CN112069377A - Session information data processing method, apparatus, computer equipment and storage medium - Google Patents

Abstract

The application relates to the technical field of instant messaging, and provides a session information data processing method, a session information data processing device, a computer device and a storage medium. The method comprises the following steps: the method comprises the steps of obtaining session data to be processed from a terminal, wherein the session data to be processed comprises attribute information of each session to be processed, inputting the session data to be processed into a session processing model, automatically classifying the sessions to be processed by the session processing model according to the attribute information of each session to be processed, obtaining a reserved session group and a deleted session group after classification, and finally deleting the sessions to be processed, of which the reservation time exceeds a preset time value, in the deleted session group by reserving the sessions to be processed in the reserved session group. A series of data processing processes of the device realize automatic clustering of sessions to be processed, and quickly realize automatic management of session interfaces and automatic cleaning of the sessions, so that the user experience is effectively improved, and the use efficiency of a chat tool is improved.

Description

Session information data processing method, apparatus, computer equipment and storage medium

technical field

The present application relates to the field of computer technology, and in particular, to a method, apparatus, computer device and storage medium for processing session information data.

Background technique

With the continuous development of computers, while computers have brought great convenience to people's lives, they have also subtly changed people's living and communication habits. Such as QQ, WeChat and other chat tools. When a terminal user uses a chat tool, there is usually a contact interface, a conversation interface, and a chat interface. The user selects a contact from the contact interface to generate a chat interface for the user to communicate with the contact. When the user exits the chat interface After that, the conversation record of the user and the contact will be displayed on the conversation interface, and the next time a conversation is conducted, the chat interface with the contact can be directly entered by clicking on the conversation record. The conversation interface is used to save various conversation records of the user, and provide an interface for quick chatting and viewing messages. In the traditional technology, the user can choose the conversation record to be deleted or manage the conversation list by clearing the conversation list, and improve the usage efficiency of the chat tool.

However, with the advent of the era of big data and informatization, the conversation interface includes not only the conversation records between various users, but also the sending or receiving records of various information, such as public account push records, group message session records, and verification messages. records, contact session records, news feed records, etc. Various complex information records are displayed on the conversation interface, resulting in a cluttered conversation interface. The existing technology still requires the user to manually clean up the conversation, resulting in poor user experience and affecting the usage rate of chat tools.

SUMMARY OF THE INVENTION

Based on this, it is necessary to provide a session information data processing method, apparatus, computer equipment and storage medium for the above technical problems.

A session information data processing method, the method comprising:

Acquire session data to be processed from the terminal, where the session data to be processed includes attribute information of the session to be processed; wherein the attribute information includes at least one of a session identifier, a session content attribute, a session category attribute, and a session object attribute;

Inputting the session data to be processed into a session processing model, so that the session processing model classifies the session to be processed according to the attribute information, and obtains a reserved session group and a deleted session group after the classification;

Send a session processing instruction to the terminal, so that the terminal reserves the pending session corresponding to the reserved session group according to the session processing instruction; Pending sessions are deleted.

In one embodiment, the training step of the session processing model includes:

obtaining a session training sample set, where the session training samples in the session training sample set carry a reserved mark or a deletion mark;

Inputting the session training sample set into the initial session processing model for classification processing, and obtaining an initial deletion session group and an initial reserved session group after the classification processing;

Comparing the sessions in the initial reserved session group with the session training samples corresponding to the reserved marks to obtain a first similarity;

Comparing and calculating the session in the initial deletion session group and the session training sample corresponding to the deletion mark to obtain a second similarity;

The parameters of the initial session processing model are adjusted according to the first similarity and the second similarity, until the initial session processing model satisfies the convergence condition, and the session processing model is obtained.

In one embodiment, the method further includes:

online learning of the conversation processing model;

The session processing model is updated in real time through learning, so that the classification processing strategy of the session processing model conforms to the usage preference of the current user.

In one embodiment, the step of online learning of the conversation processing model includes:

Acquiring historical operation data; wherein, the historical operation data includes the retention identifier or deletion identifier corresponding to the current operation, and the attribute information of the current session corresponding to the current operation;

online learning of the session processing model according to the attribute information of the current session, the reserved identifier or the deletion identifier;

So that the session processing model judges whether the attribute information of the session to be processed and the current session belong to the same type, and if they belong to the same type, the session to be processed is classified into the reservation corresponding to the current session. Session group or delete session group.

In one embodiment, the method further includes:

Get information about the object to be shared;

generating information to be shared according to the deleted conversation group and the reserved conversation group;

The to-be-shared information is sent to the to-be-shared object according to the to-be-shared object information.

In one embodiment, the method further includes:

Get priority information;

sorting the pending sessions according to session identification and priority information;

The pending sessions are processed in the sorted order.

An apparatus for processing session information data, the apparatus comprising:

A session data acquisition module, configured to acquire session data to be processed from the terminal, where the session data to be processed includes attribute information of the session to be processed; wherein the attribute information includes a session identifier, a session content attribute, a session category attribute, and a session object attribute at least one of them;

A session classification module, configured to input the session data to be processed into a session processing model, so that the session processing model classifies the session to be processed according to the attribute information, and obtains a reserved session group and a deleted session group after classification ;

a session processing module, configured to send a session processing instruction to the terminal, so that the terminal reserves the to-be-processed session corresponding to the reserved session group according to the session processing instruction; Pending sessions older than the preset time value are deleted.

In one embodiment, the apparatus further includes a session processing model training module, and the session processing model training module includes:

a sample acquisition unit, configured to acquire a session training sample set, where the session training samples in the session training sample set carry a retention mark or a deletion mark;

a sample preprocessing unit, used for inputting the session training sample set into an initial session processing model for classification processing, and obtaining an initial deletion session group and an initial reserved session group after the classification processing;

a first similarity calculation unit, configured to compare and calculate the session in the initial reserved session group and the session training sample corresponding to the reserved mark to obtain a first similarity;

A second similarity calculation unit, configured to compare and calculate the session in the initially deleted session group and the session training sample corresponding to the deletion mark to obtain a second similarity;

A parameter adjustment unit, configured to adjust parameters of the initial session processing model according to the first similarity and the second similarity, until the initial session processing model satisfies a convergence condition, and obtain the session processing model.

A computer device includes a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the computer program, the steps in each of the foregoing method embodiments are implemented.

A computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps in each of the foregoing method embodiments.

The above session information data processing method, device, computer equipment and storage medium, by acquiring the session data to be processed from the terminal, the session data to be processed includes the attribute information of each session to be processed, and then the session data to be processed is input into the session processing model, The session processing model automatically classifies the to-be-processed sessions according to the attribute information of each to-be-processed session. In the above-mentioned deletion session group, the to-be-processed sessions whose retention time exceeds the preset time value are deleted. Since the session processing model is a pre-trained model, the session data can be calculated and processed to realize automatic clustering of the to-be-processed sessions. The series of data processing in this case can quickly realize the automatic management of the conversation interface and the automatic clearing of the conversation as a whole, reducing the time for clearing the conversation, thereby effectively improving the user experience and improving the use efficiency of the chat tool.

Description of drawings

1 is an application scenario diagram of a method for processing session information data according to an embodiment;

2 is a schematic flowchart of a method for processing session information data in one embodiment;

3 is a schematic flowchart of training steps of a session processing model in one embodiment;

4 is a schematic flowchart of a method for processing session information data in yet another embodiment;

5 is a schematic flowchart of a method for processing session information data in another embodiment;

6 is a structural block diagram of an apparatus for processing session information data in one embodiment;

7 is a structural block diagram of an apparatus for processing session information data in one embodiment;

FIG. 8 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

The session information data processing method provided by this application can be applied to the application environment shown in FIG. 1 . FIG. 1 is an application environment diagram of the operation of the session information data processing method in one embodiment. As shown in FIG. 1 , the application environment includes a terminal 110 and a server 120 . Communication between the terminal 110 and the server 120 is performed through a network, and the communication network may be a wireless or wired communication network, such as an IP network, a cellular mobile communication network, etc., wherein the number of terminals and servers is not limited.

Wherein, the terminal 110 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices. The server 120 can be implemented by an independent server or a server cluster composed of multiple servers. The server 120 obtains the session data to be processed from the terminal 110, and the session data to be processed includes attribute information of the session to be processed; the server 120 inputs the session data to be processed into the session processing model, so that the session processing model classifies the session to be processed according to the attribute information , after classification, a reserved session group and a deleted session group are obtained; the server 120 retains the pending sessions in the retained session group; the server 120 deletes the pending sessions in the deleted session group whose retention time exceeds a preset time value. Since the session processing model is a pre-trained model, it can calculate and process session data and realize automatic clustering of the sessions to be processed, so that through a series of data processing in this case, the overall automatic management of the session interface can be quickly realized. The automatic clearing of the session reduces the session clearing time, thereby effectively improving the user experience.

In one embodiment, as shown in FIG. 2 , a method for processing session information data is provided, and the method is applied to the server 120 in FIG. 1 as an example for description, including the following steps:

Step 210: Obtain session data to be processed from the terminal, where the to-be-processed session data includes attribute information of the to-be-processed session; wherein the attribute information includes at least one of a session identifier, a session content attribute, a session category attribute, and a session object attribute.

Specifically, the server obtains the session data to be processed from the terminal. The session data to be processed refers to session-related data, that is, attribute information corresponding to each session displayed on the session interface of the instant messaging tool on the terminal. The attribute information includes at least one of a session identifier, a session content attribute, a session type attribute, and a session object attribute.

Further, the session ID refers to the ID of each session, which can be the session name of each specific session. For example, when user A chats with user B, the session with user B as the session name will be displayed on the instant messaging interface of user A. , where user B is the session name, that is, the session identifier of the session; for example, when user A chats in a chat group C, the session with C as the session name will be displayed on the instant messaging interface, where C is the session name, which is the session name. Session ID. The session category attribute refers to attribute information used to distinguish session types. For example, the session type includes at least one of official account push records, group messages, verification message records, contact sessions, and news push records. The session content attribute refers to attribute information used to distinguish different session contents in the same session type. For example, the session type of news feed record may include news of different contents, such as real-time news, entertainment news, and social news. Session object properties are used to distinguish different users on instant messaging tools.

Step 220: Input the session data to be processed into the session processing model, so that the session processing model classifies the sessions to be processed according to the attribute information, and obtains the reserved session group and the deleted session group after the classification.

Among them, the conversation processing model is a classification model formed based on Convolutional Neural Networks (CNN). Specifically, the server calculates the to-be-processed session data obtained through the session processing model, determines a classification strategy for the to-be-processed session, and divides the to-be-processed session into two parts: a reserved session group and a deleted session group. Retain Session Groups and Delete Session Groups refer to a collection of sessions within a certain range. The reserved session group is used to indicate that the sessions in the group are reserved, and the deletion of the session group is used to indicate that the sessions in the group are deleted.

Step 230: Send a session processing instruction to the terminal, so that the terminal retains the pending session corresponding to the reserved session group according to the session processing instruction; delete the pending session whose retention time corresponding to the deleted session group exceeds a preset time value.

Specifically, the server sends a session processing instruction to the terminal according to the reserved session group and the deleted session group obtained by classification. The session processing instruction is used to instruct the terminal to clear the session on the instant messaging interface. Specifically, the terminal reserves the to-be-processed sessions in the reserved session group according to the session processing instruction, and the server deletes the to-be-processed sessions in the deletion session group whose retention time exceeds a preset time value. Wherein, there may be a retention period of a preset time value for the to-be-processed sessions in the deletion session group, that is, they are retained for a certain period of time before deletion. The retention period can be determined with different preset time values according to attribute information of different sessions to be processed. For example, verification message records can be set to be kept for 24 hours, news feed records can be set to be kept for 36 hours, contacts can be set to be kept for a week, etc.

The above session information data processing method, by acquiring the session data to be processed in real time, and processing a series of data processing of the session data to be processed, the new session to be processed generated on the instant messaging tool is classified in real time, and the classified session to be processed is classified in real time. It can retain and delete the session interface quickly as a whole, and automatically manage the session interface and automatically clean up the session, reduce the session cleaning time, and effectively improve the user experience.

In one embodiment, as shown in Figure 3, the training steps of the session processing model include:

In step 241, a session training sample set is acquired, and the session training samples in the session training sample set carry a reserved mark or a deletion mark.

Specifically, the session training samples are data used to train the session processing model, and the data includes attribute information of the session training samples. The purpose of the training is to enable the trained session processing model to accurately and quickly classify the input session to be processed, and to output the classification result accurately. Each session training sample carries a retention mark or deletion mark.

Step 242: Input the session training sample set into the initial session processing model for classification processing, and obtain an initial deleted session group and an initial reserved session group after the classification processing.

Specifically, the initial session processing model can classify the session training samples according to the attribute information of the session training samples. That is, the session training samples in the session training sample set are classified into the initial deletion session group or the initial reservation session group.

Step 243: Comparing the sessions in the initial reserved session group with the session training samples corresponding to the reserved marks to obtain a first similarity.

Specifically, the server compares and calculates the session in the initial reserved session group with the session training sample corresponding to the reserved mark, to obtain the first similarity. The first similarity is used to reflect the similarity between the sessions classified into the initial reserved session group and the session training samples corresponding to the reserved marks. The similarity of the two sessions can be calculated by comparing and calculating the attribute information of the two sessions.

Step 244, compare and calculate the session in the initial deletion session group and the session training sample corresponding to the deletion mark to obtain a second similarity.

Specifically, the server compares and calculates the session in the initially deleted session group with the session training sample corresponding to the deletion mark, to obtain the second similarity. The second degree of similarity is used to reflect the degree of similarity between the sessions classified into the initially deleted session group and the session training samples corresponding to the deletion marks. In one embodiment, the similarity of the two sessions may be calculated by comparing and calculating the attribute information of the two sessions.

Step 245: Adjust parameters of the initial session processing model according to the first similarity and the second similarity, until the initial session processing model satisfies the convergence condition, and obtain the session processing model.

Specifically, the server adjusts the parameters of the initial session processing model according to the first similarity and the second similarity until a convergence condition is met. The convergence condition may be setting a threshold for the similarity of the attribute information of the session. When the similarity reaches the threshold value, the convergence condition is satisfied.

In this embodiment, by acquiring the session training sample set and inputting the session training sample set into the session processing model for training, the session processing model can accurately classify and process the session, thereby improving the accuracy and effectiveness of data processing.

In one embodiment, as shown in FIG. 4, a method for processing session information data is provided, and the method further includes:

Step 250, online learning is performed on the conversation processing model.

Step 260 , update the session processing model in real time by learning, so that the classification processing strategy of the session processing model conforms to the usage preference of the current user.

In this embodiment, the server learns the session processing model online, and updates the session processing model in real time by learning, so that the session processing model can learn the operation session processing habits of the current user in real time. The classification processing strategy of the updated session processing model conforms to the current user's usage preferences.

In one embodiment, as shown in Figure 5, step 250 includes:

Step 251, obtaining historical operation data.

Wherein, the historical operation data includes the reservation identifier or deletion identifier corresponding to the current operation, and attribute information of the current session corresponding to the current operation.

Step 252: Perform online learning on the session processing model according to the attribute information of the current session, the reserved identifier or the deleted identifier.

Step 253, so that the session processing model judges whether the attribute information of the to-be-processed session and the current session belong to the same type.

Specifically, the server obtains historical operation data from the terminal, and the historical operation data refers to the historical data that the current user manages the session through click operations, such as delete, retain, stick to the top, follow, ignore, view, ignore, etc. The historical operation data includes the retention flag or deletion flag corresponding to the current operation and the attribute information of the current session corresponding to the current operation. Among them, the server stores an operation identification mapping table, and the identification mapping table stores various operations in the historical operation data corresponding to a reserved identification or deletion identification. , the reserved flags corresponding to operations such as "Top", "Follow", and "View", and the deletion flags corresponding to operations such as "Don't Follow" and "Ignore".

Specifically, the server performs online learning on the session processing model according to the attribute information of the current session and the corresponding reservation or deletion identifier of the current session, so that the session processing model can judge whether the attribute information of the to-be-processed session and the current session belong to the same type. If they belong to the same type, the pending sessions are classified into the reserved session group or the deleted session group corresponding to the current session.

In this embodiment, the session processing model is learned online by acquiring the historical operation data of the current user, so that the session processing model learns the characteristics of the attribute information of the current session corresponding to the current operation and the operation mode of the current session. When classifying the to-be-processed session, it will refer to the historical operation mode to comprehensively judge whether to classify the to-be-processed session into the reserved session group or the deleted session group. Since the online learning is based on the historical operation data of each user, different session processing models can be trained for different users, providing users with personalized session processing solutions, thereby improving user experience.

In one embodiment, a method for processing session information data is provided, the method further comprising: acquiring information on objects to be shared; generating information to be shared according to the deleted session group and the retained session group; Who to share with.

Specifically, the server acquires the object information to be shared from the terminal, and determines the object to be shared according to the object information to be shared. The server generates information to be shared according to the deleted session group and the retained session group obtained by classifying the session data to be processed according to the session processing model, and sends the information to be shared to the object to be shared. The to-be-shared information is used to share the session cleaning method on the session interface of the current user, that is, the session with which attribute information the current user deletes or retains.

In this embodiment, by generating a message to be shared according to the deleted conversation group and the reserved conversation group, and sending it to the object to be shared, the sharing and interaction of the conversation list is realized, and the management method of sharing the conversation interface between users is realized, thereby improving the user experience.

In one embodiment, a method for processing session information data is provided, the method further includes: acquiring priority information; sorting the sessions to be processed according to the session identifier and the priority information; and processing the sessions to be processed according to the sorted order.

Specifically, the server obtains priority information from the terminal, and the server sorts the to-be-processed sessions according to the session identifier and priority information of the to-be-processed sessions, and processes the to-be-processed sessions according to the sorted order. The priority information may be the session generation time obtained by statistics, or the number of clicks of the session to be processed by the current user obtained by statistics. Sort the to-be-processed sessions according to the priority information and the session identifier, and process the to-be-processed sessions according to the sorting order. In this embodiment, by acquiring the priority information and processing the to-be-processed sessions one by one, the priority processing of the sessions can be implemented, and the user's management efficiency of the sessions can be effectively improved, thereby improving the user's experience.

It should be understood that although the steps in the flowcharts of FIGS. 2-5 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIGS. 2-5 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed and completed at the same time, but may be executed at different times. These sub-steps or stages are not necessarily completed at the same time. The order of execution of the steps is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of sub-steps or stages of other steps.

In one embodiment, as shown in FIG. 6, a session information data processing apparatus is provided, including: a session data acquisition module 310, a session classification module 320, and a session processing module 330, wherein:

The session data acquisition module 310 is configured to acquire session data to be processed from the terminal, the session data to be processed includes attribute information of the session to be processed; wherein the attribute information includes at least one of a session identifier, a session content attribute, a session category attribute, and a session object attribute. A sort of.

The session classification module 320 is configured to input the session data to be processed into the session processing model, so that the session processing model classifies the session to be processed according to the attribute information, and obtains the reserved session group and the deleted session group after classification.

The session processing module 330 is configured to retain the to-be-processed sessions in the reserved session group; and is also configured to delete the to-be-processed sessions in the deletion session group whose retention time exceeds a preset time value.

In one embodiment, the apparatus further includes a session processing model training module 340, as shown in FIG. 7 , the session processing model training module 340 includes:

The sample obtaining unit 341 is configured to obtain a session training sample set, where the session training samples in the session training sample set carry a reserved mark or a deletion mark.

The sample preprocessing unit 342 is configured to input the session training sample set into an initial session processing model for classification processing, and obtain an initial deleted session group and an initial reserved session group after the classification processing.

The first similarity calculation unit 343 is configured to compare and calculate the session in the initial reserved session group and the session training sample corresponding to the reserved mark to obtain a first similarity.

The second similarity calculation unit 344 is configured to compare and calculate the session in the initially deleted session group and the session training sample corresponding to the deletion mark to obtain a second similarity.

A parameter adjustment unit 345, configured to adjust parameters of the initial session processing model according to the first similarity and the second similarity, until the initial session processing model satisfies a convergence condition, and obtain the session processing model.

In one embodiment, the apparatus further includes an online learning module and a model updating module, wherein:

The online learning module is used for online learning of the conversation processing model.

The updating unit module is used to update the conversation processing model in real time through learning, so that the classification processing strategy of the conversation processing model conforms to the usage preference of the current user.

In one embodiment, the online learning module includes a historical operation data acquisition unit and an online learning unit, wherein:

The historical operation data acquisition unit is used to acquire historical operation data; wherein, the historical operation data includes the retention identifier or deletion identifier corresponding to the current operation, and the attribute information of the current session corresponding to the current operation;

The online learning unit is used for online learning of the session processing model according to the attribute information of the current session, the reservation mark or the deletion mark; so that the session processing model can judge whether the attribute information of the session to be processed and the current session belong to the same type, if If they belong to the same type, the pending sessions are classified into the reserved session group or the deleted session group corresponding to the current session.

In one embodiment, the device further includes a sharing module, the sharing module is used to obtain the information of the object to be shared; it is also used to generate the information to be shared according to the deleted conversation group and the reserved conversation group; Send the information to be shared to the person to be shared.

In one embodiment, the apparatus further includes a priority processing module, the priority processing module is configured to obtain priority information; also used to sort the sessions to be processed according to the session identifier and the priority information; also used to sort the order Process the pending session.

For the specific limitation of the session information data processing apparatus, reference may be made to the above limitation on the session information data processing apparatus, which will not be repeated here. Each module in the above session information data processing apparatus may be implemented in whole or in part by software, hardware and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in FIG. 8 . The computer device includes a processor, memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The nonvolatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store video related data. As shown in FIG. 8 , the bidirectional arrow next to the network interface is used to indicate that the network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program implements a video information data processing method when executed by the processor.

Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program: acquiring session data to be processed from a terminal, and the session data to be processed includes Attribute information of the session to be processed; wherein the attribute information includes at least one of a session identifier, a session content attribute, a session category attribute, and a session object attribute; input the session data to be processed into the session processing model, so that the session processing model is based on the attribute The information is classified into the to-be-processed sessions, and the retained session group and the deleted session group are obtained after the classification; the pending sessions in the retained session group are retained; the pending sessions in the deleted session group whose retention time exceeds the preset time value are deleted.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: acquiring session data to be processed from a terminal, and the session data to be processed includes the session to be processed attribute information; wherein, the attribute information includes at least one of session identifier, session content attribute, session category attribute, and session object attribute; input the session data to be processed into the session processing model, so that the session processing model treats the processing according to the attribute information The sessions are classified, and after the classification, a reserved session group and a deleted session group are obtained; the pending sessions in the reserved session group are retained; and the pending sessions in the deleted session group whose retention time exceeds the preset time value are deleted.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage In the medium, when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink), DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be noted that, for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (10)

1. A method of session information data processing, the method comprising:

acquiring session data to be processed from a terminal, wherein the session data to be processed comprises attribute information of a session to be processed; wherein, the attribute information comprises at least one of session identification, session content attribute, session category attribute and session object attribute;

inputting the session data to be processed into a session processing model so that the session processing model classifies the sessions to be processed according to the attribute information, and obtaining a reserved session group and a deleted session group after classification;

sending a session processing instruction to the terminal so that the terminal reserves the to-be-processed session corresponding to the reserved session group according to the session processing instruction; and deleting the to-be-processed session of which the retention time corresponding to the deleted session group exceeds a preset time value.

2. The method of claim 1, wherein the step of training the conversational processing model comprises:

acquiring a session training sample set, wherein session training samples in the session training sample set carry a reserved mark or a deleted mark;

inputting the session training sample set into an initial session processing model for classification processing, and obtaining an initial deleted session group and an initial reserved session group after the classification processing;

comparing and calculating the conversation in the initial reservation conversation group with the conversation training sample corresponding to the reservation label to obtain a first similarity;

comparing and calculating the session in the initial deletion session group with the session training sample corresponding to the deletion marker to obtain a second similarity;

and adjusting parameters of the initial session processing model according to the first similarity and the second similarity until the initial session processing model meets a convergence condition to obtain the session processing model.

3. The method of claim 1, further comprising:

performing online learning on the session processing model;

and updating the session processing model in real time through learning so as to enable the classification processing strategy of the session processing model to accord with the use preference of the current user.

4. The method of claim 3, wherein the step of learning the conversational processing model online comprises:

acquiring historical operation data; the historical operation data comprises a reserved identifier or a deleted identifier corresponding to the current operation and attribute information of the current session corresponding to the current operation;

performing online learning on the session processing model according to the attribute information of the current session and the reserved identifier or the deleted identifier;

and classifying the session to be processed into the reserved session group or the deleted session group corresponding to the current session by the session processing model by judging whether the attribute information of the session to be processed and the current session belong to the same type or not if the attribute information of the session to be processed and the current session belong to the same type.

5. The method of claim 1, further comprising:

acquiring information of an object to be shared;

generating information to be shared according to the deleted conversation group and the reserved conversation group;

and sending the information to be shared to the object to be shared according to the information of the object to be shared.

6. The method of claim 1, further comprising:

acquiring priority information;

sequencing the sessions to be processed according to the session identification and the priority information;

and processing the sessions to be processed according to the sorted sequence.

7. A session information data processing apparatus, characterized in that the apparatus comprises:

the session data acquisition module is used for acquiring session data to be processed from a terminal, wherein the session data to be processed comprises attribute information of a session to be processed; wherein, the attribute information comprises at least one of session identification, session content attribute, session category attribute and session object attribute;

the session classification module is used for inputting the session data to be processed into a session processing model so as to enable the session processing model to classify the session to be processed according to the attribute information, and a reserved session group and a deleted session group are obtained after classification;

the session processing module is used for sending a session processing instruction to the terminal so that the terminal reserves the to-be-processed session corresponding to the reserved session group according to the session processing instruction; and deleting the to-be-processed session of which the retention time corresponding to the deleted session group exceeds a preset time value.

8. The apparatus of claim 7, further comprising a session processing model training module, the session processing model training module comprising:

the system comprises a sample acquisition unit, a comparison unit and a comparison unit, wherein the sample acquisition unit is used for acquiring a session training sample set, and session training samples in the session training sample set carry a reserved mark or a deleted mark;

the sample preprocessing unit is used for inputting the session training sample set into an initial session processing model for classification processing, and an initial deleted session group and an initial reserved session group are obtained after the classification processing;

the first similarity calculation unit is used for comparing and calculating the conversation in the initial reserved conversation group with the conversation training sample corresponding to the reserved mark to obtain first similarity;

the second similarity calculation unit is used for comparing and calculating the sessions in the initial deletion session group with the session training samples corresponding to the deletion marks to obtain a second similarity;

and the parameter adjusting unit is used for adjusting the parameters of the initial session processing model according to the first similarity and the second similarity until the initial session processing model meets a convergence condition, so as to obtain the session processing model.

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.

Images