Intelligent letter dispatching method, device, medium, equipment and product

Abstract

This invention relates to a method, apparatus, medium, device, and product for intelligent mail delivery. The method includes: acquiring electronic mail from citizens to be delivered; extracting features from the electronic mail to obtain mail feature data; extracting keywords from the electronic mail; determining candidate delivery departments based on the mail feature data and the keywords; selecting a target delivery department from the candidate departments; and delivering the electronic mail to the target delivery department. This application can improve the accuracy and efficiency of mail delivery.

Description

Technical Field

[0001] This invention relates to the field of mail delivery technology, and in particular to a method, apparatus, medium, device and product for intelligent mail delivery. Background Technology

[0002] With the accelerating pace of urbanization, citizens are facing increasing problems and demands regarding their lives, work, environment, and transportation. How to respond to citizen feedback promptly and accurately has become a pressing issue for governments at all levels. Traditional citizen mailbox management relies heavily on manual dispatching by clerks. This method suffers from limitations such as limited individual information processing capabilities, low decision-making efficiency, and unstable subjective judgment, resulting in low dispatch accuracy. Therefore, an intelligent mail delivery solution is urgently needed to improve the efficiency and accuracy of citizen mail delivery. Summary of the Invention

[0003] To address at least one of the above-mentioned technical problems, embodiments of the present invention provide a method, apparatus, medium, device, and product for intelligent letter delivery, so as to improve the efficiency and accuracy of letter delivery.

[0004] According to a first aspect, embodiments of the present invention provide a method for intelligent letter delivery, comprising: Obtain citizens' electronic mail that is to be delivered; Feature extraction is performed on the citizen's electronic letters to obtain letter feature data; and Extract keywords from the citizens' electronic emails; Based on the letter feature data and the letter keywords, candidate distribution departments are determined, and a target distribution department is selected from the candidate distribution departments; The citizen's electronic mail is dispatched to the target distribution department.

[0005] In one embodiment, the step of extracting features from the citizen's electronic letters to obtain letter feature data includes: preprocessing the citizen's electronic letters; and extracting features from the preprocessed citizen's electronic letters based on natural language processing technology.

[0006] In one embodiment, extracting email keywords from the citizen's emails includes: rewriting the citizen's emails based on a preset large model to obtain rewritten text, and extracting keywords from the rewritten text to obtain the email keywords.

[0007] In one embodiment, determining candidate delivery departments based on the letter feature data and the letter keywords includes: querying a database constructed based on historical citizen emails for delivery departments corresponding to each historical feature data whose similarity to the letter feature data is greater than a preset threshold, to obtain a first delivery department; searching the database for delivery departments corresponding to each historical keyword that matches the letter keywords, to obtain a second delivery department; and selecting a preset number of candidate delivery departments from the first and second delivery departments; wherein the database includes multiple historical citizen emails and corresponding historical feature data, historical keywords, and delivery departments.

[0008] In one embodiment, selecting a target distribution department from the candidate distribution departments includes: for each candidate distribution department, determining evaluation data of the candidate distribution department based on the frequency of its occurrence; and determining the target candidate department based on the evaluation data of each candidate distribution department.

[0009] In one embodiment, the method further includes: acquiring distribution result feedback data; correcting the target distribution department based on the distribution result feedback data; and storing the letter characteristic data, letter keywords, and corrected target distribution department of the citizen's electronic letter as a historical data entry in the database.

[0010] This application provides a smart mail delivery device, comprising: The first acquisition module is used to acquire electronic letters from citizens to be delivered; The feature extraction module is used to extract features from the citizen's electronic letters to obtain letter feature data; The keyword extraction module is used to extract keywords from the citizens' electronic letters; The target determination module is used to determine candidate distribution departments based on the letter feature data and the letter keywords, and select the target distribution department from the candidate distribution departments; The mail delivery module is used to deliver the citizen's electronic mail to the target delivery department.

[0011] According to a third aspect, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method provided in the first aspect.

[0012] According to a fourth aspect, the computing device provided in the embodiments of the present invention includes a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the method provided in the first aspect.

[0013] According to a fifth aspect, the computer program product provided in the embodiments of the present invention includes a computer program that, when executed by a processor, implements the method provided in the first aspect.

[0014] The intelligent mail delivery method, apparatus, medium, device, and product provided in this invention extract features from citizens' electronic mail to obtain mail feature data; and extract mail keywords from citizens' electronic mail, and determine candidate delivery departments based on the mail feature data and the mail keywords. It is evident that considering the mail feature data and the mail keywords can improve the accuracy of candidate delivery departments, thereby helping to improve the accuracy of the target delivery department selected based on the candidate departments. Furthermore, it does not rely on dispatchers for dispatching, thus avoiding the problem of low accuracy caused by unstable subjective judgment compared to the traditional dispatcher method. Moreover, it can improve dispatching efficiency compared to the traditional dispatcher method. Therefore, this application can improve the efficiency and accuracy of citizen mail delivery. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating an intelligent letter delivery method according to an embodiment of the present invention. Figure 2 This is a structural block diagram of a smart letter delivery device according to an embodiment of the present invention; Figure 3 This is an internal structural diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0016] In a first aspect, embodiments of the present invention provide a method for intelligent letter delivery, see [link to previous document]. Figure 1 The method includes: S110, retrieve citizens' electronic mail awaiting delivery.

[0017] Among them, citizen e-mail is the electronic version of citizen letters submitted by citizens through the citizen mailbox.

[0018] S120, extract features from the citizen's electronic letters to obtain letter feature data.

[0019] The method for extracting features from citizens' electronic letters can be selected as needed and is not limited here.

[0020] In one optional implementation, the feature extraction step in S120 may specifically include: S210, Preprocess the citizen's electronic mail.

[0021] S220, based on natural language processing technology, extracts features from preprocessed citizen electronic letters.

[0022] Preprocessing methods may include text cleaning, format unification, and standardization of citizens' electronic emails.

[0023] In S220, a large language model can be used to perform natural language processing on the preprocessed citizen electronic letters, thereby achieving text feature extraction.

[0024] The above implementation method first preprocesses the citizens' electronic letters, which can improve the quality of the citizens' electronic letters; based on natural language processing technology, feature extraction is performed on the preprocessed citizens' electronic letters to extract the letter feature data of the text information in the citizens' electronic letters, which is convenient for the subsequent selection of target delivery departments.

[0025] S130, Extract email keywords from the citizen's emails.

[0026] The method for extracting keywords from citizens' electronic letters can be selected as needed and is not limited here.

[0027] In one optional implementation, the keyword extraction step in S130 includes: S310, based on a preset large model, the citizen's electronic letter is rewritten to obtain the rewritten text, and keywords are extracted from the rewritten text to obtain the letter keywords.

[0028] Rewriting can be understood as automatically correcting typos, sentence errors, removing noise information and text expressions, and of course it can also include other methods, which are not limited here.

[0029] The preset large model can be a preset large oracle model, or other models can be used, which are not limited here.

[0030] In real-world scenarios, in addition to extracting keywords from letters, semantic embedding and phrase vectors can be used to perform hierarchical analysis of the overall semantics of the text, thereby improving the ability to capture the true intentions of citizens.

[0031] S140, Based on the letter feature data and the letter keywords, determine the candidate distribution departments, and select the target distribution department from the candidate distribution departments.

[0032] In an alternative implementation, the candidate dispatch department determination step in S140 may include: S410, in the database constructed based on historical citizens' electronic letters, query the distribution department corresponding to each historical feature data whose similarity to the letter feature data is greater than a preset threshold, and obtain the first distribution department.

[0033] The database includes multiple historical citizen emails, along with corresponding historical feature data, historical keywords, and dispatching departments.

[0034] As can be seen, the database includes multiple historical data entries, each of which includes historical citizen emails, historical feature data, historical keywords, and the issuing department.

[0035] The method for determining historical feature data in historical data can refer to the feature extraction method in S120, and the method for determining historical keywords can refer to the letter keyword extraction method in S130.

[0036] In S410, the similarity between the letter feature data and each historical feature data in the database is calculated, and the distribution department in the historical data to which the historical feature data with a similarity greater than a preset threshold belongs is selected as the first distribution department.

[0037] S420, search the database for the distribution department corresponding to each historical keyword that matches the keyword of the letter, and obtain the second distribution department.

[0038] That is, in S420, the semantic matching degree between the letter keywords and each historical keyword in the database is calculated, and the dispatching department in the historical data to which the historical keywords with a matching degree greater than the preset matching degree threshold belong is selected as the second dispatching department.

[0039] S430, select a preset number of candidate distribution departments from the first distribution department and the second distribution department.

[0040] For example, the same distribution department in the first distribution department and the second distribution department is selected as a candidate distribution department.

[0041] For example, the N distribution departments with the highest similarity in the first distribution department and the N distribution departments with the highest matching degree in the second distribution department are selected as candidate distribution departments. N is a positive integer.

[0042] Of course, other methods can be used to determine the candidate distribution departments, which are not limited here.

[0043] In the above implementation method, selecting multiple distribution departments with high probability as candidate distribution departments based on feature similarity and keyword matching can improve the accuracy of subsequent determination of target distribution departments.

[0044] In one optional implementation, the target dispatch department selection step in S140 includes: S510, for each candidate distribution department, determine the evaluation data of the candidate distribution department based on the frequency of its occurrence.

[0045] The frequency of occurrence of candidate distribution departments can be understood as the frequency of occurrence in the first distribution department and the second distribution department, or as the frequency of occurrence in the database. The higher the frequency of occurrence, the greater the possibility of being selected.

[0046] Among them, there is a positive correlation between the frequency of occurrence and the evaluation data, that is, the higher the frequency of occurrence, the higher the evaluation data.

[0047] S520, Based on the evaluation data of each candidate distribution department, determine the target candidate department.

[0048] Among these, the candidate distribution department corresponding to the highest evaluation data can be selected as the target candidate department from each evaluation data.

[0049] In the above implementation method, the candidate distribution departments are evaluated based on their frequency of occurrence, and the candidate distribution department with the highest evaluation is selected as the target distribution department, which can improve the accuracy of the target distribution department.

[0050] S150, the citizen's electronic mail is dispatched to the target distribution department.

[0051] For example, citizens' electronic mail is sent to the electronic mail receiving portal of the target distribution department so that the target distribution department can receive the citizens' electronic mail.

[0052] In a real-world scenario, if the target delivery department is the department actually responsible for the citizen's electronic mail, then the correct delivery information is returned; otherwise, the correct delivery department is returned. Therefore, in one embodiment, the method provided in this embodiment may further include: S610, obtain distribution result feedback data.

[0053] S620, Based on the distribution result feedback data, the target distribution department is corrected.

[0054] Specifically, upon receiving feedback, if an error is found in the distribution, the target distribution department will be corrected, and the citizen's electronic mail will be distributed to the corrected target distribution department.

[0055] S630, the letter characteristic data, letter keywords, and the corrected target dispatch department of the citizen's electronic letter are stored as a historical data entry in the database.

[0056] In the above implementation method, in order to avoid the next distribution error, the citizen's electronic letter, letter feature data, letter keywords and the corrected target distribution department are formed into a historical data and stored in the database, so as to provide a basis for the correct selection of the target distribution department in the future.

[0057] In summary, this application extracts features from the citizen's electronic mail to obtain mail feature data; and extracts mail keywords from the citizen's electronic mail. Based on the mail feature data and the mail keywords, candidate delivery departments are determined. It is evident that considering the mail feature data and the mail keywords can improve the accuracy of candidate delivery departments, thereby helping to improve the accuracy of the target delivery department selected based on the candidate departments. Furthermore, it does not rely on dispatchers for dispatching, thus avoiding the problem of low accuracy caused by unstable subjective judgment compared to the traditional dispatcher method. Moreover, compared to the traditional dispatcher method, it can improve dispatching efficiency. Therefore, this application can improve the efficiency and accuracy of citizen mail delivery.

[0058] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0059] Based on the same inventive concept, this application also provides a smart letter delivery device for implementing the smart letter delivery method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more smart letter delivery device embodiments provided below can be found in the limitations of the smart letter delivery method described above, and will not be repeated here.

[0060] In one exemplary embodiment, such as Figure 2 As shown, a smart mail delivery device is provided, comprising: The first acquisition module is used to acquire electronic letters from citizens to be delivered; The feature extraction module is used to extract features from the citizen's electronic letters to obtain letter feature data; The keyword extraction module is used to extract keywords from the citizens' electronic letters; The target determination module is used to determine candidate distribution departments based on the letter feature data and the letter keywords, and select the target distribution department from the candidate distribution departments; The mail delivery module is used to deliver the citizen's electronic mail to the target delivery department.

[0061] In one embodiment, the feature extraction module is specifically used to: preprocess the citizen's electronic letters; and extract features from the preprocessed citizen's electronic letters based on natural language processing technology.

[0062] In one embodiment, the keyword extraction module is specifically used to: rewrite the citizen's electronic letter based on a preset large model to obtain the rewritten text, and extract keywords from the rewritten text to obtain the letter's keywords.

[0063] In one embodiment, the target determination module is specifically used to: query, in a database constructed based on historical citizen emails, the dispatching departments corresponding to each historical feature data whose similarity to the email feature data is greater than a preset threshold, to obtain a first dispatching department; search in the database for dispatching departments corresponding to each historical keyword that matches the email keyword, to obtain a second dispatching department; and select a preset number of candidate dispatching departments from the first dispatching department and the second dispatching department; wherein, the database includes multiple historical citizen emails and corresponding historical feature data, historical keywords, and dispatching departments.

[0064] In one embodiment, the target determination module is specifically used to: for each candidate distribution department, determine the evaluation data of the candidate distribution department based on the frequency of occurrence of the candidate distribution department; and determine the target candidate department based on the evaluation data of each candidate distribution department.

[0065] In one embodiment, the method further includes: acquiring distribution result feedback data; correcting the target distribution department based on the distribution result feedback data; and storing the letter characteristic data, letter keywords, and corrected target distribution department of the citizen's electronic letter as a historical data entry in the database.

[0066] Each module in the aforementioned intelligent letter delivery device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0067] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for intelligent mail delivery.

[0068] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0069] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps: Obtain citizens' electronic mail that is to be delivered; Feature extraction is performed on the citizen's electronic letters to obtain letter feature data; and Extract keywords from the citizens' electronic emails; Based on the letter feature data and the letter keywords, candidate distribution departments are determined, and a target distribution department is selected from the candidate distribution departments; The citizen's electronic mail is dispatched to the target distribution department.

[0070] In one embodiment, the step of "extracting features from the citizen's electronic letters to obtain letter feature data" implemented by the processor when executing the computer program includes: preprocessing the citizen's electronic letters; and extracting features from the preprocessed citizen's electronic letters based on natural language processing technology.

[0071] In one embodiment, the step of "extracting email keywords from the citizen's email" implemented by the processor when executing the computer program includes: rewriting the citizen's email based on a preset large model to obtain rewritten text, and extracting keywords from the rewritten text to obtain the email keywords.

[0072] In one embodiment, the step of "determining candidate delivery departments based on the letter feature data and the letter keywords" implemented by the processor when executing the computer program includes: querying the database constructed based on historical citizen electronic letters to obtain the delivery departments corresponding to each historical feature data whose similarity to the letter feature data is greater than a preset threshold, thereby obtaining a first delivery department; searching the database to obtain the delivery departments corresponding to each historical keyword that matches the letter keywords, thereby obtaining a second delivery department; and selecting a preset number of candidate delivery departments from the first delivery department and the second delivery department; wherein, the database includes multiple historical citizen electronic letters and corresponding historical feature data, historical keywords, and delivery departments.

[0073] In one embodiment, the step of "selecting a target distribution department from the candidate distribution departments" implemented by the processor when executing a computer program includes: for each candidate distribution department, determining the evaluation data of the candidate distribution department based on the frequency of occurrence of the candidate distribution department; and determining the target candidate department based on the evaluation data of each candidate distribution department.

[0074] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining distribution result feedback data; correcting the target distribution department based on the distribution result feedback data; and storing the letter feature data, letter keywords, and the corrected target distribution department of the citizen's electronic letter as a historical data entry in the database.

[0075] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Obtain citizens' electronic mail that is to be delivered; Feature extraction is performed on the citizen's electronic letters to obtain letter feature data; and Extract keywords from the citizens' electronic emails; Based on the letter feature data and the letter keywords, candidate distribution departments are determined, and a target distribution department is selected from the candidate distribution departments; The citizen's electronic mail is dispatched to the target distribution department.

[0076] In one embodiment, the step of "extracting features from the citizen's electronic letters to obtain letter feature data" implemented when the computer program is executed by the processor includes: preprocessing the citizen's electronic letters; and extracting features from the preprocessed citizen's electronic letters based on natural language processing technology.

[0077] In one embodiment, the step of "extracting email keywords from the citizen's email" implemented when the computer program is executed by the processor includes: rewriting the citizen's email based on a preset large model to obtain rewritten text, and extracting keywords from the rewritten text to obtain the email keywords.

[0078] In one embodiment, the step of "determining candidate delivery departments based on the letter feature data and the letter keywords" implemented by the computer program when executed by the processor includes: querying the database constructed based on historical citizen electronic letters to obtain the delivery departments corresponding to each historical feature data whose similarity to the letter feature data is greater than a preset threshold, thereby obtaining a first delivery department; searching the database to obtain the delivery departments corresponding to each historical keyword that matches the letter keywords, thereby obtaining a second delivery department; and selecting a preset number of candidate delivery departments from the first delivery department and the second delivery department; wherein, the database includes multiple historical citizen electronic letters and corresponding historical feature data, historical keywords, and delivery departments.

[0079] In one embodiment, the step of "selecting a target distribution department from the candidate distribution departments" implemented when the computer program is executed by a processor includes: for each candidate distribution department, determining evaluation data of the candidate distribution department based on the frequency of occurrence of the candidate distribution department; and determining the target candidate department based on the evaluation data of each candidate distribution department.

[0080] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining distribution result feedback data; correcting the target distribution department based on the distribution result feedback data; and storing the letter feature data, letter keywords, and the corrected target distribution department of the citizen's electronic letter as a historical data entry in the database.

[0081] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: Obtain citizens' electronic mail that is to be delivered; Feature extraction is performed on the citizen's electronic letters to obtain letter feature data; and Extract keywords from the citizens' electronic emails; Based on the letter feature data and the letter keywords, candidate distribution departments are determined, and a target distribution department is selected from the candidate distribution departments; The citizen's electronic mail is dispatched to the target distribution department.

[0082] In one embodiment, the step of "extracting features from the citizen's electronic letters to obtain letter feature data" implemented when the computer program is executed by the processor includes: preprocessing the citizen's electronic letters; and extracting features from the preprocessed citizen's electronic letters based on natural language processing technology.

[0083] In one embodiment, the step of "extracting email keywords from the citizen's email" implemented when the computer program is executed by the processor includes: rewriting the citizen's email based on a preset large model to obtain rewritten text, and extracting keywords from the rewritten text to obtain the email keywords.

[0084] In one embodiment, the step of "determining candidate delivery departments based on the letter feature data and the letter keywords" implemented by the computer program when executed by the processor includes: querying the database constructed based on historical citizen electronic letters to obtain the delivery departments corresponding to each historical feature data whose similarity to the letter feature data is greater than a preset threshold, thereby obtaining a first delivery department; searching the database to obtain the delivery departments corresponding to each historical keyword that matches the letter keywords, thereby obtaining a second delivery department; and selecting a preset number of candidate delivery departments from the first delivery department and the second delivery department; wherein, the database includes multiple historical citizen electronic letters and corresponding historical feature data, historical keywords, and delivery departments.

[0085] In one embodiment, the step of "selecting a target distribution department from the candidate distribution departments" implemented when the computer program is executed by a processor includes: for each candidate distribution department, determining evaluation data of the candidate distribution department based on the frequency of occurrence of the candidate distribution department; and determining the target candidate department based on the evaluation data of each candidate distribution department.

[0086] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining distribution result feedback data; correcting the target distribution department based on the distribution result feedback data; and storing the letter feature data, letter keywords, and the corrected target distribution department of the citizen's electronic letter as a historical data entry in the database.

[0087] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0088] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0089] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0090] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for intelligent letter delivery, characterized in that, include: Obtain citizens' electronic mail that is to be delivered; Feature extraction is performed on the citizen's electronic letters to obtain letter feature data; as well as Extract keywords from the citizens' electronic emails; Based on the letter feature data and the letter keywords, candidate distribution departments are determined, and a target distribution department is selected from the candidate distribution departments; The citizen's electronic mail is dispatched to the target distribution department.

2. The method according to claim 1, characterized in that, The step of extracting features from the citizen's electronic letters to obtain letter feature data includes: The citizen's electronic mail is preprocessed; Based on natural language processing technology, feature extraction is performed on preprocessed electronic letters from citizens.

3. The method according to claim 1, characterized in that, The extraction of email keywords from the citizens' emails includes: Based on a pre-defined large model, the citizen's electronic letter is rewritten to obtain the rewritten text, and keywords are extracted from the rewritten text to obtain the letter's keywords.

4. The method according to claim 1, characterized in that, The step of determining candidate distribution departments based on the letter feature data and the letter keywords includes: In a database constructed based on historical citizens' electronic letters, the dispatching department corresponding to each historical feature data whose similarity to the letter feature data is greater than a preset threshold is queried to obtain the first dispatching department. The second distribution department is obtained by searching the database for each historical keyword that matches the keyword in the letter. Select a predetermined number of candidate distribution departments from the first distribution department and the second distribution department; The database includes multiple historical citizen emails, along with corresponding historical feature data, historical keywords, and dispatching departments.

5. The method according to claim 1, characterized in that, The step of selecting a target distribution department from the candidate distribution departments includes: For each candidate distribution department, the evaluation data of the candidate distribution department is determined based on the frequency of its occurrence. The target candidate departments are determined based on the evaluation data of each candidate distribution department.

6. The method according to any one of claims 1 to 5, characterized in that, Also includes: Obtain feedback data on distribution results; Based on the feedback data of the distribution results, the target distribution department is adjusted; The letter characteristic data, letter keywords, and corrected target delivery department of the citizen's electronic letter are stored as a historical data entry in the database.

7. A smart letter delivery device, characterized in that, include: The first acquisition module is used to acquire electronic letters from citizens to be delivered; The feature extraction module is used to extract features from the citizen's electronic letters to obtain letter feature data; The keyword extraction module is used to extract keywords from the citizens' electronic letters; The target determination module is used to determine candidate distribution departments based on the letter feature data and the letter keywords, and select the target distribution department from the candidate distribution departments; The mail delivery module is used to deliver the citizen's electronic mail to the target delivery department.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images