A mail marking method, device, equipment and readable storage medium

By extracting key events and times from emails and combining TF-IDF and XGBoost algorithms to calculate email importance levels, this method solves the problem of low efficiency in existing email tagging methods, realizes automated email classification and tagging, and improves office efficiency.

CN114970451BActive Publication Date: 2024-11-29BANK OF CHINA
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202210385604.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-13
Publication Date
2024-11-29
Estimated Expiration
2042-04-13

AI Technical Summary

Technical Problem

Existing email tagging methods are insufficient for effectively distinguishing the importance of emails through automation, requiring users to review each email individually when dealing with a large volume of emails, thus impacting work efficiency.

Method used

By extracting key events and times from email information, and combining TF-IDF and XGBoost algorithms, the importance level of emails is calculated, and the emails are marked and displayed based on key information.

Benefits of technology

It enables automated classification and tagging of emails by importance, improving email processing efficiency and simplifying email preview and processing workflows.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114970451B_ABST
    Figure CN114970451B_ABST
Patent Text Reader

Abstract

The present application discloses a method, device, equipment, and readable storage medium for marking emails, which can be applied to the field of artificial intelligence or finance. The method obtains email information of the email to be marked, the email information includes the email subject and the email body, and extracts key events and the time corresponding to the key events from the email information. The importance level of the email to be marked is obtained based on the key information. The marking information of the email to be marked is displayed based on the importance level of each email to be marked. Since the key information includes key events and the time corresponding to the key events, and the marking information includes the importance level and the key information, the method classifies the importance level of the email to be marked based on the key events and the corresponding time included in the email information. Further, the importance level, key events and the corresponding time of the email to be marked are displayed based on the importance level of each email to be marked, so as to realize the preview function of the key information.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a mail marking method, device, equipment and readable storage medium. Background Art

[0002] Emails play a very important role in daily office work. Both daily notifications and important work are communicated through emails. Since the number of emails is very large, email marking is an important means to help staff improve work efficiency. However, the current email marking method can only distinguish the importance of different emails by manually adding simple marks. It is difficult to preview the key information of the email content through marking. Therefore, in actual work, when dealing with a large number of emails, it is still necessary to open each email one by one to view the email content. Obviously, the existing email marking method is difficult to meet the requirements of efficient office work. Summary of the invention

[0003] The present application provides a mail marking method, apparatus, device and readable storage medium as follows:

[0004] A mail marking method, comprising:

[0005] Obtaining email information of the email to be marked, wherein the email information includes the email subject and the email body;

[0006] Extracting key events and the time corresponding to the key events from the email information;

[0007] Obtaining the importance level of the email to be marked according to key information, wherein the key information includes the key event and the time corresponding to the key event;

[0008] According to the importance level of each of the mails to be marked, the marking information of the mails to be marked is displayed, and the marking information includes the importance level and key information.

[0009] Optionally, extracting key events and times corresponding to the key events from the email information includes:

[0010] Extracting keywords from the email information based on the TF-IDF algorithm;

[0011] Based on at least one of the keywords, at least one key event is obtained, and a start time and / or end time corresponding to the key event is acquired.

[0012] Optionally, the email information further includes: information of an attachment of the email to be marked; and the method further includes:

[0013] According to the information of the attachment of the email to be marked, the file category of the attachment is obtained.

[0014] Optionally, the key information further includes a file category of the attachment, and obtaining the importance level of the email to be marked according to the key information includes:

[0015] Obtaining the importance score of the attachment according to a preset file correspondence relationship and the file category, wherein the file correspondence relationship includes a correspondence relationship between a preset category and a score;

[0016] According to a preset event correspondence, an importance score of the key event is obtained, wherein the event correspondence includes a correspondence between preset words and scores, and the importance score of the key event is positively correlated with the score corresponding to the keyword included in the key event;

[0017] Obtain a first duration and a second duration, wherein the first duration is the time interval between the current time and the start time corresponding to the key event, and the second duration is the time interval between the start time and the end time corresponding to the key event;

[0018] The importance level of the email to be marked is obtained based on the importance score of the attachment, the importance score of the key event, the first duration and the second duration, wherein the importance level of the key event is positively correlated with the importance score of the attachment and the importance score of the key event, and is negatively correlated with the first duration and the second duration.

[0019] Optionally, displaying marking information of the emails to be marked according to the importance level of each email to be marked includes:

[0020] The mails to be marked are sorted from high to low according to their importance level, and marking information of the mails to be marked is displayed.

[0021] Optionally, before obtaining the email information of the email to be marked, the method further includes:

[0022] Obtaining a mail collection, wherein the mail collection includes a plurality of mails to be processed;

[0023] Based on the XGBoost algorithm, the emails to be processed whose classification results are important emails are obtained from the email collection as the emails to be marked.

[0024] A mail marking device, comprising:

[0025] An email information acquisition unit, used to acquire email information of the email to be marked, wherein the email information includes the email subject and the email body;

[0026] A key information acquisition unit, used to extract key events and the time corresponding to the key events from the email information;

[0027] A level acquisition unit, configured to acquire the importance level of the email to be marked according to key information, wherein the key information includes the key event and the time corresponding to the key event;

[0028] The marking display unit is used to display the marking information of the mails to be marked according to the importance level of each mail to be marked, and the marking information includes the importance level and key information.

[0029] Optionally, the key information acquisition unit is used to extract the key event and the time corresponding to the key event from the email information, including: the key information acquisition unit is specifically used to:

[0030] Extracting keywords from the email information based on the TF-IDF algorithm;

[0031] At least one of the keywords is concatenated to obtain at least one key event, and the start time and / or end time corresponding to the key event is obtained.

[0032] A mail marking device, comprising: a memory and a processor;

[0033] The memory is used to store programs;

[0034] The processor is used to execute the program to implement various steps of a mail marking method.

[0035] A readable storage medium stores a computer program, and when the computer program is executed by a processor, each step of a mail marking method is implemented.

[0036] It can be seen from the above technical scheme that the embodiment of the present application provides a method, device, equipment and readable storage medium for marking emails, which obtains the email information of the email to be marked, and the email information includes the email subject and the email body, and extracts the key events and the time corresponding to the key events from the email information. The importance level of the email to be marked is obtained based on the key information. The marking information of the email to be marked is displayed based on the importance level of each email to be marked. Since the key information includes the key events and the time corresponding to the key events, and the marking information includes the importance level and the key information, the method classifies the importance level of the email to be marked based on the key events and the corresponding time included in the email information. Further, the importance level, key events and the corresponding time of the email to be marked are displayed based on the importance level of each email to be marked. It can be seen that by marking and displaying each email to be marked according to the importance level, the preview function of the key information is realized, which is conducive to improving the processing efficiency of emails. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application 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 only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flowchart of a specific implementation method of a mail marking method provided in an embodiment of the present application;

[0039] Figure 2 A flowchart of a mail marking method provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of a mail marking device provided in an embodiment of the present application;

[0041] Figure 4 A schematic diagram of the structure of a mail marking device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] It should be noted that the mail marking method, device, equipment and readable storage medium provided by the present invention can be used in the field of artificial intelligence or finance.

[0044] The email marking method provided in the embodiment of the present application is applied to but not limited to the scenario where office emails need to be marked and displayed. Office staff need to handle a large number of office emails every day and need to extract key information from office emails in order to mark and display office emails based on the key information, thereby realizing the email preview function. Obviously, it is beneficial for office staff to handle office emails in a targeted manner.

[0045] Furthermore, the present application solution can be applied to smart devices, such as computers, tablets or smart phones. In addition, the present solution can also be applied to servers. Figure 1 A mail marking method provided by this application is introduced, such as Figure 1 The specific implementation process of a method for marking an email is illustrated, and the method includes:

[0046] S101. Obtain a mail collection.

[0047] In this embodiment, the email collection includes a plurality of to-be-processed emails. Optionally, the to-be-processed emails include unread emails. The triggering timing for obtaining the email collection includes:

[0048] 1. The processing time of the preset processing cycle is reached in the time window. For example, if the processing cycle is one hour, a mail collection is obtained every hour. The mail collection includes all unread mails received in the current processing cycle.

[0049] 2. The number of received unread emails reaches a preset threshold. For example, the preset threshold is pre-configured as 20. When the number of unread emails reaches 20, this step is executed.

[0050] 3. When the preset email processing time is reached, for example, the email processing time is pre-configured to be 9:00 a.m. and 1:30 p.m. every day, then this step is performed at 9:00 a.m. and 1:30 p.m. every day, respectively.

[0051] S102. Based on the XGBoost algorithm, the to-be-processed emails classified as important emails are obtained from the email collection as the to-be-marked emails.

[0052] In this embodiment, a prediction model built based on the XGBoost algorithm is obtained, and the training data of the prediction model includes subject words of historical emails and importance identifiers based on the importance marks of the historical emails, wherein the subject words are keywords or participles extracted from the subjects, and the importance identifiers include a first identifier for indicating important emails and a second identifier for indicating unimportant emails.

[0053] The training process of the prediction model includes: taking the subject words of historical emails as input samples, taking the importance mark as the target output, iterative training based on the XGBoost algorithm, optimizing the various parameters of the prediction model, and obtaining the trained prediction model. It can be understood that the trained prediction model takes the subject words as input and the importance mark as output, and the purpose is to predict the importance of the subject words of any email. It should be noted that the training method of the prediction model constructed based on the XGBoost algorithm can be referred to in the prior art.

[0054] Furthermore, the subject words of the email to be processed are input into the prediction model to obtain the importance mark output by the prediction model. If the importance mark is the first mark, it means that the classification result of the email to be processed is an important email. If the importance mark is the second mark, it means that the email to be processed is a non-important email.

[0055] Therefore, the pending emails classified as important emails are marked as pending emails and processed in the following steps.

[0056] It should be noted that XGBoost (extreme GradientBoosting, iterative regression tree algorithm) is a machine learning algorithm developed from the gradient boosting decision tree algorithm. Compared with other algorithms, it is parallelizable, fast, and more robust. It is simple and fast, has a wide range of references, and has high calculation accuracy. Therefore, this step is based on the XGBoost algorithm to extract important emails from the email collection as emails to be marked, and further mark and display the marked emails to improve processing efficiency.

[0057] S103: Obtain email information of the email to be marked.

[0058] In this embodiment, the email information includes the email subject, email body, and attachment information, wherein the attachment information at least includes the title of the attachment.

[0059] It should be noted that the method for obtaining the email information of the email to be marked can be found in the prior art.

[0060] S104: extract keywords from the email information based on the TF-IDF algorithm.

[0061] In this embodiment, the TF-IDF algorithm (term frequency-inverse document frequency) is a commonly used weighting technology for information retrieval and data mining.

[0062] It should be noted that the specific method for extracting keywords from email information based on the TF-IDF algorithm can be found in the prior art, and will not be described in detail in this embodiment.

[0063] S105: Based on at least one keyword, obtain at least one key event, and acquire the start time and end time corresponding to the key event.

[0064] In this embodiment, the key event is a time described by a combination of keywords. For example, if the keywords include March 11, 2022, meeting, and office 301, the key event is holding a meeting in office 301, and the starting time of the key event is March 11, 2022. For another example, if the keywords include work summary, 2021, December 21, 2022, and January 11, 2022, the key event is submitting the 2021 work summary, and the starting time of the key event is December 21, 2022, and the deadline is January 11, 2022.

[0065] It should be noted that the specific method of obtaining key events and their corresponding start time and end time based on keywords can be found in the prior art, such as natural language processing technology.

[0066] S106: Obtain importance scores of key events according to preset event correspondences.

[0067] In this embodiment, the event correspondence includes a correspondence between preset words and scores, and the importance score of the key event is positively correlated with the score corresponding to the keyword included in the key event.

[0068] Optionally, the score corresponding to the preset word is related to the importance of the preset word. For example, for the account of an accountant, the importance of the preset word related to the accounting field is higher, and the corresponding score is higher. For another example, the importance of the preset emergency word is higher, and the corresponding score is higher. For example, the preset emergency word includes words such as "as soon as possible", "urgent", and "expedited". It should be noted that the event correspondence is pre-configured based on the email information of the historical email, and the configuration method refers to the prior art.

[0069] S107: Obtain a first duration and a second duration.

[0070] In this embodiment, the first duration is the time interval between the current time and the start time corresponding to the key event, and the second duration is the time interval between the start time and the end time corresponding to the key event.

[0071] It can be understood that the shorter the first duration is, the closer the starting time of the key event is to the current time and the higher its urgency is; the shorter the second duration is, the shorter the handling time of the key event and the higher its urgency is. The higher the urgency is, the greater the need to handle it as soon as possible.

[0072] S108: Obtain the file category of the attachment according to the information of the attachment of the email to be marked.

[0073] In this embodiment, the information of the attachment includes but is not limited to the title. The file category is preset according to the application scenario. For example, the file category includes reply letter, notice, and official document. Optionally, the file category can be obtained by extracting keywords in the title of the attachment and matching them with words corresponding to the preset category. For details, refer to the prior art.

[0074] S109: Obtain an importance score of the attachment based on a preset file correspondence relationship and file category.

[0075] In this embodiment, the file correspondence includes a correspondence between a preset category and a score. Optionally, the score corresponding to the preset category is related to the importance of the attachment of the preset category.

[0076] S110, obtaining the importance level of the email to be marked according to the importance score of the attachment, the importance score of the key event, the first duration, and the second duration.

[0077] In this embodiment, the importance level of the key event is positively correlated with the importance score of the attachment and the importance score of the key event, and is negatively correlated with the first duration and the second duration.

[0078] S111. Sort the emails to be marked according to their importance from high to low, and display the marking information of each email to be marked.

[0079] In this embodiment, the marking information includes importance level and key information.

[0080] It should be noted that there are many methods for displaying the marking information of each email to be marked, for example, displaying the marking information before the subject of the email to be marked, and for another example, adding a hidden box in the list display position of the email to be marked, and when the mouse slides to the list display position of the email to be marked, the hidden box is displayed, and the hidden box includes the marking information.

[0081] It can be seen from the above technical solution that the email marking method provided by the embodiment of the present application extracts key events, the time corresponding to the key events, and the information of the attachments from the email information, and respectively obtains the importance scores corresponding to the key events, the time corresponding to the key events, and the information of the attachments, obtains the importance level of the email to be marked according to the importance scores of the three dimensions, and displays the email to be marked and the importance level of the email to be marked, the key events, the time corresponding to the key events, and the information of the attachments in a list from high to low according to the importance level. It can be seen that by marking and displaying each email to be marked according to the importance level, the preview function of key information is realized, which is conducive to improving the processing efficiency of emails.

[0082] Furthermore, since the importance level of the email to be marked is obtained based on the importance scores of the three dimensions, the accuracy and credibility of the importance level are high.

[0083] It should be noted that Figure 1Only the specific implementation process of a method for marking an email provided by an embodiment of the present application is illustrated, and the present application also includes other specific implementation processes. For example, email information is not limited to the information of the email subject, email body, and attachments, but also includes the sender. Accordingly, the method for obtaining the importance level of the email to be marked includes obtaining the importance level of the email to be marked based on the importance score of the sender (positively correlated with the importance of the sender), the importance score of the attachment, the importance score of the key event, the first duration and the second duration. For another example, S101 to S102 are optional steps. In other optional embodiments, all emails to be processed can be used as emails to be marked. For another example, S108 is an optional step. Accordingly, the method for obtaining the importance level of the email to be marked includes obtaining the importance level of the email to be marked based on the importance score of the key event, the first duration and the second duration. For another example, the prediction model is also used to predict the algorithm importance score of the email to be processed based on the XGBoost algorithm. The key information also includes the algorithm importance score. Accordingly, the algorithm importance score of the email to be marked is also used as an influencing parameter of the importance level. The higher the algorithm importance score, the higher the importance level of the email to be marked.

[0084] In summary, the email marking method provided in the embodiment of the present application is summarized as follows: Figure 2 The process shown is Figure 2 As shown, the method includes:

[0085] S201, obtaining email information of the email to be marked.

[0086] In this embodiment, the email information includes the email subject and the email body. It should be noted that the email to be marked is an email to be processed, for example, an unread email or a read email with an unprocessed mark.

[0087] It should be noted that the specific method for extracting email information can be found in the prior art.

[0088] S202: Extract key events and the time corresponding to the key events from the email information.

[0089] In this embodiment, the email information is processed by a preset key information extraction algorithm to obtain an event that can express the email subject and email body, and the time corresponding to the event is obtained based on the context semantics, where the time may include the start time, end time, and duration, etc.

[0090] It should be noted that an optional method for extracting key events and the time corresponding to the key events from the email information is shown in the above embodiment.

[0091] S203: Obtain the importance level of the email to be marked based on the key information.

[0092] In this embodiment, the key information includes key events and the time corresponding to the key events.

[0093] It can be understood that the importance of the email to be marked is determined based on the importance of the email information of the email to be marked, and the importance of the email information is determined based on the importance and urgency of the key event.

[0094] Therefore, this step obtains the importance level of the email to be marked based on the key event and the time corresponding to the key event. The higher the importance level, the more important the email to be marked is, and it needs to be processed as soon as possible or with emphasis. It should be noted that an optional method for obtaining the importance level of the email to be marked based on key information is shown in the above embodiment.

[0095] S204: Displaying marking information of the emails to be marked according to the importance level of each email to be marked.

[0096] In this embodiment, the marking information includes importance level and key information.

[0097] It should be noted that, according to the importance level of each email to be marked, there are many specific implementation methods for displaying the marking information of the emails to be marked. For example, as mentioned in the above embodiment, each email to be marked is sorted from high to low according to the importance level, and the marking information of each email to be marked is displayed. For another example, after sorting each email to be marked from high to low according to the importance level, the emails to be marked with the same importance level are sorted from large to small according to the importance of the key event, and the marking information of each email to be marked is displayed.

[0098] It can be seen from the above technical scheme that an email marking method provided by an embodiment of the present application obtains email information of the email to be marked, the email information includes the email subject and the email body, and extracts key events and the time corresponding to the key events from the email information. The importance level of the email to be marked is obtained based on the key information. The marking information of the email to be marked is displayed based on the importance level of each email to be marked. Since the key information includes key events and the time corresponding to the key events, and the marking information includes the importance level and the key information, the method classifies the importance level of the email to be marked based on the key events and the corresponding time included in the email information. Further, the importance level, key events and the corresponding time of the email to be marked are displayed based on the importance level of each email to be marked. It can be seen that by marking and displaying each email to be marked, the preview function of key information is realized, which is conducive to improving the processing efficiency of emails.

[0099] Figure 3 A schematic diagram of the structure of a mail marking device provided in an embodiment of the present application is shown. Figure 3 As shown, the device may include:

[0100] The email information acquisition unit 301 is used to acquire the email information of the email to be marked, wherein the email information includes the email subject and the email body;

[0101] A key information acquisition unit 302 is used to extract key events and the time corresponding to the key events from the email information;

[0102] A level acquisition unit 303 is used to acquire the importance level of the email to be marked according to key information, wherein the key information includes the key event and the time corresponding to the key event;

[0103] The marking display unit 304 is used to display the marking information of the emails to be marked according to the importance level of each email to be marked, and the marking information includes the importance level and key information.

[0104] Optionally, the key information acquisition unit is used to extract the key event and the time corresponding to the key event from the email information, including: the key information acquisition unit is specifically used to:

[0105] Extracting keywords from the email information based on the TF-IDF algorithm;

[0106] At least one of the keywords is concatenated to obtain at least one key event, and the start time and / or end time corresponding to the key event is obtained.

[0107] Optionally, the email information further includes: information of attachments of the email to be marked;

[0108] The device also includes: an attachment category acquisition unit, which is used to:

[0109] According to the information of the attachment of the email to be marked, the file category of the attachment is obtained.

[0110] Optionally, the key information further includes a file category of an attachment, and the level acquisition unit is used to acquire the importance level of the email to be marked according to the key information, including: the level acquisition unit is specifically used to:

[0111] Obtaining the importance score of the attachment according to a preset file correspondence relationship and the file category, wherein the file correspondence relationship includes a correspondence relationship between a preset category and a score;

[0112] According to a preset event correspondence, an importance score of the key event is obtained, wherein the event correspondence includes a correspondence between preset words and scores, and the importance score of the key event is positively correlated with the score corresponding to the keyword included in the key event;

[0113] Obtain a first duration and a second duration, wherein the first duration is the time interval between the current time and the start time corresponding to the key event, and the second duration is the time interval between the start time and the end time corresponding to the key event;

[0114] The importance level of the email to be marked is obtained based on the importance score of the attachment, the importance score of the key event, the first duration and the second duration, wherein the importance level of the key event is positively correlated with the importance score of the attachment and the importance score of the key event, and is negatively correlated with the first duration and the second duration.

[0115] Optionally, the marking display unit is used to display the marking information of the mails to be marked according to the importance level of each mail to be marked, including: the marking display unit is specifically used to:

[0116] The mails to be marked are sorted from high to low according to their importance level, and marking information of the mails to be marked is displayed.

[0117] Optionally, the device further includes: a preprocessing unit, used to obtain an email collection before obtaining the email information of the email to be marked, wherein the email collection includes multiple emails to be processed; based on the XGBoost algorithm, obtain the emails to be processed whose classification results are important emails from the email collection as the emails to be marked.

[0118] Figure 4 A schematic diagram of the structure of a mail marking device is shown, and the device may include: at least one processor 401, at least one communication interface 402, at least one memory 403 and at least one communication bus 404;

[0119] In the embodiment of the present application, the number of the processor 401, the communication interface 402, the memory 403, and the communication bus 404 is at least one, and the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404;

[0120] The processor 401 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention;

[0121] The memory 403 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0122] The memory stores a program, and the processor can execute the program stored in the memory to implement the steps of a mail marking method provided in an embodiment of the present application, as follows:

[0123] A mail marking method, comprising:

[0124] Obtaining email information of the email to be marked, wherein the email information includes the email subject and the email body;

[0125] Extracting key events and the time corresponding to the key events from the email information;

[0126] Obtaining the importance level of the email to be marked according to key information, wherein the key information includes the key event and the time corresponding to the key event;

[0127] According to the importance level of each of the mails to be marked, the marking information of the mails to be marked is displayed, and the marking information includes the importance level and key information.

[0128] Optionally, extracting key events and times corresponding to the key events from the email information includes:

[0129] Extracting keywords from the email information based on the TF-IDF algorithm;

[0130] Based on at least one of the keywords, at least one key event is obtained, and a start time and / or end time corresponding to the key event is acquired.

[0131] Optionally, the email information further includes: information of an attachment of the email to be marked; and the method further includes:

[0132] According to the information of the attachment of the email to be marked, the file category of the attachment is obtained.

[0133] Optionally, the key information further includes a file category of the attachment, and obtaining the importance level of the email to be marked according to the key information includes:

[0134] Obtaining the importance score of the attachment according to a preset file correspondence relationship and the file category, wherein the file correspondence relationship includes a correspondence relationship between a preset category and a score;

[0135] According to a preset event correspondence, an importance score of the key event is obtained, wherein the event correspondence includes a correspondence between preset words and scores, and the importance score of the key event is positively correlated with the score corresponding to the keyword included in the key event;

[0136] Obtain a first duration and a second duration, wherein the first duration is the time interval between the current time and the start time corresponding to the key event, and the second duration is the time interval between the start time and the end time corresponding to the key event;

[0137] The importance level of the email to be marked is obtained based on the importance score of the attachment, the importance score of the key event, the first duration and the second duration, wherein the importance level of the key event is positively correlated with the importance score of the attachment and the importance score of the key event, and is negatively correlated with the first duration and the second duration.

[0138] Optionally, displaying marking information of the emails to be marked according to the importance level of each email to be marked includes:

[0139] The mails to be marked are sorted from high to low according to their importance level, and marking information of the mails to be marked is displayed.

[0140] Optionally, before obtaining the email information of the email to be marked, the method further includes:

[0141] Obtaining a mail collection, wherein the mail collection includes a plurality of mails to be processed;

[0142] Based on the XGBoost algorithm, the emails to be processed whose classification results are important emails are obtained from the email collection as the emails to be marked.

[0143] The embodiment of the present application further provides a readable storage medium, which can store a computer program suitable for execution by a processor. When the computer program is executed by the processor, the steps of a mail marking method provided in the embodiment of the present application are implemented as follows:

[0144] A mail marking method, comprising:

[0145] Obtaining email information of the email to be marked, wherein the email information includes the email subject and the email body;

[0146] Extracting key events and the time corresponding to the key events from the email information;

[0147] Obtaining the importance level of the email to be marked according to key information, wherein the key information includes the key event and the time corresponding to the key event;

[0148] According to the importance level of each of the mails to be marked, the marking information of the mails to be marked is displayed, and the marking information includes the importance level and key information.

[0149] Optionally, extracting key events and times corresponding to the key events from the email information includes:

[0150] Extracting keywords from the email information based on the TF-IDF algorithm;

[0151] Based on at least one of the keywords, at least one key event is obtained, and a start time and / or end time corresponding to the key event is acquired.

[0152] Optionally, the email information further includes: information of an attachment of the email to be marked; and the method further includes:

[0153] According to the information of the attachment of the email to be marked, the file category of the attachment is obtained.

[0154] Optionally, the key information further includes a file category of the attachment, and obtaining the importance level of the email to be marked according to the key information includes:

[0155] Obtaining the importance score of the attachment according to a preset file correspondence relationship and the file category, wherein the file correspondence relationship includes a correspondence relationship between a preset category and a score;

[0156] According to a preset event correspondence, an importance score of the key event is obtained, wherein the event correspondence includes a correspondence between preset words and scores, and the importance score of the key event is positively correlated with the score corresponding to the keyword included in the key event;

[0157] Obtain a first duration and a second duration, wherein the first duration is the time interval between the current time and the start time corresponding to the key event, and the second duration is the time interval between the start time and the end time corresponding to the key event;

[0158] The importance level of the email to be marked is obtained based on the importance score of the attachment, the importance score of the key event, the first duration and the second duration, wherein the importance level of the key event is positively correlated with the importance score of the attachment and the importance score of the key event, and is negatively correlated with the first duration and the second duration.

[0159] Optionally, displaying marking information of the emails to be marked according to the importance level of each email to be marked includes:

[0160] The mails to be marked are sorted from high to low according to their importance level, and marking information of the mails to be marked is displayed.

[0161] Optionally, before obtaining the email information of the email to be marked, the method further includes:

[0162] Obtaining a mail collection, wherein the mail collection includes a plurality of mails to be processed;

[0163] Based on the XGBoost algorithm, the emails to be processed whose classification results are important emails are obtained from the email collection as the emails to be marked.

[0164] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0165] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0166] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A mail marking method, characterized in that: include: Obtaining email information of the email to be marked, wherein the email information includes the email subject and the email body; Extracting key events and the time corresponding to the key events from the email information; Obtaining the importance level of the email to be marked according to key information, wherein the key information includes the key event and the time corresponding to the key event; According to the importance level of each of the mails to be marked, display the marking information of the mails to be marked, wherein the marking information includes the importance level and key information; The step of extracting key events and the time corresponding to the key events from the email information includes: Extracting keywords from the email information based on the TF-IDF algorithm; Based on at least one of the keywords, at least one key event is obtained, and a start time and / or end time corresponding to the key event is acquired; The email information further includes: information of the attachment of the email to be marked; and the method further includes: According to the information of the attachment of the email to be marked, obtaining the file category of the attachment; The key information also includes the file category of the attachment, and obtaining the importance level of the email to be marked based on the key information includes: Obtaining the importance score of the attachment according to a preset file correspondence relationship and the file category, wherein the file correspondence relationship includes a correspondence relationship between a preset category and a score; According to a preset event correspondence, an importance score of the key event is obtained, wherein the event correspondence includes a correspondence between preset words and scores, and the importance score of the key event is positively correlated with the score corresponding to the keyword included in the key event; Obtain a first duration and a second duration, wherein the first duration is the time interval between the current time and the start time corresponding to the key event, and the second duration is the time interval between the start time and the end time corresponding to the key event; The importance level of the email to be marked is obtained based on the importance score of the attachment, the importance score of the key event, the first duration and the second duration, wherein the importance level of the key event is positively correlated with the importance score of the attachment and the importance score of the key event, and is negatively correlated with the first duration and the second duration.

2. The method according to claim 1, characterized in that The displaying of the marking information of the emails to be marked according to the importance level of each email to be marked includes: The mails to be marked are sorted from high to low according to their importance level, and marking information of the mails to be marked is displayed.

3. The method according to claim 2, characterized in that Before obtaining the email information of the email to be marked, the method further includes: Obtaining a mail collection, wherein the mail collection includes a plurality of mails to be processed; Based on the XGBoost algorithm, the emails to be processed whose classification results are important emails are obtained from the email collection as the emails to be marked.

4. A mail marking device, characterized in that: include: An email information acquisition unit, used to acquire email information of the email to be marked, wherein the email information includes the email subject and the email body; A key information acquisition unit, used to extract key events and the time corresponding to the key events from the email information; A level acquisition unit, configured to acquire the importance level of the email to be marked according to key information, wherein the key information includes the key event and the time corresponding to the key event; A marking display unit, used for displaying marking information of the mails to be marked according to the importance level of each mail to be marked, wherein the marking information includes the importance level and key information; The key information acquisition unit is used to extract the key event and the time corresponding to the key event from the email information, including: the key information acquisition unit is specifically used to: Extracting keywords from the email information based on the TF-IDF algorithm; splicing at least one of the keywords to obtain at least one key event, and obtaining the start time and / or end time corresponding to the key event; The email information further includes: information of the attachment of the email to be marked; and the method further includes: According to the information of the attachment of the email to be marked, obtaining the file category of the attachment; The key information also includes the file category of the attachment, and obtaining the importance level of the email to be marked based on the key information includes: Obtaining the importance score of the attachment according to a preset file correspondence relationship and the file category, wherein the file correspondence relationship includes a correspondence relationship between a preset category and a score; According to a preset event correspondence, an importance score of the key event is obtained, wherein the event correspondence includes a correspondence between preset words and scores, and the importance score of the key event is positively correlated with the score corresponding to the keyword included in the key event; Obtain a first duration and a second duration, wherein the first duration is the time interval between the current time and the start time corresponding to the key event, and the second duration is the time interval between the start time and the end time corresponding to the key event; The importance level of the email to be marked is obtained based on the importance score of the attachment, the importance score of the key event, the first duration and the second duration, wherein the importance level of the key event is positively correlated with the importance score of the attachment and the importance score of the key event, and is negatively correlated with the first duration and the second duration.

5. A mail marking device, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the mail marking method according to any one of claims 1 to 3.

6. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of a mail marking method according to any one of claims 1 to 3 is implemented.

Citation Information

Patent Citations

  • Mail processing method and device and storage medium

    CN113706115A