted words.

9. The method according to claim 8, characterized in that The application information includes a target application identifier, and the interface information includes a target interface identifier.

10. The method according to claim 9, characterized in that The determining and displaying the plurality of text operation suggestions according to the application information and the interface information includes: Obtaining a first association relationship between the application identifier, the interface identifier, and the text operation suggestion; The first association relationship is retrieved using the target application identifier as a first index and the target interface identifier as a second index to obtain the plurality of text operation suggestions corresponding to the target application identifier and the target interface identifier; The multiple text operation suggestions corresponding to the target application identifier and the target interface identifier are displayed.

11. The method according to claim 10, characterized in that The step of calling the language model to generate a text processing result based on at least one of the monitored second citation content and the target text operation suggestion includes: Performing semantic analysis based on the monitored second citation content and at least one of the target text operation suggestions to obtain the user intention; The first text processing module of the language model is called according to the user intention to answer and generate the text processing result.

12. The method according to claim 9, characterized in that The determining and displaying the plurality of text operation suggestions according to the application information, the interface information and the number of quoted words includes: Obtaining a second association relationship between the application identifier, the interface identifier, the quoted word count range, and the text operation suggestion; Determine the target quotation word number range within which the quotation word number falls; The second association relationship is searched using the target application identifier as a third index, the target interface identifier as a fourth index, and the target quoted word count range as a fifth index to obtain the plurality of text operation suggestions corresponding to the target application identifier, the target interface identifier, and the target quoted word count range; The multiple text operation suggestions corresponding to the target application identifier, the target interface identifier and the target quoted word count range are displayed.

13. The method according to claim 12, characterized in that The step of calling the language model to generate a text processing result based on at least one of the monitored second citation content and the target text operation suggestion includes: splicing the monitored second citation content and at least one of the target text operation suggestions with the first citation content to obtain a target context; The language model is called based on the target context to generate the text processing result.

14. The method according to claim 13, characterized in that The calling the target text processing module based on the target context to generate the text processing result includes: In response to the number of words in the quoted text being less than a preset second word count threshold, calling the second text processing module of the language model to perform text expansion and text polishing on the target context to generate the text processing result; or In response to the number of words in the quotation being greater than or equal to the second word count threshold, calling the third text processing module of the language model to perform text summarization and text polishing on the target context to generate the text processing result; The first word count threshold is smaller than the second word count threshold.

15. The method according to any one of claims 7 to 14, characterized in that: After generating the text processing result, the method further includes: Displaying the text processing result; In response to the text processing result being triggered, the text processing result is updated to the first citation content to generate target citation content.

16. The method according to claim 15, characterized in that Also includes: Continue to determine multiple text operation suggestions for display based on the application information, the interface information and the target citation content, and perform subsequent steps of obtaining text processing results to update the target citation content.

17. A display device for a text processing interface, characterized in that: include: A first display module, used to display a first interface, wherein the first interface includes a first display area and a voice assistant control for calling a second interface, and the first quotation content and an input method keyboard are displayed in the first display area; The second display module is used to display the second interface in response to detecting that the voice assistant control is touched, wherein the second interface includes a second display area, and the second display area displays one or more text operation suggestion controls.

18. A text processing device, characterized in that: include: An acquisition module, configured to acquire application information, interface information and first quotation content of the application in response to receiving a request instruction sent by the application; A determination module, configured to determine and display a plurality of text operation suggestions based on the application information, the interface information and the first cited content; A monitoring module, used to monitor whether the first citation content is updated and whether any of the text operation suggestions is triggered; A text processing module is used to call a language model to generate a text processing result based on at least one of the monitored second quotation content and the target text operation suggestion, wherein the second quotation content is the updated first quotation content and the target text operation suggestion is the triggered text operation suggestion.

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 of any one of claims 1-6 or any one of claims 7-16.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the steps of the method according to any one of claims 1-6 or the steps of the method according to any one of claims 7-16.

21. 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 6 or the steps of any one of claims 7 to 16.

Images