CN117111804A - Information processing methods, devices, electronic equipment and storage media - Google Patents
Information processing methods, devices, electronic equipment and storage media Download PDFInfo
- Publication number
- CN117111804A CN117111804A CN202311040728.2A CN202311040728A CN117111804A CN 117111804 A CN117111804 A CN 117111804A CN 202311040728 A CN202311040728 A CN 202311040728A CN 117111804 A CN117111804 A CN 117111804A
- Authority
- CN
- China
- Prior art keywords
- information
- processing
- prompt information
- result
- processing result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0483—Interaction with page-structured environments, e.g. book metaphor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
- G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
本公开提供了一种信息处理方法、装置、电子设备及存储介质，涉及数据处理技术领域，尤其涉及人工智能、深度学习以及信息处理等领域。该信息处理方法包括：获取浏览器当前显示页面所显示内容中选取信息；获取自定义的提示信息，提示信息用于表征对选取信息进行AI处理的结果意图；基于预训练的大语言模型LLM，对选取信息和提示信息进行处理，得到与提示信息匹配的目标AI处理结果。本公开实施例中，通过自定义的提示信息对选取信息进行AI处理，更加高效、及时的对选取信息进行处理，解决了目前信息处理缺乏用户定制化的灵活性的问题，用户的体验效果更好。
The present disclosure provides an information processing method, device, electronic equipment and storage medium, which relate to the field of data processing technology, especially to the fields of artificial intelligence, deep learning, information processing and other fields. The information processing method includes: obtaining the selected information in the content displayed on the currently displayed page of the browser; obtaining customized prompt information, which is used to represent the result intention of AI processing of the selected information; based on the pre-trained large language model LLM, Process the selection information and prompt information to obtain the target AI processing result that matches the prompt information. In the embodiments of the present disclosure, the selected information is processed with AI through customized prompt information, and the selected information is processed more efficiently and timely, which solves the current problem of lack of user-customized flexibility in information processing and improves the user experience. good.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to an information processing method, apparatus, electronic device, and storage medium.
Background
Currently available plug-in and AI model interactive applications are usually based on fixed AI capabilities, have limitations in interaction, and lack user customization flexibility, so that the user experience is poor.
Disclosure of Invention
The disclosure provides an information processing method, an information processing device, electronic equipment and a storage medium.
According to an aspect of the present disclosure, there is provided an information processing method including: acquiring selection information in the content displayed by the current display page of the browser; acquiring self-defined prompt information, wherein the prompt information is used for representing the result intention of AI processing on the selected information; and processing the selected information and the prompt information based on a pre-trained large language model LLM to obtain a target AI processing result matched with the prompt information.
According to another aspect of the present disclosure, there is provided an information processing apparatus including: the first acquisition module is used for acquiring selected information in the content displayed on the current display page of the browser; the second acquisition module is used for acquiring self-defined prompt information, wherein the prompt information is used for representing the result intention of AI processing on the selected information; and the processing module is used for processing the selected information and the prompt information based on a pre-trained large language model LLM to obtain a target AI processing result matched with the prompt information.
According to another aspect of the present disclosure, there is provided an electronic device comprising at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the information processing method described above.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the above-described information processing method.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the above-described information processing method.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
Fig. 1 is a schematic flow chart of an information processing method according to an embodiment of the disclosure;
fig. 2 is a schematic flow chart of an information processing method according to an embodiment of the disclosure;
FIG. 2A is an exemplary diagram of an intent acquisition component provided by an embodiment of the present disclosure;
FIG. 2B is an exemplary diagram of a display dialog provided by an embodiment of the present disclosure;
fig. 3 is a schematic flow chart of an information processing method according to an embodiment of the disclosure;
fig. 4 is a schematic flow chart of an information processing method according to an embodiment of the disclosure;
fig. 4A is an exemplary diagram of an information processing method provided by an embodiment of the present disclosure;
fig. 5 is a schematic structural view of an information processing apparatus provided in an embodiment of the present disclosure;
fig. 6 is a block diagram of an electronic device implementing an information processing method provided by the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Data Processing (Data Processing) is the collection, storage, retrieval, processing, transformation, and transmission of Data. The basic purpose of data processing is to extract and derive data that is valuable and meaningful to some particular person from a large, possibly unorganized, unintelligible, data.
Artificial intelligence (Artificial Intelligence) is a new technical science based on computer science, which is a cross discipline and an emerging discipline of cross fusion of multiple disciplines such as computer, psychology, philosophy, etc., to research, develop theories, methods, techniques and application systems for simulating, extending and expanding human intelligence, to attempt to understand the essence of the intelligence, and to produce a new intelligent machine that can react in a similar manner to human intelligence, and research in this field includes robotics, language recognition, image recognition, natural language processing, expert systems, etc.
Deep Learning (Deep Learning), which is a multi-layer neural network, is a machine Learning method. Deep learning is a special machine learning, which is a framework formed by taking reference to the characteristics of the human brain composed of a plurality of neurons. The neural network itself can automatically extract the features of the data clusters as long as there is enough learning data.
Information processing (Information Processing) refers to processing information using computer technology. The computer has extremely high running speed, can automatically process a large amount of information, and has extremely high accuracy. The original data or the data are arranged and processed into the own desired form, which is the basic link of system engineering and automatic control.
The method and the device are applicable to AI processing services for page contents in a browser scene, such as translation and search of page selected contents or expansion functions for the selected contents.
Fig. 1 is a flow chart of an information processing method according to an embodiment of the disclosure. As shown in fig. 1, the method at least comprises the following steps:
s101, acquiring selection information in the content displayed on the current display page of the browser.
In some implementations, the browser's currently displayed page may be a page that includes text information or images.
In some implementations, the displayed content may be selected using an input device such as a mouse, stylus, or the like. In some implementations, the user may also select content displayed in the browser of the touchable device directly from the finger.
In some implementations, text information in the current display page of the browser may be selected as the selection information.
Alternatively, the selection information may be one or more words, or may be one or more text segments. It can be understood that the selected information in the content displayed on the current display page of the browser is information to be processed.
In other implementations, the image in the current display page of the browser may be selected as the selection information.
S102, acquiring self-defined prompt information.
Optionally, the prompt information may be information customized by the user according to the requirement, which is used for characterizing the result intention of AI processing on the selection information, that is, for reflecting the intention of the user on the selection information processing.
Alternatively, the prompt information may be input by the user according to the intention after the selection information is acquired.
For example, assume that the user selection information is a text of "apple on tree", and the user-defined prompting information may be "translate to english", where the result of AI processing on the selection information is intended to translate the selection information to english; the self-defined prompt message can also be "write an article", and then the AI processing result of the selection message is intended to write an article with the selection message as the subject.
As another example, assuming that the user selection information is an image, the user-defined prompting information may be "extracting text information", or the like, that is, identifying and extracting text information in the image of the selection information.
S103, based on the pre-trained large language model LLM, the selection information and the prompt information are processed, and a target AI processing result matched with the prompt information is obtained.
The large language model (Large Language Model, LLM) refers to a deep learning model trained using a large amount of text data, which can generate natural language text or understand meaning of the language text, and which can process various natural language tasks such as text classification, questions and answers, conversations, etc.
In some implementations, the selection information and the prompt information are processed based on a pre-trained large language model LLM, for example, the selection information and the prompt information are spliced to form spliced information, the spliced information is input into the pre-trained large language model LLM, features in the spliced information are extracted by the large language model LLM, and a target AI processing result matched with the prompt information is output by the large language model LLM.
The exemplary illustration shows that the selection information is "apples on a tree", the prompt information is "translation to english", and the splicing processing can be performed on the selection information and the prompt information to obtain that the splicing information is "apples on a tree' translation to english", so that the large language model LLM can extract the characteristics of the splicing information based on the input splicing information, and output the target AI processing result corresponding to the splicing information as "the apples on the tree", so as to obtain the target AI processing result matched with the prompt information. Correspondingly, if the prompt information is "write an article", the splicing information can be "apple on tree" write an article ", the splicing information is input into the large language model LLM, and the target AI processing result matched with the prompt information is output, namely, an article with" apple on tree "as a theme is output. Assuming that the user selected information is an image and the user-defined prompt information is "extract text information", the image and the prompt information can be directly spliced, so that a target AI processing result matched with the prompt information is output, namely, the text information in the selected image is output.
In the embodiment of the disclosure, the selected information is subjected to AI processing through the customized prompt information to obtain the corresponding target AI processing result, personalized customization capability is provided, the corresponding prompt information is input to the selected information according to specific requirements and scenes, and then the selected information and the prompt information are processed by using the large predictive model to determine the target AI processing result, so that the selected information is processed more efficiently and timely, the problem that the current information processing lacks the flexibility of user customization is solved, and the experience effect of a user is better.
Fig. 2 is a flow chart of an information processing method according to an embodiment of the disclosure. As shown in fig. 2, the method comprises at least the following steps:
s201, acquiring selection information in the content displayed on the current display page of the browser.
In the embodiment of the present disclosure, the implementation method of step S201 may be implemented in any manner of each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
S202, in response to detecting that the selection operation of the display content is finished, displaying an intention acquisition component on the display page.
It can be understood that the selection operation is the selection of the content displayed on the current display page of the browser, and the selection information in the display content is determined by the selection operation.
Alternatively, after the selection operation of the display content is ended, an intention acquisition component is displayed on the display page, through which the prompt information can be input.
Optionally, the intent acquisition component includes at least a dialog box for entering prompt information.
S203, calling a dialog box in the intention acquisition component.
In some implementations, after the intent acquisition component is displayed on the display page, a dialog box in the intent acquisition component can be invoked to facilitate entering prompt information in the dialog box.
In some implementations, the intent acquisition component also includes basic intent options and custom intent options, as may be particularly shown in FIG. 2A. Alternatively, the basic intention option may be an option such as "copy", "search", "rewrite" or "write-through".
Optionally, monitoring a selection operation of the custom intent option; in response to monitoring the selection of the custom option, a dialog box in the intent acquisition component is invoked and displayed on the display page.
That is, when the user is monitored to click or select the custom intent option, a dialog box in the intent acquisition component is invoked and displayed on the display page, as shown in FIG. 2B.
S204, acquiring input content in the dialog box, and determining the input content as prompt information.
In some implementations, input content of a user is obtained from a dialog box and used as prompt information reflecting the intention of the user; intent information such as "translation", "renewal", or "grammar check" is used as hint information.
S205, based on the pre-trained large language model LLM, the selection information and the prompt information are processed, and a target AI processing result matched with the prompt information is obtained.
In the embodiment of the present disclosure, the implementation method of step S205 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
In the embodiment of the disclosure, after detecting that the selection operation of the display content is finished, an intention acquisition component is displayed, wherein the intention acquisition component can comprise a basic intention option and a custom intention option, the custom intention option is used for calling a dialog box, and the intention of a user is input to determine prompt information comprising the intention of the user so as to determine the prompt information comprising the intention of the user, and a target AI processing result is acquired based on the prompt information comprising the intention of the user and the selection information, so that the capability of the user to customize the intention is provided, and the experience of the user is improved.
Fig. 3 is a flow chart of an information processing method according to an embodiment of the disclosure. As shown in fig. 3, the method comprises at least the following steps:
s301, acquiring selection information in the content displayed on the current display page of the browser.
In the embodiment of the present disclosure, the implementation method of step S301 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
S302, acquiring self-defined prompt information.
In the embodiment of the present disclosure, the implementation method of step S302 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
S303, combining the selection information and the prompt information to generate an input sequence.
In some implementations, a combined template of the selection information and the hint information may be obtained, and the selection information and the hint information may be combined according to the combined template to generate the input sequence.
Alternatively, the combined template may be "preset word: prompt + selection information ", such as" description: translating into English+apples on a tree, wherein 'explanation' is a preset word, 'translating into English' is prompt information, and 'apples on a tree' is selection information. That is, the selection information and the prompt information are combined according to the combination template to generate an input sequence, for example, the input sequence is "description: translated into english + apples on a tree).
In other implementations, the insertion location of the selection information in the hint information may be determined and the selection information written at the insertion location to generate the input sequence.
That is, the insertion position of the selection information in the prompt information can be determined by user definition, and the selection information is written in the insertion position, for example, the prompt information is "translated into english", the selection information is "apples on the tree", if the insertion position is before the prompt information, the input sequence may be "apples on the tree are translated into english", and if the insertion position is in the prompt information, the input sequence may be "apples on the translation tree are english". The selection information and the prompt information are combined to generate an input sequence.
S304, inputting the input sequence into a large language model LLM for processing, and obtaining a target AI processing result.
Optionally, inputting the input sequence into a large language model LLM; and analyzing the selection information by using a large language model LLM to obtain an analysis result of the selection information, and generating a target AI processing result based on the prompt information and the analysis result.
It can be understood that a large language model is a model trained on a large scale to fully learn a wide range of language knowledge and semantic understanding capabilities; in the development and optimization stage of the large language model, the verification data set is used for testing and adjusting the model so as to ensure that the output of the large language model meets the expected requirement. In the actual use process, the trained large language model can be deployed in a plug-in of the browser so as to conveniently interact with the selection information and the prompt information of the user and generate a target AI processing result.
Alternatively, the large language model LLM may be a language-to-heart model. Inputting the input sequence into a pre-trained text-to-speech model, analyzing the selected information in the input sequence by the text-to-speech model to obtain an analysis result of the selected information, wherein the analysis result can be a semantic result of the selected information or an understanding result of the selected information, and generating a target AI processing result according to the prompt information in the input sequence and the analysis result of the selected information.
In some implementations, an initial AI processing result that matches the hint information may be generated based on the hint information and the analysis result; and acquiring the input interaction information, and optimizing the initial AI processing result based on the interaction information to obtain a target AI processing result.
Optionally, the interaction information may be a further interaction command such as a question or an adjustment parameter. That is, after the selected information is analyzed by the large language model to obtain an analysis result, an initial AI processing result is obtained according to the analysis result and the prompt information; further, the interactive information, such as the proposed problem, is input, and the initial AI processing result is optimized based on the interactive information, such as the proposed problem, so as to obtain the target AI processing result, so as to ensure that the target AI processing result can be more fit with the intention and the requirement of the user.
Further, it is also possible to display a result output frame on the display page and display the initial AI processing result or the target AI processing result in the result output frame. That is, the target AI processing result or the initial AI processing result may be presented on the display page of the browser through the result output frame.
In some implementations, a dialog box for entering prompt information may also be input detected to obtain interactive information entered in the dialog box. That is, after the initial AI processing result is output, input detection may be continuously performed on the dialog box to obtain the interaction information in the dialog box, and the initial AI processing result may be optimized according to the interaction information.
Optionally, an interaction area may also be displayed on the display page, wherein the interaction area includes a dialog box and a result output box; in the initial AI processing result optimizing process, the size of a result output frame in the interaction area is adjusted based on the AI processing result which is output currently. That is, the dialog box and the result output box are displayed on the display page, and the size of the result output box in the interaction area is adjusted according to the AI processing result currently output, so that the result output box can more reasonably and intuitively display the AI processing result, for example, when the AI processing result currently output occupies a larger area, the result output box can occupy a larger position in the display page, and when the AI processing result currently output occupies a smaller area, the result output box can occupy a smaller position in the display page.
Alternatively, a maximum range threshold may be set, and the size of the resulting output frame needs to be equal to or smaller than the maximum range threshold.
In the embodiment of the disclosure, the selection information and the prompt information can be combined through the combined template or the custom insertion position, so that an input sequence is generated, and the acquisition method of the input sequence is more flexible; analyzing the selected information in the input sequence based on the large language model which is pre-trained to obtain an analysis result of semantic understanding, and further obtaining an initial AI processing result based on the analysis result and prompt information of the input sequence, wherein the obtained initial AI processing result is accurate; further, input information of the dialog box can be continuously detected so as to obtain subsequent interaction information, the initial AI processing result is optimized through multiple rounds of dialog and multiple rounds of interaction, and a final target AI processing result is obtained, so that the target AI processing result is ensured to be more fit with requirements and intentions of users, the accuracy of the target AI processing result is improved, and the target AI processing result is displayed through the result output box so that the users can intuitively obtain the target AI processing result.
Fig. 4 is a flowchart of an information processing method according to an embodiment of the present disclosure. As shown in fig. 4, the method at least comprises the following steps:
S401, acquiring selection information in the content displayed on the current display page of the browser.
In the embodiment of the present disclosure, the implementation method of step S401 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
S402, in response to detecting that the selection operation of the display content is finished, displaying an intention acquisition component on the display page.
In the embodiment of the present disclosure, the implementation method of step S402 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
S403, calling a dialog box in the intention acquisition component.
In the embodiment of the present disclosure, the implementation method of step S403 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
S404, acquiring input content in the dialog box and determining the input content as prompt information.
In the embodiment of the present disclosure, the implementation method of step S404 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
S405, combining the selection information and the prompt information to generate an input sequence.
In the embodiment of the present disclosure, the implementation method of step S405 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
S406, inputting the input sequence into a large language model LLM for processing, and obtaining a target AI processing result.
As shown in fig. 4A, after the selection information is obtained and the prompt information is obtained according to the user-defined intent option, a schematic diagram of the target AI processing result is obtained based on the selection information and the prompt information, where the prompt information is "add emoji, making the document more attractive", and the large language model LLM outputs the target AI processing result, that is, the result of adding emoji to the selection information.
In the embodiment of the present disclosure, the implementation method of step S406 may be implemented in any manner in each embodiment of the present disclosure, which is not limited herein, and is not described herein again.
In the embodiment of the disclosure, after detecting that the selection operation of the display content is finished, a user-defined intention option can be displayed for calling a dialog box, and intention determination prompt information of a user is input; further, the selection information and the prompt information can be combined through a combined template or a custom insertion position, so that an input sequence is generated, and the selection information in the input sequence is analyzed based on the large language model with the pre-training completed, so that an initial AI processing result is obtained; the method can further continuously detect subsequent interaction information, optimize the initial AI processing result through multiple rounds of dialogue and multiple rounds of interaction to obtain a final target AI processing result, so that the target AI processing result is ensured to be more fit with the requirements and intentions of users, the accuracy of the target AI processing result is improved, the target AI processing result is displayed through a result output box, the target AI processing result is conveniently and intuitively acquired by the users, and the experience of the users is improved.
Based on the above embodiments, in some implementations, the embodiments of the present disclosure may be suitable for language generation and authoring, for example, a user selects a paragraph of an article on a browser, and inputs prompt information, such as "writing in" using the custom intent option in the embodiments of the present disclosure, the large language model may process the selected paragraph based on the prompt information, so as to generate corresponding writing in content, and assist the user in text authoring.
In some implementations, the embodiments of the present disclosure may also be applicable to document processing, for example, a user selects a piece of text on a browser, and inputs prompt information, such as "grammar checking", using the custom intent option in the embodiments of the present disclosure, then the large language model may perform grammar checking on the selected text based on the prompt information, thereby generating a target result of whether there is a grammar problem, and providing the functions of intelligent text editing and document processing.
In some implementations, the embodiments of the present disclosure may also be applicable to data analysis, for example, a user selects a piece of data or a statistical result on a browser, and by using the custom intent option in the embodiments of the present disclosure to input a prompt message, such as "chart generation", the large language model may process the selected data or statistical result to generate a corresponding chart or report, so as to help the user to quickly generate a visualized data analysis result.
In some implementations, the embodiments of the present disclosure may also be applied to time management and scheduling, for example, a user selects a time description on a browser, and inputs prompt information, such as "scheduling", using the custom intent options in the embodiments of the present disclosure, then the large language model may process the selected time description to generate corresponding schedule suggestions to help the user reasonably schedule and manage the schedule.
In some implementations, the embodiments of the present disclosure may also be applicable to file management and searching, for example, a user selects a piece of content related to a file description on a browser, and inputs prompt information, such as "related file searching", using the custom intent option in the embodiments of the present disclosure, the large language model may process the selected content of the file description, and generate a search result of the related file, so as to help the user to quickly find and manage the related file.
Fig. 5 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present disclosure. As shown in fig. 5, the apparatus 500 includes:
the first obtaining module 501 is configured to obtain selection information in content displayed on a current display page of the browser;
the second obtaining module 502 is configured to obtain a customized prompt message, where the prompt message is used to characterize a result intention of AI processing on the selected information;
And a processing module 503, configured to process the selection information and the prompt information based on the pre-trained large language model LLM, so as to obtain a target AI processing result matched with the prompt information.
In some implementations, the second acquisition module 502 includes:
in response to detecting that the selection operation of the display content is finished, displaying an intention acquisition component on the display page, wherein the intention acquisition component at least comprises a dialog box for inputting prompt information;
invoking a dialog box in the intent acquisition component;
and acquiring input contents in the dialog box, and determining the input contents as prompt information.
In some implementations, the intent acquisition component further includes a base intent option and a custom intent option, the second acquisition module 502 including:
monitoring the selection operation of the custom intention option;
in response to monitoring the selection of the custom option, a dialog box in the intent acquisition component is invoked and displayed on the display page.
In some implementations, the processing module 503 includes:
combining the selected information and the prompt information to generate an input sequence;
and inputting the input sequence into a large language model LLM for processing to obtain a target AI processing result.
In some implementations, the processing module 503 includes:
And acquiring a combined template of the selection information and the prompt information, and combining the selection information and the prompt information according to the combined template to generate an input sequence.
In some implementations, the processing module 503 includes:
determining the insertion position of the selection information in the prompt information, and writing the selection information in the insertion position to generate an input sequence.
In some implementations, the processing module 503 includes:
inputting the input sequence into a large language model LLM;
and analyzing the selection information by using a large language model LLM to obtain an analysis result of the selection information, and generating a target AI processing result based on the prompt information and the analysis result.
In some implementations, the processing module 503 includes:
generating an initial AI processing result matched with the prompt information based on the prompt information and the analysis result;
and acquiring the input interaction information, and optimizing the initial AI processing result based on the interaction information to obtain a target AI processing result.
In some implementations, the apparatus 500 further includes:
and displaying a result output frame on the display page, and displaying the initial AI processing result or the target AI processing result in the result output frame.
In some implementations, the apparatus 500 further includes:
input detection is performed on a dialog box for inputting prompt information to acquire interactive information input in the dialog box.
In some implementations, the apparatus 500 further includes:
displaying an interaction area on a display page, wherein the interaction area comprises a dialog box and a result output box;
in the initial AI processing result optimizing process, the size of a result output frame in the interaction area is adjusted based on the AI processing result which is output currently.
In the embodiment of the disclosure, the selected information is subjected to AI processing through the customized prompt information to obtain the corresponding target AI processing result, personalized customization capability is provided, the corresponding prompt information is input to the selected information according to specific requirements and scenes, and then the selected information and the prompt information are processed by using the large predictive model to determine the target AI processing result, so that the selected information is processed more efficiently and timely, the problem that the current information processing lacks the flexibility of user customization is solved, and the experience effect of a user is better.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 6 illustrates a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the respective methods and processes described above, such as an information processing method. For example, in some embodiments, the information processing method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When a computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the information processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the information processing method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (25)
1. An information processing method, wherein the method comprises:
acquiring selection information in the content displayed by the current display page of the browser;
acquiring self-defined prompt information, wherein the prompt information is used for representing the result intention of AI processing on the selected information;
and processing the selected information and the prompt information based on a pre-trained large language model LLM to obtain a target AI processing result matched with the prompt information.
2. The method of claim 1, wherein the obtaining the customized alert information comprises:
in response to detecting that the selection operation of the display content is finished, displaying an intention acquisition component on the display page, wherein the intention acquisition component at least comprises a dialog box for inputting prompt information;
invoking the dialog box in the intent acquisition component;
and acquiring the input content in the dialog box, and determining the input content as the prompt information.
3. The method of claim 2, wherein the intent acquisition component further includes a base intent option and a custom intent option, the invoking the dialog in the intent acquisition component comprising:
monitoring the selection operation of the custom intention option;
and in response to monitoring the selection operation of the custom option, invoking and displaying a dialog box in the intention acquisition component on the display page.
4. The method of any of claims 1-3, wherein the processing the selection information and the hint information based on the pre-trained large language model LLM to obtain a target AI processing result that matches the hint information comprises:
Combining the selected information and the prompt information to generate an input sequence;
and inputting the input sequence into the large language model LLM for processing to obtain the target AI processing result.
5. The method of claim 4, wherein the combining the selection information and the hint information to generate an input sequence includes:
and acquiring a combined template of the selected information and the prompt information, and combining the selected information and the prompt information according to the combined template to generate the input sequence.
6. The method of claim 4, wherein the combining the selection information and the hint information to generate an input sequence includes:
determining the insertion position of the selection information in the prompt information, and writing the selection information in the insertion position to generate the input sequence.
7. The method of claim 4, wherein the inputting the input sequence into the large language model LLM for processing results in the target AI process comprises:
inputting the input sequence into the large language model LLM;
analyzing the selection information by the large language model LLM to obtain an analysis result of the selection information, and generating the target AI processing result based on the prompt information and the analysis result.
8. The method of claim 7, wherein the generating the target AI processing result based on the hint information and the analysis result comprises:
generating an initial AI processing result matched with the prompt information based on the prompt information and the analysis result;
and acquiring input interaction information, and optimizing the initial AI processing result based on the interaction information to obtain the target AI processing result.
9. The method of claim 8, wherein the method further comprises:
and displaying a result output frame on the display page, and displaying the initial AI processing result or the target AI processing result on the result output frame.
10. The method of claim 8, wherein after displaying the initial AI-processing result in the result input box, further comprising:
and performing input detection on a dialog box for inputting prompt information to acquire the interaction information input in the dialog box.
11. The method of claim 10, wherein the method further comprises:
displaying an interaction area on the display page, wherein the interaction area comprises the dialog box and the result output box;
And in the initial AI processing result optimization process, the size of the result output frame in the interaction area is adjusted based on the AI processing result which is currently output.
12. An information processing apparatus comprising:
the first acquisition module is used for acquiring selected information in the content displayed on the current display page of the browser;
the second acquisition module is used for acquiring self-defined prompt information, wherein the prompt information is used for representing the result intention of AI processing on the selected information;
and the processing module is used for processing the selected information and the prompt information based on a pre-trained large language model LLM to obtain a target AI processing result matched with the prompt information.
13. The apparatus of claim 12, wherein the second acquisition module comprises:
in response to detecting that the selection operation of the display content is finished, displaying an intention acquisition component on the display page, wherein the intention acquisition component at least comprises a dialog box for inputting prompt information;
invoking the dialog box in the intent acquisition component;
and acquiring the input content in the dialog box, and determining the input content as the prompt information.
14. The apparatus of claim 13, wherein the intent acquisition component further includes a base intent option and a custom intent option, the second acquisition module comprising:
Monitoring the selection operation of the custom intention option;
and in response to monitoring the selection operation of the custom option, invoking and displaying a dialog box in the intention acquisition component on the display page.
15. The apparatus of any of claims 12-14, wherein the processing module comprises:
combining the selected information and the prompt information to generate an input sequence;
and inputting the input sequence into the large language model LLM for processing to obtain the target AI processing result.
16. The apparatus of claim 15, wherein the processing module comprises:
and acquiring a combined template of the selected information and the prompt information, and combining the selected information and the prompt information according to the combined template to generate the input sequence.
17. The apparatus of claim 15, wherein the processing module comprises:
determining the insertion position of the selection information in the prompt information, and writing the selection information in the insertion position to generate the input sequence.
18. The apparatus of claim 15, wherein the processing module comprises:
Inputting the input sequence into the large language model LLM;
analyzing the selection information by the large language model LLM to obtain an analysis result of the selection information, and generating the target AI processing result based on the prompt information and the analysis result.
19. The apparatus of claim 18, wherein the processing module comprises:
generating an initial AI processing result matched with the prompt information based on the prompt information and the analysis result;
and acquiring input interaction information, and optimizing the initial AI processing result based on the interaction information to obtain the target AI processing result.
20. The apparatus of claim 19, wherein the apparatus further comprises:
and displaying a result output frame on the display page, and displaying the initial AI processing result or the target AI processing result on the result output frame.
21. The apparatus of claim 19, wherein the apparatus further comprises:
and performing input detection on a dialog box for inputting prompt information to acquire the interaction information input in the dialog box.
22. The apparatus of claim 21, wherein the apparatus further comprises:
Displaying an interaction area on the display page, wherein the interaction area comprises the dialog box and the result output box;
and in the initial AI processing result optimization process, the size of the result output frame in the interaction area is adjusted based on the AI processing result which is currently output.
23. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.
24. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-11.
25. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method according to any of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311040728.2A CN117111804A (en) | 2023-08-17 | 2023-08-17 | Information processing methods, devices, electronic equipment and storage media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311040728.2A CN117111804A (en) | 2023-08-17 | 2023-08-17 | Information processing methods, devices, electronic equipment and storage media |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117111804A true CN117111804A (en) | 2023-11-24 |
Family
ID=88812106
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311040728.2A Pending CN117111804A (en) | 2023-08-17 | 2023-08-17 | Information processing methods, devices, electronic equipment and storage media |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117111804A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119376606A (en) * | 2024-11-15 | 2025-01-28 | 维沃移动通信有限公司 | Object processing method, device, electronic device, storage medium and program product |
| CN119692303A (en) * | 2024-12-11 | 2025-03-25 | 中国工商银行股份有限公司 | Page chart adjustment method, device, electronic device and storage medium |
-
2023
- 2023-08-17 CN CN202311040728.2A patent/CN117111804A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119376606A (en) * | 2024-11-15 | 2025-01-28 | 维沃移动通信有限公司 | Object processing method, device, electronic device, storage medium and program product |
| CN119692303A (en) * | 2024-12-11 | 2025-03-25 | 中国工商银行股份有限公司 | Page chart adjustment method, device, electronic device and storage medium |
| CN119692303B (en) * | 2024-12-11 | 2025-09-23 | 中国工商银行股份有限公司 | Page chart adjustment method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12204851B2 (en) | Method for generating pre-trained language model, electronic device and storage medium | |
| JP6909832B2 (en) | Methods, devices, equipment and media for recognizing important words in audio | |
| EP4113357A1 (en) | Method and apparatus for recognizing entity, electronic device and storage medium | |
| CN111428010B (en) | Man-machine intelligent question-answering method and device | |
| CN116012481B (en) | Image generation and processing method, device, electronic equipment and storage medium | |
| CN112287085B (en) | Semantic matching method, system, equipment and storage medium | |
| EP4109324A2 (en) | Method and apparatus for identifying noise samples, electronic device, and storage medium | |
| CN112579733A (en) | Rule matching method, rule matching device, storage medium and electronic equipment | |
| CN108121699A (en) | For the method and apparatus of output information | |
| CN117111804A (en) | Information processing methods, devices, electronic equipment and storage media | |
| KR102469712B1 (en) | Electronic device and Method for generating Natural Language thereof | |
| CN118363977A (en) | Structured query language statement generation method, device, equipment and storage medium | |
| CN113641724B (en) | Knowledge tag mining methods, devices, electronic equipment and storage media | |
| CN117371428B (en) | Text processing method and device based on large language model | |
| CN117422068A (en) | Information processing methods, devices, electronic equipment and storage media | |
| CN117806622A (en) | Application generation method, device, electronic device and storage medium | |
| CN112818096A (en) | Dialog generating method and device | |
| CN117174177A (en) | Training methods, devices and electronic equipment for protein sequence generation models | |
| CN114490967B (en) | Training method of dialogue model, dialogue method of dialogue robot, device and electronic equipment | |
| CN113342179B (en) | Input text processing method, device, electronic device and storage medium | |
| CN116932739B (en) | Data generation methods, devices, equipment, and storage media based on artificial intelligence | |
| CN119179777A (en) | Customer service dialogue quality inspection method and device, computer equipment and storage medium | |
| CN119271690A (en) | Data processing method, human-computer interaction method, intelligent agent system and device | |
| CN113705206B (en) | Emotion prediction model training method, device, equipment and storage medium | |
| CN113343668B (en) | Method and device for solving selected questions, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |