Mail processing method, mail processing device, electronic device and storage medium

By performing word segmentation processing and semantic analysis on email information, and using semantic analysis model to predict processing methods, the problem of poor timeliness of email processing is solved, labor and time costs are reduced, and automatic processing capabilities are improved.

CN113343682BActive Publication Date: 2024-12-03INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110634376.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-07
Publication Date
2024-12-03
Estimated Expiration
2041-06-07

AI Technical Summary

Technical Problem

When the business department processes a large number of emails, the timeliness of survey and feedback emails are poor, resulting in no significant decrease in labor and time costs, and the inability to process them automatically after the introduction of the robot process automation system, resulting in a backlog of emails.

Method used

By performing word-partitioning processing on email information, semantic feature vectors are generated, and semantic analysis models are used to predict the processing methods of emails, including forwarding, supervision and non-processing, and optimizing model training to improve automatic processing capabilities.

Benefits of technology

It effectively reduces the labor and time cost of business departments for processing emails, improves the timeliness of email processing, and at least partially solves the problem of emails that cannot be processed automatically.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113343682B_ABST
    Figure CN113343682B_ABST
Patent Text Reader

Abstract

The present disclosure provides an email processing method that can be used in the field of artificial intelligence, computer technology, finance or other fields. The method includes: obtaining email information of an email to be processed; performing word segmentation processing on the email information to obtain multiple keywords of the email to be processed; parsing the parts of speech of multiple keywords to determine the part-of-speech category to which the keywords belong; generating a first semantic feature vector of the email to be processed based on the first keyword whose part-of-speech category is a noun or a verb; and inputting the first semantic feature vector into a first semantic analysis model, and outputting a processing method for the email to be processed, wherein the processing methods for the email to be processed include forwarding, supervision and non-processing. In addition, the present disclosure also provides an email processing device, an electronic device, a readable storage medium and a computer program product.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the fields of computer technology, artificial intelligence, and finance, and more specifically, to a mail processing method, a mail processing device, an electronic device, a readable storage medium, and a computer program product. Background Art

[0002] As the business develops, the public mailboxes of business departments receive a large number of emails every day, and processing these emails requires huge manpower and time costs.

[0003] In the process of realizing the concept disclosed herein, the inventors discovered that in the judgment mechanism of the relevant email processing method, survey and feedback emails, which account for a large proportion of the total daily email volume, still need to be processed manually, the timeliness of email processing is poor, and the manpower and time costs have not been significantly reduced. Summary of the invention

[0004] In view of this, the present disclosure provides a mail processing method, a mail processing device, an electronic device, a readable storage medium and a computer program product.

[0005] One aspect of the present disclosure provides an email processing method, including: obtaining email information of an email to be processed; performing word segmentation processing on the email information to obtain multiple keywords of the email to be processed; parsing the parts of speech of the multiple keywords to determine the part-of-speech categories to which the keywords belong; generating a first semantic feature vector of the email to be processed based on a first keyword whose part-of-speech category is a noun or a verb; and inputting the first semantic feature vector into a first semantic analysis model to output a processing method for the email to be processed, wherein the processing methods for the email to be processed include forwarding, supervision and non-processing.

[0006] According to an embodiment of the present disclosure, the above-mentioned first keyword includes multiple; the above-mentioned first keyword based on the belonging part of speech category of noun or verb is used to generate the first semantic feature vector of the above-mentioned email to be processed, including: determining the weight of each of the above-mentioned first keywords; converting each of the above-mentioned first keywords into a first feature vector; and converting the multiple above-mentioned first feature vectors into the above-mentioned first semantic feature vector based on the weights of the multiple above-mentioned first keywords.

[0007] According to an embodiment of the present disclosure, the above-mentioned email information includes an email title and an email body text; wherein, the above-mentioned determination of the weight of each of the above-mentioned first keywords includes: determining the weights of multiple above-mentioned first keywords based on the original position relationship of the multiple above-mentioned first keywords, wherein the weight of the first keyword extracted from the above-mentioned email title is greater than the weight of the first keyword extracted from the above-mentioned email body text.

[0008] According to an embodiment of the present disclosure, when the file type of the email attachment of the above-mentioned email to be processed is a preset type, the above-mentioned email information also includes the attachment body text of the above-mentioned email to be processed; wherein the weight of the first keyword extracted from the above-mentioned attachment body text is less than the weight of the first keyword extracted from the above-mentioned email body text.

[0009] According to an embodiment of the present disclosure, when the processing method of the above-mentioned pending email is forwarding, the above-mentioned method also includes: determining the processing personnel of the above-mentioned pending email based on the second keyword whose part of speech category is a person's name and the recipient information and carbon copy information of the above-mentioned pending email; sending the above-mentioned pending email to the above-mentioned processing personnel; and moving the above-mentioned pending email to the processed list.

[0010] According to an embodiment of the present disclosure, when the processing method of the above-mentioned pending email is supervision, the above-mentioned method also includes: determining the processing personnel of the above-mentioned pending email based on the second keyword whose part of speech category is a person's name and the recipient information and cc information of the above-mentioned pending email; determining the supervisor of the above-mentioned pending email based on the duty roster of the supervisor; sending the above-mentioned pending email to the above-mentioned processing personnel and the above-mentioned supervisor; and moving the above-mentioned pending email to the supervision list.

[0011] According to an embodiment of the present disclosure, it also includes: generating a second semantic feature vector of the above-mentioned email to be processed based on a third keyword whose part of speech category is adjective and interjection; and inputting the above-mentioned second semantic feature vector into a second semantic analysis model to output the priority of the above-mentioned email to be processed.

[0012] According to an embodiment of the present disclosure, it also includes: determining the frequency of email reminders based on the priority of the emails in the above-mentioned supervision list; determining the processing time limit of the emails in the above-mentioned supervision list based on the fourth keyword whose part of speech category is a time name and the receipt time information of the above-mentioned emails to be processed; and within the above-mentioned processing time limit, sending reminder emails to the above-mentioned processing personnel and the above-mentioned supervision personnel based on the above-mentioned email reminder frequency.

[0013] According to an embodiment of the present disclosure, it also includes: performing a confidence analysis on the processing method of the above-mentioned pending email obtained through the above-mentioned first semantic analysis model to obtain the credibility of the above-mentioned processing method; and when the above-mentioned credibility is lower than a preset threshold, transferring the above-mentioned pending email to a manual processing list.

[0014] According to an embodiment of the present disclosure, it also includes: obtaining the actual processing method of the emails in the above-mentioned manual processing list; and using the emails in the above-mentioned manual processing list and their actual processing methods as training samples to optimize the training of the above-mentioned first semantic analysis model.

[0015] Another aspect of the present disclosure provides an email processing device, including: an acquisition module, a first processing module, a parsing module, a first generation module and a first output module. Among them: the acquisition module is used to acquire the email information of the email to be processed; the first processing module is used to perform word segmentation processing on the above email information to obtain multiple keywords of the above email to be processed; the parsing module is used to parse the parts of speech of the above multiple keywords to determine the part of speech category to which the above keywords belong; the first generation module is used to generate the first semantic feature vector of the above email to be processed based on the first keyword whose part of speech category is a noun or a verb; and the first output module is used to input the above first semantic feature vector into the first semantic analysis model, and output the processing method of the above email to be processed, wherein the processing methods of the above email to be processed include forwarding, supervision and non-processing.

[0016] Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more instructions, wherein when the one or more instructions are executed by the one or more processors, the one or more processors implement the method as described above.

[0017] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0018] Another aspect of the present disclosure provides a computer program product, which includes computer executable instructions. When the computer executable instructions are executed, the computer executable instructions are used to implement the method described above.

[0019] According to an embodiment of the present disclosure, by performing word segmentation processing on the email information of the email to be processed, multiple keywords are obtained, and the parts of speech of the multiple keywords are analyzed, and a feature vector is generated using the keywords with the part of speech category of noun or verb. Then, the feature vector is input into the semantic analysis model to obtain the processing method of the email to be processed predicted by the model, which at least partially solves the problem that the emails that need to be supervised cannot be processed automatically, thereby effectively reducing the manpower and time costs required by the business department to process the emails, and improving the timeliness of email processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0021] Figure 1 Schematically illustrates an exemplary system architecture 100 to which the mail processing method according to an embodiment of the present disclosure can be applied;

[0022] Figure 2The flowchart of the mail processing method 200 according to the embodiment of the present disclosure is schematically shown;

[0023] Figure 3 A schematic diagram of a mail processing method 300 according to another embodiment of the present disclosure is schematically shown;

[0024] Figure 4 A flowchart of a method 400 for processing emails in a to-do list according to another embodiment of the present disclosure is schematically shown;

[0025] Figure 5 A schematic diagram schematically shows a mail processing system according to an embodiment of the present disclosure;

[0026] Figure 6 Schematically shows a block diagram of a mail processing device 600 according to an embodiment of the present disclosure;

[0027] Figure 7 A block diagram of an electronic device suitable for implementing a mail processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0029] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0030] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0031] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0032] The Robotic Process Automation (RPA) system provides a way to automate users' manual operation processes by imitating the users' manual operation methods on computers, which can improve business efficiency and automate repetitive work.

[0033] In the related technology, after the business department introduces the robotic process automation system, the departmental emails received can be classified into automatic processing and manual processing. However, surveys, feedback and other emails that require human supervision and have certain timeliness requirements for email processing are usually not simply identified and automatically processed. Due to the high time cost of manual processing, it is easy to cause email backlogs, and there is a hidden danger that emails cannot be processed in time; on the other hand, in some business departments, such emails can account for more than half of the total daily emails, so after the introduction of the robotic process automation system, the labor and time costs of processing emails have not decreased significantly.

[0034] In view of this, the embodiments of the present disclosure utilize related methods of robotic process automation and natural language processing (NLP) to capture information and perform sample learning on email titles, email bodies, and email attachments, and automatically send emails and supervise emails by judging key information.

[0035] Specifically, the embodiments of the present disclosure provide a mail processing method, a mail processing device, an electronic device, a readable storage medium and a computer program product. The method includes obtaining mail information of a mail to be processed; performing word segmentation processing on the mail information to obtain multiple keywords of the mail to be processed; parsing the parts of speech of multiple keywords to determine the part-of-speech category to which the keywords belong; generating a first semantic feature vector of the mail to be processed based on the first keyword whose part-of-speech category is a noun or a verb; and inputting the first semantic feature vector into a first semantic analysis model to output a processing method of the mail to be processed, wherein the processing methods of the mail to be processed include forwarding, supervision and non-processing.

[0036] It should be noted that the mail processing method and device provided by the embodiments of the present disclosure can be used in the field of artificial intelligence, computer technology or finance. For example, the mail processing method can be used in the backend server of a bank to automatically send mails received in a public mailbox. The mail processing method provided by the embodiments of the present disclosure can also be used in other fields besides the above fields. For example, in the field of military science and technology, the only interface between the internal network of a military enterprise and the external network is generally a public mailbox. Therefore, a large number of mails are received in the public mailbox every day. The mail processing method can greatly reduce the manpower and time costs of military enterprises in processing mails, and ensure the timeliness of mail processing. The mail processing method and device provided by the embodiments of the present disclosure do not limit the application field.

[0037] Figure 1 The exemplary system architecture 100 to which the mail processing method according to the embodiment of the present disclosure can be applied is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0038] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a system terminal device 102 , a network 103 , and user terminal devices 104 , 105 .

[0039] The system terminal device 102 may be any electronic device that supports information storage and information processing functions, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, a server, a server cluster, etc.

[0040] The network 103 is used to provide a medium for a communication link between the system terminal device 102 and the user terminal devices 104 and 105. The network 103 may include various connection types, such as wired and / or wireless communication links.

[0041] The user terminal devices 104 and 105 may be various electronic devices having a display screen and supporting network communication and mail processing functions, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0042] The mail processing method provided in the embodiment of the present disclosure may be executed on the system terminal device 102, and accordingly, the mail processing apparatus provided in the embodiment of the present disclosure may also be arranged in the system terminal device 102. After receiving the mail 101 to be processed, the system terminal device 102 may determine the processing method of the mail 101 to be processed by the mail processing method, and send the mail 101 to be processed to the corresponding processing personnel through the network 103 according to the processing method, and the processing personnel may process the received mail 101 to be processed by using the user terminal device (such as the user terminal device 104).

[0043] In addition, the mail processing method provided in the embodiment of the present disclosure may also be executed by a server or server cluster that can communicate with the system terminal device 102. Accordingly, the mail processing device provided in the embodiment of the present disclosure may also be arranged in a server or server cluster that can communicate with the system terminal device 102. At this time, after receiving the mail 101 to be processed, the system terminal device 102 may upload the mail 101 to the above-mentioned server or server cluster to obtain the processing method of the mail 101 to be processed, and based on the processing method, send the mail 101 to be processed to the corresponding processing personnel through the network 103.

[0044] It should be understood that Figure 1 The number of the mails to be processed, system terminal devices, networks and user terminal devices is only illustrative. According to the implementation requirements, there can be any number of system terminal devices, networks and user terminal devices, and the number of mails to be processed 101 can also be any number.

[0045] Figure 2 The flowchart of the mail processing method 200 according to the embodiment of the present disclosure is schematically shown.

[0046] like Figure 2 As shown, the mail processing method 200 includes operations S201 to S205.

[0047] In operation S201, the mail information of the mail to be processed is obtained.

[0048] In operation S202, the email information is segmented to obtain a plurality of keywords of the email to be processed.

[0049] In operation S203, the parts of speech of the plurality of keywords are analyzed to determine the part of speech categories to which the keywords belong.

[0050] In operation S204, a first semantic feature vector of the email to be processed is generated based on the first keywords whose attributed part-of-speech categories are nouns or verbs.

[0051] In operation S205, the first semantic feature vector is input into the first semantic analysis model, and a processing method for the email to be processed is output, where the processing method for the email to be processed includes forwarding, supervision, and non-processing.

[0052] According to an embodiment of the present disclosure, emails to be processed can be obtained through different methods. For example, a robot process automation system can be used to monitor the public mailbox of a business department in real time to obtain emails to be processed; for another example, for a mailbox using the POP3 protocol, emails to be processed in the inbox can be obtained through an interface; for a Domino Notes mailbox, the mailbox can be opened through a COM component to obtain emails to be processed.

[0053] According to an embodiment of the present disclosure, after receiving an email to be processed, a robot process automation system can be used to parse the email to be processed to obtain email information including the email title, sender information, recipient information, carbon copy recipient information, email body text, and email attachments.

[0054] According to an embodiment of the present disclosure, before performing word segmentation processing on the obtained email information, the email information can also be preprocessed, including but not limited to removing punctuation and special symbols in the email title and email body, etc.

[0055] According to an embodiment of the present disclosure, word segmentation methods can include dictionary-based word segmentation methods represented by the maximum matching word segmentation algorithm and the shortest path word segmentation algorithm, and character-based word segmentation methods represented by the generative model word segmentation algorithm and the neural network word segmentation algorithm.

[0056] According to an embodiment of the present disclosure, the part-of-speech tagging method can tag each keyword in the word segmentation result with a correct part of speech. Specifically, the part-of-speech parsing of keywords can be implemented by using methods such as part-of-speech tagging based on maximum entropy, maximum probability output of part of speech based on statistics, and part-of-speech tagging based on hidden Markov.

[0057] According to an embodiment of the present disclosure, the part-of-speech categories of keywords can include nouns, verbs, adjectives, other proper names, personal names, place names, institutional groups, conjunctions, discriminative words, interjections, adverbs, locative words, prefixes, suffixes, numerals, onomatopoeias, quantifiers, prepositions, locative words, pronouns, auxiliary words, time words, punctuation marks, modal particles, state words, etc. The same keyword can belong to multiple part-of-speech categories. For example, "up" can belong to both "verb" and "locative word" at the same time.

[0058] According to an embodiment of the present disclosure, keywords can be converted into one-hot or distributed representation word vectors by methods such as SVD, CBOW, and Skip-gram. All word vectors obtained by converting the first keyword are vectorized to obtain a first semantic feature vector.

[0059] According to an embodiment of the present disclosure, word vectors with the same or similar meanings are close in the vector space.

[0060] According to an embodiment of the present disclosure, the first semantic analysis model can be obtained by using a general Chinese text analysis model as an initial model, using the collected historical manually processed email information and processing methods as training samples, and training using a machine learning algorithm such as SVM and GBDT.

[0061] According to the embodiments of the present disclosure, after obtaining the processing method of the pending email, the email can be processed according to the specific email processing method corresponding to the processing method. For example, for a pending email whose processing method is forwarding, the email can be forwarded to the set processing personnel to complete the processing of the email; for a pending email whose processing method is supervision, after sending the email information to the relevant personnel, the progress of the email needs to be supervised; for a pending email whose processing method is not processing, the email can be directly moved to the list that does not need to be processed.

[0062] According to an embodiment of the present disclosure, by performing word segmentation processing on the email information of the email to be processed, multiple keywords are obtained, and the parts of speech of the multiple keywords are analyzed, and a feature vector is generated using the keywords with the part of speech category of noun or verb. Then, the feature vector is input into the semantic analysis model to obtain the processing method of the email to be processed predicted by the model, which at least partially solves the problem that the emails that need to be supervised cannot be processed automatically, thereby effectively reducing the manpower and time costs required by the business department to process the emails, and improving the timeliness of email processing.

[0063] Reference below Figure 3 to Figure 5 , combined with specific embodiments Figure 2 The method shown is further explained.

[0064] Figure 3 A schematic diagram of a mail processing method 300 according to another embodiment of the present disclosure is schematically shown.

[0065] like Figure 3 As shown, the mail processing method 300 includes operations S301 to S312.

[0066] In operation S301, keywords are extracted from the email information of the email to be processed.

[0067] In operation S302, a semantic analysis model is used to predict a processing method of the email based on the keywords.

[0068] In operation S303, it is determined whether the mail processing method is credible. If the mail processing method is not credible, it is considered that there is doubt about the specific processing method of the mail to be processed, and operations S304 to S305 are performed; if the mail processing method is credible, operation S306 is performed.

[0069] In operation S304, the mail to be processed is transferred to a manual processing list, and the on-duty personnel are notified to process it manually.

[0070] In operation S305, the semantic analysis model is optimized according to the processed emails in the manual processing list and the actual processing methods.

[0071] In operation S306, it is determined whether the mail processing mode is not to process. If the mail processing mode is not to process, operation S307 is executed; if the mail processing mode is other, operation S308 is executed.

[0072] In operation S307, the mails to be processed are transferred to a list that does not need to be processed.

[0073] In operation S308, the actual person who processes the mail to be processed is obtained.

[0074] In operation S309, it is determined whether the mail processing mode is supervision. If the mail processing mode is supervision, operations S310 to S311 are performed; if the mail processing mode is forwarding, operation S312 is performed.

[0075] In operation S310, a supervisor of the mail is determined.

[0076] In operation S311, the mail to be processed is sent to the actual processing personnel and the supervisor, and the mail to be processed is transferred to the supervision list.

[0077] In operation S312, the mail to be processed is sent to the actual processing personnel, and the mail to be processed is transferred to the processed list.

[0078] According to an embodiment of the present disclosure, operations S301 to S302 may be implemented according to operations S201 to S205 in the mail processing method 200 .

[0079] According to an embodiment of the present disclosure, when the file type of the email attachment of the email to be processed is a file type that can directly read text, such as word, excel, pdf, etc., the extracted keywords can also include keywords extracted from the attachment body text.

[0080] According to an embodiment of the present disclosure, the feature vector converted from the keyword can be used to obtain the input feature vector of the semantic analysis model through weighted summation.

[0081] According to an embodiment of the present disclosure, the weight of a keyword can be determined according to the position of the keyword. For example, the weight of a keyword extracted from an email title can be set to be greater than the weight of a keyword extracted from the email body text, and the weight of a keyword extracted from the email body text can be set to be greater than the weight of a keyword extracted from the attachment body text. The weights of keywords extracted from different positions in the email body text can also be different. For example, the weight of a keyword extracted from the beginning or end of the body text can be set to be greater than the weight of keywords extracted from other parts.

[0082] According to an embodiment of the present disclosure, the weight of a keyword can also be determined based on an empirical rule developed using historical manual processing experience. For example, if the keywords obtained from the email title are words such as "know", "notify", and "process", a higher weight can be set for these keywords.

[0083] According to an embodiment of the present disclosure, the output result of the semantic analysis model is a three-dimensional vector.

[0084] According to an embodiment of the present disclosure, the output vector of the semantic analysis model can be normalized and used to determine whether the email processing method is credible. When the maximum value of the normalized output vector is less than a preset threshold, it can be considered that the prediction result is not accurate enough. The preset threshold can be set arbitrarily, for example, it can be set to 0.9.

[0085] According to an embodiment of the present disclosure, when the semantic analysis model has no output or reports an error, the email may also be transferred to a manual processing list.

[0086] According to an embodiment of the present disclosure, the emails in the manually processed list can also be used as training data to perform intensive training on the semantic analysis model to improve the accuracy of the model prediction.

[0087] According to an embodiment of the present disclosure, the actual person who handles the mail to be processed can be determined based on the keyword of the name to which the part-of-speech category belongs and the recipient information and the carbon copy information of the mail to be processed.

[0088] According to the embodiments of the present disclosure, the actual person who handles the email to be processed can also be determined based on the comparison results of keywords in the pre-built data dictionary. For example, proper nouns such as relevant teams, systems, departments, matters, and names of personnel are pre-entered in the data dictionary, and the association relationship between the names of personnel and the relevant teams, systems, departments, and matters is set; after comparing the keywords with the proper nouns, the actual person who handles the email can be determined through the pre-set association relationship.

[0089] According to the embodiments of the present disclosure, when the mail processing method is forwarding, the mail to be processed can be directly sent to the actual processing personnel, and then the mail to be processed is moved to the processed list to end the processing of the mail.

[0090] According to the embodiments of the present disclosure, the supervisor of the mail to be processed can be determined based on the supervisor's duty table, or based on a pre-built data dictionary, wherein the data dictionary pre-sets the association between the supervisor and the team, system, department, matter or personnel, etc. Accordingly, the supervisor can accurately supervise the actual person who handles the mail, so as to improve the refined management of the mail.

[0091] According to an embodiment of the present disclosure, when the mail processing mode is supervision, the mails to be processed can be sent to the actual processing personnel and the supervision personnel, and the mails to be processed can be moved to the supervision list.

[0092] Figure 4 The flowchart of a method 400 for processing emails in a to-do list according to another embodiment of the present disclosure is schematically shown.

[0093] like Figure 4 As shown, the method 400 includes operations S401 to S407.

[0094] In operation S401 , the priority of the mail is determined to determine the reminder frequency.

[0095] In operation S402, a time limit for processing the mail is determined.

[0096] In operation S403, a reminder email is sent to the processing personnel and the supervisor according to the reminder frequency.

[0097] In operation S404, it is determined whether the mail processing time limit has been exceeded. If the mail processing time limit has not been exceeded, operation S403 is continued to be performed; if the mail processing time limit has been exceeded, operation S405 is performed.

[0098] In operation S405, it is determined whether the mail has been processed. After the mail has been processed, operation S406 is executed; if it is determined that the mail has not been processed, operation S407 is executed.

[0099] In operation S406, the mail is transferred to a processed list.

[0100] In operation S407, the mail is transferred to a manual processing list.

[0101] According to an embodiment of the present disclosure, the emails in the supervision list may be emails whose processing method is determined to be supervision through a related method in the email processing method 200 or the email processing method 300 .

[0102] According to an embodiment of the present disclosure, the priority of an email can be predicted by a sentiment analysis method. For example, a sentiment feature vector of the email can be generated based on keywords belonging to adjectives and interjections, and then the sentiment feature vector is input into a sentiment analysis model to output the priority of the email.

[0103] According to an embodiment of the present disclosure, the priority of an email can also be determined based on an empirical rule formulated using historical manual processing experience. For example, when the email title or email body contains words such as "urgent" or "important", the priority of the email is determined to be higher.

[0104] According to the embodiments of the present disclosure, the semantic analysis model in the email processing method 200 or the email processing method 300 is combined with the sentiment analysis model in the present method 400 to obtain the classification result of the email, and the corresponding processing rules can be established based on the classification result to automatically send the email. For example, an email titled "Notification on the Production of XX", the model predicts that the processing method is "forwarding", the priority is "medium", the systems or personnel involved are extracted, and the email is sent to the relevant personnel according to the association relationship configured in the data dictionary; an email titled "Research on [Important] XX", the model predicts that the processing method is "supervision", the priority is "high", the systems involved and the required completion date are extracted, and the email is sent to the person in charge of the system.

[0105] According to the embodiments of the present disclosure, the processing time limit of the email can be determined based on the keywords whose part of speech category is time name and the email receiving time information. For example, the words matching the common date formats "YYYY-M-D-D", "M-D-D", "YYYY-MD", "MD", etc. in the email information can be used as the processing time limit of the email; or the words matching "week X", "next week X", etc. can be used as keywords to determine the time required for replying to the email, and then combined with the email receiving time information, the processing time limit of the email can be obtained.

[0106] According to an embodiment of the present disclosure, the email processing time limit may be compared with the system time to determine whether the email processing time limit has been exceeded.

[0107] According to an embodiment of the present disclosure, it is possible to determine whether an email in the supervision list has been processed based on the feedback email of the actual processing personnel or the instruction email of the sender of the email. For example, if the keywords extracted from the feedback email or the instruction email contain words such as "completed" or "processed", the email is considered to have been processed.

[0108] It should be noted that, unless it is explicitly stated that there is a sequence of execution between different operations shown in the flowchart in the embodiments of the present disclosure, or there is a sequence of execution between different operations in technical implementation, otherwise, the execution order of multiple operations may not be prioritized, and multiple operations may also be executed simultaneously.

[0109] Figure 5 The schematic diagram of a mail processing system according to an embodiment of the present disclosure is schematically shown.

[0110] like Figure 5 As shown, the email processing system includes an email text extraction module 501 , a semantic analysis module 502 , a rule module 503 and a to-do center module 504 .

[0111] According to an embodiment of the present disclosure, the text extraction module 501 can implement operation S201 in the mail processing method 200 and operation S301 in the mail processing method 300 .

[0112] According to an embodiment of the present disclosure, the semantic analysis module 502 can implement operations S202 to S205 in the mail processing method 200 , operations S302 to S312 in the mail processing method 300 , and operations S401 to S402 in the processing method 400 .

[0113] According to an embodiment of the present disclosure, the rule module 503 may include empirical rules for determining keyword weights, processing personnel configuration rules for determining actual processing personnel from a data dictionary, supervisory personnel configuration rules for determining supervisory personnel from a supervisory personnel duty list, and corresponding email processing rules established based on the processing method and priority output by the model, etc.

[0114] According to an embodiment of the present disclosure, the to-do center module 504 can implement operations S403 to S406 in the processing method 400 .

[0115] According to an embodiment of the present disclosure, the to-do center module 504 may be established based on a project or team management tool represented by JIRA or REDMINE, and may provide an online interface for other modules to call.

[0116] According to an embodiment of the present disclosure, the emails in the supervision list can be processed in the to-do center module 504. Through the online interface, the to-do center module 504 can set a to-do title for the emails in the supervision list, and record information such as the actual processing personnel, supervising personnel, processing time limit, priority, notes, etc.

[0117] According to an embodiment of the present disclosure, the to-do center module 504 can also provide to-do statistical analysis, statistically analyzing data such as the time spent on email processing by each actual processing personnel, the number of emails processed, to-do tags, and hot spots of item classification analysis, so that business personnel can analyze problems based on statistical information and propose targeted countermeasures.

[0118] Figure 6 The block diagram of the mail processing device 600 according to the embodiment of the present disclosure is schematically shown.

[0119] like Figure 6 As shown, the mail processing device 600 includes an acquisition module 610, a first processing module 620, a parsing module 630, a first generating module 640 and a first output module 650. Among them:

[0120] The acquisition module 610 is used to acquire the email information of the email to be processed.

[0121] The first processing module 620 is used to perform word segmentation processing on the email information to obtain multiple keywords of the email to be processed.

[0122] The parsing module 630 is used to parse the parts of speech of multiple keywords to determine the part of speech category to which the keywords belong.

[0123] The first generating module 640 is configured to generate a first semantic feature vector of the to-be-processed email based on the first keyword whose part of speech category is a noun or a verb.

[0124] The first output module 650 is used to input the first semantic feature vector into the first semantic analysis model, and output a processing method for the mail to be processed, wherein the processing methods for the mail to be processed include forwarding, supervision and non-processing.

[0125] According to an embodiment of the present disclosure, by performing word segmentation processing on the email information of the email to be processed, multiple keywords are obtained, and the parts of speech of the multiple keywords are analyzed, and a feature vector is generated using the keywords with the part of speech category of noun or verb. Then, the feature vector is input into the semantic analysis model to obtain the processing method of the email to be processed predicted by the model, which at least partially solves the problem that the emails that need to be supervised cannot be processed automatically, thereby effectively reducing the manpower and time costs required by the business department to process the emails, and improving the timeliness of email processing.

[0126] According to an embodiment of the present disclosure, the first keyword may include multiple ones.

[0127] According to an embodiment of the present disclosure, the first generation module 640 includes a first generation unit, a second generation unit and a third generation unit.

[0128] The first generating unit is used to determine the weight of each first keyword.

[0129] The second generating unit is configured to convert each first keyword into a first feature vector.

[0130] The third generating unit is configured to convert the plurality of first feature vectors into a first semantic feature vector based on the weights of the plurality of first keywords.

[0131] According to an embodiment of the present disclosure, the mail information may include a mail title and a mail body text.

[0132] According to an embodiment of the present disclosure, the first generation unit 640 is also used to determine the weights of multiple first keywords based on the original position relationship of the multiple first keywords, wherein the weight of the first keyword extracted from the email title is greater than the weight of the first keyword extracted from the email body text.

[0133] According to an embodiment of the present disclosure, when the file type of the email attachment of the email to be processed is a preset type, the email information may also include the attachment body text of the email to be processed; wherein the weight of the first keyword extracted from the attachment body text is less than the weight of the first keyword extracted from the email body text.

[0134] According to an embodiment of the present disclosure, the mail processing device 600 may further include a first sending module, which is used to process the pending mails whose processing mode is forwarding. The first sending module includes a first sending unit, a second sending unit and a third sending unit, wherein:

[0135] The first sending unit is used to determine a person who processes the mail to be processed based on the second keyword whose part of speech category is a person's name and the recipient information and the carbon copy information of the mail to be processed.

[0136] The second sending unit is used to send the mail to be processed to the processing personnel.

[0137] The third sending unit is used to move the to-be-processed mail to the processed list.

[0138] According to an embodiment of the present disclosure, the mail processing device 600 may further include a second sending module, which is used to process pending mails whose processing mode is supervision. The second sending module includes a fourth sending unit, a fifth sending unit, a sixth sending unit and a seventh sending unit, wherein:

[0139] The fourth sending unit is used to determine a person who will process the mail to be processed based on the second keyword whose part of speech category is a person's name and the recipient information and the carbon copy information of the mail to be processed.

[0140] The fifth sending unit is used to determine the supervisor of the mail to be processed based on the supervisor's duty list.

[0141] The sixth sending unit is used to send the mails to be processed to the processing personnel and the supervisory personnel.

[0142] The seventh sending unit is used to move the pending emails to the supervision list.

[0143] According to an embodiment of the present disclosure, the mail processing device 600 may further include a second generating module and a second output module, wherein:

[0144] The second generating module is used to obtain a second semantic feature vector of the to-be-processed email based on the third keyword whose part of speech category is adjective and interjection.

[0145] The second output module is used to input the second semantic feature vector into the second semantic analysis model, and output the priority of the email to be processed.

[0146] According to an embodiment of the present disclosure, the mail processing device 600 may further include a third sending module. The third sending module includes an eighth sending unit, a ninth sending unit and a tenth sending unit, wherein:

[0147] The eighth sending unit is used to determine the frequency of email reminders based on the priorities of the emails in the supervision list.

[0148] The ninth sending unit is used to determine the processing time limit of the emails in the supervision list based on the fourth keyword whose part of speech category is the time name and the receipt time information of the email to be processed.

[0149] The tenth sending unit is used to send reminder emails to the processing personnel and the supervisory personnel within the processing time limit based on the email reminder frequency.

[0150] According to an embodiment of the present disclosure, the mail processing device 600 may further include an analysis module, wherein the analysis module includes a first analysis unit and a second analysis unit, wherein:

[0151] The first analysis unit is used to perform a confidence analysis on the processing method of the to-be-processed email obtained through the first semantic analysis model to obtain the credibility of the processing method.

[0152] The second analysis unit is used to transfer the mail to be processed into a manual processing list when the credibility is lower than a preset threshold.

[0153] According to an embodiment of the present disclosure, the mail processing device 600 may further include a training module, wherein the training module includes a first training unit and a second training unit, wherein:

[0154] The first training unit is used to obtain actual processing methods of emails in the manual processing list.

[0155] The first training unit is used to use the emails in the manual processing list and their actual processing methods as training samples to optimize the first semantic analysis model.

[0156] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0157] For example, any multiple of the acquisition module 610, the first processing module 620, the parsing module 630, the first generation module 640 and the first output module 650 can be combined in one module / unit / sub-unit for implementation, or any one of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more modules / units / sub-units in these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the acquisition module 610, the first processing module 620, the parsing module 630, the first generation module 640 and the first output module 650 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware and firmware or by a suitable combination of any of them. Alternatively, at least one of the acquisition module 610, the first processing module 620, the parsing module 630, the first generation module 640 and the first output module 650 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0158] It should be noted that the mail processing device part in the embodiment of the present disclosure corresponds to the mail processing method part in the embodiment of the present disclosure. The description of the mail processing device part specifically refers to the mail processing method part, which will not be repeated here.

[0159] Figure 7 A block diagram of an electronic device suitable for implementing a mail processing method according to an embodiment of the present disclosure is schematically shown. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0160] like Figure 7 As shown, the computer electronic device 700 according to the embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage part 708 to the random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0161] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0162] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0163] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0164] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0165] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0166] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 702 and / or the RAM 703 described above and / or one or more memories other than the ROM 702 and the RAM 703 .

[0167] The embodiments of the present disclosure also include a computer program product, which includes a computer program, and the computer program contains program code for executing the method provided by the embodiments of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the email processing method provided by the embodiments of the present disclosure.

[0168] When the computer program is executed by the processor 701, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0169] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 709, and / or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0170] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0171] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0172] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A mail processing method, comprising: Get the email information of the email to be processed; Perform word segmentation processing on the email information to obtain multiple keywords of the email to be processed; Analyzing the parts of speech of the multiple keywords to determine the part of speech category to which the keywords belong; Generating a first semantic feature vector of the to-be-processed email based on the first keyword whose part of speech category is a noun or a verb; as well as Inputting the first semantic feature vector into a first semantic analysis model, and outputting a processing method for the pending email, wherein the processing methods for the pending email include forwarding, supervision, and non-processing; In the case where the processing mode of the pending mail is supervision, the method further includes: Generating a second semantic feature vector of the to-be-processed email based on the third keyword whose part of speech category is adjective and interjection; and The second semantic feature vector is input into a second semantic analysis model, and the priority of the pending email is obtained as an output to determine the email reminder frequency of the pending email in the supervision list.

2. The method according to claim 1, wherein: The first keyword includes a plurality of; The first semantic feature vector of the to-be-processed email is generated based on the first keyword whose part of speech category is a noun or a verb, including: Determining a weight of each of the first keywords; converting each of the first keywords into a first feature vector; and Based on the weights of the first keywords, the first feature vectors are converted into the first semantic feature vector.

3. The method according to claim 2, wherein: The email information includes the email title and the email body text; The step of determining the weight of each of the first keywords includes: The weights of the plurality of first keywords are determined according to the original position relationship of the plurality of first keywords, wherein the weight of the first keyword extracted from the email title is greater than the weight of the first keyword extracted from the email body text.

4. The method according to claim 3, wherein: In the case where the file type of the mail attachment of the mail to be processed is a preset type, the mail information further includes the body text of the attachment of the mail to be processed; The weight of the first keyword extracted from the attachment body text is smaller than the weight of the first keyword extracted from the email body text.

5. The method according to claim 1, wherein: In the case where the processing mode of the to-be-processed email is forwarding, the method further includes: Determine the person who will handle the email to be processed based on the second keyword whose part of speech category is a person's name and the recipient information and the carbon copy information of the email to be processed; Sending the pending email to the processing personnel; and Move the pending mail to the processed list.

6. The method according to claim 1, wherein: In the case where the processing mode of the pending mail is supervision, the method further includes: Determine the person who will handle the email to be processed based on the second keyword whose part of speech category is a person's name and the recipient information and the carbon copy information of the email to be processed; Determine the supervisor for the mail to be processed based on the supervisor duty list; Sending the pending mail to the processing personnel and the supervising personnel; and Move the pending emails to the to-do list.

7. The method according to claim 6, further comprising: Determine the processing time limit of the emails in the supervision list based on the fourth keyword whose part of speech category is a time name and the receipt time information of the email to be processed; as well as Within the processing time limit, based on the email reminder frequency, a reminder email is sent to the processing personnel and the supervisory personnel.

8. The method according to any one of claims 1 to 7, further comprising: Performing a confidence analysis on the processing method of the to-be-processed email obtained through the first semantic analysis model to obtain the credibility of the processing method; as well as When the credibility is lower than a preset threshold, the mail to be processed is transferred to a manual processing list.

9. The method according to claim 8, further comprising: Obtaining the actual processing method of the emails in the manual processing list; as well as The emails in the manual processing list and their actual processing methods are used as training samples to optimize the first semantic analysis model.

10. A mail processing device, comprising: The acquisition module is used to obtain the email information of the email to be processed; A first processing module is used to perform word segmentation processing on the email information to obtain multiple keywords of the email to be processed; A parsing module, used for parsing the parts of speech of the multiple keywords to determine the part of speech category to which the keywords belong; A first generating module, configured to generate a first semantic feature vector of the to-be-processed email based on a first keyword whose part of speech category is a noun or a verb; as well as A first output module, used for inputting the first semantic feature vector into a first semantic analysis model, and outputting a processing method for the mail to be processed, wherein the processing methods for the mail to be processed include forwarding, supervision and non-processing; In the case where the processing method of the to-be-processed mail is supervision, the mail processing device further includes: A second generating module is used to generate a second semantic feature vector of the to-be-processed email based on a third keyword belonging to an adjective and an interjection; and The second output module inputs the second semantic feature vector into a second semantic analysis model, and outputs the priority of the pending email to determine the email reminder frequency of the pending email in the supervision list.

11. An electronic device, comprising: one or more processors; A memory for storing one or more instructions, Wherein, when the one or more instructions are executed by the one or more processors, the one or more processors are enabled to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having executable instructions stored thereon, wherein when the executable instructions are executed by a processor, the processor is enabled to implement the method according to any one of claims 1 to 9.

13. A computer program product, comprising computer executable instructions, which are used to implement the method of any one of claims 1 to 9 when executed.