Processing method and electronic equipment

Abstract

The invention discloses a processing method and electronic equipment. The processing method comprises the following steps: acquiring first input information of a user; based on the first input information, screening a target cue word from a cue word library; inputting the first input information and the target cue word into a target model to obtain first output information; wherein the processing operation executed by the user on the first output information can update the prompt word bank, and the processing operation can represent the user portrait of the user.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and particularly to a processing method and an electronic device. Background Art

[0002] With the rapid development of large models, more and more electronic devices integrate large models to assist users in completing related tasks such as text generation, summarization, and polishing. However, due to the fixed current large models and related parameters used by the large models, the generated text content is relatively single in terms of structure, style, writing style, word usage, etc., and cannot meet the personalized needs of users. Therefore, users need to manually modify the text content output by the large model to obtain the desired text content.

[0003] Therefore, how to use large models to output the text content desired by users has become an urgent problem to be solved. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a processing method and an electronic device.

[0005] In a first aspect, the embodiments of this application provide a processing method, including:

[0006] Obtain the first input information of the user;

[0007] Based on the first input information, screen target prompt words from the prompt word library;

[0008] Input the first input information and the target prompt words into the target model to obtain the first output information;

[0009] Wherein, the processing operation performed by the user on the first output information can update the prompt word library, and the processing operation can characterize the user profile of this user.

[0010] In a possible implementation manner, after obtaining the first output information, it further includes:

[0011] Monitor the processing operation performed by the user on the first output information;

[0012] Based on the processing operation, determine the second output information;

[0013] Based on the first output information and the second output information, update the prompt word library.

[0014] In a possible implementation manner, the updating the prompt word library based on the first output information and the second output information includes:

[0015] Compare the first output information with the second output information to obtain difference information; wherein, the difference information includes at least one of the following: architectural differences, syntactic differences, and lexical usage differences between the first output information and the second output information;

[0016] Update the prompt word library based on the difference information.

[0017] In a possible implementation manner, the updating the prompt word library based on the difference information includes:

[0018] Determine whether the difference information meets the update condition; wherein, the update condition includes that the proportion of the difference information in the first output information is greater than a threshold, or the difference information includes a target difference, and the target difference is determined based on the user profile;

[0019] If it meets the condition, update the prompt word library based on the difference information.

[0020] In a possible implementation manner, the comparing the first output information with the second output information to obtain difference information includes:

[0021] Determine the text length of the first output information or the second output information;

[0022] When the text length is greater than or equal to a preset length, sequentially determine the architectural differences, syntactic differences, and lexical usage differences between the first output information and the second output information;

[0023] When the text length is less than the preset length, determine the lexical usage differences between the first output information and the second output information.

[0024] In a possible implementation manner, the determining the second output information based on the processing operation includes:

[0025] Obtain the response interface obtained in response to the processing operation;

[0026] Extract the second output information based on the response interface; or

[0027] Obtain the instruction generated by the input device for executing the processing operation;

[0028] Obtain the second output information based on the instruction and the first output information.

[0029] In a possible implementation manner, the processing operation performed by the user on the first output information includes at least one of the following: copy, paste, delete, and modify.

[0030] In a possible implementation, monitoring the processing operations performed by the user on the first output information includes:

[0031] Monitoring the interface information and / or instruction information of the electronic device;

[0032] Based on the interface information and / or the instruction information, determining the processing operations performed by the user on the first output information;

[0033] Wherein, the interface information at least includes the position of the mouse pointer in the interface and the position of the first output information in the interface; the object of the instruction information is the first output information, and the instruction information is generated based on the input device.

[0034] In a possible implementation, the target model is located in the cloud or the user terminal.

[0035] In a second aspect, an embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory. When the electronic device runs, the processor executes the following steps in the computer program:

[0036] Obtaining the first input information of the user;

[0037] Based on the first input information, screening target prompt words from the prompt word library;

[0038] Inputting the first input information and the target prompt words into the target model to obtain the first output information;

[0039] Wherein, the processing operations performed by the user on the first output information can update the prompt word library, and the processing operations can characterize the user profile of the user.

[0040] The embodiment of the present application uses the target model to process the first input information and the target prompt words screened from the prompt word library to obtain the first output information. Moreover, the processing operations performed by the user on the first output information can update the prompt word library, so that the target model can use the updated prompt word library to generate output information that conforms to the user profile, that is, the target model can use the updated prompt word library to meet the user's requirements for the output information; and, without changing the model structure of the target model, that is, ensuring the stability of the target model. Description of the Drawings

[0041] To more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 The flowchart of a processing method provided by the present application is shown;

[0043] Figure 2 The flowchart of the method for updating the prompt word library by using the processing operation performed by the user on the first output information in a processing method provided by the present application is shown;

[0044] Figure 3 The flowchart of the method for obtaining the difference information in a processing method provided by the present application is shown;

[0045] Figure 4 The structural schematic diagram of a processing device provided by the present application is shown;

[0046] Figure 5 The structural schematic diagram of an electronic device provided by the present application is shown. Detailed implementation manners

[0047] The various solutions and features of the present application are described herein with reference to the accompanying drawings.

[0048] It should be understood that various modifications can be made to the embodiments applied herein. Therefore, the above description should not be regarded as a limitation, but only as an example of the embodiments. Those skilled in the art will think of other modifications within the scope and spirit of the present application.

[0049] The accompanying drawings included in the specification and constituting a part of the specification show the embodiments of the present application, and are used to explain the principles of the present application together with the general description of the present application given above and the detailed description of the embodiments given below.

[0050] By the following description of the preferred forms of the embodiments given as non-limiting examples with reference to the accompanying drawings, these and other features of the present application will become apparent.

[0051] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art can surely implement many other equivalent forms of the present application, which have the features as described in the claims and thus are all within the protection scope defined hereby.

[0052] When combined with the accompanying drawings, the above and other aspects, features, and advantages of the present application will become more apparent in view of the following detailed description.

[0053] Specific embodiments of the present application will be described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments claimed are merely examples of the present application, which can be implemented in various ways. Well-known and / or repetitive functions and structures are not described in detail to avoid obscuring the present application with unnecessary or redundant details. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but rather are merely a basis and representative basis for the claims to teach those skilled in the art to use the present application in substantially any suitable detailed structure in a variety of ways.

[0054] This specification may use the phrases "in one embodiment", "in another embodiment", "in yet another embodiment", or "in other embodiments", which may each refer to one or more of the same or different embodiments according to the present application.

[0055] For ease of understanding of the present application, a processing method provided by the present application will be introduced in detail first. Figure 1 The flowchart of the processing method provided by the embodiment of the present application is shown, where the specific steps include S101 - S103.

[0056] S101, obtain the first input information of the user.

[0057] Optionally, when the user uses a large model based on an electronic device, the input information is determined through an input device such as a touch screen, a mouse, a keyboard, etc., so that the large model can receive the input information, and then analyze and process the input information to obtain a corresponding output result.

[0058] As an example, the input device associated with the electronic device is monitored in real time to obtain the first input information determined by the user through the input device.

[0059] In yet another example, after obtaining the input information through the input device, it is further determined whether the input information is the first input information. For example, it is determined whether the application program corresponding to the input information is associated with a large model. If the application program corresponding to the input information is associated with a large model, it is determined that the input information is the first input information, and the subsequent S102 and S103 are processed. If the application program corresponding to the input information is not associated with a large model, the subsequent steps of S102 and S103 do not need to be executed. For another example, it is determined whether the input information is located in the target input box. If so, it is determined that the input information is the first input information, where the target input box is associated with the large model, that is, the information in the target input box is used as the input of the large model.

[0060] S102. Based on the first input information, screen the target prompt words from the prompt word library.

[0061] After obtaining the first input information, based on the first input information, screen the target prompt words from the prompt word library. Among them, the prompt words in the prompt word library are generated based on the corresponding historical information of the user, and the historical information includes at least one of the following: the historical input information determined by the user, the historical output information, and other text information determined by the user through other platforms, applications, etc. It should be noted that when the user uses the prompt word library for the first time, the prompt words in the prompt word library can include general prompt words, etc.

[0062] Optionally, there can be one or more prompt word libraries. In the scenario where there is one prompt word library, the prompt word library can be applicable to different large models; in the scenario where there are multiple prompt word libraries, each prompt word library can correspond to a different large model respectively, and the prompt words included in different prompt word libraries are different.

[0063] After determining the first input information, the large model currently called can be determined according to the first input information, and then the corresponding prompt word library can be determined, so as to screen the target prompt words from the prompt word library based on the first input information.

[0064] S103. Input the first input information and the target prompt words into the target model to obtain the first output information.

[0065] After screening the target prompt words, input the first input information and the target prompt words into the target model to obtain the first output information. Among them, the target model is the model used to process and analyze the first output information. Among them, both the first input information and the first output information are text information.

[0066] Here, the electronic device can be associated with one or more large models. For example, different applications correspond to different large models, and the electronic device itself is configured with a system-level large model, etc. Moreover, the large model can be directly configured on the electronic device or can be configured in the cloud, and the cloud can communicate with the electronic device. That is to say, the target model is located in the cloud or the user terminal. In the scenario where the target model is located in the cloud, for the same target model, different prompt word libraries are configured for different users, and there is an association relationship between the user and the corresponding prompt word library.

[0067] Among them, after the target model outputs the first output information, it can be displayed to the user. After that, the user can perform a processing operation on the first output information according to the requirement, so that the processed first output information meets the requirement. Correspondingly, the processing operation performed by the user on the first output information can characterize the user portrait of the user.

[0068] Here, the processing operation performed by the user on the first output information can update the prompt word library, so that the target model can use the updated prompt word library to generate output information that conforms to the user profile, that is, the target model can use the updated prompt word library to meet the user's requirements for the output information; moreover, without changing the model structure of the target model, that is, ensuring the stability of the target model.

[0069] As an example, Figure 2 The flowchart of the method for updating the prompt word library by using the processing operation performed by the user on the first output information is shown, where the specific steps include S201 - S203.

[0070] S201, monitor the processing operation performed by the user on the first output information.

[0071] S202, determine the second output information based on the processing operation.

[0072] S203, update the prompt word library based on the first output information and the second output information.

[0073] After obtaining the first output information, monitor the processing operation performed by the user on the first output information. Among them, the processing operation performed by the user on the first output information includes at least one of the following: copy, paste, delete, and modify.

[0074] Optionally, when monitoring the processing operation performed by the user on the first output information, the interface information of the electronic device can be monitored to determine the processing operation performed by the user on the first output information based on the interface information; the instruction information of the electronic device can also be monitored to determine the processing operation performed by the user on the first output information based on the instruction information; the interface information and the instruction information of the electronic device can also be monitored simultaneously, and then based on the interface information and the instruction information, determine the processing operation performed by the user on the first output information.

[0075] Among them, the interface information can be obtained by taking a screenshot of the display interface of the electronic device. The interface information at least includes the position of the mouse pointer in the interface and the position of the first output information in the interface. The instruction information in the embodiments of the present application is generated based on the input device. Based on this, the instruction information can be obtained by obtaining the instructions of the input device, and the object of the instruction information is the first output information.

[0076] For example, when the distance between the position of the mouse pointer included in the interface information and the position of the first output information in the interface is less than a preset distance, it is determined that the user performs a processing operation on the first output information; or, when the movement trajectory formed by the mouse pointer included in consecutive multiple interface information points to the position of the first output information in the interface, it is determined that the user performs a processing operation on the first output information. After the user performs a processing operation on the first output information, two consecutive interface information obtained: the first interface information contains the first output information, and the second interface information does not contain the first output information. At this time, it is characterized that the processing operation performed by the user on the first output information is deletion; two consecutive interface information obtained: the first output information included in the first interface information is at the target position, and the difference between the information at the target position in the second interface information and the first output information is several characters. At this time, it is characterized that the processing operation performed by the user on the first output information is modification.

[0077] For another example, when the input device is a mouse, obtain the instructions transmitted by the mouse. According to the instructions of the mouse, it can be determined how many pixels the cursor has moved on the display interface, whether the cursor has passed through the position where the first output information is located, which button of the mouse is pressed, etc. If the cursor passes through the position where the first output information is located, it can be determined that the user performs a processing operation on the first output information, etc. If the instruction of the mouse is to paste the first output information into the clipboard, it is determined that the processing operation performed by the user on the first output information is copying.

[0078] Further, after determining that the user has performed a processing operation on the first output information, determine the second output information based on the processing operation. As an example, when determining the second output information based on the processing operation, a response interface obtained in response to the processing operation can be obtained, so as to extract the second output information based on the response interface. For example, perform a screenshot processing on the response interface obtained in response to the processing operation to obtain interface information. Then, use text analysis or a language model to extract the second output information from the interface information according to the first output information.

[0079] Among them, in the case where the processing operation is copying or pasting, the second output information is the same as the first output information; in the case where the processing operation is deletion, the second output information is empty; in the case where the processing operation is modification, there are certain differences between the second output information and the first output information, and there is an overlapping area between the area where the second output information is located in the response interface and the area where the first output information is located in the initial interface. The initial interface is the interface where the first output information is located before the response processing operation.

[0080] As another example, when determining the second output information based on a processing operation, instructions generated by an input device for performing the processing operation can also be obtained, so as to obtain the second output information based on the instructions and the first output information. For example, if it is recognized that the instruction generated by the mouse is to delete the characters passed by the cursor in the first output information, at this time, the characters passed by the cursor can be determined and deleted from the first output information, thereby obtaining the second output information.

[0081] In the embodiments of the present application, the second output information is obtained based on the response interface obtained by responding to the processing operation or the instructions generated by the input device for performing the processing operation. This process is implemented by using system-level events and is not restricted by application programs. Therefore, the processing method of the embodiments of the present application does not rely on a single application program and has a wide range of applications.

[0082] After obtaining the second output information, the prompt word library is updated based on the first output information and the second output information. Optionally, when updating the prompt word library based on the first output information and the second output information, the first output information is compared with the second output information to obtain difference information, and the prompt word library is updated based on the difference information. The difference information includes at least one of the following: architectural differences, syntactic differences, and lexical usage differences between the first output information and the second output information.

[0083] As one example, Figure 3 A method flow chart for obtaining difference information is shown, and the specific steps include S301-S303.

[0084] S301, determine the text length of the first output information or the second output information.

[0085] S302, when the text length is greater than or equal to the preset length, sequentially determine the architectural differences, syntactic differences, and lexical usage differences between the first output information and the second output information.

[0086] S303, when the text length is less than the preset length, determine the lexical usage differences between the first output information and the second output information.

[0087] Optionally, when comparing the first output information and the second output information, determine the text length of the first output information or the second output information. For example, determine the number of characters included in the first output information or the second output information.

[0088] Further compare the text length with the preset length. If the text length is greater than or equal to the preset length, it indicates that the first output information or the second output information has a certain structure and grammar. Therefore, successively determine the structural differences, grammatical differences, and lexical usage differences between the first output information and the second output information. Of course, a comparison model can be pre-trained. Input the first output information and the second output information into the comparison model, and the comparison model will analyze and compare the first output information and the second output information, and then obtain the structural differences, grammatical differences, and lexical usage differences between the first output information and the second output information. After that, the comparison model outputs the obtained structural differences, grammatical differences, and lexical usage differences. This scenario is to simultaneously determine the structural differences, grammatical differences, and lexical usage differences between the first output information and the second output information. The embodiments of the present application do not specifically limit the sequence of obtaining the structural differences, grammatical differences, and lexical usage differences, as long as the structural differences, grammatical differences, and lexical usage differences can be obtained.

[0089] In another example, if the text length is less than the preset length, it indicates that the first output information or the second output information may not involve structure and grammar, or the involved structure and grammar cannot represent the user portrait. At this time, only determine the lexical usage differences between the first output information and the second output information.

[0090] By setting different methods for determining difference information according to the text length of the first output information or the second output information, not only can the efficiency of determining difference information be improved, but also the situation of wasting resources when determining difference information can be avoided.

[0091] After obtaining the difference information, update the prompt word library based on the difference information. In a specific implementation, since the degree of difference between the first output information and the second output information may be large or small, when updating the prompt word library based on the difference information, first determine whether the difference information meets the update conditions; if the difference information meets the update conditions, then update the prompt word library based on the difference information.

[0092] Among them, the update conditions include that the proportion of the difference information in the first output information is greater than the threshold, or the difference information includes a target difference, and the target difference is determined based on the user profile. For example, if the text length of the difference information is 10 characters and the text length of the first output information is 20 characters, the proportion of the difference information in the first output information is 50% at this time. This proportion is greater than the threshold of 10%. At this time, it indicates that the degree of modification of the first output information by the user is relatively large. Compared with the first output information, the modified second output information is more in line with the user profile, that is, more in line with the user's needs. At this time, the prompt word library is updated based on the difference information, so that the target model can use the updated prompt word library to meet the user's needs for the output information. For another example, according to the user profile, it can be known that the user pays more attention to the grammar usage when expressing text. Therefore, the grammar difference is determined as the target difference. Then, after determining the difference information between the first output information and the second output information, it is traversed whether the target difference is included in the difference information. If it is included, the prompt word library is updated based on the difference information.

[0093] In another example, if the difference information does not meet the update conditions, that is, the proportion of the difference information in the first output information is less than or equal to the threshold, and the difference information does not include the target difference, at this time, the personal knowledge graph of the user can be updated using the difference information. The personal knowledge graph is pre-constructed and is associated with the user profile.

[0094] When the number of times of updating the personal knowledge graph reaches the preset number of times, the prompt word library is updated using the personal knowledge graph. While ensuring that the prompt word library can be updated in a timely manner, the number of updates is reduced, and problems such as incorrect and repeated prompt words in the prompt word library caused by frequent updates are avoided.

[0095] The present application also provides a processing device corresponding to the processing method. Since the principle of solving problems by the processing device in the present application is similar to the above-mentioned processing method of the present application, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be described again.

[0096] Figure 4 The structural schematic diagram of the processing device provided by the embodiment of the present application is shown, which specifically includes:

[0097] An acquisition module 401, configured to acquire the first input information of the user;

[0098] A screening module 402, configured to screen target prompt words from the prompt word library based on the first input information;

[0099] A obtaining module 403, configured to input the first input information and the target prompt words into the target model to obtain the first output information;

[0100] Among them, the processing operation performed by the user on the first output information can update the prompt word library, and the processing operation can characterize the user portrait of this user.

[0101] An embodiment of the present application provides an electronic device, and the schematic structural diagram of the electronic device can be as Figure 5 shown. The electronic device includes a memory 501, a processor 502, and a computer program stored in the memory 501. When the electronic device runs, the processor 502 executes the steps S11 to S13 in the computer program on the memory 501 as follows:

[0102] S11, obtain the first input information of the user;

[0103] S12, based on the first input information, screen target prompt words from the prompt word library;

[0104] S13, input the first input information and the target prompt words into the target model to obtain the first output information;

[0105] Among them, the processing operation performed by the user on the first output information can update the prompt word library, and the processing operation can characterize the user portrait of this user.

[0106] An embodiment of the present application provides a storage medium, which is a computer-readable medium and stores a computer program. When the computer program is executed by a processor, it implements the method provided in any embodiment of the present application, including the following steps S21 to S23:

[0107] S21, obtain the first input information of the user;

[0108] S22, based on the first input information, screen target prompt words from the prompt word library;

[0109] S23, input the first input information and the target prompt words into the target model to obtain the first output information;

[0110] Among them, the processing operation performed by the user on the first output information can update the prompt word library, and the processing operation can characterize the user portrait of this user.

[0111] An embodiment of the present application uses the target model to process the first input information and the target prompt words screened from the prompt word library to obtain the first output information. Moreover, the processing operation performed by the user on the first output information can update the prompt word library, so that the target model can use the updated prompt word library to generate output information that conforms to the user portrait, that is, the target model can use the updated prompt word library to meet the user's requirements for the output information; and, without changing the model structure of the target model, that is, ensuring the stability of the target model.

[0112] Optionally, in this embodiment, the above storage medium may include, but is not limited to: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), external hard drives, magnetic disks, or optical discs that can store program codes. Optionally, in this embodiment, the processor executes the method steps described in the above embodiments according to the program codes stored in the storage medium. Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and details are not described herein again. Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a sequence different from that here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to implement. In this way, the present application is not limited to any specific combination of hardware and software.

[0113] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present application having equivalent elements, modifications, omissions, combinations (e.g., schemes that cross various embodiments), adaptations, or alterations. The elements in the claims will be broadly interpreted based on the language employed in the claims and are not limited to the examples described in the specification or during the implementation of the present application. The examples will be interpreted as non-exclusive. Thus, the specification and examples are intended to be considered only as examples, and the true scope and spirit are indicated by the full scope of the following claims and their equivalents.

[0114] The above description is intended to be illustrative and not restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art can use other embodiments when reading the above description. Additionally, in the above specific implementation manners, various features can be grouped together to simplify the present application. This should not be construed as an intention that a disclosed feature not claimed is necessary for any claim. On the contrary, the subject matter of the present application may be less than all the features of a specific disclosed embodiment. Thus, the following claims are incorporated herein as examples or embodiments into the specific implementation manners, where each claim independently serves as a separate embodiment, and it is contemplated that these embodiments can be combined with each other in various combinations or permutations. The scope of the present application should be determined with reference to the appended claims and the full scope of the equivalents to which these claims are entitled.

[0115] The above has described multiple embodiments of the present application in detail. However, the present application is not limited to these specific embodiments. Based on the concept of the present application, those skilled in the art can make various variations and modifications to the embodiments, and these variations and modifications should all fall within the scope of protection required by the present application.

Claims

1. A processing method comprising: Obtain the user's first input information; Based on the first input information, selecting a target prompt word from a prompt word library; Inputting the first input information and the target prompt word into a target model to obtain first output information; The processing operation performed by the user on the first output information can update the prompt word library, and the processing operation can represent the user portrait of the user.

2. The processing method according to claim 1, after obtaining the first output information, further comprising: monitoring a processing operation performed by the user on the first output information; Based on the processing operation, determining second output information; The prompt word library is updated based on the first output information and the second output information.

3. The processing method according to claim 2, wherein updating the prompt word library based on the first output information and the second output information comprises: Comparing the first output information with the second output information to obtain difference information; wherein the difference information includes at least one of the following: a structural difference, a grammatical difference, and a vocabulary usage difference between the first output information and the second output information; Based on the difference information, the prompt word library is updated.

4. The processing method according to claim 3, wherein updating the prompt word library based on the difference information comprises: Determine whether the difference information meets an update condition; wherein the update condition includes that the proportion of the difference information in the first output information is greater than a threshold, or the difference information includes a target difference, and the target difference is determined based on the user portrait; If they match, the prompt word library is updated based on the difference information.

5. The processing method according to claim 3, wherein comparing the first output information with the second output information to obtain difference information comprises: determining a text length of the first output information or the second output information; When the text length is greater than or equal to a preset length, sequentially determining the architecture difference, grammatical difference, and vocabulary usage difference between the first output information and the second output information; When the text length is less than a preset length, a vocabulary usage difference between the first output information and the second output information is determined.

6. The processing method according to claim 2, wherein determining the second output information based on the processing operation comprises: Obtaining a response interface in response to the processing operation; Based on the response interface, extracting second output information; or obtaining an instruction generated by an input device for performing the processing operation; Based on the instruction and the first output information, the second output information is obtained. 7 . The processing method according to claim 2 , wherein the processing operation performed by the user on the first output information comprises at least one of the following: copying, pasting, deleting, and modifying.

8. The processing method according to claim 7, wherein monitoring the processing operation performed by the user on the first output information comprises: Monitor interface information and / or command information of electronic devices; Determining, based on the interface information and / or the instruction information, a processing operation performed by the user on the first output information; The interface information at least includes the position of the mouse pointer in the interface and the position of the first output information in the interface; The object of the instruction information is the first output information, and the instruction information is generated based on an input device.

9. According to the processing method according to any one of claims 1 to 8, the target model is located in the cloud or in a user terminal.

10. An electronic device, comprising a memory, a processor, and a computer program stored in the memory, wherein when the electronic device is running, the processor executes the following steps in the computer program: Obtain the user's first input information; Based on the first input information, selecting a target prompt word from a prompt word library; Inputting the first input information and the target prompt word into a target model to obtain first output information; The processing operation performed by the user on the first output information can update the prompt word library, and the processing operation can represent the user portrait of the user.

Images