Information processing method and apparatus, and electronic device

Abstract

Embodiments of the present disclosure provide an information processing method and apparatus, and an electronic device. The method comprises: acquiring interaction information in a target interaction tool; automatically writing the acquired interaction information into a first cell of a target table, the first cell being associated with a preset function; in response to the interaction information being written into the first cell of the target table, processing the interaction information on the basis of the preset function, and obtaining a first processing result; and writing the first processing result into a second cell of the target table, or modifying content of the first cell, or executing a preset action on the basis of the first processing result.

Description

Information processing method, apparatus and electronic device

[0001] Cross-reference to Related Applications

[0002] This application claims the benefit of Chinese Patent Application No. 202411392241.5, filed September 30, 2024. The entire teachings of the above application are incorporated herein by reference. TECHNICAL FIELD

[0003] Embodiments of the present disclosure relate to the technical field of computer, and particularly, to an information processing method, apparatus and electronic device. BACKGROUND

[0004] With the development of Internet technology, the amount of data exchanged between users using the Internet for information interaction is also increasing. Users face a large amount of data and it is difficult to efficiently obtain the required information, and the information processing efficiency is low. SUMMARY

[0005] Embodiments of the present disclosure provide an information processing method, apparatus and electronic device.

[0006] In a first aspect, embodiments of the present disclosure provide an information processing method, comprising: obtaining interaction information in a target interaction tool; automatically writing the obtained interaction information to a first cell of a target table, the first cell being associated with a preset function; in response to the interaction information being written to the first cell of the target table, processing the interaction information based on the preset function associated with the first cell to obtain a first processing result; writing the first processing result into a second cell of the target table, or modifying the content of the first cell, or executing a preset action based on the first processing result.

[0007] In a second aspect, embodiments of the present disclosure provide an information processing apparatus, comprising: an obtaining unit configured to obtain interaction information in a target interaction tool; a writing unit configured to automatically write the obtained interaction information to a first cell of a target table, the first cell being associated with a preset function; a first processing unit configured to, in response to the interaction information being written to the first cell of the target table, process the interaction information based on the preset function associated with the first cell to obtain a first processing result; and a second processing unit configured to write the first processing result into a second cell of the target table, or modify the content of the first cell, or execute a preset action based on the first processing result.

[0008] In a third aspect, embodiments of the present disclosure provide an electronic device, comprising: a processor and a memory.

[0009] The memory stores computer execution instructions.

[0010] The processor executes the computer-executed instructions stored in the memory, so that the at least one processor executes the method as described in the first aspect and various possible designs of the first aspect.

[0011] In a fourth aspect, the embodiments of the present disclosure provide a computer-readable storage medium, which stores computer-executed instructions. When a processor executes the computer-executed instructions, the method as described in the first aspect and various possible designs of the first aspect is implemented.

[0012] In a fifth aspect, the embodiments of the present disclosure provide a computer program product, which includes a computer program. When a processor executes the computer program, the method as described in the first aspect and various possible designs of the first aspect is implemented. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor.

[0014] FIG. 1 is a schematic flowchart of an information processing method according to an embodiment of the present disclosure;

[0015] FIG. 2 is a schematic flowchart of an information processing method according to an embodiment of the present disclosure;

[0016] FIG. 3 is a schematic flowchart of an information processing method according to an embodiment of the present disclosure;

[0017] FIG. 4 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present disclosure;

[0018] FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present disclosure.

[0020] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0021] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can autonomously select whether to provide personal information to the software or hardware such as an electronic device, an application program, a server or a storage medium, etc. performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0022] As an optional but non-limiting implementation manner, in response to receiving an active request of a user, the manner of sending a prompt information to the user may, for example, be a pop-up window manner, and the prompt information may be presented in a text manner in the pop-up window. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0023] It can be understood that the above notification and obtaining of user authorization process is only illustrative, and does not limit the implementation manner of the present disclosure, and other manners meeting relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0024] It can be understood that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solutions should comply with the requirements of relevant laws and regulations and relevant provisions.

[0025] Users can interact information through the Internet, for example, a user uses an application with information interaction function to communicate with other users.

[0026] User needs and potential problems can be obtained according to analysis of the interaction information.

[0027] In some application scenarios, the interaction information can be manually analyzed to extract useful information such as user needs and potential problems. However, with the increase of the amount of interaction information data, it is difficult for the user to efficiently obtain useful information from the massive interaction information.

[0028] In one example, a preset keyword list can be set to filter the interaction information, and the interaction information related to the keywords in the keyword list is filtered out. Such a scheme has a limited coverage and cannot comprehensively obtain useful information, and may also have the problem of detection error.

[0029] In another example, a series of rules and conditions can be defined to classify and process the interaction information, which has the problem of high labor cost, and the flexibility and scalability need to be improved. In addition, in the above two examples, each processing stage of the interaction information is performed separately, and the interaction information is collected and then uniformly processed and analyzed, so that the efficiency of processing and responding to the interaction information is low.

[0030] The scheme provided by the present disclosure acquires interaction information, writes the interaction information into a spreadsheet, processes the interaction information by a data analysis tool integrated in the spreadsheet, and fills the processing result into the table. The spreadsheet can integrate each stage of the processing process of collecting, analyzing, processing, writing the processing result in the table, or responding to the processing result, etc. The efficiency of processing the interaction information is improved, which helps to improve the speed of responding to the interaction information.

[0031] Please refer to FIG. 1, which is a flowchart of an information processing method according to an embodiment of the present disclosure. As shown in FIG. 1, the method comprises the following steps:

[0032] S101: Acquire interaction information in a target interaction tool.

[0033] The target interaction tool herein can be an application program for information interaction, such as an application program with instant messaging function, etc.

[0034] Users can use the target interaction tool to communicate information. In the target interaction tool, multiple interaction information can be generated by information interaction between users.

[0035] The execution subject of the information processing method can be a terminal device, such as an application program running in the terminal device. In some application scenarios, the application program can integrate a spreadsheet application and an information interaction application. In these application scenarios, the target interaction tool can be an information interaction application integrated in the application program. The execution subject can periodically acquire interaction information in the target interaction tool.

[0036] S102: Automatically write the acquired interaction information into a first cell of a target table, and the first cell is associated with a preset function.

[0037] The target table can include multiple cells, and the multiple cells can include a first cell associated with a preset function.

[0038] In some application scenarios, the first cell is located in column A of the target table, and the preset function is set in one cell or multiple cells of column B, wherein column A is associated with column B.

[0039] In some application scenarios, the preset function can be associated with a column storing information having certain characteristics and / or types, for example, the content stored in a column can be content described using a preset language, and the column can be associated with a translation function. The cell in the column can be the first cell.

[0040] After the execution subject obtains the interaction information in the target interaction tool, the interaction information can be automatically written into the first cell in the target table. For example, the interaction information can be written into one or more first cells in the target table according to a preset writing rule.

[0041] S103: In response to the interaction information being written into the first cell of the target table, the interaction information is processed based on a preset function to obtain a first processing result.

[0042] When it is detected that the interaction information is written into the first cell of the target table, the interaction information can be processed by a preset function associated with the first cell to obtain a first processing result.

[0043] The above-mentioned preset function can have the function of semantic analysis of the interaction information. By processing the interaction information through the above-mentioned preset function, a first processing result of processing the interaction information can be obtained.

[0044] The above-mentioned processing of the interaction information includes translation, semantic understanding, abstract generation, etc. of the interaction information according to the preset function.

[0045] S104: The first processing result is written into a second cell of the target table, or the content of the first cell is modified, or a preset action is performed based on the first processing result.

[0046] In some application scenarios, the first processing result can be written into the second cell, and the second cell can be a cell different from the first cell, for example, a cell located in a different column or row from the first cell.

[0047] In some application scenarios, after obtaining the first processing result, the content of the first cell can be modified according to the first result. The above-mentioned modification of the content of the first cell can include but is not limited to one of the following: replacing the original content in the first cell; keeping the original content in the first cell unchanged and adding the first processing result; modifying the original content in the first cell.

[0048] The above-mentioned replacement of the original content in the first cell, that is, the interaction information in the first cell is replaced by the first processing result.

[0049] The original content in the first cell is kept unchanged and the first processing result is newly added, for example, the first processing result can be added to a specified position of the interactive information stored in the first cell (for example, after the interactive information), so as to splice the first processing result with the interactive information.

[0050] The original content in the first cell is modified, including modifying part of the content (including words and sentences) in the interactive information stored in the first cell by using the first processing result.

[0051] In some application scenarios, after obtaining the first processing result, a preset action can be performed based on the first processing result. For example, when the first processing result meets certain conditions, the interactive information is sent to a target object. The target object here can be a contact or a conversation.

[0052] The execution of the preset action here can be combined with writing the first processing result into the second cell or modifying or replacing the content of the first cell. For example, the second cell is associated with a preset action, and in response to the first processing result being written into the second cell, the preset action is executed based on the first processing result.

[0053] In this embodiment, the interactive information in the target interactive tool is obtained; the obtained interactive information is automatically written into the first cell of the target table, and the first cell is associated with a preset function; in response to the interactive information being written into the first cell of the target table, the interactive information is processed based on the preset function associated with the first cell to obtain a first processing result; the first processing result is written into the second cell of the target table, or the content of the first cell is modified, or a preset action is executed based on the first processing result, so that the stages of obtaining interactive information from the target interactive tool, processing the interactive information to generate a target object based on the table, and displaying the target object or executing a preset action are connected into a complete processing flow, improving the intelligence and efficiency of interactive information processing and processing result display.

[0054] In some embodiments, the step S103 comprises:

[0055] Based on the interactive information, prompt information is sent to a preset model, and based on the feedback of the preset model, the first processing result is obtained.

[0056] In these embodiments, the preset function can call the preset model through model calling information. The preset model can be any model with natural language processing capability. The model calling information may, for example, include a model calling interface.

[0057] When the interaction information is written into the first cell, according to an association relationship between the first cell and a preset function, the preset function is triggered to call a preset model through model calling information. In the process of calling the preset model, the preset function can refer to the interaction information in the first cell and send the interaction information to the preset model, so that the preset model processes the interaction information, and the preset model can send feedback to the execution subject. The execution subject can generate a first processing result according to the feedback of the preset model.

[0058] In these embodiments, prompt information including interaction information can be sent to a preset model, and the preset model can process the interaction information according to the prompt information, which can improve the efficiency of processing the interaction information.

[0059] Please refer to FIG. 2, which is a flowchart of an information processing method provided by an embodiment of the present disclosure. As shown in FIG. 2, the method comprises the following steps:

[0060] S201: extracting interaction information from a target interaction tool using a virtual object.

[0061] The interaction information comprises at least one of the following: target interaction information, and association information of the target interaction information. The target interaction tool may, for example, be a target session or a target meeting. The target interaction tool satisfies a preset condition, for example, the target session has a preset member, or the target meeting has a preset keyword in the subject and a target person in the participants.

[0062] In this embodiment, the execution subject of the information processing method can be a terminal device, and specifically can be an application program running in the terminal device.

[0063] When the target interaction tool comprises a target session, the target session herein can be one or more sessions generated in the target interaction tool. The one or more sessions can be sessions in which a preset user is a session member or sessions that satisfy other preset conditions. The preset user can be a user who logs in the application program. The virtual object can be a session member of the target session.

[0064] The target session can be a session that satisfies a preset condition. The preset condition may, for example, be one or more of the following: a session in which a specified user is a session member, one or more sessions corresponding to a specified session topic, and a preset session type. The preset session type can be a session organized in a topic manner.

[0065] For example, the target session can be a session in which a user S is a session member. The user S herein can be any specified user. If it is detected that a session has a user S as a session member, the session satisfies the preset condition.

[0066] For example, the target session can be one or more sessions with a session topic T. If it is detected that the session corresponds to the session topic T, the session satisfies the preset condition.

[0067] The virtual object can be a virtual object application client, for example. The virtual object can obtain one or more pieces of interaction information of the target session.

[0068] As an example, the virtual object can be a member of the target session, and the virtual object collects interaction information in the target session according to authorization.

[0069] In another example, a target session in which the preset user is located is determined according to a preset user identifier, and the virtual object is added to the target session. In this example, the target session in which the preset user is located can be determined from a plurality of sessions according to the user identifier of the preset user, and then the virtual object is added to the target session, so that the virtual object becomes a session member of the target session.

[0070] In some embodiments, the virtual object can be used to periodically collect updated interaction information in the target session.

[0071] In some other embodiments, the virtual object can be used to collect updated interaction information when it is detected that there is updated interaction information in the target session.

[0072] The interaction information includes target interaction information and associated information of the target interaction information. The associated information includes but is not limited to one or more of the following: sender information, sending time information, reply person information, reply content, attachment, and number of replies.

[0073] The sender information indicates a sender of the target interaction information, and includes but is not limited to a user identifier of the sender.

[0074] The reply person information indicates an information replier of the target interaction information, and includes but is not limited to a user identifier of the information replier.

[0075] The attachment includes an attachment of the target interaction information, and can also include an attachment in the reply content.

[0076] S202: The obtained interaction information is automatically written into a first cell of a target table, and the first cell is associated with a preset function.

[0077] In some embodiments, after obtaining the interaction information in the target session, the execution subject can automatically write the interaction information into the first cell of the target table. The target table can be a pre-created electronic table for carrying the interaction information, the preset function, and a processing result of the interaction information.

[0078] As an implementation manner, the execution subject can establish an association relationship between the virtual object and the target table according to a user operation, and the virtual object can write the interaction information into the first cell of the target table after collecting the interaction information in the target conversation.

[0079] The target table can include multiple rows and multiple columns. The first cell can include one or more cells belonging to the same row or the same column.

[0080] In one example, the first cell can include multiple cells belonging to the same row and different columns. For example, the first cell can include cells in the kth row, the jth column to the j+nth column of the target table. Here, k, j and n are all integers greater than 0.

[0081] The interaction information obtained from the target conversation can be written into the first cell. The interaction information includes target interaction information (e.g., original information) and associated information of the target interaction information.

[0082] Each piece of information in the target conversation has an information type attribute, which includes an original information type and a reply information type. For each piece of information, it can be determined whether the information is original information or reply information of the original information according to the information type attribute of the information. The reply information can be regarded as associated information of the original information.

[0083] In one example, the target interaction information and the associated information of the target interaction information can be stored in the same first cell.

[0084] In some embodiments, the target interaction information can be stored in the first cell corresponding to the kth row and the jth column of the target table, and the associated information of the target interaction information can be stored in other first cells from the kth row, the jth column to the j+nth column. For example, each associated information is stored in one other first cell.

[0085] In these embodiments, the jth column to the j+nth column of each row of the target table can store one target interaction information and the associated information corresponding to the one target interaction information, respectively.

[0086] As an example, it can be preconfigured that each column in the jth column to the j+nth column records which information data, for example, the jth column records target interaction information. The j+1th column records the first attachment in the target interaction information. The j+2th column can record one or more reply contents corresponding to the target interaction information. The j+3th column can record the second attachment carried by the one or more reply contents. The j+4th column can record the number of interactions corresponding to the target interaction information. The j+5th column can record the source (such as a conversation) of the recorded interaction information, the j+6th column can record the conversation identifier where the target interaction information is located, and the j+7th column can record time information of the target interaction information. It can be understood that other related information of the target interaction information can also be recorded in other columns of the above target table. The recorded other related information can be set according to specific application scenarios, which is not limited here.

[0087] S203: In response to the interaction information being written into the first cell of the target table, sending prompt information to a preset model based on a preset function and the interaction information, and obtaining a first processing result based on feedback of the preset model.

[0088] In the embodiment, the above-mentioned preset function can be built-in in the target table, for example, integrated in the first cell of the target table or other cells other than the first cell. The above-mentioned preset function can call the preset model through an interface. The above-mentioned preset model can have the ability to analyze and process natural language.

[0089] In some application scenarios, the preset function can also be set in a sub-table of the target table, which can be a different sub-table of the target table from the sub-table where the cell recording the interaction information is located.

[0090] In some application scenarios, the above-mentioned preset function can be set in one or more cells associated with the first cell in the sub-table where the first cell is located, which can belong to the same column or the same row.

[0091] The above-mentioned preset function can be a custom function, and the triggering mode of the preset function is a target cell writing information event trigger. The above-mentioned preset function can call the preset model through a model calling information. The above-mentioned preset model can be a model with natural language processing capability.

[0092] When the interaction information is written into the first cell, the preset function is triggered to call the preset model according to the association relationship between the first cell and the preset function. In the process of calling the above-mentioned preset model, the prompt information is sent to the preset model through the model calling information, so that the preset model processes the interaction information according to the above-mentioned prompt information, and the processing result of processing the interaction information is sent to the preset function through the above-mentioned preset model calling interface.

[0093] In some embodiments, the preset function can further include processing information indicating how to process the interaction information. Illustratively, the processing information can include information indicating to classify the interaction information, information indicating to extract keywords, information indicating to translate the interaction information, and the like. Correspondingly, the prompt information generated according to the preset function can also include the processing information.

[0094] In these embodiments, the preset function can send the prompt information to a preset model, and the preset model can process the interaction information according to the processing information in the prompt information.

[0095] Correspondingly, the preset function can include one or more of the following:

[0096] a classification function, a keyword extraction function, a content summary generation function, a text translation function, and a custom information processing function.

[0097] For each preset function, a corresponding cell can be integrated in the preset function. Different preset functions can be integrated in different cells.

[0098] The classification function can be used to classify the interaction information according to a preset classification result. The preset classification result can include two or more preset classification results. Each preset classification result corresponds to a classification label. The preset classification result can include, for example, functional appeal, performance optimization, interaction and operation editing, functional consultation, product defect, and the like. In addition, the preset classification result can also include positive evaluation and negative evaluation. In some examples, the prompt information can include the two or more preset classification results and the interaction information.

[0099] The keyword extraction function can be used to extract keywords from the interaction information. Correspondingly, the prompt information can include the interaction information and the processing information of keyword extraction from the interaction information.

[0100] The content summary generation function can be used to generate a content summary of the interaction information. Correspondingly, the prompt information can include the interaction information and the processing information of content summary generation of the interaction information.

[0101] The text translation function can be used to translate the interaction information. Correspondingly, the prompt information can include the interaction information, a target language to which the interaction information is translated, and the processing information of translation of the interaction information.

[0102] The custom information processing function can be used to indicate custom processing of the interaction information. The custom processing can be set according to application scenarios.

[0103] The preset function can indicate to write the first processing result in the second cell. In some application scenarios, the preset function can be integrated in the second cell.

[0104] Illustratively, if the preset function is a classification function, when the interaction information is written into the first cell, the preset model can be sent prompt information based on the interaction information, the prompt information being used to instruct the preset model to classify the interaction information in the first cell to obtain a classification result of the interaction information. The preset model returns the classification result as feedback information to the preset function. The preset function can write the classification result indicated by the feedback information into the second cell.

[0105] Illustratively, if the preset function is a translation function, when the interaction information is written into the first cell, the preset model can be sent prompt information based on the interaction information, the prompt information being used to instruct the preset model to translate the interaction information in the first cell into a target language (such as English, Chinese, etc.) to obtain a translation result, and the translation result is returned as feedback information to the preset function. The preset function can write the translation result indicated by the feedback information into the second cell.

[0106] Illustratively, if the preset function is a keyword extraction function, when the interaction information is written into the first cell, the preset model can be sent prompt information based on the interaction information, the prompt information being used to instruct the preset model to extract keywords from the interaction information in the first cell to obtain one or more keywords of the interaction information. The preset model feeds back the one or more keywords to the keyword extraction function, and the keyword extraction function can write the one or more keywords into the second cell.

[0107] In some embodiments, the step S203 includes the following sub-steps:

[0108] First, based on a prompt information generation rule corresponding to the preset function, the prompt information is generated, the prompt information including at least a part of the interaction information and processing information for processing at least a part of the interaction information;

[0109] Second, based on model calling information associated with the preset function, the prompt information is sent to the preset model, and the preset model performs information processing according to the prompt information.

[0110] In these embodiments, the prompt information generation rule can include the processing information, at least a part of the interaction information, preset text content connecting at least a part of the interaction information and the processing information, and output prompt information. The at least a part of the interaction information can be, for example, original information in the interaction information. The output prompt information is used to instruct to output the processing result, and in some examples, the output prompt information can also include an output format.

[0111] Illustratively, the above prompt information generation rule can be, for example: "help me extract the keyword in the cell recording the original information of the keyword, output the keyword", wherein "help me extract" and "of" are at least part of the connection interaction information and the preset text content of the processing information, the above "keyword" is the processing information. The above "output keyword" is the output prompt information.

[0112] According to the prompt information generated by the prompt information generation rule, the preset model can be prompted to process at least part of the interaction information according to the processing information.

[0113] The above model calling information can include a model calling interface, the above preset function can be associated with the model calling information, and the above execution subject can send the prompt information to the preset model through the above model calling information, so that the preset model processes at least part of the interaction information according to the processing information in the prompt information.

[0114] It can be understood that the plurality of interaction information obtained from the target conversation can be written into the first cells in different rows or different columns. The interaction information written into the respective corresponding first cells constitutes the input set of the preset function, X={x1, x2, …, xn}, xk represents the interaction information recorded in one or more first cells in the kth row of the target table.

[0115] In some application scenarios, the above input set can be composed of the original information of the interaction information, that is, for each interaction information, the original information in the interaction information and the corresponding processing information can be taken as the input of the preset function.

[0116] After writing the plurality of interaction information in the target conversation into the respective corresponding first cells of the target table, the respective corresponding preset functions of the first cells can be automatically triggered, which can call the preset model according to the model calling information, and input the prompt information corresponding to the interaction information in each first cell to the preset model. The preset model processes each prompt information. Specifically, for each prompt information, the preset model can extract the original information and the processing information from the prompt information, and process the original information according to the processing information.

[0117] The above process can be described by the following formula (1):

[0118] y = preset function (x) (1);

[0119] Wherein, y is the first processing result, and x is the original information input in the first cell.

[0120] The preset function receives the feedback of the preset model, obtains the first processing result according to the feedback, writes the first processing result into the second cell for display, so that the user can view.

[0121] S204: write the first processing result into a second cell of the target table, or modify the content of the first cell, or perform a preset action based on the first processing result.

[0122] The specific implementation of step S204 can refer to the related part of the embodiment shown in FIG. 1, and will not be described here.

[0123] In this embodiment, the virtual object automatically obtains the interaction information of the target conversation; the obtained interaction information is automatically written into the first cell of the target table, the first cell is associated with a preset function, in response to the interaction information being written into the first cell of the target table, prompt information is sent to the preset model based on the preset function associated with the first cell and the interaction information, and based on the feedback of the preset model, a first processing result is obtained, which realizes automatic acquisition of conversation information in the target conversation by the virtual object, and a preset function for calling the preset model is set in the table, and the preset model is called by the preset function to process the interaction information, which can further improve the efficiency of processing the interaction information.

[0124] In these embodiments, when the interaction information is input into the first cell of the target table, the preset function referencing the first cell generates prompt information according to the prompt information generation rule, and inputs the prompt information into the preset model through the model calling interface. Since the above-mentioned prompt information includes interaction information and processing information, the preset model can analyze the interaction information according to the processing information, so that the accuracy of the output processing result is higher.

[0125] In some embodiments, the above-mentioned prompt information indicates classification of the interaction information to obtain a classification result of the interaction information, and the prompt information further includes a preset label set used for classification.

[0126] In these embodiments, the above-mentioned preset function can be a function for classifying the interaction information. The above-mentioned preset label set can include one or more preset labels.

[0127] As an implementation manner, the prompt information generation rule corresponding to the preset function can include a preset label set. That is, the preset label set can be written in the prompt information generation rule. The prompt information generated according to the above-mentioned prompt information generation rule can include at least part of the interaction information, the processing information and the preset label set.

[0128] As an implementation manner, the preset label set in the prompt information is obtained by referencing a cell or a sub-table recording the preset label set.

[0129] In the implementation, the preset label set can include one or more classification labels. Each classification label can correspond to a preset classification result. The preset label set can be recorded in a cell of the target table or a cell of another table.

[0130] The prompt information generation rule can refer to the cell recording the preset label set, so that the preset label set is written in the prompt information. The cell recording the preset label set can be in the target table or in another table.

[0131] In some embodiments, the preset label set includes a user-defined label.

[0132] In these embodiments, the user can edit one or more user-defined labels in the cell recording the preset label set. The preset function can obtain the user-defined label by referring to the cell. For example, the user can edit the user-defined label in a cell of a sub-table of the target table, and the preset function can obtain the user-defined label by referring to the sub-table.

[0133] In the embodiment, the user-defined label can be used to classify the interaction information according to the personalized needs of the user, so that the obtained classification result matches the personalized needs of the user.

[0134] In some embodiments, the preset label set includes multi-level classification labels. The multi-level classification labels can be recorded in different cells.

[0135] In these embodiments, the first-level classification labels can include different types of first-level classification labels. For each first-level classification label, a second-level classification label set belonging to the first-level classification label can be corresponded, and the second-level classification label set can be recorded in a cell. The second-level classification label sets belonging to different first-level classification labels can be recorded in different cells.

[0136] The second-level classification label set can also include different types of second-level classification labels. For each second-level classification label, a third-level classification label set belonging to the second-level classification label can be corresponded, and the third-level classification label set can be recorded in a cell. The third-level classification label sets belonging to different second-level classification labels are recorded in different cells, and the same applies to the subsequent levels.

[0137] Therefore, for multi-level classification labels, each type of classification label of a previous level corresponds to a classification label set of a subsequent level. The classification label sets of the subsequent level corresponding to different classification labels of the previous level are recorded in different cells.

[0138] In the embodiments, by setting the multi-level classification labels, the multi-level classification of the interaction information can be facilitated.

[0139] In some embodiments, the writing of the first processing result into the second cell of the target table, or the modification of the content of the first cell, or the execution of the preset action based on the first processing result, comprises:

[0140] In response to the i-th level classification result of the interaction information being written into the second cell, triggering the (i+1)-th level classification of the interaction information; wherein the i-th level classification result is obtained by processing the first prompt information by a preset model, and the first prompt information comprises an i-th level classification label set used for the i-th level classification of the interaction information, wherein i is an integer greater than or equal to 1.

[0141] The following takes a two-level classification as an example. In response to the interaction information obtained from the target session being written into the first cell, a preset function for triggering the first level classification of the interaction information is triggered, which can generate the first prompt information according to the associated prompt information generation rule. The first prompt information comprises at least part of the interaction information, a first level classification label set and processing information indicating the classification of at least part of the interaction information.

[0142] The first level classification label set can be obtained by the prompt information generation rule from the reference of the cell recording the first level classification label set. As an example, the prompt information generation rule can be, for example: please classify “XXXX”, output one of the classification label set in the reference of T2 table row 1 column 2. A plurality of first level classification labels are recorded in T2 table row 1 column 2, and the plurality of first level classification labels can include user-defined classification labels.

[0143] The generated first prompt information indicates that the preset model classifies at least part of the interaction information according to the plurality of first level classification labels in the first level classification label set.

[0144] The preset function corresponding to the first level classification can be integrated in a fourth cell other than the first cell. In an example, the fourth cell can be in the same row or the same column as the first cell. After obtaining the first level classification result of the interaction information, the first level classification result can be written into the second cell.

[0145] In response to the first level classification result of the interaction information being written into the second cell, triggering the second level classification of the interaction information, thereby obtaining the two-level classification result of the interaction information.

[0146] The multi-level classification of the interaction information helps to establish the hierarchical structure of the interaction information, and is conducive to the systematic storage of the interaction information.

[0147] In some embodiments, the triggering the i+1-level classification of the interaction information comprises the following steps:

[0148] First, generating second prompt information based on a preset function for the i+1-level classification of the interaction information; the second prompt information comprises a classification label set corresponding to the i+1-level classification;

[0149] Second, sending the second prompt information to a preset model based on model calling information, and performing the i+1-level classification of the interaction information by the preset model according to the second prompt information to obtain an i+1-level classification result, and writing the i+1-level classification result into a third cell; wherein the classification label set corresponding to the i+1-level classification changes with the i-level classification result.

[0150] Still taking the two-level classification as an example, the interaction information obtained from the target conversation is written into the first cell, triggering the first-level classification of the interaction information. After the first-level classification result is written into the second cell, the second-level classification of the interaction information is triggered.

[0151] The first-level classification result of the interaction information is written into the second cell, triggering the preset function calling prompt information generation rule of the second-level classification of the interaction information to generate the second prompt information; the second prompt information comprises at least a part of the above-mentioned interaction information, a second-level classification label set belonging to the first-level classification result, and processing information indicating the classification of at least a part of the interaction information.

[0152] The prompt information generation rule can be, for example, "please classify XXXX, output 'T2 table row 1 to row n, column 2 to column m' belonging to 'T1 table row 2, column 4' record in the first-level classification result of the second-level classification label set". Among them, "T2 table row 1 to row n, column 2 to column m" can record the label set corresponding to each level of classification, and can also record the corresponding relationship between each classification label of the first level and the classification label set of the second level. Therefore, after the classification result of the first level is determined, the corresponding second-level classification label set can be found in the multiple cells or sub-tables recording the multi-level classification label set according to the above-mentioned corresponding relationship.

[0153] Illustratively, the first-level classification label in the first-level classification label set includes: document, table, and the like. The second-level classification label set corresponding to the first-level classification label "document" includes: format brush, font modification, undo, copy, paste, and the like. The second-level classification label set corresponding to the first-level classification label "table" includes: worksheet, add cell, delete cell, set row, and the like. The first-level classification label set is recorded in the sub-table T2. Illustratively, the plurality of cells in the jth column of the sub-table T2 record the multi-level classification label set respectively, and the identification corresponding to each label set can be recorded in the ith column. The identification of each classification label set can include the classification level corresponding to the classification label set, and the corresponding information of the classification label set and the classification label in the previous level classification label set.

[0154] If the classification result of the first-level classification of the interaction information is "document", when "document" is written into the second cell, the preset function associated with the second cell is triggered, and the second prompt information is generated according to the prompt information generation rule associated with the preset function.

[0155] The identification of the target second-level classification label set corresponding to the document can be found in the ith column of the sub-table T2 according to the identification of the label set. After the identification of the target second-level classification label set is found, for example, the identification of the target second-level classification label set is located in the rth row, the jth column of the rth row can be used as the cell referenced by the prompt information rule. Wherein, r is an integer greater than 0. Through the above reference, the second-level classification label set recorded in the jth column of the rth row can be written in the second prompt information. The second-level classification label set includes format brush, font modification, undo, copy, paste, and the like.

[0156] When the classification result of the first-level classification of the interaction information is "table", after "table" is written into the second cell, the preset function associated with the second cell is triggered to generate the second prompt information according to the prompt information generation rule; the second prompt information includes at least part of the interaction information, the second-level classification label set belonging to "table", and the processing information indicating the classification of at least part of the interaction information.

[0157] The above execution subject can send the second prompt information to the preset model, and the preset model can perform second-level classification on the interaction information according to the second prompt information to obtain a second-level classification result, and send the second-level classification result to the above execution subject. The above execution subject can write the second-level classification result into the third cell. Here, the third cell can be a cell located in the same row as the second cell.

[0158] That is, for the scenario of multi-level classification of interaction information, after the first-level classification result is determined, the corresponding second-level classification label set is determined automatically according to the first-level classification result, so that the second-level classification label is dynamically adjusted according to the first-level classification result, and the accuracy and flexibility of multi-level classification are improved.

[0159] In some embodiments, the prompt information further includes:

[0160] One or more examples; wherein the examples include example interaction information and example processing results generated by the example interaction information, or the examples include context information for generating the processing results corresponding to the application scenario.

[0161] In some application scenarios, the above examples can include example interaction information and example processing results generated by the example interaction information. In these application scenarios, writing the above examples in the above prompt information can convey an explicit intention to the preset model, so that the preset model can better understand the user's demand; in addition, the above examples can make the preset model better capture the task requirements, so as to generate more accurate output.

[0162] In some application scenarios, the above examples can also include context information for generating the processing results. The above context information is background information related to the task, and the context information can provide historical scene information. Adding context information to the examples helps the preset model better understand the environment or situation in which the task is located, and helps to obtain processing results with better coherence with the context.

[0163] In these embodiments, by adding examples to the prompt information, the preset model can better understand the task, so as to obtain processing results with higher accuracy.

[0164] In some embodiments, the prompt information obtains one or more examples by referencing a cell or a sub-table used to record the examples.

[0165] In some application scenarios, one or more examples are recorded in the corresponding cell, and the prompt information can obtain one or more examples by referencing the above cell.

[0166] The cell recording one or more examples can be located in the same target table as the first cell, or can be located in a different table. If the cell recording one or more examples is not in the same table as the first cell, the above reference can specify the table and cell where one or more examples are located.

[0167] In some application scenarios, one or more examples are recorded in a sub-table of the target table, and in these application scenarios, the above prompt information can obtain one or more examples by referencing the sub-table.

[0168] In these embodiments, by referencing the cells or sub-tables, one or more examples are written in the prompt information, which facilitates improving the efficiency of writing examples in the prompt information, and improves the generation efficiency of the prompt information.

[0169] In some embodiments, the above examples are editable. In these embodiments, the user can edit the examples in the cells where the examples are located, such as adding examples matching the scene according to the scene, deleting redundant examples, changing existing examples according to the scene requirements, etc. By editing the examples by the user, the user personalized examples can be provided to the preset model, so that the processing of the interaction information by the model has a higher matching degree with the personalized requirements of the user.

[0170] In some embodiments, the prompt information generation rule can be editable. That is, the user can edit the prompt information generation rule according to the personalized requirements, such as modifying the reference to the examples, modifying the reference to the label set, editing the custom text, etc. In these embodiments, by editing the prompt information generation rule, the prompt information that has a higher adaptation degree with the user requirements and is more matched with the application scene can be generated, thereby improving the accuracy of the processing result generated according to the prompt information.

[0171] Please refer to FIG. 3, which is a schematic flowchart of the information processing method provided by the embodiments of the present disclosure, as shown in the figure, the method comprises the following steps:

[0172] S301: Obtain the interaction information in the target interaction tool.

[0173] S302: Automatically write the obtained interaction information into the first cell of the target table, and the first cell is associated with a preset function;

[0174] S303: In response to the interaction information being written into the first cell of the target table, process the interaction information based on the preset function associated with the first cell to obtain a first processing result;

[0175] S304: Write the first processing result into the second cell of the target table, or modify the content of the first cell, or execute a preset action based on the first processing result.

[0176] The specific implementation of the above steps S301-S304 can refer to the specific description of the steps S101-S103 of the embodiment shown in FIG. 1, which will not be repeated here.

[0177] S305: Send a prompt message to the target user or a preset conversation, and the prompt message is generated according to the first processing result.

[0178] The interaction information with high importance degree can be determined according to the first processing result. The prompt message can be generated in real time for the interaction information with high importance degree, and the prompt message can be sent to the target user or the preset session. The prompt message sent to the target user is not limited, for example, the prompt message can also be sent to the user by email and the like.

[0179] The target user can be a user designated in advance, and the preset session can be a session designated in advance. The target user can process or reply to the interaction information. The preset session can include a user capable of processing or replying to the interaction information.

[0180] Illustratively, if the classification result of an interaction information is product defect feedback, the importance degree of the interaction information is high.

[0181] In some embodiments, the prompt message is displayed as an interaction information card. The interaction information card can be provided with different regions, and each region records a specified part of the prompt message. For example, the interaction information card can include a first region, a second region, a third region, and a fourth region, the first region records the category of the interaction information, the second region records the target session information, the third region records the time information of the generation of the interaction information, and the fourth region records the original interaction information. In addition, the interaction information card further includes a control for responding to the interaction information. By triggering the control, the session in which the interaction information is located can be displayed and positioned to the position of the interaction information in the session. By displaying the interaction information card, the user can quickly obtain relevant information from the interaction information card.

[0182] In the embodiment, by generating the prompt message of the interaction information according to the first processing result, the interaction information that needs to be processed quickly can be identified from the interaction information recorded in the target table, the workload of manually identifying the interaction information that needs to be processed quickly can be reduced, and the time required for identifying the interaction information that needs to be processed quickly can be shortened, so as to improve the response speed of the interaction information. By automatically generating the prompt message from the first processing result of the interaction information in the table, the operation continuity can be conveniently maintained, and the continuity and stability of the business operation can be maintained.

[0183] In addition, the scheme provided in the embodiment integrates the functions of different stages of processing the interaction information in the target table by obtaining the interaction information from the target session, calling the preset model to process the interaction information to generate the first processing result, displaying the first processing result, and triggering the sending of the prompt message according to the first processing result, so as to simplify the code for implementing the processing of the interaction information in the different stages of the multiple sessions by using the functions of the table itself, and reduce the development difficulty. In addition, the efficiency and accuracy of information processing are realized.

[0184] In some embodiments, the method further comprises periodically sending graphical statistical information to the target user or the preset session, the graphical statistical information being generated according to the first processing result corresponding to each of the plurality of interaction information.

[0185] The period length of the periodicity can be, for example, one natural day or one week.

[0186] The graphical statistical information can include one or more of the following: an interaction information category classification column chart, a word cloud, and a sorting result of different interaction information according to occurrence frequency.

[0187] The interaction information category classification column chart can include a column chart corresponding to each classification result in a period, each classification result being generated by the number of interaction information belonging to the classification result in the period.

[0188] The classification result can include, for example, a function request, a performance problem, and a user interface improvement suggestion. The number of interaction information belonging to each classification result in a period can be counted, and then an interaction information category classification column chart can be generated according to the number of interaction information corresponding to each classification result. Through the interaction information category classification column chart, the number of interaction information corresponding to each classification result can be displayed, and the urgency and frequency of each classification result can be clearly indicated.

[0189] In some embodiments, keywords can be extracted from each interaction information in a period, and the frequency of occurrence of each keyword can be counted. A word cloud can be constructed according to the hotness of each keyword according to the frequency of occurrence. Through the word cloud, the focus of user discussion can be intuitively reflected.

[0190] In some embodiments, the interaction information can be sorted, for example, according to the order of the number of interactions from large to small, and the popular interaction information can be displayed.

[0191] Corresponding to the information processing method of the embodiments shown in FIGS. 1-3, FIG. 4 is a schematic structural block diagram of an information processing device provided by the embodiments of the present disclosure. For ease of illustration, only the parts related to the embodiments of the present disclosure are shown. Referring to FIG. 4, the device 40 includes an acquisition unit 401, a writing unit 402, a first processing unit 403, and a second processing unit 404. Among them,

[0192] The acquisition unit 401 is configured to acquire interaction information in a target interaction tool.

[0193] The writing unit 402 is configured to automatically write the acquired interaction information into a first cell of a target table, the first cell being associated with a preset function.

[0194] The first processing unit 403 is configured to, in response to the interaction information being written into the first cell of the target table, process the interaction information based on a preset function to obtain a first processing result.

[0195] The second processing unit 404 is configured to write the first processing result into a second cell of the target table, or modify the content of the first cell, or perform a preset action based on the first processing result.

[0196] In some embodiments, the first processing unit 403 is further configured to: send prompt information based on the interaction information to a preset model, and obtain the first processing result based on feedback of the preset model.

[0197] In some embodiments, the obtaining unit 401 is further configured to:

[0198] extract the interaction information from the target session using the virtual object, the interaction information including at least one of: the target interaction information, and associated information of the target interaction information; wherein the target session satisfies a preset condition.

[0199] In some embodiments, the target interaction tool includes a target session, and the virtual object is set as a session member of the target session by a preset user; or,

[0200] determine a target session in which the preset user is located according to a preset user identifier, and add the virtual object to the target session.

[0201] In some embodiments, the first processing unit 403 is further configured to:

[0202] generate the prompt information based on a rule corresponding to the preset function, the prompt information including at least part of the interaction information or processing information for processing at least part of the interaction information;

[0203] send the prompt information to a preset model based on model calling information associated with the preset function, and perform information processing according to the prompt information by the preset model.

[0204] In some embodiments, the prompt information indicates classification of the interaction information to obtain a classification result of the interaction information, and the prompt information further includes a preset label set for classification.

[0205] In some embodiments, the preset label set in the prompt information is obtained by referencing a cell or a sub-table recording the preset label set.

[0206] In some embodiments, the preset label set includes a user-defined label.

[0207] In some embodiments, the preset label set includes a label set corresponding to a multi-level classification respectively.

[0208] In some embodiments, the second processing unit 404 is further configured to:

[0209] in response to the i-th level classification result of the interaction information being written into the second cell, triggering i+1-th level classification of the interaction information;

[0210] wherein the i-th level classification result is obtained by processing the first prompt information by a preset model, and the first prompt information includes an i-th level classification label set used for i-th level classification of the interaction information, wherein i is an integer greater than or equal to 1.

[0211] In some embodiments, the second processing unit 404 is further configured to:

[0212] generate second prompt information based on a preset function for i+1-th level classification of the interaction information; the second prompt information includes a classification label set corresponding to i+1-th level classification;

[0213] send the second prompt information to the preset model based on the model calling information, and obtain i+1-th level classification result by the preset model according to the second prompt information for i+1-th level classification of the interaction information, and write the i+1-th level classification result into the third cell; wherein the classification label set corresponding to i+1-th level classification changes with the i-th level classification result.

[0214] In some embodiments, the prompt information further includes:

[0215] one or more examples; wherein the examples include example interaction information and example processing results generated by the example interaction information, or the examples include a context for generating processing results corresponding to an application scenario.

[0216] In some embodiments, the prompt information is obtained by referencing a cell or a sub-table used for recording examples.

[0217] In some embodiments, the one or more examples are editable.

[0218] In some embodiments, the preset function includes one or more of the following:

[0219] a classification function, a keyword extraction function, a content summary generation function, a text translation function, and a custom information processing function.

[0220] In some embodiments, the apparatus further includes a first sending unit (not shown in the figure), which is configured to:

[0221] send a prompt message to a target user or a preset session, the prompt message being generated according to the first processing result.

[0222] In some embodiments, the apparatus further comprises a second sending unit (not shown in the figure), configured to periodically send graphical statistical information to the target user or the preset session, the graphical statistical information being generated according to the first processing result corresponding to each of the plurality of interaction information.

[0223] To implement the above-mentioned embodiments, the present disclosure further provides an electronic device.

[0224] Referring to FIG. 5, a structural diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure is shown, which can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (PDA), tablet computers, portable multimedia players (PMP), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in FIG. 5 is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present disclosure.

[0225] As shown in FIG. 5, the electronic device 500 can include a processing device (e.g., a central processor, a graphics processor, etc.) 501, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 502 or loaded into a random access memory (RAM) 503 from a storage device 508. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0226] In general, the following devices can be connected to the I / O interface 505: input devices 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, and the like; output devices 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 508 including, for example, a magnetic tape, a hard disk, and the like; and communication devices 509. The communication devices 509 can allow the electronic device 500 to communicate wirelessly or wired with other devices to exchange data. While FIG. 5 illustrates the electronic device 500 with various devices, it is understood that all of the illustrated devices are not required to be implemented or possessed. More or less devices can alternatively be implemented or possessed.

[0227] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 509, or installed from the storage devices 508, or installed from the ROM 502. When the computer program is executed by the processing devices 501, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0228] It should be noted that the computer-readable medium in the above disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium containing or storing a program (computer execution instructions) that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer-readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to electrical wires, optical cables, RF (radio frequency), or the like, or any suitable combination thereof.

[0229] The computer-readable medium described above can be contained in the electronic device described above; or can exist separately and not be assembled into the electronic device.

[0230] The computer-readable medium described above carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

[0231] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0232] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0233] The units described in the embodiments of the present disclosure can be implemented by software, or by hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself.

[0234] The functions described in this description above can be performed or facilitated by one or more hardware logic components. For example, non-limiting examples of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0235] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0236] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0237] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0238] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An information processing method, comprising: obtaining interaction information in a target interaction tool; automatically writing the obtained interaction information into a first cell of a target table, the first cell being associated with a preset function; in response to the interaction information being written into the first cell of the target table, processing the interaction information based on the preset function to obtain a first processing result; writing the first processing result into a second cell of the target table, or modifying the content of the first cell, or executing a preset action based on the first processing result.

2. The method of claim 1, wherein, The processing of the interaction information to obtain a first processing result comprises: sending prompt information to a preset model based on the interaction information, and obtaining a first processing result based on the feedback of the preset model.

3. The method of claim 1, wherein, The obtaining of the interaction information in the target interaction tool comprises: extracting interaction information from the target interaction tool using a virtual object, the interaction information comprising at least one of the following: target interaction information, associated information of the target interaction information; wherein the target interaction tool satisfies a preset condition.

4. The method of claim 3, wherein, The target interaction tool comprises a target session, and the virtual object is set as a session member of the target session by a preset user; or determining a target session in which the preset user is located according to a preset user identifier, and adding the virtual object to the target session.

5. The method of claim 2, wherein, The sending of the prompt information to the preset model, and the obtaining of the first processing result based on the feedback of the preset model, comprises: generating the prompt information based on a generation rule corresponding to the prompt information of the preset function, the prompt information comprising at least part of the interaction information or processing information of at least part of the interaction information; sending the prompt information to the preset model based on model calling information associated with the preset function, and performing information processing on the prompt information by the preset model.

6. The method of claim 5, wherein, The prompt information indicates classification of the interaction information to obtain a classification result of the interaction information, and the prompt information further comprises a preset label set for classification.

7. The method of claim 6, wherein, The preset label set in the prompt information is obtained by referencing a cell or a sub-table recording the preset label set.

8. The method of claim 6, wherein, The preset label set comprises a custom label.

9. The method of claim 6, wherein, The preset label set comprises a label set corresponding to a multi-level classification.

10. The method of claim 9, wherein, The writing of the first processing result into the second cell of the target table, or the modification of the content of the first cell, or the execution of a preset action based on the first processing result, comprises: in response to an i-th level classification result of the interaction information being written into the second cell, triggering an (i+1)-th level classification of the interaction information; wherein the i-th level classification result is obtained by processing a first prompt information by a preset model, the first prompt information comprising an i-th level classification label set for the i-th level classification of the interaction information, wherein i is an integer greater than or equal to 1.

11. The method of claim 10, wherein, The triggering of the (i+1)-th level classification of the interaction information comprises: generating a second prompt information based on a preset function for the (i+1)-th level classification of the interaction information; the second prompt information comprising a classification label set corresponding to the (i+1)-th level classification. The second prompt information is sent to the preset model based on the model calling information, the preset model classifies the interaction information according to the second prompt information to obtain an (i+1)th-level classification result, and the (i+1)th-level classification result is written into a third cell; wherein the classification label set corresponding to the (i+1)th-level classification changes with the (i)th-level classification result.

12. The method of claim 5, wherein, The prompt information further comprises: one or more examples; wherein the examples comprise example interaction information and example processing results generated by the example interaction information, or the examples comprise contexts corresponding to application scenarios for generating processing results.

13. The method of claim 12, wherein, The prompt information is obtained by referencing a cell or a sub-table used for recording examples.

14. The method of claim 12, wherein, The one or more examples are editable.

15. The method of any one of claims 1-14, wherein, The preset function comprises one or more of the following: a classification function, a keyword extraction function, a content summary generation function, a text translation function, and a custom information processing function.

16. The method of any one of claims 1-14, wherein, The method further comprises: sending a prompt message to a target user or a preset session, the prompt message being generated according to the first processing result.

17. The method of any one of claims 1-14, wherein, The method further comprises: periodically sending graphical statistical information to a target user or a preset session, the graphical statistical information being generated according to first processing results corresponding to a plurality of interaction information respectively.

18. An information processing apparatus, comprising: an acquisition unit configured to acquire interaction information in a target interaction tool; a writing unit configured to automatically write the acquired interaction information into a first cell of a target table, the first cell being associated with a preset function; a first processing unit configured to, in response to the interaction information being written into the first cell of the target table, process the interaction information based on the preset function associated with the first cell to obtain a first processing result; a second processing unit configured to write the first processing result into a second cell of the target table, or modify content of the first cell, or execute a preset action based on the first processing result.

19. An electronic device, comprising: comprises: a processor and a memory; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, so that the processor executes the method of any one of claims 1 to 16.

20. A computer readable storage medium, wherein, The computer readable storage medium stores computer execution instructions, and when the processor executes the computer execution instructions, the method of any one of claims 1 to 17 is implemented.

21. A computer program product comprising a computer program, wherein, The computer program is executed by the processor to implement the method of any one of claims 1 to 17.

Images