Processing method and device

Abstract

The invention discloses a processing method and device.The method comprises the steps that in response to a deletion instruction, an indication object indicated by the deletion instruction is deleted; in response to the deletion instruction, obtaining a target parameter; and if the target parameter meets the trigger condition, processing an associated object associated with the indication object based on a target model to obtain a target object.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of information processing, and relate to but are not limited to a processing method and device. Background Art

[0002] When editing long paragraphs, users often encounter problems such as unclear words, chaotic structure, and inadvertent typos. In this case, how to recommend more reasonable expressions to users in a timely manner has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] In view of this, an embodiment of the present application provides a processing method and device.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides a processing method, including:

[0006] In response to the deletion instruction, deleting the indicated object indicated by the deletion instruction;

[0007] In response to the delete instruction, obtaining a target parameter;

[0008] If the target parameter meets the trigger condition, the target object is obtained by processing the associated objects associated with the indicated object based on the target model.

[0009] In a second aspect, an embodiment of the present application provides a processing device, including:

[0010] A deletion module, configured to delete the indicated object indicated by the deletion instruction in response to the deletion instruction;

[0011] An acquisition module, used for obtaining target parameters in response to a deletion instruction;

[0012] The processing module is used to obtain the target object by processing the associated object associated with the indicated object based on the target model if the target parameter meets the trigger condition.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the above method is implemented when the processor executes the program.

[0014] In a fourth aspect, an embodiment of the present application provides a storage medium storing executable instructions for implementing the above method when executed by a processor.

[0015] In a fifth aspect, a computer program product includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the steps in the above method are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an implementation flow of a processing method provided in an embodiment of the present application;

[0017] Figure 2A A schematic diagram of a text input interface provided in an embodiment of the present application;

[0018] Figure 2B A schematic diagram of generating a target object provided in an embodiment of the present application;

[0019] Figure 2C A schematic diagram of generating a target object provided in an embodiment of the present application;

[0020] Figure 3 A schematic diagram of a process of polishing a text provided in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of a process for updating a record table provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the structure of a processing device provided in an embodiment of the present application;

[0023] Figure 6 A hardware entity schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the specific technical solution of the embodiments of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0025] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0026] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0028] The present application embodiment provides a processing method, such as Figure 1 As shown, the method includes:

[0029] Step S110, in response to the deletion instruction, deleting the indicated object indicated by the deletion instruction;

[0030] Here, the deletion instruction refers to an instruction or command for removing data or an object from a text file, an image file, or a voice file.

[0031] The indication object includes at least one of the following: a text object, an image object and a voice object.

[0032] Here, the text object may be text input by the user. For example, the indication object may be a word, phrase or paragraph deleted by the user on a chat page or a text editing page.

[0033] The image object may be a photo edited by a user. For example, the reference object of the image object may be a beautification effect on a certain part (such as a face or a body) deleted by the user in the photo.

[0034] The voice object may be a voice file recorded by the user. For example, the reference object of the voice object may be a voice segment deleted by the user in the voice file.

[0035] In some embodiments, the indicated object may also be a video object. Here, there is no restriction on the category of the indicated object, and any object that can be edited by the user may be used as the indicated object.

[0036] During implementation, the electronic device can monitor the delete command triggered by the user in real time to delete the corresponding indicated object based on the delete command. For example, when the user is editing text, the delete key can be monitored, and when it is determined that the user triggers the delete key, the corresponding indicated text is deleted.

[0037] Step S120, in response to the deletion instruction, obtaining target parameters;

[0038] Here, the target parameter is obtained based on the delete instruction.

[0039] In some embodiments, the target parameter may be a counted number of times the delete instruction is executed.

[0040] In some embodiments, the target parameter may also be attribute information of the deleted indication object, including the content of the indication object, the location information of the indication object, and whether the indication object is deleted from the same indication object.

[0041] In some embodiments, the target parameter may also be a statistical time interval between multiple deletion indication objects.

[0042] Step S130: If the target parameter meets the trigger condition, the associated object associated with the indicated object is processed based on the target model to obtain the target object.

[0043] Here, the corresponding trigger condition can be determined according to the target parameter. For example, when the target parameter is the number of times the deletion instruction is executed, the trigger condition can be set to the number threshold, that is, to determine whether the number of deletions reaches the number threshold. When the target parameter is to determine the content of the indicated object, the trigger condition can be set to the matching preset content, that is, to determine whether the content of the indicated object matches the preset content. When the target parameter is the time interval between multiple deletions of the indicated object, the trigger condition can be set to the preset duration, that is, to determine whether the time interval between multiple deletions of the indicated object meets the preset duration.

[0044] The associated object associated with the indicated object may be the environment information of the indicated object. For example, when the indicated object is a word deleted in text editing, the associated object may be the sentence, paragraph or article where the word is located; when the indicated object is a beautification effect on a certain part deleted in image editing, the associated object may be the certain part and the background where the certain part is located; when the indicated object is a certain voice paragraph deleted in a voice file, the associated object may be the voice paragraphs above and below the voice paragraph.

[0045] The target object is obtained by processing the associated object associated with the indicated object using the target model. For example, when the associated object is a sentence, paragraph or article where the deleted word is located, the target object can be processed by the language model to obtain a sentence, paragraph or article that has been polished based on the input deleted word and the sentence, paragraph or article where the deleted word is located. Among them, the model that can achieve text polishing can use natural language processing (Natural Language Processing, NLP) technology to optimize the quality, readability and expression of the text. Including the GPT series of models, it provides a deep understanding and generation capability of language processing, and can generate fluent, coherent and logical text. The Natural Language Generation (NLG) model can automatically convert structured data (such as information in a database) into natural language text. The Python-based AI text polishing tool can automatically proofread, grammar check, spelling correction, etc. of the input text, and perform structural optimization, keyword optimization and style unification on the article. When the specific tasks of text polishing are clear, such as recommending appropriate words, correcting grammar, checking spelling, improving language fluency, and unifying style, different model structures and training strategies can be designed according to different tasks to train a model for text polishing.

[0046] In the case where the associated object is a part and the background where the part is located, the target object can be processed by the image processing model, and the beautification effect for a certain part, the part, and the background where the part is located based on the input is obtained, and the beautified part or image is output. In the case where the associated object is the upper and lower paragraphs of the deleted speech paragraph, the target object can be processed by the speech processing model, and the speech file of the deleted speech paragraph and the upper and lower paragraphs of the deleted speech paragraph is output based on the input.

[0047] In some embodiments, the above trigger conditions may be combined to set multiple trigger conditions, so that when the target parameters meet the trigger conditions, the target object is obtained by processing the associated objects associated with the indicated object based on the target model.

[0048] In the embodiment of the present application, in response to a delete instruction, the indicated object indicated by the delete instruction is deleted; in response to the delete instruction, a target parameter is obtained; if the target parameter satisfies the trigger condition, the associated object associated with the indicated object is processed based on the target model to obtain the target object. In this way, when it is determined that a delete operation is to be performed, and the target parameter obtained based on the delete operation satisfies the trigger condition, the target model is automatically triggered to process the associated object associated with the indicated object to obtain the target object, thereby providing more target objects for the user to choose from for the delete operation, solving the problem that the user repeatedly deletes the indicated object but cannot obtain a satisfactory target object.

[0049] In some embodiments, the above step S120 "obtaining target parameters in response to the deletion instruction" can be implemented by the following steps:

[0050] Step 121, in response to the deletion instruction, accumulating the number of deletions of the indicated object;

[0051] During the implementation process, each time the electronic device monitors a deletion instruction, it accumulates the number of deletions last time to obtain the number of deletions of the indicated object by the user.

[0052] In some embodiments, the monitoring is for deletion instructions, so the accumulated number may be the number of deletions of different indicated objects. For example, when a user is editing a text, he can delete words at different positions, and the monitoring may be the deletion operations of words at multiple different positions.

[0053] Figure 2A A schematic diagram of a text input interface provided in an embodiment of the present application, such as Figure 2A As shown, the schematic diagram includes: a text input box 21, wherein:

[0054] In some embodiments, the text input box inputs the text "West Lake Park is like a pearl embellishing the garden city of Fuzhou. It is a beautiful scenery that makes me linger all year round. It is both an unforgettable memory of Fuzhou people growing up together and my happy world." If, based on the deletion instruction, it is determined to delete "linger", the number of deletions of "linger" in the text can be accumulated.

[0055] In some embodiments, the user may perform a deletion operation on "linger", "unforgettable memories" or "happy", and the number of deletions counted is the number of deletions of all deleted words.

[0056] Correspondingly, in the above step S130, the target parameter meets the trigger condition, which can be achieved by the following steps:

[0057] Step S140: When it is determined that the number of deletions is greater than or equal to the number threshold, it is determined that the trigger condition is satisfied.

[0058] During implementation, the number threshold may be set according to actual conditions. For example, the number threshold may be set to 3. When it is determined that the number of deletions reaches 3 or more, it is determined that the trigger condition is met.

[0059] In the embodiment of the present application, in response to the deletion instruction, the number of deletions of the indicated object is accumulated; when it is determined that the number of deletions is greater than or equal to the number threshold, it is determined that the trigger condition is met. In this way, it is possible to use the accumulated number of deletions to determine whether the trigger condition is met, so that when the number of deletions reaches the preset number, the target object is obtained by processing the associated object associated with the indicated object using the target object model.

[0060] In some embodiments, "determining that the number of deletions is greater than or equal to the number threshold" in the above step S140 can be implemented by the following steps:

[0061] Step 141, obtaining a preset duration;

[0062] Here, the preset time length can be preset. For example, the preset time length can be set to 10 seconds.

[0063] Step 142: Determine whether the number of deletions executed within the preset time period is greater than or equal to the number threshold.

[0064] During implementation, if the number of deletions is greater than or equal to the number threshold within a preset time period, it can be determined that the user has repeatedly considered the indicated object within the preset time period and cannot determine a suitable indicated object. For example, when the user is editing text, if the deletion operation is performed more than 3 times within 10 seconds, it can be determined that the trigger condition is met.

[0065] In the embodiment of the present application, a preset duration is obtained; and it is determined that the number of deletions executed within the preset duration is greater than or equal to the number threshold. In this way, it can be determined that the trigger condition is met when the user repeatedly deletes within the preset duration, so as to further recommend a more suitable indicated object to the user.

[0066] In some embodiments, the above step 121 "accumulating the number of deletions of the indicated object in response to the deletion instruction" can be implemented by the following steps:

[0067] Step 1211, in response to the deletion instruction, obtaining first input information corresponding to the indicated object before being deleted, and second input information corresponding to the indicated object after being deleted;

[0068] Here, the first input information is information before the indicated object is deleted. For example, when the indicated object is a deleted word, the first input information is a sentence in which the word is not deleted.

[0069] The second input information is information after the indicated object is deleted. For example, when the indicated object is a deleted word, the second input information is a sentence in which the word has been deleted.

[0070] During the implementation process, the first input information corresponding to the indicated object before being deleted and the second input information corresponding to the indicated object after being deleted may be obtained.

[0071] Step 1212: Compare the second input information with the first input information to determine the target position of the indicated object;

[0072] Since the difference between the second input information and the first input information lies in the deleted indication object, the target position of the indication object in the first input information can be determined by comparing the second input information with the first input information. For example, when the indication object is a deleted word, the target position is the position of the deleted word in the sentence.

[0073] Step 1213: Count the number of deletions performed at the target location.

[0074] In the embodiment of the present application, first, in response to the deletion instruction, the first input information corresponding to the indicated object before being deleted and the second input information corresponding to the indicated object after being deleted are obtained; then, the second input information is compared with the first input information to determine the target position of the indicated object; finally, the number of deletions performed at the target position is accumulated. In this way, the number of deletions of the indicated object deleted at the same position can be obtained.

[0075] In some embodiments, the above step S130 of "processing the associated object associated with the indicating object based on the target model to obtain the target object" can be implemented by the following steps:

[0076] Step 131: determine multiple indicating objects corresponding to multiple deletion operations as the associated objects;

[0077] Here, the associated object can be different indicated objects deleted at the same target position. For example, when the user inputs text information, he can repeatedly consider the words at the same position and perform a deletion operation, and the deleted unsatisfactory words are used as associated objects.

[0078] Step 132: Use the target model to process the multiple indicated objects to obtain the target object.

[0079] During the implementation, the target model can be used to process the associated object to obtain the target object. For example, the language model can be used to recommend similar words to the deleted unsatisfactory words to obtain other words with the same pronunciation as the unsatisfactory words.

[0080] In the embodiment of the present application, multiple indicating objects corresponding to multiple deletion operations are determined as associated objects, and the multiple indicating objects are processed using the target model to obtain the target object. In this way, it is possible to process the indicating objects repeatedly deleted by the user to obtain the target object.

[0081] In some embodiments, the above step S130 of "processing the associated object associated with the indicating object based on the target model to obtain the target object" can be implemented by the following steps:

[0082] Step 133: determine the first input information corresponding to the indicated object before being deleted and / or the second input information corresponding to the indicated object after being deleted as the associated object;

[0083] For example, the sentence before and after the deletion in which the deleted word is located may be taken as the associated objects.

[0084] Step 134: Use the target model to process the first output information and / or the second input information to obtain the target object.

[0085] For example, the sentence before and after the deletion of the deleted word may be input into a language processing model to obtain processed sentences, so as to recommend sentences that are more suitable for the semantic environment to the user.

[0086] Figure 2B A schematic diagram of generating a target object provided in an embodiment of the present application is as follows: Figure 2B As shown, the schematic diagram includes a text editing box 21 and an AI polished text 22, wherein:

[0087] The text "West Lake Park is like a pearl embellishing the garden city of Fuzhou. It is a beautiful sight that makes me linger all year round. It is not only an unforgettable memory of Fuzhou people growing up together, but also my happy world" is entered in the text editing box 21.

[0088] During the implementation process, based on the sentence containing the word "linger and forget to return" that the user has repeatedly deleted, the AI ​​polished text "This scenery changes with the seasons, and I am intoxicated by it and I don't want to leave for a long time" can be output for the user to confirm whether to modify it.

[0089] For example, the entire text containing the deleted words can be input into the language processing model to obtain the completed processing as a whole, so as to recommend sentences that are more suitable for the semantic environment to the user.

[0090] Figure 2C A schematic diagram of generating a target object is provided for an embodiment of the present application, such as Figure 2C As shown, the schematic diagram includes a text editing box 21 and an AI polished text 23, wherein:

[0091] The text "West Lake Park is like a pearl embellishing the garden city of Fuzhou. It is a beautiful sight that makes me linger all year round. It is not only an unforgettable memory of Fuzhou people growing up together, but also my happy world" is entered in the text editing box 21.

[0092] During the implementation process, based on the repeatedly deleted words “linger”, “city garden”, “unforgettable” and “happy” by the user, an AI polished text 23 of an entire input text can be output. “West Lake Park is like a shining pearl inlaid in the garden city of Fuzhou, shining brightly. It is not just a landscape, but also a never-fading painting in the changing seasons. Every time I visit it, I am intoxicated and reluctant to leave. This place not only carries the warm memories of the common growth of the people of Fuzhou, but every frame of the picture is engraved with the mark of time, becoming an indelible and precious memory in my heart; at the same time, it is also a safe haven for my soul, a world full of laughter, happiness and freedom. Here, the changing of the seasons is like a symphony of nature, playing a beautiful and moving hymn, making every moment seem so precious and unforgettable.” For the user to confirm whether to replace the entire text.

[0093] In the embodiment of the present application, the first input information corresponding to the indicated object before being deleted and / or the second input information corresponding to the indicated object after being deleted are determined as associated objects; the first output information and / or the second input information are processed using the target model to obtain the target object. In this way, the environment information where the indicated object is located can be used to input the target model for processing to obtain a target object that better conforms to the environment information.

[0094] In some embodiments, the above step S130 of "processing the associated object associated with the indicating object based on the target model to obtain the target object" can be implemented by the following steps:

[0095] Step 135: obtaining user information of the target object, wherein the user information includes at least one of the following information: gender information, age information, and identity information;

[0096] In the implementation process, the user information can be determined by using the information input by the user, or the information of the text reading object of the text editing software can be obtained as the user information. For example, the information of the text message, message or multimedia message sending object can be used as the user information.

[0097] Step 136: Based on the user information, use the target model to process the associated object associated with the indicated object to obtain the target object.

[0098] During the implementation process, user information can also be input into the target model to obtain a target object that is more consistent with the user information.

[0099] In the embodiment of the present application, the user information of the target object is first obtained, and then based on the user information, the target object is obtained by processing the associated object associated with the indicated object using the target model. In this way, the user information can be input into the target model to obtain a target object that better matches the user information.

[0100] In some embodiments, the above processing method further includes the following steps:

[0101] Step 150: display the target object to obtain an instruction on whether to adopt the target object;

[0102] In the implementation process, after obtaining the target object, the target object can be displayed on the user's editing interface, and the user's instruction on whether to adopt the target object can be obtained. For example, the recommended words can be displayed on the user's text editing interface, and the user's instruction on whether to adopt the recommended words can be obtained.

[0103] Step 160: In response to the adoption instruction, determine the target object;

[0104] During the implementation process, the user's adoption instruction can be obtained to determine the target object. For example, when the user determines the recommended word, the recommended word can be filled in the deleted position.

[0105] Step 170: In response to not adopting the instruction, the associated object associated with the indicating object is processed using the target model based on the target object to obtain the target object again.

[0106] In the implementation process, if the user does not approve the target object triggering the non-adoption instruction, the target model can be used to process the associated objects associated with the indicated object based on the target object to obtain the target object again. For example, if the user does not use the recommended word, the recommended word and the deleted word can be input into the voice model to obtain a new recommended word.

[0107] In the embodiment of the present application, the target object is displayed to obtain an instruction on whether to adopt the target object; in response to the instruction to adopt, the target object is determined; in response to the instruction not to adopt, the associated objects associated with the indicated object are processed based on the target object using the target model to obtain the target object again. In this way, the user interaction function can be realized to enable the user to determine whether the target object needs to be adopted, and in the case that the user is not satisfied with the target object, an updated target object is output, providing the user with a variety of different recommendation solutions.

[0108] Figure 3 A flowchart of a text polishing process provided in an embodiment of the present application is as follows: Figure 3 As shown, this can be achieved by following the steps below:

[0109] Step S300, receiving a text input and recording it as a first input text, wherein the length of the first input text is a first length;

[0110] The text obtained in the input box is recorded as the first input text (Input), and the number of characters in the text Input is recorded as the first length (length1);

[0111] Step S310, determining whether the first length is greater than a preset length;

[0112] During the implementation process, the trigger start condition can be set according to actual needs: the length of the input box text, i.e., length1, is greater than the set value, such as 30 characters.

[0113] If it is determined that the first length is greater than the preset length, step S330 is executed; if it is determined that the first length is less than or equal to the preset length, step S320 is executed.

[0114] Step S320, temporarily storing the first input text as basic target data;

[0115] When the trigger condition is met, the content of the input box Input is temporarily saved as Temp, and the number of characters is recorded as lengthT.

[0116] Step S330, continue to receive text input, when the length of the text input changes, the changed text length is the second length;

[0117] When the user continues to operate the input box, the content Input in the input box after the operation is obtained, and the number of characters is updated to the second length.

[0118] Step S340, determining whether the second length is less than the first length;

[0119] If it is determined that the second length is less than the first length, step S360 is executed; if it is determined that the second length is greater than or equal to the first length, step S350 is executed.

[0120] Step S350, determining to add text;

[0121] If the second length is greater than or equal to the first length, it is recorded that the user input action is to add text, and no operation is performed, and the system continues to wait for user operation.

[0122] Step S360: Determine the deletion operation;

[0123] If it is determined that the second length is less than the first length, it is considered that the user has performed a deletion operation, and the text content temp before the deletion is saved in the source text (source) of the record table as input data for the artificial intelligence (AI) model.

[0124] Step S370, determining whether the specific source text in the record table has reached a set number;

[0125] During the implementation, step S340 may be continued to determine whether the second length is less than the first length. If the number of times identified as the deletion action in step S340 is a specified value, such as 3 times, that is, there are 3 data in the record table source, step S380 is executed.

[0126] Step S380: input the source text into the AI ​​model;

[0127] During the implementation process, the source record table is input into the AI ​​text model, and the AI ​​text model generates one or more polished text contents based on the three input data.

[0128] Step S390: The AI ​​text model polishes the content of the source text input and outputs it, prompting the user at an appropriate location on the device.

[0129] After the text polishing is completed, a polished text will be displayed on the interface first. When the user selects AI polishing, the page can be jumped to display the entire content of AI text polishing in detail.

[0130] In an embodiment of the present application, an AI model processing method is provided for when it is determined that a text has been deleted multiple times. The method can realize the function of automatically triggering the AI ​​model to polish the text when it is determined that a user has deleted multiple times while editing the text.

[0131] Figure 4 A schematic diagram of a process for updating a record table provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, this can be achieved by following the steps below:

[0132] Step S410, determining whether the input text has changed;

[0133] Step S420, comparing the changes of the first input text and the second input text to determine the position information of the text modification;

[0134] Step S430, using the position information as a reference and punctuation as a way to determine the start and end of a sentence, determining a target sentence to be modified in the first input text and the second input text, corresponding to the first sentence and the second sentence;

[0135] Here, the target sentence corresponds to the first sentence (Target1) in the first input text and corresponds to the second sentence (Target2) in the second input text.

[0136] Step S440, determining whether the second sentence is longer than the first sentence;

[0137] When it is determined that the second sentence is longer than the first sentence, it can be determined that the user is adding text, and step S450 is executed; when it is determined that the second sentence is shorter than the first sentence, it can be determined that the user is deleting text, and step S460 is executed.

[0138] Step S450, determining whether to update the record table;

[0139] Here, the record table is used to record the update information of the sentence. The first column of the record table is used to record the update information of the current sentence (Current) 1. The current sentence 1 is a sentence with a recorded deletion operation. The second column of the record table is used to record the update information of the current sentence (Current) 2. The current sentence 2 is another sentence with a recorded deletion operation that is different from the current sentence 1.

[0140] Source sentence (Source) 11 and source sentence (Source) 12 are the historical editing information of current sentence (Current) 1.

[0141] Source sentence (Source) 21 and source sentence (Source) 22 are the historical editing information of current sentence (Current) 2.

[0142] In the implementation process, Target1 can be matched with all source sentences (Source) and current sentences (Current) in the record table (Table). If they match, it means that the first sentence has been modified, and if not, it means that the first sentence has not been modified before.

[0143] Determine whether the first sentence has been modified. If so, update the corresponding current sentence record in the Table. Otherwise, do nothing.

[0144] Step S460: Add or update the record table.

[0145] The operation of updating the record table is: determine if the first sentence has been modified, and update the corresponding modification Current in Table to the second sentence. Determine whether the last modification in Source has been modified from the first sentence. If so, add Source as the first sentence. Otherwise, do not add Source.

[0146] The operation of adding a new column to the record table is: determine that the first sentence has not been modified, add a new entry to the Table, Current is Target2, and Source is Target1.

[0147] In the embodiment of the present application, a method is provided for using a record table to record sentences with deletion operations in the input text, the number of times a word in each sentence is deleted, and the historical information of the deletions when it is determined that the input text has changed. The record table can be further used to automatically trigger the AI ​​model to polish the sentence when it is determined that a word in a sentence has been deleted multiple times.

[0148] Based on the foregoing embodiments, the embodiments of the present application provide a processing device, which includes the modules included, each module includes each sub-module, each sub-module includes a unit, which can be implemented by a processor in an electronic device; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0149] Figure 5 A schematic diagram of the structure of the processing device provided in the embodiment of the present application is shown in FIG. Figure 5 As shown, the device 500 includes:

[0150] A deletion module 510, configured to delete the indicated object indicated by the deletion instruction in response to the deletion instruction;

[0151] An acquisition module 520, configured to obtain target parameters in response to the deletion instruction;

[0152] The processing module 530 is used to process the associated object associated with the indicating object based on the target model to obtain the target object if the target parameter meets the trigger condition.

[0153] In some embodiments, the acquisition module 520 is also used to accumulate the number of deletions of the indicated object in response to the deletion instruction; correspondingly, the processing device also includes a first determination module, which is used to determine that the trigger condition is met when the number of deletions is greater than or equal to a number threshold.

[0154] In some embodiments, the determination module includes a first acquisition submodule and a first determination submodule, wherein the acquisition submodule is used to acquire a preset duration; and the determination submodule is used to determine whether the number of deletions executed within the preset duration is greater than or equal to the number threshold.

[0155] In some embodiments, the acquisition module 520 includes a second acquisition submodule, a comparison submodule and an accumulation submodule, wherein the second acquisition submodule is used to respond to the deletion instruction to obtain the first input information corresponding to the indicated object before it is deleted, and the second input information corresponding to the indicated object after it is deleted; the comparison submodule is used to compare the second input information with the first input information to determine the target position of the indicated object; the accumulation submodule is used to accumulate the number of deletions performed at the target position.

[0156] In some embodiments, the processing module 530 includes a second determination submodule and a first processing submodule, wherein the second determination submodule is used to determine multiple indication objects corresponding to multiple deletion operations as the associated objects; and the first processing submodule is used to use the target model to process the multiple indication objects to obtain the target object.

[0157] In some embodiments, the processing module 530 includes a third determination submodule and a second processing submodule, wherein the third determination submodule is used to determine the first input information corresponding to the indicated object before deletion and / or the second input information corresponding to the indicated object after deletion as the associated object; and the second processing submodule is used to use the target model to process the first output information and / or the second input information to obtain the target object.

[0158] In some embodiments, the processing module 530 includes a second acquisition submodule and a third processing submodule, wherein the second acquisition submodule is used to acquire user information for operating the target object, and the user information includes at least one of the following information: gender information, age information and identity information; the third processing submodule is used to obtain the target object by processing the associated object associated with the indicated object using the target model based on the user information.

[0159] In some embodiments, the indication object includes at least one of the following: a text object, an image object, and a voice object.

[0160] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0161] It should be noted that in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable an electronic device (which can be a mobile phone, a tablet computer, a laptop computer, a desktop computer, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0162] Correspondingly, an embodiment of the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the processing method provided in the above embodiment are implemented.

[0163] Correspondingly, an embodiment of the present application provides an electronic device, Figure 6 A hardware entity diagram of an electronic device provided in an embodiment of the present application, such as Figure 6 As shown, the hardware entity of the device 600 includes: a memory 601 and a processor 602, wherein the memory 601 stores a computer program that can be run on the processor 602, and the processor 602 implements the steps in the processing method provided in the above embodiment when executing the program.

[0164] The memory 601 is configured to store instructions and applications executable by the processor 602, and can also cache data to be processed or processed by the processor 602 and various modules in the electronic device 600 (for example, image data, audio data, voice communication data, and video communication data), which can be implemented through flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0165] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0166] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0167] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0169] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0170] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0171] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0172] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including several instructions to enable an electronic device (which can be a mobile phone, a tablet computer, a laptop computer, a desktop computer, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0173] The methods disclosed in several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0174] The features disclosed in several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0175] The features disclosed in several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0176] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A processing method, the method comprising: In response to a deletion instruction, deleting the indicated object indicated by the deletion instruction; In response to the deletion instruction, obtaining a target parameter; If the target parameter meets the trigger condition, the associated object associated with the indicated object is processed based on the target model to obtain the target object.

2. The method of claim 1, wherein in response to the deletion instruction, obtaining the target parameter comprises: In response to the deletion instruction, accumulating the number of deletions of the indicated object; Correspondingly, the target parameter satisfies the triggering condition, including: When it is determined that the number of deletions is greater than or equal to the number threshold, it is determined that the trigger condition is met.

3. The method according to claim 2, wherein determining that the number of deletions is greater than or equal to a number threshold comprises: Get the preset duration; Determine whether the number of deletions executed within the preset time period is greater than or equal to the number threshold.

4. The method of claim 2, wherein in response to the deletion instruction, accumulating the number of deletions of the indicated object comprises: In response to the deletion instruction, obtaining first input information corresponding to the indicated object before being deleted and second input information corresponding to the indicated object after being deleted; comparing the second input information with the first input information to determine a target position of the indicated object; Cumulative number of deletions performed at the target location.

5. The method according to any one of claims 1 to 4, wherein the step of processing the associated object associated with the indicating object based on the target model to obtain the target object comprises: Determine multiple indication objects corresponding to multiple deletion operations as the associated objects; The target model is used to process the multiple indicated objects to obtain the target object.

6. The method according to any one of claims 1 to 4, wherein the step of processing the associated object associated with the indicating object based on the target model to obtain the target object comprises: Determine the first input information corresponding to the indicated object before being deleted and / or the second input information corresponding to the indicated object after being deleted as the associated object; The first output information and / or the second input information is processed using the target model to obtain the target object.

7. The method according to any one of claims 1 to 4, wherein the step of processing the associated object associated with the indicating object based on the target model to obtain the target object comprises: Acquire user information of the target object, wherein the user information includes at least one of the following information: gender information, age information, and identity information; Based on the user information, the associated object associated with the indicated object is processed using a target model to obtain a target object.

8. The method according to any one of claims 1 to 4, further comprising: Displaying the target object to obtain an instruction on whether to adopt the target object; In response to the adoption instruction, determining the target object; In response to not adopting the instruction, the associated object associated with the indicating object is processed by using the target model based on the target object to obtain the target object again.

9. The method according to any one of claims 1 to 4, wherein the indication object comprises at least one of the following: a text object, an image object and a voice object.

10. A processing device, comprising: A deletion module, configured to delete the indicated object indicated by the deletion instruction in response to the deletion instruction; An acquisition module, used for obtaining target parameters in response to the deletion instruction; The processing module is used for processing the associated object associated with the indicating object based on the target model to obtain the target object if the target parameter meets the trigger condition.

Images