Information processing method, apparatus and electronic device

Abstract

The embodiment of the disclosure provides an information processing method, device and electronic equipment, the method comprises the following steps: in response to receiving a first instruction for text content, obtaining explanation information associated with the text content, wherein the explanation information is associated with pre-constructed dictionary content; according to the explanation information, determining target text content; displaying the target text content, which helps to improve communication efficiency.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer and artificial intelligence, and particularly, to an information processing method and device and electronic equipment. BACKGROUND

[0002] A user can browse text content or edit text content as an editor through an electronic device. When browsing text content, the user can refer to a dictionary to understand the interpretation of obscure or infrequently used words in the text content.

[0003] In some application scenarios, the text content edited by the user when editing the text content is also usually edited by the user again during the editing process. SUMMARY

[0004] Embodiments of the present disclosure provide an information processing method and device and electronic equipment.

[0005] In a first aspect, embodiments of the present disclosure provide an information processing method, which includes: in response to receiving a first instruction for text content, obtaining interpretation information associated with the text content, wherein the interpretation information is associated with pre-constructed dictionary content; determining target text content according to the interpretation information; and displaying the target text content.

[0006] In a second aspect, embodiments of the present disclosure provide an information processing method, which includes: displaying a first content interface according to a received display operation; receiving a first selection operation for target content, the first selection operation being used to select part of displayed content from content displayed in the first content interface as the target content; and displaying a second content interface according to the first selection operation, and displaying at least two entity words associated with the target content and the interpretation of the at least two entity words in the second content interface.

[0007] In a third aspect, embodiments of the present disclosure provide an information processing method, which includes: receiving an operation for text content; and displaying a second content interface and displaying interpretation information in the second content interface, wherein the interpretation information includes one or more of the following: interpretation text of the text content, entity words associated with the text content, and interpretation of at least part of the entity words.

[0008] In a fourth aspect, an information processing method is provided. The method includes: displaying a first content interface; receiving a second selection operation for a target content, the second selection operation being used to select the target content from content displayed in the first content interface; and displaying a third content interface based on the target content, the third content interface including: first explanation information of the target content; or the first explanation information of the target content and second explanation information of at least one entity word, the at least one entity word being contained in the target content.

[0009] In a fifth aspect, an information processing apparatus is provided. The apparatus includes: an acquisition unit configured to acquire explanation information associated with text content in response to receiving a first instruction for the text content, wherein the explanation information is associated with pre-constructed dictionary content; a determination unit configured to determine target text content according to the explanation information; and a first display unit configured to display the target text content.

[0010] In a sixth aspect, an information processing apparatus is provided. The apparatus includes: a second display unit configured to display a first content interface according to a received display operation; a first receiving unit configured to receive a first selection operation for a target content, the first selection operation being used to select partial display content from content displayed in the first content interface as the target content; and a third display unit configured to display a second content interface according to the first selection operation, the second content interface displaying at least two entity words associated with the target content and paraphrasing of the at least two entity words.

[0011] In a seventh aspect, an information processing apparatus is provided. The apparatus includes: a second receiving unit configured to receive an operation for text content; and a fourth display unit configured to display a second content interface, the second content interface displaying paraphrasing information, wherein the paraphrasing information includes one or more of the following: explanation text of the text content, entity words associated with the text content, and paraphrasing of at least part of the entity words.

[0012] In an eighth aspect, an information processing apparatus is provided. The apparatus includes: a fifth display unit configured to display a first content interface; a third receiving unit configured to receive a second selection operation for a target content, the second selection operation being used to select the target content from content displayed in the first content interface; and a sixth display unit configured to display a third content interface based on the target content, the third content interface including: first explanation information of the target content; or the first explanation information of the target content and second explanation information of at least one entity word, the at least one entity word being contained in the target content.

[0013] In a ninth aspect, an electronic device is provided, and includes a processor and a memory. The memory stores computer-executable instructions. The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to the first aspect, the second aspect, the third aspect, the fourth aspect, and the method according to the first aspect, the second aspect, the third aspect, and the fourth aspect.

[0014] In a tenth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the method according to the first aspect, the second aspect, the third aspect, the fourth aspect, and the method according to the first aspect, the second aspect, the third aspect, and the fourth aspect are implemented.

[0015] In an eleventh aspect, a computer program product is provided, and the computer program product includes a computer program. When a processor executes the computer program, the method according to the first aspect, the second aspect, the third aspect, the fourth aspect, and the method according to the first aspect, the second aspect, the third aspect, and the fourth aspect are implemented.

[0016] The information processing method, device, and electronic device provided in this embodiment achieve the following effects. In response to receiving a first instruction for text content, explanation information associated with the text content is obtained, where the explanation information is associated with pre-constructed dictionary content. According to the explanation information, target text content is determined. The target text content is displayed, which achieves the following effects. According to the text content, target text content that can assist a user in understanding the text content is provided to the user. For the user, the user can better understand the text content through the target text content. In addition, for an editing user of the text content, by displaying the target content to the editing user, it is helpful for the editing user to confirm whether the text content is the true expression of the editing user, and thus it is helpful for assisting the user in expression. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present disclosure, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0018] Figure 1 Schematic flow of the information processing method provided by the present disclosure Figure 1 ;

[0019] Figure 2 Schematic flow of the information processing method provided by the present disclosure Figure 2 ;

[0020] Figure 3 An application scenario is illustrated;

[0021] Figure 4A An application scenario is illustrated;

[0022] Figure 4B An application scenario is illustrated;

[0023] Figure 5 An illustrative flowchart of the information processing method provided by the present disclosure Figure 3 ;

[0024] Figure 6 An illustrative flowchart of the information processing method provided by the present disclosure

[0025] Figure 7 An application scenario is illustrated;

[0026] Figure 8 An illustrative flowchart of the information processing method provided by the present disclosure

[0027] Figure 9 An application scenario is illustrated;

[0028] Figure 10 An illustrative flowchart of the information processing method provided by the present disclosure

[0029] Figure 11 An application scenario is illustrated;

[0030] Figure 12 An illustrative flowchart of the information processing method provided by the present disclosure

[0031] Figure 13 An illustrative flowchart of the information processing method provided by the present disclosure

[0032] Figure 14 A structural block diagram of the information processing device provided by the present disclosure

[0033] Figure 15 A structural block diagram of the information processing device provided by the present disclosure

[0034] Figure 16 A structural block diagram of the information processing device provided by the present disclosure

[0035] Figure 17 A structural block diagram of the information processing device provided by the present disclosure

[0036] Figure 18 A hardware structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

[0038] Different users can use natural language to edit text content to realize information communication. For text content (including words and sentences) that is difficult to understand, the meanings of the above words and sentences can be understood with the help of a dictionary, and then the text content can be better understood. The dictionary here can be various dictionaries, such as an online dictionary.

[0039] The above-mentioned manner can understand the text content by using the entry interpretation of the dictionary. However, in some application scenarios, even if the entry interpretation is used, the user still cannot accurately grasp the meaning of the above-mentioned text content.

[0040] The information processing method provided by the present disclosure can provide target text content determined by interpretation information of text content according to an instruction, facilitate the user to better understand the text content, or accurately convey the meaning, and can improve the efficiency of information communication.

[0041] Please refer to Figure 1 , Figure 1 The flowchart of the information processing method provided by the present disclosure is shown in Figure 1 . As shown in Figure 1 , the information processing method comprises the following steps:

[0042] S101: In response to receiving a first instruction for text content, obtaining interpretation information associated with the text content, wherein the interpretation information is associated with pre-constructed dictionary content.

[0043] The execution subject of the information processing method in the present disclosure can be a client running in a terminal device, or a server providing services for the above-mentioned client. The above-mentioned client can be an independently running client, or one of a series of functional modules in a suite client.

[0044] As an illustrative example, the above-mentioned client can be a smart assistant client. The above-mentioned smart assistant can assist the user in processing natural language.

[0045] The above-mentioned text content can be text content in various application scenarios. For example, text content in a cloud document, text content for information communication in a social software, and text content in instant messaging.

[0046] In some application scenarios, the text content can be text content that a user is browsing. In these application scenarios, the method provided by the method can be used to obtain target text content that is easy to understand to help the user understand the text content.

[0047] In some application scenarios, the text content can be text content that a user is editing. In these application scenarios, the method provided by the method can be used to help the user determine whether the expression of the text content is accurate.

[0048] The first instruction can indicate an instruction to obtain interpretation information and generate corresponding content according to the interpretation information.

[0049] As an illustrative example, in the scenario of browsing a document, after the user performs a selection operation on the text content in the document, the user can perform an operation to invoke the client, and thus display an interactive interface of the client. The interactive interface can display a first selection item for generating auxiliary understanding of the text content. The user can perform a triggering operation on the first selection item, and thus send a first instruction to the execution subject.

[0050] The text content can be any content in the browsed or edited content, including one or more of a word, a phrase, and a sentence.

[0051] The dictionary can include a set of information for interpretation information for further understanding of the text. For example, a set of information in the Internet, a set of knowledge content, and various dictionaries. The dictionary can include a plurality of entries and corresponding explanations of the entries. In some application scenarios, the execution subject obtains interpretation information associated with the text content, including obtaining interpretation information of the text content from a set of information in the network, a set of knowledge content, and a dictionary.

[0052] Illustratively, the execution subject can obtain the interpretation information through the network. For example, using the text content to search in the background, and determining the interpretation information of the text content according to the matching degree.

[0053] Illustratively, the execution subject can obtain the interpretation information from the network according to the text content and the context. In this way, the interpretation information obtained by the execution subject is interpretation information related to the text content and the context. The accuracy of the generated interpretation information can be improved.

[0054] In some embodiments, the text content is determined in response to a user operation, or the text content is determined according to context consistency.

[0055] In some application scenarios, the user performs a selection operation to select the text content. After the user selects the text content, the text content can be highlighted.

[0056] In these application scenarios, the target text content is generated from the text content according to the user selection operation, so as to facilitate the user to selectively obtain the auxiliary understanding content.

[0057] In some application scenarios, the execution subject can determine the consistency of the text content with the context. The text content with poor consistency with the context is determined.

[0058] In these embodiments, the text content with poor consistency with the context is determined according to the context consistency determination, and the explanation or rewriting content is generated, which helps the user to quickly understand the text content.

[0059] In some application scenarios, when the content is edited by using the document application, the document application can communicate with the intelligent assistant if the intelligent optimization setting is enabled. For example, the content received and edited by the user or the electronic device is sent to the intelligent assistant through a preset interface, and the intelligent assistant determines the text content that needs to be assisted to explain or express, such as the text content with poor consistency with the context or the text content with incomplete sentence structure. The intelligent assistant can feed back the text content to the document application. The document application can highlight the text content.

[0060] The highlighting of the text content includes but is not limited to adding a background color different from other text content to the text content, displaying the text content in a display style different from other text content, and adding an underline to the text content.

[0061] In these application scenarios, the text content can be automatically recognized by the client during the editing process of the user, and then the target text content can be determined and displayed according to the execution of the first instruction, so as to actively prompt the user that the content to be written needs to be optimized, and provide the user with optimization suggestions for the text content by displaying the target text content. It does not depend on the initiation of the editor, but the client automatically prompts the user to optimize the edited content, so as to help the editor to find the text content that is ignored or easily missed and difficult to understand for optimization. It helps to improve the readability of the text and improve the communication efficiency.

[0062] S102: Determine the target text content according to the explanation information.

[0063] The target text is content generated according to the explanation information and used for assisting understanding of the text content.

[0064] In some embodiments, the target text content includes at least one of:

[0065] Explanation text for auxiliary explanation of the text content;

[0066] Rewriting content for rewriting the text content;

[0067] The association information of the entity word associated with the text content.

[0068] In some application scenarios, the target text content includes an explanation text that assists in explaining the text content.

[0069] In these application scenarios, the target text content can be an explanation text generated according to the explanation information, and the explanation text can assist the user in understanding the text content.

[0070] In some application scenarios, the target text content can be rewritten content generated according to the explanation information. For example, an optimized expression that is easier to understand is generated for the text content and the explanation information.

[0071] The semantics of the target text content can be the same as the text content. The target text content can be easier for people to understand than the text content. For example, the target text content uses more colloquial expressions than the text content, and for example, the target text content replaces abbreviations in the text content with the full name of the abbreviation. For example, in the target text content, the missing sentence structure in the text content is supplemented according to the context.

[0072] As an implementation manner, the execution subject can send the explanation information and the text content and the context information to a pre-trained natural language processing model, and the natural language processing model outputs the target text content according to the explanation information and the text content. Optionally or additionally, the natural language processing model outputs the target text content according to the explanation information and the text content.

[0073] In some application scenarios, the natural language processing model can run in a server, and the execution subject can access the natural language processing model through an interface.

[0074] As an implementation manner, the execution subject can determine the semantics of the text content according to the context and the words in the text content, and generate target text content that can express the semantics using common words and / or complete sentence structures according to the semantics of the text content.

[0075] As an example, the text content can be a sentence including an abbreviation. Then, the target text content can include the full name corresponding to the abbreviation and / or the corresponding explanation.

[0076] As an example, the text content can include a sentence with an obscure word. The target text can include a sentence in which the obscure word is replaced with a synonym of the obscure word.

[0077] In some application scenarios, the target text content includes association information of an entity word associated with the text content. The association information of the entity word can include an entity word identifier and an entity word interpretation, etc.

[0078] The association information of the entity word associated with the text content includes:

[0079] The association information of at least two entity words associated with the text content.

[0080] In these embodiments, the target text content can assist the user in understanding the text content, or determine whether the text content input by the user is the real meaning expressed by the user, or optimize the expression of the text content input by the user.

[0081] The entity word can be an entity word matched from a pre-constructed dictionary, and the interpretation of the entity word can be an interpretation determined from the pre-constructed dictionary.

[0082] S103: Display the target text content.

[0083] As an implementation manner, the execution subject can send the target text content to the client. The client displays the target text content.

[0084] By displaying the target text content, the user can browse the target text content on the client. The target text content is content that assists in understanding the text content.

[0085] If the text content is the text content being browsed by the user, the user can understand the meaning of the text content by reading the target text content. Thus, the target text content can assist the user in understanding the text content.

[0086] If the text content is the text content being edited by the user, by showing the target text content to the user, the user can determine whether the text content is the real meaning expressed by the user and / or optimize the expression of the text content.

[0087] In this embodiment, in response to receiving the first instruction for the text content, the explanation information associated with the text content is acquired, wherein the explanation information is associated with the pre-constructed dictionary content; the target text content is determined according to the explanation information; and the target text content is displayed, which realizes providing the target text content that can assist the user to understand the text content according to the explanation information associated with the text content. For the user, the user can better understand the text content through the target text content, and the reading efficiency of the user can be improved. In addition, for the editing user of the text content, by displaying the target content to the editing user, it is helpful for the editing user to confirm whether the text content is the true intention of the editing user and / or to optimize the expression manner of the text content, and thus it can be helpful to realize the effective expression of the user.

[0088] In some embodiments, acquiring the explanation information of the text content can include:

[0089] The text content is matched with the pre-constructed dictionary to obtain the entry information related to the text content, wherein the pre-constructed dictionary carries the knowledge content of a preset group.

[0090] In some application scenarios, the group members in the preset group can belong to the same organization. In this way, the pre-constructed dictionary can be a dictionary constructed according to the knowledge content within the organization. The dictionary can include a plurality of entries, for example, a plurality of entries constructed from the knowledge content within the organization. The entry can include entry name (or called entry, or entity word), explanation, example, link, etc.

[0091] In these application scenarios, the dictionary can include a plurality of entries extracted from the communication content commonly used in the communication between the members within the organization. The entry of the entry can include abbreviations, special terms, etc.

[0092] Specifically, the text content can be matched in the dictionary, and the target entry in the dictionary associated with the text content is determined according to the matching result.

[0093] In this way, the target text content generated in step S102 according to the explanation information is the target text content generated by referring to the knowledge content within the organization. Since the target text content is generated according to the entry carrying the knowledge content within the group, the target text content is generated on the basis of the knowledge content within the group, so that the user who does not understand the knowledge content within the group can also better understand the meaning of the text content through the target text content.

[0094] Please refer to Figure 2 which shows the flowchart of the information processing method provided by the present disclosure Figure 2 . As Figure 2As shown, the information processing method comprises the following steps:

[0095] S201: In response to receiving the first instruction for the text content, obtaining explanation information associated with the text content, wherein the explanation information is associated with pre-constructed dictionary content.

[0096] S202: Generating prompt information sent to the natural language processing model based on the explanation information.

[0097] S203: Generating target text content according to the output of the natural language processing model.

[0098] S204: Displaying the target text content.

[0099] In this embodiment, the execution subject can be a client or a server.

[0100] The natural language processing model described above can be a model that is pre-trained to perform semantic recognition on the input explanation information to generate restated content.

[0101] The execution subject described above can fill the explanation information described above into a prompt template (prompt template) to generate prompt information. The prompt template described above can set the input area and input format of the text content and explanation information. The prompt template described above can also include output indication information indicating what data the natural language processing model outputs. The execution subject described above sends the prompt information generated by the prompt template to the natural language processing model. The natural language processing model analyzes and processes the input prompt information to generate target text content that meets the user's intention. As an implementation manner, the output of the natural language can be directly used as the target text content described above.

[0102] In some embodiments, the step S203 comprises: performing sensitive word filtering processing on the output of the natural language processing model to obtain the target text content.

[0103] The sensitive word described above can be various words that cause adverse effects that are pre-set.

[0104] The execution subject described above can match the output described above with a pre-generated sensitive word library, and perform filtering processing such as replacement, deletion, modification, etc. on the matched sensitive words to obtain the target text content.

[0105] In these embodiments, by filtering the sensitive words described above, the generated target text content avoids negative effects and is conducive to the user's positive understanding of the text content.

[0106] With Figure 1Compared with the illustrated embodiments, in the embodiments, the prompt information is generated according to the interpretation information, and the natural language processing model is sent to generate the target text content. Because the prompt information has a corresponding format template, the natural language processing model can better understand the user's intention, which helps to generate the target text content for intent matching.

[0107] In Figure 1 and Figure 2 In some optional implementations of the illustrated embodiments, the information processing method further includes: displaying the glossary information related to the target text content.

[0108] In these embodiments, the glossary in the target text content can be a glossary that exists in a pre-constructed glossary. In these embodiments, the execution subject can read the glossary interpretation corresponding to the glossary from the pre-constructed glossary, and display the glossary information. When the user performs a triggering operation on the glossary information, the glossary interpretation of the glossary can be displayed.

[0109] The glossary can also be a glossary generated according to the interpretation information when generating the target text content. The glossary is not in the pre-constructed glossary.

[0110] In these embodiments, the glossary information is displayed when the target text content is displayed, so that the user can browse the glossary interpretation and facilitate understanding of the target text content.

[0111] In some embodiments, the information processing method further includes:

[0112] In response to detecting that the glossary involved in the target text content is a to-be-created glossary, the to-be-created glossary is added to the pre-constructed glossary based on the user operation.

[0113] In these embodiments, the glossary in the target content includes a to-be-created glossary that is not included in the glossary. The execution subject can match the glossary related to the target content with the pre-constructed glossary. If there is a glossary that does not match successfully, the glossary is a to-be-created glossary.

[0114] The pre-constructed glossary can be a professional glossary, a general glossary, or a glossary constructed according to the knowledge content in the group.

[0115] The glossary name of the to-be-created glossary can be a target word that appears in the target text content, including abbreviations, characters, etc. The glossary name can be an entity word determined by the execution subject, such as a professional term determined by the execution subject; or a word that can be understood by group members only in group communication, such as an abbreviation, etc.

[0116] After determining the target text content, the execution subject can determine the word included in the target text content.

[0117] As an implementation manner, the execution subject can send the explanation information, the text content, and the context of the text content to a natural language processing model, determine the target text content and the word in the target text content by the natural language processing model. The natural language processing model can output the target text content and the word in the target text content.

[0118] In this implementation manner, the natural language processing model can be a pre-trained model that can generate the target text content for assisting in understanding the text content and generate the associated word of the target text content according to the explanation information.

[0119] For the to-be-created word that does not exist in the pre-constructed dictionary, the user can perform an adding operation on the to-be-created word, for example, perform a right-click operation on the to-be-created word to call the word editing control. The word editing control includes an adding control for adding the to-be-created word to the pre-constructed dictionary. After receiving a trigger operation performed on the adding control, the execution subject can communicate with the server of the dictionary, send the to-be-created word and the word explanation and the like to the server of the dictionary, so that the server of the dictionary adds the to-be-created word to the dictionary.

[0120] In these embodiments, by adding the to-be-created word in the target text content to the pre-constructed dictionary, the words in the dictionary can be enriched, which is helpful for the user to understand the to-be-created word later.

[0121] In some embodiments, the text content is text content being browsed or edited, and the first instruction is generated in the following manner:

[0122] First, the text content is selected according to the selection operation of the user;

[0123] Second, in response to receiving the calling operation on the intelligent assistant, an interactive interface of the intelligent assistant is displayed; the interactive interface includes an interactive input area and at least one operable control;

[0124] Finally, a trigger operation performed by the user on a target operable control in the at least one operable control for indicating generation of the target text content is received, or an editing operation instruction for indicating generation of the target text content input by the user in the interactive input area is received.

[0125] In these embodiments, a user performs a selection operation on displayed textual content, which can be textual content in a document being browsed or textual content being edited by the user in various text editing applications. After the user selects the textual content, an operation to invoke an intelligent assistant can be performed. After receiving the operation to invoke the intelligent assistant, an interactive interface of the intelligent assistant is presented. At least one operable control is presented in the interactive interface. Each operable control can correspond to an editing function. Illustratively, the target operable control can indicate a control to obtain explanation information and generate target textual content that is easier for the user to understand based on the explanation information. By triggering the target operable control by the user, a first instruction can be generated.

[0126] In these embodiments, by providing the operable controls in the interactive interface, the user can quickly issue the first instruction, and the efficiency of generating the target textual content can be improved. In addition, the user can input an editing operation instruction for indicating generation of the target textual content in the interactive input area, such as inputting “generate more understandable content”. After receiving the editing operation instruction, the first instruction can be generated.

[0127] Reference is made to Figure 3 , which shows an application scenario. As shown in Figure 3 , the textual content is textual content in a document displayed by a document application. The document can be an online document or a locally stored document. The document application can display a document display interface, and the textual content of document 1 is displayed in the document display interface 31. The textual content of document 1 includes subheading 1 and content belonging to subheading 1. As shown in Figure 3 , the content includes “XXXXXX, growth is benefited from T2I, complement and repair of pictures / videos and other new technologies”. The user can perform a selection operation on the textual content “growth is benefited from T2I, complement and repair of pictures / videos and other new technologies” 32. After the user performs the selection operation on the textual content 32, an operation to invoke an intelligent assistant can be performed. For example, after selecting the textual content 32, a right-click operation menu is invoked, and an intelligent assistant option is displayed in the operation menu. The user can perform a triggering operation on the intelligent assistant option to invoke the intelligent assistant.

[0128] After the intelligent assistant is invoked, an interactive interface 33 of the intelligent assistant can be displayed in the form of a floating window or a pop-up window. The intelligent assistant can be an application client integrated in the document application or an independently running application client. When the intelligent assistant is an independently running application client, the document application can invoke the intelligent assistant client through a preset interface.

[0129] As shown in Figure 3As shown, after the user invokes the intelligent assistant client, an interactive interface 33 of the intelligent assistant can be displayed in the document display interface 31. The above-mentioned interactive interface 33 can be displayed in the form of a floating window or a pop-up window. The above-mentioned interactive interface 33 can include a main interaction window 34. The main interaction window 34 can display an identifier 37 of the intelligent assistant and an input operation window. The input operation window can show the user guide information on how to interact with the intelligent assistant. The guide information can include, for example, “Please enter a question or select an instruction”, as shown in the following figure. Figure 3 As shown, when the user performs a trigger operation on the above-mentioned main interaction window, a list of operable controls can be displayed. The above-mentioned list of operable controls includes an explanation control 35, an expansion control, a contraction control, and the like. The user can perform a trigger operation on the displayed list of operable controls to select a target operable control. As shown in the following figure, Figure 3 In the above-mentioned example, the user performs a trigger operation on the explanation control 35, i.e., the explanation control 35 is the target operable control. In addition, the user can also input “explain” in the main interaction window to quickly invoke the above-mentioned explanation control 35. After receiving the trigger operation performed by the user on the target operable control 35, it can be considered that a first instruction is received. The above-mentioned first instruction indicates the target text content of the text content 32, so that the user can understand the text content 32.

[0130] After receiving the above-mentioned first instruction, the above-mentioned intelligent assistant can obtain explanation information related to the text content 32. Then, the target text content is determined according to the above-mentioned explanation information. For example, prompt information generated according to the above-mentioned explanation information, the text content 32 and the context of the text content 32 is sent to a natural language processing model. The execution subject determines the target text content according to the output from the natural language processing model. After determining the target text content, the above-mentioned execution subject can display the above-mentioned target text content. For example, the target text content corresponding to the text content 32 is “Growth is due to the use of several new technologies, including text-to-image (T2I), completion and repair of images / videos, etc.” 36. By displaying the above-mentioned target text content 36, it is helpful for the user to understand the meaning of the text content 32.

[0131] Please refer to 4A, which shows an application scenario diagram. As shown in the following figure, Figure 4A As shown, the above-mentioned document application can display a document display interface, and the user edits a document 1 in the document display interface 41. The text content of the document 1 edited by the user is as shown in the following figure, Figure 4AAs shown, the edited text content includes "XXXXXX, growth benefited from T2I, image / video supplementation and repair, and other new technologies". The user can perform a selection operation on the edited text content "XXXXXX, growth benefited from T2I, image / video supplementation and repair, and other new technologies" 42. After the user performs the selection operation on the text content, a call operation of invoking the intelligent assistant can be performed. For example, after the text content is selected, a right-click operation menu is invoked, and the intelligent assistant option is displayed in the operation menu. The user can perform a trigger operation on the intelligent assistant option to invoke the intelligent assistant client.

[0132] After the intelligent assistant client is invoked, an interactive interface of the intelligent assistant can be displayed in the form of a floating window or a pop-up window. As shown, Figure 4A As shown, after the user invokes the intelligent assistant, an interactive interface 43 of the intelligent assistant can be displayed in the document display interface 41. The interactive interface 43 can be displayed in the form of a floating window or a pop-up window. The main interactive window 44 can be included in the interactive interface 43. The identification 47 of the intelligent assistant and the input operation window can be displayed in the main interactive window 44. The input operation window can show the user guide information on how to interact with the intelligent assistant. The guide information can include "Please enter a question or select an instruction", as shown. Figure 4A As shown, when the user performs a trigger operation on the main interactive window 44, a list of operable controls can be displayed. The list of operable controls includes the polishing control 45 (the polishing control is used to indicate the generation of a rewritten text), the expansion control, and the continuation control. The user can perform a trigger operation on the displayed list of operable controls to select a target operable control. As shown, Figure 4A In the main interactive window, the user performs a trigger operation on the polishing control 45, that is, the polishing control is the target operable control. In addition, the user can also input "polish" in the main interactive window to quickly invoke the polishing control. After receiving the trigger operation performed by the user on the target operable control 45, a first instruction is considered to be received. The first instruction indicates the target text content for polishing the text content 42 so that the user can understand the text content 42.

[0133] After the intelligent assistant receives the first instruction, the intelligent assistant can obtain the explanation information related to the text content 42. Then, the target text content 46 is determined according to the explanation information. After the target text content is determined, the execution subject can display the target text content 46. For example, the target text content corresponding to the text content 42 is "growth benefited from the use of several new technologies, including text-to-image (T2I), image / video supplementation and repair, and other new technologies" 46. By showing the target text content to the user, it is helpful for the user to determine whether the meaning of the text content is accurate.

[0134] In addition, the term information associated with the target text is also displayed in the interactive interface. As shown,Figure 4A As shown, the word information 48 associated with the target text content is displayed in the interaction interface 43, and the word information 48 indicates that the target text content contains a word. When the user performs a trigger operation on the word information 48, the word name (entity word) and the explanation of the word associated with the target text content can be displayed.

[0135] As shown, the word information 48 indicates that the word is, for example, “T2I”, and the word “T2I” in the target text content can be highlighted, for example, underlined, as shown. Figure 4A

[0136] Please refer to Figure 5 , which shows the schematic flow of the information processing method provided by the present disclosure Figure 3 . As shown in Figure 5 , the method includes the following steps:

[0137] S501: In response to receiving a first instruction for text content, obtaining explanation information associated with the text content, wherein the explanation information is associated with pre-constructed dictionary content.

[0138] S502: According to the explanation information, determine the target text content.

[0139] S503: Display the target text content.

[0140] In this embodiment, the specific implementation of the above steps S501-S503 can refer to the related part of the embodiment shown in Figure 1 , which will not be described here.

[0141] S504: In response to the target text content including rewritten content, replacing the text content according to the target text content based on the received replacement instruction.

[0142] In this embodiment, the above-mentioned text content can be text content edited by the user. The information processing method in this embodiment can be a client or a server providing services for the client. The above-mentioned client can be, for example, a smart assistant client.

[0143] Please refer to Figure 4A and Figure 4B . Figure 4B is a schematic diagram of an application scenario. As shown in Figure 4A ​As shown in FIG. 13, after displaying the target text content 46 in the interaction interface 43 of the intelligent assistant, the interaction interface 43 can further display operable controls such as replace, adjust, retry, and exit. The user can perform a trigger operation on the replace operable control to send a replace instruction to the intelligent assistant. After receiving the replace instruction, the intelligent assistant can send the target text content to the document application, and the document application can replace the text content with the target text content 46. After replacing the text content with the target text content, the display content of the document 1 can be as shown in FIG. 14. Figure 4B As shown in FIG. 14, after the target text content 46 replaces the text content, the background color of the target text content 46 can be different from the background color of other text content, so as to prompt the user that this part is the replaced text content.

[0144] Compared with the embodiment shown in FIG. 13, the embodiment described herein replaces the text content with the target text content according to the received replace instruction, thereby helping the user to rewrite the content. From the perspective of whether the reader can easily understand, providing the user with editing suggestions can improve the readability of the edited content of the user, and helps to improve the communication efficiency. Figure 1

[0145] Please refer to FIG. 15, which shows a schematic flowchart of an information processing method provided by the present disclosure. As shown in FIG. 15, the method comprises the following steps: Figure 6 Figure 6

[0146] S601: Display a first content interface according to a received display operation.

[0147] The execution subject of the information processing method described above can be a client or a server.

[0148] The first content interface described above can be various application content display interfaces, such as a document display interface, a content display interface of a social application, a content display interface of an instant messaging application, etc.

[0149] The display operation described above can be an operation performed by the user, or a display operation performed by the server or the execution subject according to a display instruction.

[0150] The display operation described above can be any operation for opening the first content interface, such as clicking an application icon in the display interface of the terminal device to open the first content interface of the application. For example, selecting a target page in an opened application to display the first content interface of the target page.

[0151] Various types of information content can be displayed in the first content interface described above, including but not limited to text content, picture content, etc.

[0152] ​​​S602: receiving a first selection operation for a target content, the first selection operation being used to select a part of displayed content in the first content interface as the target content.

[0153] In one example, the user can perform the first selection operation for any part of the displayed content in the first content interface. The first selection operation can be any operation for selecting the displayed content.

[0154] Illustratively, the execution subject can receive the first selection operation of the user, and determine the target content selected by the first selection operation according to the region acted by the first selection operation.

[0155] S603: displaying a second content interface according to the first selection operation, the second content interface displaying at least two entity words associated with the target content and associated information of the at least two entity words.

[0156] After the target content selected by the first selection operation is determined according to the first selection operation, at least two entity words associated with the target content and the respective paraphrases of the at least two entity words can be identified.

[0157] In addition, the second content interface can be displayed, in which the at least two entity words and the respective associated information of the at least two entity words are displayed.

[0158] The following will be described in conjunction with Figure 7 Please refer to Figure 7 which shows an application scenario diagram. As shown in Figure 7 , a user edits a document using a document application. The first content interface is a document editing interface. The user can edit the text content of document 1 in the document editing interface (first content interface) 71. The text content of document 1 edited by the user is shown in Figure 4A , including "growth benefits from T2I, figure / video supplement and repair new technologies, etc." 72. The user can perform a selection operation on the text content 72 (target content). After the user performs the selection operation on the text content 72, a second content interface (i.e., a first interaction interface of the intelligent assistant) 73 can be displayed. The first interaction interface of the intelligent assistant 73 can display at least two entity words associated with the text content 72 and the respective paraphrases of the at least two entity words. For example, entity word 1 and the paraphrase of entity word 1, entity word 2 and the paraphrase of entity word 2, etc. By displaying the paraphrases of the at least two entity words in the second content interface, the user can browse the entity word information in the second content interface, which is helpful for understanding the text content.

[0159] In some embodiments, the display of the second content interface includes:

[0160] The second content interface includes a first region and a second region, the first region is configured to display the association information of the first entity word, and the second region is configured to display the association information of the second entity word; the first entity word and the second entity word are contained in the target content.

[0161] The first region and the second region can be non-overlapping. Please continue to refer to Figure 7 , the first region and the second region in the second content interface 73 can be regions 741 and 742 in Figure 7 respectively. The association information of the entity word 1 can be displayed in the first region 741. The association information of the entity word 2 is displayed in the second region 742. The entity word 1 and the entity word 2 can be any entity word. The association information of the entity word 1 can include, for example, the entity word 1 and the explanation of the entity word 1 as shown in Figure 7 . The association information of the entity word 2 can include, for example, the entity word 2 and the explanation of the entity word 2 as shown in Figure 7 .

[0162] Displaying the association information of the first entity word and the association information of the second entity word in the first region and the second region respectively facilitates the user to clearly browse the association information of the first entity word and the second entity word, and helps the user to understand the target content.

[0163] In some embodiments, the first content interface described above includes an interactive input region; the information processing method further includes:

[0164] In response to receiving an editing operation instruction in the interactive input region, operation prompt information is generated based on the editing operation instruction and sent to the natural language processing model, so that the natural language processing model performs the operation indicated by the operation instruction according to the operation prompt information.

[0165] The operation prompt information is generated based on at least one of the following:

[0166] The operation indicated by the editing operation instruction;

[0167] Text content;

[0168] At least two entity words and the explanation of the at least two entity words.

[0169] Please continue to refer to Figure 7 , the second content interface 73 described above can also include an interactive input region 76, and the user can input an editing operation instruction in the interactive input region 76 described above. Illustratively, the user can input "rewrite". Thus, the editing operation instruction of rewriting the text content 72 is sent to the execution subject described above.

[0170] In addition, the user can also perform a trigger operation on the operable control, for example, perform a trigger operation on the "rewrite" operable control, so as to input an editing operation instruction indicating rewriting the text content 72.

[0171] After receiving the above editing operation instruction, the execution subject can generate prompt information according to the editing operation instruction. For example, the prompt information can be generated by filling in the prompt template.

[0172] The prompt information can be generated based on one or more of the operation, the text content, the at least two entity words, and the paraphrase of the at least two entity words indicated by the editing operation instruction. That is, one or more of the operation, the text content, the at least two entity words, and the paraphrase of the at least two entity words indicated by the editing operation instruction is filled into the prompt template to generate the prompt information.

[0173] The execution subject sends the prompt information to a natural language processing model, and the natural language processing model processes the prompt information and outputs a processing result, such as target text content that helps to explain the text content or rewritten content for rewriting the text content.

[0174] In these embodiments, by generating operation prompt information, the operation prompt information is sent to a natural language processing model, and the natural language processing model performs the operation indicated by the editing operation instruction. An accurate and fast editing operation result for the text content can be obtained.

[0175] In this embodiment, according to the first selection operation on the target content, the at least two entity words and the paraphrase of the at least two entity words are displayed, and the user does not need to separately perform the operation of displaying the paraphrase information for each entity. This can help the user quickly obtain the paraphrase of each entity word in the target content and quickly understand the target content.

[0176] Please refer to Figure 8 , which shows a schematic flowchart of an information processing method provided by the present disclosure. As Figure 8 shown, the method includes the following steps:

[0177] S801: receiving an operation on text content.

[0178] The execution subject of the information processing method can be a client or a server.

[0179] The text content can be text content in various application scenarios. For example, text content in a document, text content for information communication in a social software, and text content in instant messaging.

[0180] The text content can be text content being browsed or text content being edited.

[0181] The text content can be part of the text content displayed on a page or all of the text content.

[0182] In one example, the user can perform a selection operation on at least part of the text content displayed by the page, thereby selecting the part of the text content. The execution subject can display the explanation information associated with the part of the text content in the second content display interface. S802: display the second content interface, and display the explanation information in the second content interface, wherein the explanation information comprises one or more of the following:

[0183] the explanation text of the text content, the entity words associated with the text content, and the explanation of at least part of the entity words.

[0184] The following Figure 9 is described with reference to Figure 9 , which shows an application scenario. As Figure 9 shown, a user edits a document using a document application. For example, the user edits the text content of document 1 in the document application editing interface 91. The text content of document 1 edited by the user includes “growth benefits from T2I, complement and repair of pictures / videos, and new technologies such as repair” 92, as Figure 4A shown. The user can perform a selection operation on the text content 92. After the user performs the selection operation on the text content 92, a second interaction interface (i.e., a second content interface) 93 of the intelligent assistant can be displayed. The second interaction interface 93 of the intelligent assistant can display the explanation text 94, the term associated with the text content, and the explanation of at least part of the term. Illustratively, the term can include term 1, and the term 1 and the explanation 96 of the term 1 can be displayed in the second interaction interface 93. Information 95 of other terms can also be displayed. The user can perform a trigger operation on the information 95 of the other terms to display more terms and term explanations. This facilitates the user to browse the term information in the second interaction interface to facilitate the understanding of the text content.

[0185] In this embodiment, by displaying the explanation text and the term associated with the text content and the explanation of at least part of the term in the second interaction interface, the understanding of the text content is facilitated.

[0186] Please refer to Figure 10 , which shows a schematic flowchart of an information processing method provided by the present disclosure. As Figure 10 shown, the method comprises the following steps:

[0187] S1001: display a first content interface.

[0188] The execution subject of the information processing method described above can be a client or a server.

[0189] The first content interface can be various application content display interfaces. For example, a document display interface, a content display interface of a social application, a content display interface of an instant messaging application, and the like.

[0190] The first content interface can display content including text, pictures, and the like.

[0191] S1002: receiving a second selection operation for the target content, the second selection operation being used to select the target content from the content displayed in the first content interface.

[0192] The second selection operation can be a selection operation performed by a user, or a selection operation performed by a server or the subject according to a selection instruction. The second selection operation can select at least part of the content in the first content interface as the target content.

[0193] S1003: displaying a third content interface based on the target content, the third content interface including:

[0194] first explanation information of the target content; or

[0195] first explanation information of the target content, and second explanation information of at least one entity word contained in the target content.

[0196] In some application scenarios, the first explanation information of the target content can be obtained from a server according to the target content, and the first explanation information can be displayed in the displayed third interface. It can be understood that the loading of the third content interface can be synchronized with the obtaining of the first explanation information. The first explanation information can assist the user in understanding any information of the target content.

[0197] In some other application scenarios, the first explanation information of the target content and the second explanation information of at least one entity word in the target content can be obtained from a server according to the target content, and the first explanation information and the second explanation information of the at least one entity word can be displayed in the displayed third interface.

[0198] In some optional implementation manners, the third content interface includes a third region and a fourth region.

[0199] The third region is used to display the first explanation information.

[0200] The fourth region is used to display the second explanation information.

[0201] The display styles of the third region and the fourth region are different.

[0202] Please refer to Figure 11 , Figure 11 for an application scenario. As Figure 11As shown, the first content display interface 111 can display text content, pictures, etc. The user can perform a second selection operation on at least part of the content in the first content display interface 111. For example, the text content "growth benefits from T2I, complement and repair of pictures / videos, and new technologies such as repair" 112 is selected, and the above text content 112 is taken as the target content.

[0203] The execution subject can acquire the first explanation information of the target content according to the target content, or acquire the first explanation information of the target content and the second explanation information of the entity words included in the target content.

[0204] The execution subject can display a third content interface 113 according to the target content, and display the first explanation information in the third content interface 113.

[0205] In addition, the first explanation information and the second explanation information of at least one entity word of the target content can also be displayed in the third content interface.

[0206] As shown, Figure 11 The third content interface 113 includes a third area 114 and a fourth area 115. The first explanation information of the target content is displayed in the third area 114, and the explanation (second explanation information) of the entity word 1 is displayed in the fourth area 115. The above-mentioned entity word 1 can be any one of the entity words in the target content.

[0207] The display styles of the third area and the fourth area are different. For example, the display width of the third area is greater than that of the fourth area, or the background color of the third area is different from that of the fourth area, or the font style in the third area is different from that in the fourth area, etc. By setting the third area and the fourth area to different display styles, the user can quickly distinguish which is the first explanation information and which is the second explanation information in the third content interface, and the user can selectively browse the content in the third content interface according to his own needs, to assist the user in understanding the target content.

[0208] In this embodiment, the third content interface is displayed for the selected target content, and the first explanation information of the target content is displayed in the third content interface, or the first explanation information of the target content and the explanation information of the entity word of the target content are displayed, which can assist the user in understanding the target content. The following will be described in combination with Figure 12 and Figure 13 , Figure 12 One of the principle schematic diagrams for implementing the information processing method of the present disclosure. Figure 13 One of the principle flowcharts for implementing the information processing method of the present disclosure.

[0209] The user can perform a selection operation on text content displayed in a display interface (for example, a display interface of a document application) of the first application 1301, and the first application 1301 can send the text content indicated by the selection operation and a context in which the text content is located to the intelligent assistant 1302. The intelligent assistant can send the text content to the server 1303 through a preprocessing interface, and the server can obtain relevant information related to the text content according to the text content. For example, an explanation word is extracted from the text content. The explanation word is matched in a pre-constructed dictionary, and a first entry in the dictionary that matches the explanation word is determined according to a matching result. An external entry corresponding to the explanation word can also be obtained from the Internet through the preprocessing interface. The external entry and the first entry can be aggregated to obtain an entry set, that is, a relevant information set.

[0210] The intelligent assistant can configure the text content, the relevant information, and the context of the text content in a prompt template, and send the prompt template to the natural language processing model 1304. The natural language processing model 1304 can output initial target text content in a streaming manner. After obtaining the initial target text content, post-processing can be performed. For example, the initial target text content is sent to the server 1303 through a post-processing interface. The server analyzes the initial target text content, performs entry mapping, and then filters sensitive words in the initial target text content. The initial target text content after filtering of the sensitive words is intervened to obtain target text content. The target text content can be output in a streaming manner. In the display interface of the first application, the intelligent assistant can display the target text content in a streaming manner.

[0211] The information processing method corresponding to the above Figure 1 embodiment, Figure 14 The structure block diagram of the information processing apparatus provided by the embodiment of the present disclosure is shown in FIG. 14. For ease of illustration, only parts related to the embodiment of the present disclosure are shown. Referring to Figure 14 The apparatus 140 includes an obtaining unit 1401, a determining unit 1402, and a first display unit 1403. Wherein,

[0212] The obtaining unit 1401 is configured to, in response to receiving a first instruction for text content, obtain explanation information associated with the text content, wherein the explanation information is associated with pre-constructed dictionary content;

[0213] The determining unit 1402 is configured to determine target text content according to the explanation information;

[0214] The first display unit 1403 is configured to display the target text content.

[0215] In an embodiment of the present disclosure, the obtaining unit 1401 is further configured to:

[0216] The text content is matched with a pre-constructed dictionary to obtain article information related to the text content, wherein the pre-constructed dictionary carries knowledge content of a preset group.

[0217] In an embodiment of the present disclosure, the determining unit 1402 is further configured to:

[0218] generate prompt information based on the interpretation information and send the prompt information to the natural language processing model;

[0219] generate the target text content according to an output of the natural language processing model.

[0220] In an embodiment of the present disclosure, the first displaying unit 1403 is further configured to:

[0221] display article information related to the target text content.

[0222] In an embodiment of the present disclosure, the apparatus 140 further comprises an article adding unit (not shown in the figure), which is configured to:

[0223] in response to detecting that the article involved in the target text content is a to-be-created article, add the to-be-created article to the pre-constructed dictionary based on a user operation.

[0224] In an embodiment of the present disclosure, the text content is determined in response to a user operation, or the text content is determined according to context consistency determination.

[0225] In an embodiment of the present disclosure, the text content is text content being browsed or edited, and the apparatus further comprises a first instruction generating unit (not shown in the figure), which is configured to generate a first instruction by:

[0226] selecting the text content according to a selection operation of the user;

[0227] in response to receiving a calling operation on the intelligent assistant, display an interaction interface of the intelligent assistant; the interaction interface comprises an interaction input area and at least one operable control;

[0228] receive a trigger operation performed by the user on a target operable control in the at least one operable control, or receive an editing operation instruction input by the user in the interaction input area for indicating generation of the target text content.

[0229] In an embodiment of the present disclosure, the determining unit 1402 is further configured to:

[0230] perform sensitive word filtering processing on the output of the natural language processing model to obtain the target text content.

[0231] In an embodiment of the present disclosure, the target text content includes at least one of the following:

[0232] an explanation text for auxiliary explanation of the text content;

[0233] rewritten content for rewriting the text content;

[0234] association information of an entity word associated with the text content.

[0235] In an embodiment of the present disclosure, the apparatus 140 further includes a replacing unit (not shown in the figure), which is configured to:

[0236] in response to the target text content including the rewritten content, replace the text content according to the target text content based on the received replacement instruction.

[0237] In an embodiment of the present disclosure, the entity word information of the entity word associated with the text content includes:

[0238] association information of at least two entity words associated with the text content respectively.

[0239] the information processing method corresponding to the above Figure 6 embodiment, Figure 15 a structural block diagram of the information processing apparatus provided by the embodiment of the present disclosure. For ease of illustration, only parts related to the embodiment of the present disclosure are shown. Referring to Figure 15 , the apparatus 1500 includes a second display unit 1501, a first receiving unit 1502 and a third display unit 1503, wherein,

[0240] The second display unit 1501 is configured to display a first content interface according to the received display operation.

[0241] The first receiving unit 1502 is configured to receive a first selection operation for target content, the first selection operation being used to select part of the displayed content from the content displayed in the first content interface as the target content.

[0242] The third display unit 1503 is configured to display a second content interface according to the first selection operation, and display at least two entity words associated with the target content and the paraphrases of the at least two entity words in the second content interface.

[0243] In some embodiments, the first content interface includes an interactive input area; the apparatus 150 further includes a sending unit (not shown in the figure), which is configured to:

[0244] in response to receiving an editing operation instruction in the interactive input area, generate operation prompt information sent to the natural language processing model based on the editing operation instruction, so that the natural language processing model performs the operation indicated by the operation prompt information according to the operation prompt information.

[0245] In some embodiments, the operation prompt information is generated based on at least one of the following:

[0246] Edit the operation instructions;

[0247] Text content;

[0248] At least two entity words and the definitions of at least two entity words.

[0249] In some embodiments, displaying the second content interface includes:

[0250] The second content interface includes a first area and a second area. The first area is used to display the association information of the first entity word, and the second area is used to display the association information of the second entity word. The first entity word and the second entity word are contained in the target content.

[0251] Corresponding to the above text Figure 8 The information processing method of the embodiment shown, Figure 16 This is a structural block diagram of an information processing apparatus provided according to embodiments of the present disclosure. For ease of explanation, only the parts relevant to embodiments of the present disclosure are shown. (Refer to...) Figure 16 The device 160 includes a second receiving unit 1601 and a third display unit 1602. Among them,

[0252] The second receiving unit 1601 is used to receive operations on text content;

[0253] The fourth display unit 1602 is used to display a second content interface, on which explanatory information is displayed, wherein the explanatory information includes one or more of the following:

[0254] The explanatory text of the text content, the entity words associated with the text content, and the definitions of at least some of the entity words.

[0255] Corresponding to the above text Figure 10 The information processing method of the embodiment shown, Figure 17 This is a structural block diagram of an information processing apparatus provided according to embodiments of the present disclosure. For ease of explanation, only the parts relevant to embodiments of the present disclosure are shown. (Refer to...) Figure 17 The device 170 includes a fifth display unit 1701, a third receiving unit 1702, and a sixth display unit 1703.

[0256] The fifth display unit 1701 is used to display the first content interface;

[0257] The third receiving unit 1702 is used to receive a second selection operation for the target content, the second selection operation being used to select the target content from the content displayed on the first content interface;

[0258] The sixth display unit 1703 is configured to display a third content interface based on the target content, the third content interface comprising:

[0259] first explanation information of the target content; or

[0260] first explanation information of the target content, and second explanation information of at least one entity word contained in the target content.

[0261] In some embodiments, the third content interface comprises a third region and a fourth region.

[0262] The third region is configured to display the first explanation information.

[0263] The fourth region is configured to display the second explanation information.

[0264] The third region and the fourth region have different display styles.

[0265] To implement the above-mentioned embodiments, the present disclosure further provides an electronic device.

[0266] Reference Figure 18 is a structural schematic diagram of an electronic device 1800 suitable for implementing the embodiments of the present disclosure, which can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (PDA), tablet computers (Portable Android Device, PAD), portable multimedia players (Portable Media Player, PMP), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. Figure 18 The electronic device shown is only an example and should not impose any limitations on the functions and use range of the embodiments of the present disclosure.

[0267] As Figure 18As shown, the electronic device 1800 can include a processing device (e.g., a central processor, a graphics processor, etc.) 1801 that can perform various suitable actions and processes according to programs stored in a Read Only Memory (ROM) 1802 or loaded into a Random Access Memory (RAM) 1803 from a storage device 1808. Various programs and data required by the electronic device 1800 for operation are also stored in the RAM 1803. The processing device 1801, the ROM 1802, and the RAM 1803 are connected to each other by a bus 1804. An Input / Output (I / O) interface 1805 is also connected to the bus 1804.

[0268] Generally, the following devices can be connected to the I / O interface 1805: input devices 1806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 1807 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, etc.; storage devices 1808 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1809. The communication devices 1809 can allow the electronic device 1800 to communicate wirelessly or wired with other devices to exchange data. Although Figure 18 The electronic device 1800 is shown with various devices, but it is understood that all of the illustrated devices are not required to implement or have the electronic device. More or less devices can alternatively be implemented or have.

[0269] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 1809, or installed from the storage devices 1808, or installed from the ROM 1802. When the computer program is executed by the processing device 1801, the above-mentioned functions defined in the methods of embodiments of the present disclosure are performed.

[0270] It is noted that the aforementioned computer-readable medium of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium can be, for example and without limitation, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program (computer-executable instructions) which can be used by or in connection with an instruction execution system, apparatus or device. In the present disclosure, the computer-readable signal medium can include a data signal which propagates in baseband or as part of a carrier wave by any suitable medium, in which computer-readable program code is carried. Such a propagated signal can take any suitable form, including but not limited to an electromagnetic signal, an optical signal or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium that is not a storage medium and which can communicate, propagate or transport program for use by or in connection with an instruction execution system, apparatus or device. The program code contained in the computer-readable medium can be transmitted by any suitable medium, including but not limited to wire, cable, RF (radio frequency) or the like, or any suitable combination thereof.

[0271] The aforementioned computer-readable medium can be contained in the aforementioned electronic device; or can exist separately from the electronic device and not be assembled into the electronic device.

[0272] The aforementioned computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to perform the method shown in the aforementioned embodiments.

[0273] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0274] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0275] The units described in the embodiments of the present disclosure can be implemented by software, or by hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself. For example, the acquisition unit can also be described as a unit that acquires the explanation information associated with the text content in response to receiving the first instruction for the text content.

[0276] The functions described in this specification can be performed at least in part by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Program-specific Integrated Circuits (ASICs), Program-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0277] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0278] The above description is only preferred embodiments of the present disclosure and the explanation of the applied technical principles. It should be understood by those skilled in the art that the disclosure range involved in the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and also covers other technical solutions formed by any combination of the above technical features or equivalent features without departing from the above disclosed concept. For example, the technical solutions formed by replacing the above features with the technical features disclosed in the present disclosure (but not limited to) having similar functions.

[0279] In addition, although each operation is described in a particular order, this should not be understood as requiring the operations to be performed in the specific order shown or in a sequential order. In certain circumstances, multitasking and parallel processing can be advantageous. Similarly, although several implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments can also be combined in a single embodiment. Conversely, various features described in the context of a single embodiment can also be separated and implemented in multiple embodiments.

[0280] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. An information processing method, comprising: in response to receiving a first instruction for text content, obtaining explanation information associated with the text content, wherein the explanation information is associated with pre-constructed dictionary content, and the pre-constructed dictionary carries a preset group of knowledge content, including a plurality of entries constructed according to knowledge content within the preset group; based on the explanation information, the text content and a context of the text content, invoking a natural language processing model to generate target text content, wherein the target text content includes rewritten content for rewriting the text content, and the rewritten content is an optimized expression easy for a user to understand based on the text content and the explanation information; displaying the target text content; in response to detecting that the target text content involves a to-be-created entry, adding the to-be-created entry to the pre-constructed dictionary based on a user operation.

2. The method of claim 1, wherein, The obtaining of the explanation information associated with the text content comprises: matching the text content with the pre-constructed dictionary to obtain entry information related to the text content.

3. The method of claim 1, wherein, The invoking of the natural language processing model to generate the target text content based on the explanation information, the text content and the context of the text content comprises: generating prompt information sent to the natural language processing model based on the explanation information; generating the target text content according to an output of the natural language processing model.

4. The method of claim 1, wherein, The method further comprises: displaying entry information involved in the target text content.

5. The method of claim 1, wherein, The text content is determined in response to a user operation, or the text content is determined according to context consistency.

6. The method of claim 1, wherein, The text content is text content being browsed or edited, and the first instruction is generated by: selecting text content according to a selection operation of a user; in response to receiving a calling operation on an intelligent assistant, displaying an interactive interface of the intelligent assistant, wherein the interactive interface includes an interactive input area and at least one operable control; receiving a trigger operation performed by a user on a target operable control in the at least one operable control, or receiving an editing operation instruction input by the user in the interactive input area for indicating generation of the target text content.

7. The method of claim 3, wherein, The generating of the target text content according to the output of the natural language processing model comprises: performing sensitive word filtering processing on the output of the natural language processing model to obtain the target text content.

8. The method according to any one of claims 1 to 7, characterized in that, The target text content further includes: explanation text for auxiliary explanation of the text content; and / or, association information of an entity word associated with the text content.

9. The method of claim 8, wherein, The method further comprises: in response to the target text content including rewritten content, replacing the text content according to the target text content based on a received replacement instruction.

10. The method of claim 8, wherein, The association information of the entity word associated with the text content comprises: association information of at least two entity words associated with the text content. 11.An information processing method, comprising: displaying a first content interface according to a received display operation; receiving a first selection operation for target content, the first selection operation being used to select part of displayed content from the content displayed in the first content interface as the target content; displaying a second content interface according to the first selection operation, in which at least two entity words associated with the target content and the explanations of the at least two entity words are displayed; each entity word and explanation corresponds to an entity word and explanation in a pre-constructed dictionary, the pre-constructed dictionary carrying knowledge content of a preset group, including a plurality of entries constructed according to the knowledge content within the preset group; The method further comprises: generating prompt information based on one or more of the operation indicated by the editing operation instruction, the target content, the context of the target content, the at least two entity words and the explanations of the at least two entity words; sending the prompt information to a natural language processing model, and outputting target text content by the natural language processing model, the target text content including rewriting content for rewriting the target content; the rewriting content is an optimized expression easy for a user to understand generated based on the target content and the explanation information; in response to detecting that the target text content involves a to-be-created entry, adding the to-be-created entry to the pre-constructed dictionary based on a user operation.

12. The method of claim 11, wherein, The first content interface includes an interactive input area; the method further comprises: in response to receiving an editing operation instruction in the interactive input area, generating operation prompt information sent to a natural language processing model based on the editing operation instruction, so that the natural language processing model performs the operation indicated by the operation instruction according to the operation prompt information.

13. The method of claim 12, wherein, The operation prompt information is generated based on at least one of the following: the operation indicated by the editing operation instruction; text content; the at least two entity words and the explanations of the at least two entity words.

14. The method of claim 11, wherein, The display of the second content interface comprises: The second content interface includes a first area and a second area, the first area being used to display associated information of a first entity word, and the second area being used to display associated information of a second entity word; the first entity word and the second entity word are contained in the target content.

15. An information processing method, comprising: receiving an operation for text content; displaying a second content interface in which explanation information is displayed, wherein the explanation information includes one or more of the following: an explanation text of the text content, an entity word associated with the text content, and an explanation of at least part of the entity word; wherein the explanation text is generated according to explanation information of the text content; the explanation information is associated with pre-constructed dictionary content; the pre-constructed dictionary carries knowledge content of a preset group, including a plurality of entries constructed according to the knowledge content within the preset group; calling a natural language processing model to generate target text content according to the explanation information, the text content and the context of the text content; wherein the target text content includes rewriting content for rewriting the text content; the rewriting content is an optimized expression easy for a user to understand generated based on the text content and the explanation information; In response to detecting that the target text content involves a to-be-created term, the to-be-created term is added to the pre-constructed dictionary based on a user operation.

16. An information processing method, comprising: displaying a first content interface; receiving a second selection operation for target content, the second selection operation being used to select the target content from content displayed by the first content interface; displaying a third content interface based on the target content, the third content interface including: first explanation information of the target content; or first explanation information of the target content and second explanation information of at least one entity word contained in the target content; wherein the first explanation information includes explanation text and / or rewritten content used to assist a user in understanding the target content; the first explanation information and the second explanation information are associated with pre-constructed dictionary content; the pre-constructed dictionary carries a preset group of knowledge content, including a plurality of terms constructed according to knowledge content within the preset group; based on the first explanation information, the second explanation information, the target content, and a context of the target content, a natural language processing model is invoked to generate target text content; wherein the target text content includes rewritten content used to rewrite the target content; the rewritten content is an optimized expression easy for a user to understand, which is generated based on the target text content and the explanation information; in response to detecting that the target text content involves a to-be-created term, the to-be-created term is added to the pre-constructed dictionary based on a user operation.

17. The method of claim 16, wherein, the third content interface includes a third region and a fourth region; the third region is used to display the first explanation information; the fourth region is used to display the second explanation information; the third region and the fourth region have different display styles.

18. An information processing apparatus, comprising: an acquisition unit configured to, in response to receiving a first instruction for text content, acquire explanation information associated with the text content, wherein the explanation information is associated with pre-constructed dictionary content; the pre-constructed dictionary carries a preset group of knowledge content, including a plurality of terms constructed according to knowledge content within the preset group; and a determination unit configured to determine target text content based on the explanation information; a first determination unit configured to, based on the explanation information, the text content, and a context of the text content, invoke a natural language processing model to generate target text content; wherein the target text content includes rewritten content used to rewrite the text content; the rewritten content is an optimized expression easy for a user to understand, which is generated based on the text content and the explanation information; a first display unit configured to display the target text content; a first adding unit configured to, in response to detecting that the target text content involves a to-be-created term, add the to-be-created term to the pre-constructed dictionary based on a user operation.

19. An information processing apparatus, comprising: a second display unit configured to display a first content interface based on a received display operation; The first receiving unit is configured to receive a first selection operation for target content, the first selection operation being used to select part of displayed content from content displayed on the first content interface as the target content; The third display unit is configured to display a second content interface according to the first selection operation, the second content interface displaying at least two entity words associated with the target content and explanations of the at least two entity words; each entity word and explanation corresponds to an entity word and an explanation in a pre-constructed dictionary, the pre-constructed dictionary carrying knowledge content of a preset group, including a plurality of entries constructed according to knowledge content in the preset group; The target text content determination unit is configured to: generate prompt information based on one or more of the operation indicated by the editing operation instruction, the target content, a context of the target content, the at least two entity words and the explanations of the at least two entity words; send the prompt information to a natural language processing model, and output target text content from the natural language processing model, the target text content including rewritten content used to rewrite the target content; the rewritten content is an optimized expression easy for a user to understand, which is generated based on the target content and the explanation information; The second adding unit is configured to add a to-be-created entry to the pre-constructed dictionary based on a user operation in response to detecting that the target text content involves the to-be-created entry.

20. An information processing apparatus, comprising: The second receiving unit is configured to receive an operation for text content; The fourth display unit is configured to display a second content interface, and the second content interface displays explanation information, wherein the explanation information includes one or more of the following: an explanation text of the text content, an entity word associated with the text content, and an explanation of at least part of the entity word; The explanation text is generated according to the text content and explanation information of the text content; the explanation information is associated with pre-constructed dictionary content; the pre-constructed dictionary carries knowledge content of a preset group, including a plurality of entries constructed according to knowledge content in the preset group; The second determination unit is configured to call a natural language processing model to generate target text content according to the explanation information, the text content and a context of the text content; wherein the target text content includes rewritten content used to rewrite the text content; the rewritten content is an optimized expression easy for a user to understand, which is generated based on the text content and the explanation information; The third adding unit is configured to add a to-be-created entry to the pre-constructed dictionary based on a user operation in response to detecting that the target text content involves the to-be-created entry.

21. An information processing apparatus, comprising: The fifth display unit is configured to display a first content interface; The third receiving unit is configured to receive a second selection operation for target content, the second selection operation being used to select the target content from content displayed on the first content interface; The sixth display unit is configured to display a third content interface based on the target content, the third content interface including: first explanation information of the target content; or, The first explanation information of the target content and the second explanation information of at least one entity word contained in the target content; wherein The first explanation information includes explanation text and / or rewritten content for assisting the user in understanding the target content; the first explanation information and the second explanation information are associated with pre-constructed dictionary content; the pre-constructed dictionary carries a preset group of knowledge content, including a plurality of entries constructed according to the knowledge content within the preset group; A third determination unit is configured to call a natural language processing model to generate target text content according to the first explanation information, the second explanation information, the target content and the context of the target content; wherein the target text content includes rewritten content for rewriting the target content; the rewritten content is an optimized expression easy for the user to understand, which is generated based on the target content and the explanation information; A fourth adding unit is configured to add a to-be-created entry to the pre-constructed dictionary based on a user operation in response to detecting that the target text content involves the to-be-created entry.

22. An electronic device, comprising: Comprise: A processor and a memory; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method of any one of claims 1 to 17.

23. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and when the processor executes the computer execution instructions, the method of any one of claims 1 to 17 is realized. The computer readable storage medium stores computer execution instructions, and when the processor executes the computer execution instructions, the method of any one of claims 1 to 17 is realized.

Images