Information processing method and device and electronic equipment

Abstract

Embodiments of the invention provide an information processing method and apparatus, and an electronic device. The method comprises the steps of obtaining interaction information in a target interaction tool; automatically writing the obtained interaction information into a first cell of a target table, wherein the first cell is associated with a preset function; processing the interaction information based on a preset function in response to the interaction information written into a first cell of the target table to obtain a first processing result; and 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. All stages of obtaining the interaction information from the target interaction tool based on the table, processing the interaction information to generate the target object, displaying the target object or executing the preset action are connected into a complete processing flow, so that the intelligence and efficiency of interaction information processing are improved; the processing efficiency of scenes such as product problem repair and order processing can be improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to an information processing method, device, and electronic device. Background Art

[0002] With the development of Internet technology, the amount of data exchanged between users using the Internet is increasing. Faced with massive amounts of data, it is difficult for users to efficiently obtain the information they need, and the information processing efficiency is low. Summary of the invention

[0003] Embodiments of the present disclosure provide an information processing method, device, and electronic device.

[0004] In a first aspect, an embodiment of the present disclosure provides an information processing method, comprising: acquiring interaction information within 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 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 performing a preset action based on the first processing result.

[0005] In a second aspect, an embodiment of the present disclosure provides an information processing device, comprising: an acquisition unit, used to acquire interaction information within a target interaction tool; a writing unit, used to automatically write the acquired interaction information into a first cell of a target table, wherein the first cell is associated with a preset function; a first processing unit, used to process the interaction information based on the preset function associated with the first cell in response to the interaction information being written into the first cell of the target table, to obtain a first processing result; and a second processing unit, used to write the first processing result into a second cell of the target table, or to modify the content of the first cell, or to perform a preset action based on the first processing result.

[0006] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0007] The memory stores computer-executable instructions;

[0008] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method described in the first aspect and various possible designs of the first aspect.

[0009] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the method described in the first aspect and various possible designs of the first aspect are implemented.

[0010] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect and various possible designs of the first aspect.

[0011] The information processing method, device and electronic device provided by the present embodiment obtain interactive information in a target interactive tool; automatically write the obtained interactive information into a first cell of a target table, wherein 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, based on the preset function, process the interactive information to obtain a first processing result; 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, thereby connecting the various stages of obtaining interactive information from a target interactive tool, processing the interactive information to generate a target object, and displaying the target object or performing a preset action into a complete processing flow based on a table, thereby improving the intelligence and efficiency of interactive information processing and display of processing results. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0013] Figure 1 Schematic flow chart of the information processing method provided in the embodiment of the present disclosure Figure 1 ;

[0014] Figure 2 Schematic flow chart of the information processing method provided in the embodiment of the present disclosure Figure 2 ;

[0015] Figure 3 Schematic flow chart of the information processing method provided in the embodiment of the present disclosure Figure 3 ;

[0016] Figure 4 A schematic structural diagram of an information processing device provided in an embodiment of the present disclosure;

[0017] Figure 5A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0019] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0020] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0021] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0022] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0024] Users can exchange information through the Internet, for example, users use applications with information exchange functions to communicate with other users.

[0025] User needs and potential problems can be obtained based on the analysis of interactive information.

[0026] In some application scenarios, the interaction information can be manually analyzed to extract useful information such as user needs and potential problems. However, as the amount of interaction information increases, it is difficult for users to efficiently obtain useful information from the massive amount of interaction information.

[0027] In one example, a preset keyword list may be set to filter the interaction information, filtering out the interaction information related to the keywords in the keyword list. Such a solution has limited coverage, cannot fully obtain useful information, and may also result in detection errors.

[0028] In another example, a series of rules and conditions can be defined to classify and process the interactive information. However, such a solution has the problem of high labor cost, and the flexibility and scalability need to be improved. In addition, in the above two examples, the various processing stages of the interactive information are decentralized, first collected and then processed and analyzed uniformly. Therefore, the efficiency of processing and responding to the interactive information is low.

[0029] The solution provided by the present disclosure obtains interactive information, writes the interactive information into a spreadsheet, and uses a data analysis tool integrated in the spreadsheet to process the interactive information and fills the processing results into the spreadsheet. The spreadsheet can be used to integrate various stages of processing such as collecting, analyzing, and processing interactive information, writing processing results in the spreadsheet, or responding to processing results, thereby improving the efficiency of processing interactive information and helping to increase the speed of responding to interactive information.

[0030] Please refer to Figure 1 , Figure 1 A schematic diagram of an information processing method provided in an embodiment of the present disclosure Figure 1 ,like Figure 1 As shown, the method comprises the following steps:

[0031] S101: Acquire interaction information in a target interaction tool.

[0032] The target interaction tool here may be an application program for information interaction, such as an application program with an instant messaging function.

[0033] Users can use the target interaction tool to exchange information. In the target interaction tool, multiple interactive information can be generated by information interaction between users.

[0034] The execution subject of the information processing method may be a terminal device, such as an application running in the terminal device. In some application scenarios, the application may integrate a spreadsheet application and an information interaction application. In these application scenarios, the target interaction tool may be an information interaction application integrated in the application. The execution subject may periodically obtain the interaction information in the target interaction tool.

[0035] S102: Automatically write the acquired interaction information into a first cell of a target table, where the first cell is associated with a preset function.

[0036] The target table may include a plurality of cells, and the plurality of cells may include a first cell associated with a preset function.

[0037] In some application scenarios, the first cell is located in column A of the target table, and the preset function is set in one or more cells in other columns B, wherein column A is associated with column B.

[0038] In some application scenarios, a preset function may be associated with a column storing information having certain characteristics and / or types. For example, the content stored in a column may be content described in a preset language, and the column may be associated with a translation function. The cell in the column may be the first cell.

[0039] After acquiring the interaction information in the target interaction tool, the execution subject may automatically write the interaction information into the first cell in the target table, for example, the interaction information may be written into one or more first cells of the target table according to a preset writing rule.

[0040] 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.

[0041] When it is detected that the interaction information is written into the first cell of the target table, the interaction information may be processed by a preset function associated with the first cell to obtain a first processing result.

[0042] The preset function may have the function of semantically analyzing the interaction information. By processing the interaction information through the preset function, a first processing result of the interaction information may be obtained.

[0043] The above-mentioned processing of the interactive information includes translating the interactive information according to a preset function, understanding the semantics, generating a summary, etc.

[0044] S104: writing the first processing result into the second cell of the target table, or modifying the content of the first cell, or performing a preset action based on the first processing result.

[0045] In some application scenarios, the first processing result may be written into a second cell, where the second cell may be a cell different from the first cell, for example, a cell located in a different column or row from the first cell.

[0046] 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 modification of the content of the first cell may 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.

[0047] The replacing of the original content in the first cell means replacing the interactive information in the first cell with the first processing result.

[0048] The above-mentioned keeping the original content in the first cell unchanged and adding the first processing result, for example, can be to add the first processing result to a specified position of the interactive information stored in the first cell (for example, after the interactive information), and thereby splicing the first processing result with the above-mentioned interactive information.

[0049] The above-mentioned modification of the original content in the first cell includes modifying part of the content (including words and sentences) in the interactive information stored in the first cell using the first processing result.

[0050] In some application scenarios, after obtaining the first processing result, a preset action may be performed based on the first processing result. For example, when the first processing result meets certain conditions, interactive information may be sent to a target object. The target object here may be a contact or a conversation.

[0051] 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 writing the first processing result into the second cell, the preset action is executed based on the first processing result.

[0052] In this embodiment, the interaction information in the target interaction tool is obtained; 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, the interaction 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 performed based on the first processing result, thereby connecting the various stages of obtaining the interaction information from the target interaction tool, processing the interaction information to generate a target object, and displaying the target object or performing a preset action into a complete processing flow based on the table, thereby improving the intelligence and efficiency of the interaction information processing and the display of the processing results.

[0053] In some embodiments, the above step S103 includes:

[0054] Prompt information is sent to the preset model based on the interaction information, and a first processing result is obtained based on feedback from the preset model.

[0055] In these embodiments, the preset function may call the preset model through model calling information. The preset model may be any model with natural language processing capability. The model calling information may include, for example, a model calling interface.

[0056] When the interaction information is written into the first cell, the preset function is triggered to call the preset model through the model calling information according to the association relationship between the first cell and the preset function. 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.

[0057] In these embodiments, the prompt information including the interaction information may be sent to a preset model, and the preset model processes the interaction information according to the prompt information, thereby improving the efficiency of processing the interaction information.

[0058] Please refer to Figure 2 , Figure 2 A schematic diagram of an information processing method provided in an embodiment of the present disclosure Figure 2 ,like Figure 2 As shown, the method comprises the following steps:

[0059] S201: Extracting interaction information from a target interaction tool using a virtual object.

[0060] The interaction information includes at least one of the following: target interaction information and associated information of the target interaction information; the target interaction tool may be, for example, a target conversation or a target conference. The target interaction tool satisfies a preset condition, for example, there are preset members in the target conversation, or there are preset keywords in the subject words of the target conference, and there are target persons among the participants.

[0061] In this embodiment, the execution subject of the information processing method may be a terminal device, specifically an application program running in the terminal device.

[0062] When the target interactive tool includes a target session, the target session here may be one or more sessions generated in the target interactive tool, and the one or more sessions may be sessions with preset users as session members, or sessions that meet other preset conditions. The preset users may be users who log in to the application. The virtual objects may be session members of the target session.

[0063] The target session may be a session that meets preset conditions. The preset conditions may be, for example, one or more of the following: a session in which the session members include a specified user, one or more sessions corresponding to a specified session topic, and a preset session type. The preset session type may be a session organized in a topic manner.

[0064] For example, the target session may be a session whose session members include user S, where user S may be any specified user. If it is detected that a session member includes user S, then the session meets the preset condition.

[0065] For another example, the target session may be one or more sessions with a session topic of T. If it is detected that the session topic corresponding to the session is T, then the session meets the preset condition.

[0066] The virtual object may be, for example, a virtual object application client, and the virtual object may obtain one or more pieces of interaction information of a target session.

[0067] As an example, the virtual object may be a member of a target session. In the target session, the virtual object collects interaction information in the target session according to authorization.

[0068] In another example, the target session where the preset user is located is determined according to the preset user identifier, and the virtual object is added to the target session. In this example, the target session where the preset user is located can be determined from multiple 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.

[0069] In some implementations, virtual objects may be used to periodically collect and update interaction information in a target session.

[0070] In some other implementations, when updated interaction information is detected in the target session, the updated interaction information may be collected using a virtual object.

[0071] The interaction information here 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, replyer information, reply content, attachments, reply quantity, etc.

[0072] The sender information indicates the sender of the target interaction information, including but not limited to the sender's user ID.

[0073] The above-mentioned responder information indicates the responder of the target interactive information, including but not limited to the user ID of the responder.

[0074] The above attachments include attachments of target interactive information and may also include attachments in reply content.

[0075] S202: Automatically write the acquired interaction information into a first cell of a target table, where the first cell is associated with a preset function.

[0076] In some implementations, after acquiring the interaction information in the target session, the execution subject may automatically write the interaction information into the first cell of the target table. The target table may be a pre-created electronic table for carrying the interaction information, preset functions, and processing results of the interaction information.

[0077] As an implementation method, the execution subject may establish an association relationship between the virtual object and the target table according to the user operation. After the virtual object collects the interaction information in the target session, the interaction information may be written into the first cell of the target table.

[0078] The target table may include multiple rows and multiple columns. The first cell may include one or more cells belonging to the same row or the same column.

[0079] In one example, the first cell may include multiple cells belonging to the same row but different columns. For example, the first cell may include cells in the kth row and the jth to j+nth columns in the target table. Here, k, j, and n are all integers greater than 0.

[0080] The interaction information obtained from the target session may be written into the first cell. The interaction information includes target interaction information (eg, original information) and associated information of the target interaction information.

[0081] Each message in the target session has a message type attribute, which includes an original message type and a reply message type. For each message, it can be determined whether the message is an original message or a reply message to the original message based on the message type attribute of the message. The reply message here can be regarded as associated information of the original message.

[0082] In an example, the target interaction information and the associated information of the target interaction information may be stored in the same first cell.

[0083] In some implementations, the target interaction information may be stored in the first cell corresponding to the kth row and jth column of the target table, and the associated information of the target interaction information may be stored in other first cells of the kth row and jth to j+nth columns. For example, each associated information is stored in another first cell.

[0084] In these implementations, the j-th column to the j+n-th column of each row of the target table may respectively store one target interaction information and the associated information corresponding to the one target interaction information.

[0085] As an example, it is possible to pre-configure which information data is recorded in each column from the jth column to the j+nth column, for example, the jth column records the 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 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 of the recorded interaction information (such as a session), and the j+6th column can record the session identifier of the target interaction information. The j+7th column can record the time information when the target interaction information is generated, etc. It is understandable that other relevant information of the target interaction information can also be recorded in other columns of the above-mentioned target table. The other relevant information recorded can be set according to the specific application scenario, which is not limited here.

[0086] S203: In response to the interaction information being written into the first cell of the target table, prompt information is sent to a preset model based on a preset function and the interaction information, and a first processing result is obtained based on feedback from the preset model.

[0087] In this embodiment, the preset function can be built into the target table, for example, integrated into the first cell or other cells other than the first cell in the target table. The preset function can call the preset model through the interface. The preset model can have the ability to analyze and process natural language.

[0088] In some application scenarios, the preset function may also be set in a subtable of the target table, and the subtable and the subtable where the cell recording the interactive information is located may be different subtables of the target table.

[0089] In some application scenarios, the above-mentioned preset function may be set in one or more cells associated with the first cell in the subtable where the first cell is located, and the one or more cells may belong to the same column or the same row.

[0090] The preset function may be a custom function, and the preset function is triggered by a target cell writing information event. The preset function may call a preset model through model calling information. The preset model may be a model with natural language processing capabilities.

[0091] 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 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 prompt information, and sends the processing result obtained by processing the interaction information to the preset function through the above preset model calling interface.

[0092] In some implementations, the preset function may further include processing information indicating what kind of processing is performed on the interaction information. Illustratively, the processing information may include, for example, information indicating how to classify the interaction information, information indicating how to extract keywords, information indicating how to translate the interaction information, etc. Correspondingly, the prompt information generated according to the preset function may also include the processing information.

[0093] In these implementations, the preset function may send the prompt information to a preset model, and the preset model processes the interaction information according to the processing information in the prompt information.

[0094] Correspondingly, the above preset functions may include one or more of the following:

[0095] Classification function, keyword extraction function, content summary generation function, text translation function, and custom information processing function.

[0096] Each preset function can be integrated into a cell corresponding to the preset function. Different preset functions are integrated into different cells.

[0097] The above-mentioned classification function is used to classify the interaction information according to the preset classification results. The above-mentioned classification results may, for example, include more than two preset classification results. Each preset classification result corresponds to a classification label. The above-mentioned preset classification results may, for example, include: functional demands, performance optimization, interaction and operation editability, functional consultation, product defects, etc. In addition, the above-mentioned preset classification results may also include positive evaluations and negative evaluations. In some examples, the above-mentioned prompt information may include the above-mentioned more than two preset classification results and the above-mentioned interaction information.

[0098] The keyword extraction function is used to extract keywords from the interaction information. Correspondingly, the prompt information may include the interaction information and processing information for extracting keywords from the interaction information.

[0099] The content summary generation function is used to summarize the content of the interaction information. Correspondingly, the prompt information may include the interaction information and processing information for summarizing the content of the interaction information.

[0100] The text translation function is used to summarize the content of the interactive information. Correspondingly, the prompt information may include the interactive information, the target language into which it is translated, and the processing information of translating the interactive information.

[0101] The above-mentioned custom information processing function may indicate to perform custom processing on the interaction information, and the above-mentioned custom processing may be set according to the application scenario.

[0102] The preset function may indicate that the first processing result is written into the second cell. In some application scenarios, the preset function may be integrated into the second cell.

[0103] In an illustrative manner, if the preset function is a classification function, when the interaction information is written into the first cell, a prompt message may be sent to the preset model based on the interaction information, and the prompt message is 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 to the preset function as feedback information. The preset function may write the classification result indicated by the feedback information into the second cell.

[0104] In an illustrative manner, if the preset function is a translation function, when the interaction information is written into the first cell, a prompt message can be sent to the preset model based on the interaction information, and the prompt message is used to instruct the preset model to translate the interaction information in the first cell, and translate it into a target language (such as English, Chinese, etc.) to obtain a translation result, and return the translation result to the preset function as feedback information. The preset function can write the translation result indicated by the feedback information into the second cell.

[0105] In an illustrative manner, if the preset function is a keyword extraction function, when the interaction information is written into the first cell, prompt information can be sent to the preset model based on the interaction information, and the prompt information is 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.

[0106] In some implementations, the above step S203 includes the following sub-steps:

[0107] First, based on a prompt information generation rule corresponding to a preset function, prompt information is generated, where the prompt information includes at least a portion of the interaction information and processing information for processing at least a portion of the interaction information;

[0108] Secondly, based on the 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.

[0109] In these implementations, the prompt information generation rule may include processing information, at least a portion of the interaction information, a preset text content of the connection interaction information and processing information, and output prompt information. At least a portion of the interaction information may be, for example, the original information in the interaction information. The output prompt information is used to indicate the output processing result. In some examples, the output prompt information may also include an output format.

[0110] Illustratively, the prompt information generation rule may be, for example: "Help me extract the keywords of "information in the cell recording the original information", and output the keywords", wherein "help me extract" and "of" are preset text contents connecting at least a part of the interactive information and the processed information, and the "keywords" are the processed information. The "output keywords" are output prompt information.

[0111] The prompt information generated according to the prompt information generation rule can prompt the preset model to process at least a part of the interactive information according to the processing information.

[0112] The above-mentioned model calling information may include, for example, a model calling interface, the above-mentioned preset function may be associated with the model calling information, and the above-mentioned execution subject may send the prompt information to the preset model through the above-mentioned model calling information, and the preset model may process at least part of the interactive information according to the processing information in the prompt information.

[0113] It is understandable that the multiple interaction information obtained from the target session can be written into the first cells of different rows or columns. The interaction information written into the first cells corresponding to each other 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 in the target table.

[0114] In some application scenarios, the input set may consist of original information of the interaction information, that is, for each interaction information, the original information and corresponding processed information in the interaction information may be used as inputs of the preset function.

[0115] After the plurality of interaction information in the target session is written into the first cells corresponding to the target table, the preset functions corresponding to the first cells can be automatically triggered. The preset function can call the preset model according to the model calling information, and input the prompt information corresponding to the interaction information in the first cells into 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 processed information from the prompt information, and process the original information according to the processed information.

[0116] The above process can be described by the following formula (1):

[0117] y = preset function (x) (1);

[0118] Among them, y is the first processing result, and x is the original information entered in the first cell.

[0119] The preset function receives feedback from the preset model, obtains a first processing result according to the feedback, and writes the first processing result into the second cell for display so that the user can view it.

[0120] S204: writing the first processing result into the second cell of the target table, or modifying the content of the first cell, or performing a preset action based on the first processing result.

[0121] The specific implementation of step S204 can refer to Figure 1 The relevant parts of the illustrated embodiment are not described in detail here.

[0122] 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, a prompt message is sent to the preset model based on the preset function associated with the first cell and the interaction information, and a first processing result is obtained based on feedback from the preset model, thereby realizing automatic acquisition of the conversation information in the target conversation by the virtual object, and setting a preset function for calling the preset model in the table, and the preset function calls the preset model to process the interaction information, which can further improve the efficiency of processing the interaction information.

[0123] In these embodiments, when interaction information is input into the first cell of the target table, the preset function referencing the first cell is triggered to generate prompt information according to prompt information generation rules, and the prompt information is input into the preset model through the model calling interface. Since the above prompt information includes interaction information and processing information, the preset model can conduct targeted analysis of the interaction information based on the processing information, so that the output processing result has a higher accuracy rate.

[0124] In some embodiments, the prompt information indicates to classify the interaction information to obtain a classification result of the interaction information, and the prompt information also includes a preset tag set for classification.

[0125] In these embodiments, the preset function may be a function for classifying the interaction information. The preset tag set may include one or more preset tags.

[0126] As an implementation, the prompt information generation rule corresponding to the preset function may include a preset tag set. That is, the preset tag set may be written into the prompt information generation rule. The prompt information generated according to the prompt information generation rule may include at least a part of the interaction information, the processing information and the preset tag set.

[0127] As an implementation manner, the preset label set in the prompt information is obtained by referencing the cell or subtable that records the preset label set.

[0128] In this implementation, the preset tag set may include one or more classification tags. Each classification tag may correspond to a preset classification result. The preset tag set may be recorded in a cell of the target table or in a cell of another table.

[0129] The prompt information generation rule may reference a cell recording a preset label set, so that the preset label set is written into the prompt information. The cell recording the preset label set may be located in the target table or in other tables.

[0130] In some embodiments, the preset tag set includes user-defined tags.

[0131] In these embodiments, the user can edit one or more custom tags in a cell that records a preset tag set. The preset function can obtain the user-defined tag by referencing the cell. For another example, the user can edit the user-defined tag in a cell of a sub-table of the target table, and the preset function can obtain the user-defined tag by referencing the sub-table.

[0132] In this embodiment, the interaction information can be classified according to the personalized needs of the user through the user-defined tags, so that the obtained classification results match the personalized needs of the user.

[0133] In some embodiments, the preset tag set includes multi-level classification tags. The multi-level classification tags can be recorded in different cells.

[0134] In these embodiments, the first-level classification tags may include different types of first-level classification tags. For each first-level classification tag, there may be a corresponding second-level classification tag set belonging to the first-level classification tag, and the second-level classification tag set may be recorded in one cell. Second-level classification tag sets belonging to different first-level classification tags may be recorded in different cells.

[0135] The second-level classification label set may also include different types of second-level classification labels. For each second-level classification label, there may be a corresponding third-level classification label set belonging to the second-level classification label, and the third-level classification label set may be recorded in one cell. The third-level classification label sets belonging to different second-level classification labels are recorded in different cells, and so on.

[0136] Therefore, for multi-level classification labels, each type of classification label in the previous level corresponds to a classification label set in the next level. The classification label sets in the next level corresponding to different classification labels in the previous level are recorded in different cells.

[0137] In these embodiments, by setting multi-level classification labels, it is possible to facilitate multi-level classification of the interaction information.

[0138] In some embodiments, the above-mentioned writing the first processing result into the second cell of the target table, or modifying the content of the first cell, or performing a preset action based on the first processing result, includes:

[0139] In response to the i-th level classification result of the interaction information being written into the second cell, the i+1-th level classification of the interaction information is triggered; 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 the i-th level classification label set for performing the i-th level classification of the interaction information, wherein i is an integer greater than or equal to 1.

[0140] The following is an example of multi-level classification including secondary classification. In response to the interaction information obtained from the target session being written into the first cell, a preset function for performing the first-level classification on the interaction information is triggered, and the preset function can generate the first prompt information according to the associated prompt information generation rule. The first prompt information includes at least a portion of the above-mentioned interaction information, a first-level classification label set, and processing information indicating that at least a portion of the interaction information is classified.

[0141] The first-level classification label set can be obtained by the reference of the cell recording the first-level classification label set by the prompt information generation rule. As an exemplary illustration, the prompt information generation rule can be, for example: please classify "XXXX" and output one of the classification label sets "reference T2 table row 1 column 2". Multiple first-level classification labels are recorded in T2 table row 1 column 2, and the multiple first-level classification labels can include user-defined classification labels.

[0142] The generated first prompt information instructs the preset model to classify at least a portion of the above-mentioned interactive information according to multiple first-level classification labels in the first-level classification label set.

[0143] The preset function corresponding to the first level classification can be integrated in a fourth cell outside the first cell. In one example, the fourth cell can be in the same row or column as the first cell. After obtaining the first level classification result of the interactive information, the first level classification result can be written into the second cell.

[0144] In response to the first level classification result of the interaction information being written into the second cell, a second level classification of the interaction information is triggered, thereby obtaining a secondary classification result of the interaction information.

[0145] Multi-level classification of interactive information helps to establish a hierarchical structure of interactive information and facilitates systematic storage of interactive information.

[0146] In some embodiments, the triggering of the i+1th level classification of the interaction information includes the following steps:

[0147] First, second prompt information is generated based on a preset function for classifying the interactive information at the i+1 level; the second prompt information includes a classification label set corresponding to the i+1 level classification;

[0148] Secondly, based on the model call information, the second prompt information is sent to the preset model, and the preset model performs the i+1th level classification on the interaction information according to the second prompt information to obtain the i+1th level classification result, and writes the i+1th level classification result into the third cell; wherein the classification label set corresponding to the i+1th level classification changes with the change of the classification result of the i-th level.

[0149] Still taking the secondary classification as an example, the interaction information obtained from the target session 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.

[0150] The first-level classification result of the interaction information is written into the second cell, triggering a preset function call prompt information generation rule for the second-level classification of the interaction information to generate second prompt information; the second prompt information includes 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.

[0151] The above-mentioned prompt information generation rule can be, for example, "Please classify XXXX, and output one of the classification results in the second-level classification label set of "row 1 to row n, column 2 to column m of T2 table" that belongs to the first-level classification result recorded in "row 2, column 4 of T1 table". Among them, "row 1 to row n, column 2 to column m of T2 table" can record the label sets corresponding to multiple levels of classification, and can also record the correspondence between each classification label of the first level and the classification label set of the second level. Therefore, after determining the classification results of the first level, the corresponding second-level classification label set can be found in multiple cells or subtables recording the multi-level classification label set according to the above-mentioned correspondence.

[0152] Schematically, the first-level classification tags in the first-level classification tag set include: document, table, etc. The second-level classification tag set corresponding to the first-level classification tag "document" includes: format brush, font modification, undo, copy, paste, etc. The second-level classification tag set corresponding to the first-level classification tag "table" includes: worksheet, add cell, delete cell, set row height, etc. The above-mentioned first-level classification tag set is recorded in sub-table T2. Schematically, the multi-level classification tag sets are respectively recorded in multiple cells of the j-th column of the above-mentioned sub-table T2, and the identifier corresponding to each tag set can be recorded in the i-th column. The identifier of each classification tag set may include the classification level corresponding to the classification tag set, and the corresponding information between the classification tag set and the classification tags in the previous level classification tag set.

[0153] If the classification result of the first-level classification corresponding to the interactive 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 above preset function.

[0154] The identifier of the target second-level classification tag set corresponding to the document can be found in the i-th column of subtable T2 according to the identifier of the tag set. After finding the identifier of the target second-level classification tag set, for example, the identifier of the target second-level classification tag set is located in the r-th row, and the r-th row and j-th column can be used as the cell referenced by the above prompt information rule. Wherein, r is an integer greater than 0. Through the above reference, the second-level classification tag set recorded in the r-th row and j-th column can be written into the above second prompt information, and the second-level classification tag set includes format brush, font modification, undo, copy, paste, etc.

[0155] When the classification result of the first-level classification of the interactive information is "table", after "table" is written into the second cell, the preset function associated with the second cell is triggered to generate second prompt information according to the prompt information generation rule; the second prompt information includes at least part of the above-mentioned interactive information, a second-level classification label set belonging to "table", and processing information indicating the classification of at least part of the interactive information.

[0156] The execution subject may send the second prompt information to the preset model, and the preset model performs a second-level classification on the interactive information according to the second prompt information to obtain a second-level classification result, and sends the second-level classification result to the execution subject, and the execution subject may write the second-level classification result into a third cell. The third cell here may be a cell in the same row as the second cell.

[0157] That is, in the scenario of multi-level classification of interactive information, after the classification results of the previous level are determined, the corresponding classification label set of the next level is automatically determined based on the classification results of the previous level, thereby realizing dynamic adjustment of the secondary classification labels according to the classification results of the previous level, thereby improving the accuracy and flexibility of multi-level classification.

[0158] In some embodiments, the prompt information also includes:

[0159] One or more examples; wherein the example includes example interaction information and example processing results generated by the example interaction information, or the example includes a context corresponding to an application scenario for generating a processing result.

[0160] In some application scenarios, the above examples may 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 clear intentions to the preset model, so that the preset model can better understand user needs; in addition, the above examples can enable the preset model to better capture task requirements, thereby generating more accurate outputs.

[0161] In some application scenarios, the above examples may also include context information for generating processing results. The above context information is background information related to the task, and the context information may provide historical scene information. Adding context information to the examples helps the preset model better understand the environment or scenario of the task, and helps to obtain processing results that are more consistent with the context.

[0162] In these embodiments, by adding examples to the prompt information, the preset model can understand the task more accurately, thereby obtaining a processing result with higher accuracy.

[0163] In some embodiments, the prompt information obtains one or more examples by referencing a cell or a subtable used to record the examples.

[0164] In some application scenarios, one or more examples are recorded in corresponding cells, and the prompt information can obtain the one or more examples by referencing the above cells.

[0165] The cell recording one or more examples may be located in the same target table as the first cell, or 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 may specify the table and cell where the one or more examples are located.

[0166] In some application scenarios, one or more examples are recorded in a sub-table of the target table. In these application scenarios, the above prompt information can obtain one or more examples by referencing the sub-table.

[0167] In these embodiments, one or more examples are written in the prompt information by referencing a cell or a sub-table, which helps to improve the efficiency of writing examples in the prompt information and improves the efficiency of generating the prompt information.

[0168] In some embodiments, the above examples are editable. In these embodiments, users can edit the examples in the cells where the examples are located, for example, adding examples that match the scenario, deleting redundant examples, changing existing examples according to scenario requirements, etc. By editing the examples by the user, user-personalized examples can be provided to the preset model, so that the model's processing of the interactive information is more compatible with the user's personalized needs.

[0169] In some embodiments, the prompt information generation rules may be editable. That is, the user may edit the prompt information generation rules according to personalized needs, such as modifying the reference to the example, modifying the reference to the tag set, editing the custom text, etc. In these embodiments, by editing the prompt information generation rules, prompt information that is more adaptable to the user's needs and more compatible with the application scenario may be generated, thereby improving the accuracy of the processing results generated according to the prompt information.

[0170] Please refer to Figure 3 , Figure 3 Schematic flow chart of the information processing method provided in the embodiment of the present disclosure Figure 3 , as shown in the figure, the method includes the following steps:

[0171] S301: Acquire interaction information in a target interaction tool.

[0172] S302: Automatically write the acquired interaction information into a first cell of a target table, where the first cell is associated with a preset function;

[0173] S303: In response to the interaction information being written into the first cell of the target table, based on a preset function associated with the first cell, the interaction information is processed to obtain a first processing result;

[0174] S304: writing the first processing result into the second cell of the target table, or modifying the content of the first cell, or performing a preset action based on the first processing result.

[0175] The specific implementation of the above steps S301 to S304 can refer to Figure 1 The detailed description of steps S101 to S103 of the illustrated embodiment is omitted here.

[0176] S305: Send a prompt message to the target user or the preset session, where the prompt message is generated according to the first processing result.

[0177] The interactive information with a high degree of importance may be determined according to the first processing result. A prompt message may be generated in real time for the interactive information with a high degree of importance, and the prompt message may be sent to the target user or a preset session. There is no limitation on the method of sending the prompt message to the target user, for example, the prompt message may be sent to the user by email or the like.

[0178] The target user may be a pre-specified user, and the preset session may be a pre-specified session. The target user may process or reply to the interaction information. The preset session may include users who can process or reply to the interaction information.

[0179] Illustratively, if the classification result of a piece of interactive information is product defect feedback, the importance of the interactive information is relatively high.

[0180] In some embodiments, the above-mentioned prompt message is displayed as an interactive information card. The above-mentioned interactive information card can be set with different areas, and each area records a specified part of the content in the prompt message. For example, the interactive information card may include a first area, a second area, a third area, and a fourth area. The first area records the interactive information category, the second area records the target session information, the third area records the time information when the interactive information is generated, and the fourth area records the original interactive information. In addition, the above-mentioned interactive information card also includes a control for responding to the interactive information. By triggering the control, the session where the interactive information is located can be displayed and the location where the interactive information appears in the session can be located. By displaying the interactive information card, it can help users quickly obtain relevant information from the interactive information card.

[0181] In this embodiment, by generating a prompt message of the interactive information according to the first processing result, the interactive information that needs to be processed quickly can be identified from the interactive information recorded in the target table, reducing the workload of manually identifying the interactive information that needs to be processed quickly. In addition, the time required to identify the interactive information that needs to be processed quickly can be shortened to improve the response speed of the interactive information. By automatically generating the above prompt message from the first processing result generated by the interactive information in the table, operational continuity can be easily maintained, which helps to maintain the continuity and stability of business operations.

[0182] In addition, the solution provided by this embodiment obtains interactive information from the target session, calls a preset model to process the interactive information to generate a first processing result, displays the first processing result, and triggers the sending of a prompt message according to the first processing result, so that these functions of different stages of interactive information processing are integrated into the target table, and the functions of the table itself are used to simplify the code for implementing the above-mentioned different stages of processing of interactive information of multiple sessions, which can reduce the difficulty of development. In addition, the efficiency and accuracy of information processing are achieved.

[0183] In some embodiments, the method further includes: periodically sending graphical statistical information to a target user or a preset session, where the graphical statistical information is generated according to first processing results corresponding to the plurality of interaction information.

[0184] The period length corresponding to the above periodicity may be, for example, 1 natural day, 1 week, etc. The above period length may be set according to a specific application scenario and is not limited here.

[0185] The graphical statistical information includes one or more of the following: a bar chart of interaction information categories, a word cloud chart, and a ranking result of different interaction information according to the frequency of occurrence.

[0186] The interactive information classification histogram may include histograms corresponding to different classification results in a period, and each classification result is generated by the amount of interactive information belonging to the classification result in the period.

[0187] In an illustrative manner, the above classification results may include, for example, function requests, performance issues, user interface improvement suggestions, etc. The number of interactive information belonging to each classification result in a period may be counted, and then an interactive information classification bar chart may be generated according to the number of interactive information corresponding to the multiple classification results. The interactive information classification bar chart may display the number of interactive information corresponding to each classification result, and may clearly indicate the urgency and frequency of each classification result.

[0188] In some embodiments, keywords can be extracted from each interactive information within a period, and then the frequency of occurrence of each keyword is counted, and a word cloud diagram is constructed according to the hot spots of each keyword according to the frequency of occurrence and the popularity of different keywords. The word cloud diagram can intuitively reflect the focus of user discussion.

[0189] In some embodiments, the interaction information may be sorted, for example, the interaction information may be sorted in descending order according to the number of interactions of the interaction information, and popular interaction information may be displayed.

[0190] Corresponding to the above Figure 1 to Figure 3 The information processing method of the illustrated embodiment, Figure 4 A schematic structural block diagram of an information processing device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 4 The device 40 includes: an acquisition unit 401, a writing unit 402, a first processing unit 403 and a second processing unit 404.

[0191] An acquisition unit 401 is used to acquire interaction information in a target interaction tool;

[0192] A writing unit 402, used to automatically write the acquired interaction information into a first cell of a target table, the first cell being associated with a preset function;

[0193] A first processing unit 403 is configured to process the interaction information based on a preset function to obtain a first processing result in response to the interaction information being written into the first cell of the target table;

[0194] The second processing unit 404 is used to write the first processing result into the 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.

[0195] In some embodiments, the first processing unit 403 is further used to: send prompt information to a preset model based on the interaction information, and obtain a first processing result based on feedback from the preset model.

[0196] In some embodiments, the acquisition unit 401 is further configured to:

[0197] The virtual object is used to extract interaction information from the target session, where the interaction information includes at least one of the following: target interaction information and associated information of the target interaction information; wherein the target session meets a preset condition.

[0198] In some embodiments, the target interaction tool includes a target session, and the virtual object is set by a preset user as a session member of the target session; or,

[0199] The target session where the preset user is located is determined according to the preset user identifier, and the virtual object is added to the target session.

[0200] In some embodiments, the first processing unit 403 is further configured to:

[0201] Generate prompt information based on a prompt information generation rule corresponding to a preset function, where the prompt information includes at least a portion of the interaction information or processing information for processing at least a portion of the interaction information;

[0202] Based on the 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.

[0203] In some embodiments, the prompt information indicates to classify the interaction information to obtain a classification result of the interaction information, and the prompt information also includes a preset tag set for classification.

[0204] In some embodiments, the preset tag set in the prompt information is obtained by referencing a cell or a sub-table that records the preset tag set.

[0205] In some embodiments, the preset tag set includes user-defined tags.

[0206] In some embodiments, the preset label set includes label sets corresponding to multiple levels of classification.

[0207] In some embodiments, the second processing unit 404 is further configured to:

[0208] 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;

[0209] 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 for performing i-th level classification on the interactive information, wherein i is an integer greater than or equal to 1.

[0210] In some embodiments, the second processing unit 404 is further configured to:

[0211] Generate second prompt information based on a preset function for classifying the interactive information at the i+1 level; the second prompt information includes a classification label set corresponding to the i+1 level classification;

[0212] Based on the model call information, the second prompt information is sent to the preset model, and the preset model performs an i+1th level classification on the interaction information according to the second prompt information to obtain an i+1th level classification result, and writes the i+1th level classification result into the third cell; wherein the classification label set corresponding to the i+1th level classification changes with the change of the classification result of the i-th level.

[0213] In some embodiments, the prompt information also includes:

[0214] One or more examples; wherein the example includes example interaction information and example processing results generated by the example interaction information, or the example includes a context corresponding to an application scenario for generating a processing result.

[0215] In some embodiments, the prompt information obtains one or more examples by referencing a cell or a subtable used to record the examples.

[0216] In some embodiments, one or more examples may be editable.

[0217] In some embodiments, the preset function includes one or more of the following:

[0218] Classification function, keyword extraction function, content summary generation function, text translation function, and custom information processing function.

[0219] In some embodiments, the device further includes a first sending unit (not shown in the figure), and the first sending unit is used to:

[0220] A prompt message is sent to the target user or the preset session, where the prompt message is generated according to the first processing result.

[0221] In some embodiments, the device further includes a second sending unit (not shown in the figure), which is used to periodically send graphical statistical information to a target user or a preset session, where the graphical statistical information is generated according to first processing results corresponding to a plurality of interaction information.

[0222] In order to implement the above embodiment, the embodiment of the present disclosure also provides an electronic device.

[0223] refer to Figure 5 , which shows a schematic diagram of the structure of an electronic device 500 suitable for implementing the embodiment of the present disclosure, and the electronic device 500 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0224] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 to a random access memory (RAM) 503. 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 via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0225] Typically, the following devices may 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, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication devices 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0226] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0227] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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, a computer-readable storage medium may be any tangible medium containing or storing a program (computer-executable instructions), which may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0228] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0229] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0230] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0231] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0232] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, constitute a limitation on the unit itself.

[0233] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0234] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 foregoing.

[0235] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0236] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0237] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, 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. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An information processing method, comprising: Obtaining interaction information in a target interaction tool; Automatically writing the acquired interaction information into a first cell of a target table, wherein 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, processing the interaction information based on the preset function to obtain a first processing result; 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.

2. The method according to claim 1, wherein: The processing of the interaction information to obtain a first processing result includes: Prompt information is sent to the preset model based on the interaction information, and a first processing result is obtained based on feedback from the preset model.

3. The method according to claim 1, wherein: The step of obtaining the interaction information in the target interaction tool includes: The virtual object is used to extract interaction information from the target interaction tool, where the interaction information includes at least one of the following: target interaction information and associated information of the target interaction information; wherein the target interaction tool meets a preset condition.

4. The method according to claim 3, wherein: The target interaction tool includes a target session, and the virtual object is set by a preset user as a session member of the target session; or The target session where the preset user is located is determined according to the preset user identifier, and the virtual object is added to the target session.

5. The method according to claim 2, wherein: The sending of prompt information to the preset model and obtaining a first processing result based on feedback from the preset model include: generating the prompt information based on a prompt information generation rule corresponding to the preset function, wherein the prompt information includes at least a portion of the interaction information or processing information for processing at least a portion of the interaction information; Based on the 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.

6. The method according to claim 5, wherein: The prompt information indicates to classify the interaction information to obtain a classification result of the interaction information, and the prompt information also includes a preset label set for classification.

7. The method according to claim 6, wherein: The preset label set in the prompt information is obtained by referencing a cell or a subtable recording the preset label set.

8. The method according to claim 6, wherein: The preset label set includes custom labels.

9. The method according to claim 6, wherein: The preset label set includes label sets corresponding to multiple levels of classification.

10. The method according to claim 9, wherein: The step of writing the first processing result into the second cell of the target table, or modifying the content of the first cell, or performing a preset action based on the first processing result includes: 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; 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 for performing i-th level classification on the interaction information, wherein i is an integer greater than or equal to 1.

11. The method according to claim 10, wherein: The triggering of performing the i+1th level classification on the interaction information includes: Generate second prompt information based on a preset function for classifying the interaction information at the i+1 level; the second prompt information includes a classification label set corresponding to the i+1 level classification; Based on the model calling information, the second prompt information is sent to the preset model, and the preset model performs an i+1th level classification on the interaction information according to the second prompt information to obtain an i+1th level classification result, and writes the i+1th level classification result into a third cell; wherein the classification label set corresponding to the i+1th level classification changes with the change of the classification result of the i-th level.

12. The method according to claim 5, wherein: The prompt information also includes: One or more examples; wherein the example includes example interaction information and example processing results generated by the example interaction information, or the example includes a context corresponding to an application scenario for generating a processing result.

13. The method according to claim 12, wherein: The prompt information obtains the one or more examples by referencing a cell or a subtable used to record the examples.

14. The method according to claim 12, wherein: The one or more examples may be editable.

15. The method according to any one of claims 1 to 14, wherein: The preset function includes one or more of the following: Classification function, keyword extraction function, content summary generation function, text translation function, and custom information processing function.

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

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

18. An information processing device, comprising: An acquisition unit, used for acquiring interaction information in a target interaction tool; A writing unit, used for automatically writing the acquired interaction information into a first cell of a target table, wherein the first cell is associated with a preset function; A first processing unit, configured to, in response to the interaction information being written into a first cell of a target table, process the interaction information based on a preset function associated with the first cell to obtain a first processing result; The second processing unit is used to write the first processing result into a second cell of the target table, or to modify the content of the first cell, or to perform a preset action based on the first processing result.

19. An electronic device, wherein: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 16.

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

21. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 17 is implemented.

Images