Work content processing method, device, electronic device and storage medium

By segmenting and summarizing employee work content and generating representative statements and their labels, the problem of difficult to quantify and classify work content is solved, the quantification and classification of work content is realized, and the burden on auditors is reduced.

CN118644155BActive Publication Date: 2024-11-29BEIJING TOPFENGLIAN INFORMATION TECH CO LTD +1
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
CN202411045427.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-29
Estimated Expiration
2044-07-31

AI Technical Summary

Technical Problem

In institutions and enterprises and institutions, it is difficult to quantify and gather the work content of employees, which leads to difficulties in reviewing and understanding and increases the burden on auditors.

Method used

By obtaining the work content of employees, segmenting the work content statements to determine the title and work content statements, and summarizing these statements, generating representative statements and their corresponding labels and categories, realizing the quantification and classification of work content.

Benefits of technology

Enable employees to clearly understand their work content and classification, reduce the audit burden of auditors, and quickly understand employees' job responsibilities through representative statements and labels.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118644155B_ABST
    Figure CN118644155B_ABST
Patent Text Reader

Abstract

The present disclosure provides a work content processing method, device, electronic device and storage medium, the method comprising: obtaining the original work content to be summarized, the original work content is the work content written by the employee within a preset time period; segmenting the original work content to obtain a plurality of segmented sentences corresponding to the original work content; determining the title sentence and the work content sentence from the plurality of segmented sentences; for the work content sentence, summarizing each of the work content sentences to obtain a summary result, the summary result includes at least one representative sentence for characterizing the employee's work content, and a label and category corresponding to each representative sentence. The present disclosure embodiment can summarize the work content, which is not only conducive to quantifying the employee's work, but also conducive to the review of the auditor, thereby reducing the audit burden.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of text processing, and in particular to a work content processing method, device, electronic device and storage medium. Background Art

[0002] At present, in some institutions, enterprises and other units, in order to facilitate the management of employees and the assessment of their work, employees are usually required to write and summarize their work content within a preset time period. For example, in some units, each staff member writes the work content of surrounding units, which is also called documentary content.

[0003] However, due to the lack of a fixed template, each work content is written by different employees based on their own habits and writing style, resulting in the work content being unable to be quantified and difficult to be aggregated and organized, which in turn affects others (such as colleagues) in reviewing and understanding different work contents, and increases the review burden on reviewers. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a work content processing method, device, electronic device and storage medium, which can not only quantify the work content of employees, but also facilitate others to check.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for processing work content, the method comprising:

[0006] Acquire original work content to be summarized, where the original work content is work content written by employees within a preset time period;

[0007] Segmenting the original work content to obtain a plurality of segmented sentences corresponding to the original work content;

[0008] Determining a title sentence and a work content sentence from the plurality of segmented sentences;

[0009] For the work content statements, each of the work content statements is summarized to obtain a summary result, wherein the summary result includes at least one representative statement for characterizing the employee's work content, and a label and a category corresponding to each representative statement.

[0010] In a possible implementation manner, the aggregating the work content statements to obtain a summary result includes:

[0011] Segment each work content sentence to obtain the segmentation result;

[0012] Based on the word segmentation results corresponding to each of the work content sentences, the work content sentences are summarized according to similarity to obtain the at least one representative sentence;

[0013] For each representative sentence, the category corresponding to the representative sentence is determined according to the title corresponding to the representative sentence, and the label corresponding to the representative sentence is determined according to the word segmentation result of the representative sentence and the correspondence between the preset category and the label.

[0014] In a possible implementation, based on the word segmentation results corresponding to the respective work content sentences, the respective work content sentences are aggregated according to similarity to obtain the at least one representative sentence, including:

[0015] Determine the similarity between the work content sentences based on the word segmentation results corresponding to the work content sentences;

[0016] Classifying the first work content sentences whose similarity is greater than a preset similarity threshold among the work content sentences as the same representative sentence;

[0017] In the case where the first work content statement includes numbers, the numbers in each of the first work content statements are accumulated to obtain an accumulated result, and the accumulated result is used as the numerical result in the same representative statement.

[0018] In a possible implementation, determining the category corresponding to the representative sentence according to the title corresponding to the representative sentence includes:

[0019] The department to which the employee belongs is determined, and the category corresponding to the representative sentence is determined according to the title corresponding to the representative sentence and the preset correspondence between the department and the category.

[0020] In a possible implementation, the original work content includes a plurality of sub-work contents; each sub-work content is used to represent the work content of the employee in units of weeks; based on the word segmentation results corresponding to each of the work content sentences, each of the work content sentences is summarized according to similarity to obtain the at least one representative sentence, including:

[0021] Taking the work content sentences corresponding to the sub-work content of the first week as a benchmark, the work content sentences corresponding to the sub-work content of other weeks are matched with the work content sentences corresponding to the sub-work content of the first week in turn for similarity to obtain the at least one representative sentence.

[0022] In a possible implementation manner, the segmenting of the original work content includes:

[0023] If there is a line break character, the original work content is segmented using the line break character as the first segmentation character;

[0024] If there is a sequence number, the original work content is segmented using the sequence number as a second separator; wherein the sequence numbers are continuous;

[0025] If there is a date, the original work content is segmented using the date as the third separator;

[0026] The original work content is segmented using punctuation marks as fourth separators; wherein the punctuation marks include periods and semicolons.

[0027] In a possible implementation manner, determining the title sentence and the work content sentence from the plurality of segmented sentences includes:

[0028] Identify each sequence number in the original work content, and determine at least one sequence number group according to the expression form of each sequence number;

[0029] For each sequence number group, when the sequence number group is nested by other sequence number groups, determining the segmented sentence corresponding to the sequence number group as the work content sentence;

[0030] In the case where the sequence number group is nested with other sequence number groups, the segmented sentence corresponding to the sequence number group is determined as the title sentence.

[0031] In a second aspect, the present disclosure also provides a work content processing device, including:

[0032] A work content acquisition module is used to acquire original work content to be summarized, where the original work content is work content written by employees within a preset time period;

[0033] A work content segmentation module, used to segment the original work content to obtain a plurality of segmentation statements corresponding to the original work content;

[0034] A segmentation sentence determination module, used to determine a title sentence and a work content sentence from the plurality of segmentation sentences;

[0035] The work content summary module is used to summarize the work content statements to obtain a summary result, wherein the summary result includes at least one representative statement for characterizing the employee's work content, and a label and a category corresponding to each representative statement.

[0036] In a possible implementation manner, the work content summary module is specifically used to:

[0037] Segment each work content sentence to obtain the segmentation result;

[0038] Based on the word segmentation results corresponding to each of the work content sentences, the work content sentences are summarized according to similarity to obtain the at least one representative sentence;

[0039] For each representative sentence, the category corresponding to the representative sentence is determined according to the title corresponding to the representative sentence, and the label corresponding to the representative sentence is determined according to the word segmentation result of the representative sentence and the correspondence between the preset category and the label.

[0040] In a possible implementation manner, the work content summary module is specifically used to:

[0041] Determine the similarity between the work content sentences based on the word segmentation results corresponding to the work content sentences;

[0042] Classifying the first work content sentences whose similarity is greater than a preset similarity threshold among the work content sentences as the same representative sentence;

[0043] In the case where the first work content statement includes numbers, the numbers in each of the first work content statements are accumulated to obtain an accumulated result, and the accumulated result is used as the numerical result in the same representative statement.

[0044] In a possible implementation manner, the work content summary module is specifically used to:

[0045] The department to which the employee belongs is determined, and the category corresponding to the representative sentence is determined according to the title corresponding to the representative sentence and the preset correspondence between the department and the category.

[0046] In a possible implementation manner, the original work content includes a plurality of sub-work contents; and the work content summary module is specifically used to:

[0047] Taking the work content sentences corresponding to the sub-work content of the first week as a benchmark, the work content sentences corresponding to the sub-work content of other weeks are matched with the work content sentences corresponding to the sub-work content of the first week in turn for similarity to obtain the at least one representative sentence.

[0048] In a possible implementation manner, the work content segmentation module is specifically used to:

[0049] If there is a line break character, the original work content is segmented using the line break character as the first segmentation character;

[0050] If there is a sequence number, the original work content is segmented using the sequence number as a second separator; wherein the sequence numbers are continuous;

[0051] If there is a date, the original work content is segmented using the date as the third separator;

[0052] The original work content is segmented using punctuation marks as fourth separators; wherein the punctuation marks include periods and semicolons.

[0053] In a possible implementation manner, the segmentation sentence determination module is specifically used to:

[0054] Identify each sequence number in the original work content, and determine at least one sequence number group according to the expression form of each sequence number;

[0055] For each sequence number group, when the sequence number group is nested by other sequence number groups, determining the segmented sentence corresponding to the sequence number group as the work content sentence;

[0056] In the case where the sequence number group is nested with other sequence number groups, the segmented sentence corresponding to the sequence number group is determined as the title sentence.

[0057] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the work content processing method described in any possible embodiment of the first aspect above are performed.

[0058] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the work content processing method as described in any possible embodiment of the first aspect above are executed.

[0059] The work content processing method, device, electronic device and storage medium provided by the embodiments of the present disclosure can segment the original work content after acquiring the original work content, obtain multiple segmented sentences corresponding to the original work content, and then determine the title sentence and the work content sentence from the multiple segmented sentences, and summarize each of the work content sentences to obtain a summary result, and the summary result includes at least one representative sentence for characterizing the employee's work content, and a label and category corresponding to each representative sentence. In this way, employees can learn the quantitative results of the work content based on the summary results, which is conducive to employees' clear understanding of their work content and classification. In addition, for auditors, they can understand the main work content of employees through representative sentences, and can quickly understand the job responsibilities of employees based on categories and labels, which is conducive to reducing the audit burden of auditors.

[0060] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0062] Figure 1 A flowchart of a method for processing work content provided by an embodiment of the present disclosure is shown;

[0063] Figure 2 A flow chart of a method for summarizing various work content statements provided by an embodiment of the present disclosure is shown;

[0064] Figure 3 A schematic diagram showing the structure of a work content processing device provided by an embodiment of the present disclosure is shown;

[0065] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0067] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0068] In the embodiments of the present disclosure, the term "plurality" refers to two or more than two, and other quantifiers are similar. In the embodiments of the present disclosure, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previously associated objects are in an "or" relationship. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, and may represent any one or more elements selected from the set consisting of A, B, and C.

[0069] The disclosed embodiment provides a work content processing method, comprising: obtaining original work content to be summarized, wherein the original work content is work content written by an employee within a preset time period; segmenting the original work content to obtain a plurality of segmented sentences corresponding to the original work content; determining a title sentence and a work content sentence from the plurality of segmented sentences; and for the work content sentences, aggregating each of the work content sentences to obtain a summary result, wherein the summary result includes at least one representative sentence for characterizing the employee's work content, and a label and a category corresponding to each representative sentence.

[0070] In the disclosed embodiment, after the original work content is obtained, the original work content can be segmented to obtain a plurality of segmented sentences corresponding to the original work content, and then the title sentence and the work content sentence are determined from the plurality of segmented sentences, and each of the work content sentences is summarized to obtain a summary result, and the summary result includes at least one representative sentence for characterizing the employee's work content, and a label and category corresponding to each representative sentence. In this way, employees can learn the quantitative results of the work content based on the summary results, which is conducive to employees' clear understanding of their work content and classification. In addition, for auditors, they can understand the main work content of employees through representative sentences, and can quickly understand the job responsibilities of employees according to categories and labels, which is conducive to reducing the audit burden of auditors.

[0071] To facilitate understanding of this embodiment, the execution subject of a work content processing method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the work content processing method may also be an electronic device with certain computing capabilities, wherein the electronic device may include, for example: a terminal device or a server or other processing device, and the terminal device may be a user terminal, a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data, and artificial intelligence platforms.

[0072] In addition, the data processing method can also be implemented by a processor calling computer-readable instructions stored in a memory.

[0073] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0074] See also Figure 1 FIG. 1 is a flowchart of a method for processing work content provided by an embodiment of the present disclosure. The method includes:

[0075] S101, obtaining original work content to be summarized, where the original work content is work content written by employees within a preset time period.

[0076] Exemplarily, the employee may be an employee of any institution, enterprise, department, or other unit, without specific limitation. In the disclosed embodiment, the employee is an employee of a government unit. In addition, the work content of the preset time period may be the work content of a week (i.e., weekly summary), the work content of a month (monthly summary), the work content of half a year, or the work content of a year, etc., without specific limitation.

[0077] In some embodiments, the original work content includes multiple sub-work contents; wherein each sub-work content is used to represent the work content of the employee in weeks. For example, the original work content may include two sub-work contents, and the two sub-work contents correspond to the weekly work content of the employee for two consecutive weeks. Of course, the embodiment of the present disclosure does not limit the number of sub-work contents, and it can be determined according to actual needs.

[0078] S102: Segment the original work content to obtain a plurality of segmented sentences corresponding to the original work content.

[0079] It can be understood that, under normal circumstances, employees will record their work content item by item. Therefore, after obtaining the original work content, the original work content can be segmented to obtain multiple segmented statements corresponding to the original work content, which is convenient for subsequent work content summarization.

[0080] Exemplarily, according to different writing habits, some employees will use line breaks to divide different work contents, some employees will use serial numbers as identifiers to sort the work contents, and some employees may record the work contents by date. Therefore, in some embodiments, in order to avoid omission of segmentation, when segmenting the original work content, the following steps may be included:

[0081] If there is a line break, use the line break as the first delimiter to segment the original work content;

[0082] If there are serial numbers, use the serial numbers as the second delimiter to segment the original work content; wherein, the serial numbers are consecutive;

[0083] If there is a date, use the date as the third delimiter to segment the original work content;

[0084] Use punctuation marks as the fourth delimiter to segment the original work content; wherein, the punctuation marks include full stops and semicolons.

[0085] Among them, the representation form of the serial numbers is not limited. For example, it can be represented by capital Chinese characters such as "one", "Chapter One", "Section One", "(one)", etc.; it can also be represented by numbers such as "1,", "1)", etc.; it can also be represented by special numbers such as "1.1", "1.2", etc., and special symbols such as "①", "②", "A", and "B", etc.

[0086] In addition, the representation form of the date can be "XX month XX day, 2024", "2024 / XX / XX", "XX / XX", etc.

[0087] It can be understood that in order to implement the segmentation processing of the original work content into sentences, first, the serial numbers in the original work content need to be recognized to obtain multiple candidate recognized serial numbers; then, the candidate recognized serial numbers are subjected to synonymous replacement; then, serial number groups are selected from the replaced multiple candidate recognized serial numbers, and the serial numbers in each serial number group are subjected to unified format processing.

[0088] For example, the serial number recognition can be performed separately for the different serial number representations mentioned above to obtain multiple candidate identification serial numbers; then synonym symbol replacement can be performed, specifically, the serial number in English format can be replaced with the serial number in Chinese format, or the decimal points in different formats can be uniformly replaced, such as half-width and full-width conversion; then the serial number group is selected from the replaced multiple candidate identification serial numbers according to the preset rules. Among them, the preset rules may include the continuity of the numbers, whether the forward identifiers are the same, and whether the backward identifiers are the same. For example, the candidate identification serial numbers "1.1 content, 1.2 output, 15.5 jin, 1.3 content" are identified, where for the numbers [1 2 5 3], the numbers [1 2 3] have a common forward identifier "1.", so 15.5 can be excluded by the continuity of the numbers and the difference in the forward identifiers. For another example, for the candidate identification numbers [(one), (two), four, (three)], convert them into numbers: 1 24 3 to calculate the continuity, and the common backward identifier is "Chinese character number sum)", and a set of numbers [(one), (two), (three)] is obtained, excluding four.

[0089] In this way, when the second segmentation process is performed based on the signal group after screening and unified format processing, the segmentation accuracy of the original work content can be improved.

[0090] S103, determining a title sentence and a work content sentence from the plurality of segmented sentences.

[0091] During the writing process, a title and sentences representing the actual work content are usually included, but in the actual processing process, only the work content needs to be summarized. Therefore, after the original work content is segmented and multiple segmented sentences corresponding to the original work content are obtained, in order to improve the accuracy of the summary, it is necessary to determine the sentence representing the work content from the multiple segmented sentences.

[0092] Therefore, in some implementations, when determining the title sentence and the work content sentence from the plurality of segmented sentences, the following (a) to (c) may be included:

[0093] (a) identifying each serial number in the original work content, and determining at least one serial number group according to the expression form of each serial number;

[0094] (b) for each sequence number group, when the sequence number group is nested by other sequence number groups, determining the segmented sentence corresponding to the sequence number group as the work content sentence;

[0095] (c) When the sequence number group is nested within another sequence number group, the segmented sentence corresponding to the sequence number group is determined as the headline sentence.

[0096] For example, for the original work content of [I. Title 1. Content 2. Content II. Title (1) Content (2) Content (3) Content], the results after segmentation are as follows:

[0097] 1. Title

[0098] 1. Content

[0099] 2. Content

[0100] 2. Title

[0101] (1) Content

[0102] (2) Content

[0103] (3) Content

[0104] According to the nested relationship of the sequence number groups, it can be determined that the work content statements include the following:

[0105] 1. Content

[0106] 2. Content

[0107] (1) Content

[0108] (2) Content

[0109] (3) Content

[0110] That is, here it can be determined whether the current statement is a work content statement according to whether the sequence number contains the parent sequence number.

[0111] S104, for the work content statements, summarizing the work content statements to obtain a summary result, wherein the summary result includes at least one representative statement for characterizing the employee's work content, and a label and a category corresponding to each representative statement.

[0112] Following the above embodiment, it is only necessary to summarize the various work content statements to obtain the summary result. Among them, the representative statement is used to represent the result after summarizing multiple similar statements. The category corresponding to the representative statement is used to represent the major category to which the work content corresponding to the representative statement belongs, and the tag is used to represent the keywords associated with the category for representing the specific work content.

[0113] Specifically, with respect to step S104, when the summary result is obtained by summarizing the various work content statements, the following steps S1041 to S1043 may be included:

[0114] S1041, segment each work content sentence to obtain a segmentation result.

[0115] Specifically, the work content statement can be processed as follows:

[0116] The abnormal symbols in the current segmented sentence are removed, the letters are converted into lowercase / uppercase letters, the quotation marks and the contents in brackets are removed, the paired punctuation marks are removed, and the current segmented sentence is segmented.

[0117] Here, the work content sentence may include abnormal symbols, inconsistent capitalization of letters, and may also contain book title marks, brackets, quotation marks (paired punctuation marks), etc. These contents are removed, and then the segmented sentence is segmented for subsequent processing.

[0118] For example, if the segmented sentence is "complete work within the scope of responsibilities", the results after word segmentation are "complete", "responsibilities", "scope", "within", and "work".

[0119] S1042: Based on the word segmentation results corresponding to the respective work content sentences, the respective work content sentences are aggregated according to similarities to obtain the at least one representative sentence.

[0120] Exemplarily, after each work content sentence is segmented, the similarity between any two work content sentences can be determined based on the segmentation results, and then summarized according to the similarity. Specifically, based on the segmentation results corresponding to each of the work content sentences, the work content sentences are summarized according to the similarity to obtain the at least one representative sentence, which may include the following (I) to (III):

[0121] (I) determining the similarity between the work content sentences based on the word segmentation results corresponding to the work content sentences;

[0122] (II) classifying the first work content sentences whose similarity is greater than a preset similarity threshold among the work content sentences as the same representative sentence;

[0123] (III) When the first work content statement includes numbers, the numbers in each of the first work content statements are accumulated to obtain an accumulated result, and the accumulated result is used as the numerical result in the same representative statement.

[0124] The similarity calculation method may be based on an existing calculation method, such as determining whether the same words exist in the word segmentation results and the position of the word sequence, which will not be described in detail here.

[0125] For example, if the work content statement corresponding to the original work content includes the following:

[0126]

[0127] After merging, we get two representative sentences, namely "helped answer 50 issues related to enterprise registration in districts and counties" and "coordinated districts and counties to carry out enterprise archive migration work."

[0128] Among them, for the work content statements of "helping to answer 20 related tasks of enterprise registration" and "helping to answer 30 related tasks of districts and counties regarding enterprise registration", since the similarity between the two is greater than the similarity threshold, the two work content statements can be used as the first work content statement and summarized. In addition, since the first work content statement includes numbers, the numbers need to be accumulated, and the accumulated result is used as the numerical result in the representative statement. Therefore, the representative statement is "helping to answer 50 related tasks of districts and counties regarding enterprise registration".

[0129] In some embodiments, the original work content includes a plurality of sub-work contents, each of which is used to represent the work content of the employee in units of weeks; the word segmentation results corresponding to each of the work content sentences are respectively based on the word segmentation results corresponding to each of the work content sentences, and the at least one representative sentence is obtained by aggregating the work content sentences according to the similarity, which may include the following:

[0130] Taking the work content sentences corresponding to the sub-work content of the first week as a benchmark, the work content sentences corresponding to the sub-work content of other weeks are respectively matched with the work content sentences corresponding to the sub-work content of the first week for similarity to obtain the at least one representative sentence.

[0131] For example, when summarizing the monthly work content, since a month includes four weeks, the first week's content can be used as a benchmark for matching, and the work content statements corresponding to the second, third, and fourth weeks are matched with the work content statements of the first week in turn. If there is a work content statement in the second week that has not been successfully matched with the first week, the work content statement is determined to be new work content. In addition to matching the work content statements of the first week, the work content statements corresponding to the third and fourth weeks also need to be matched with the new work content statements of the second week, and so on, until the match is completed. This can improve the efficiency of similarity matching.

[0132] S1043, for each representative sentence, determine the category corresponding to the representative sentence according to the title corresponding to the representative sentence, and determine the label corresponding to the representative sentence according to the word segmentation result of the representative sentence and the correspondence between the preset category and the label.

[0133] Among them, the correspondence between categories and tags can be established in advance. For example, a large number of employees' work contents can be obtained in advance, and the categories can be extracted from the titles of the work contents, and the tag keywords can be extracted from the contents, and then the correspondence between the categories and the tag keywords corresponding to them can be established. In this way, in the application, the category can be determined first, and then the tag keywords that match the segmentation results can be filtered out from the tag keywords corresponding to the category according to the segmentation results as the tags of the representative sentences.

[0134] Exemplarily, the extracted categories may be as follows:

[0135] "Meeting", "Activity", "Study", "Reception", "Job Work", etc.

[0136] As another example, after at least one representative sentence is obtained through aggregation, the corresponding category and label need to be determined for each representative sentence. For example, for the representative sentence of "helping to answer 50 questions related to enterprise registration in districts and counties", the corresponding category is "job work" and the corresponding label is "enterprise registration"; and for the representative sentence of "coordinating districts and counties to carry out enterprise archive migration work", the corresponding category is "job work" and the corresponding label is "enterprise archive migration".

[0137] It can be understood that since the category is used to characterize the major category of the work content corresponding to the representative sentence, and employees in different departments have different work responsibilities, the category corresponding to the representative sentence can be determined based on the department to which the employee belongs. This not only improves the efficiency of category determination, but also improves the accuracy of category determination.

[0138] Therefore, in some implementations, when determining the category corresponding to the representative statement based on the title corresponding to the representative statement, it can include: determining the department to which the employee belongs, and determining the category corresponding to the representative statement based on the title corresponding to the representative statement and the preset correspondence between the department and the category.

[0139] Specifically, the correspondence between departments and categories can be established in advance. For example, for Department A, it can be divided into two major categories according to job responsibilities, namely Category H and Category G. Similarly, for Department B, at least one category can be divided according to job responsibilities. In this way, after determining the department to which the employee belongs, at least one category corresponding to the department can be determined according to the correspondence between the department and the category, and then the target category can be determined from the at least one category according to the title corresponding to the representative sentence. For example, if it is determined that the employee belongs to Department A, the target category that matches the title corresponding to the representative sentence can be screened from Category H and Category G. For example, after matching, it can be determined that Category H is the category corresponding to the representative sentence.

[0140] The work content processing method provided by the embodiment of the present disclosure can segment the original work content after obtaining the original work content, obtain multiple segmented sentences corresponding to the original work content, and then determine the title sentence and the work content sentence from the multiple segmented sentences, and summarize each of the work content sentences to obtain a summary result, and the summary result includes at least one representative sentence for characterizing the employee's work content, and a label and category corresponding to each representative sentence. In this way, employees can learn the quantitative results of the work content based on the summary results, which is conducive to employees' clear understanding of their work content and classification. In addition, for auditors, they can understand the main work content of employees through representative sentences, and can quickly understand the job responsibilities of employees based on categories and labels, which is conducive to reducing the audit burden of auditors.

[0141] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0142] See also Figure 3 FIG. 3 is a functional module diagram of a work content processing device provided by an embodiment of the present disclosure. The work content processing device 300 includes:

[0143] The work content acquisition module 301 is used to acquire the original work content to be summarized, where the original work content is the work content written by the employee within a preset time period;

[0144] A work content segmentation module 302 is used to segment the original work content to obtain a plurality of segmentation statements corresponding to the original work content;

[0145] A segmentation sentence determination module 303, used to determine a title sentence and a work content sentence from the plurality of segmentation sentences;

[0146] The work content summary module 304 is used to summarize the work content statements to obtain a summary result, wherein the summary result includes at least one representative statement for characterizing the employee's work content, and a label and a category corresponding to each representative statement.

[0147] In a possible implementation, the work content summary module 304 is specifically used to:

[0148] Segment each work content sentence to obtain the segmentation result;

[0149] Based on the word segmentation results corresponding to each of the work content sentences, the work content sentences are summarized according to similarity to obtain the at least one representative sentence;

[0150] For each representative sentence, the category corresponding to the representative sentence is determined according to the title corresponding to the representative sentence, and the label corresponding to the representative sentence is determined according to the word segmentation result of the representative sentence and the correspondence between the preset category and the label.

[0151] In a possible implementation, the work content summary module 304 is specifically used to:

[0152] Determine the similarity between the work content sentences based on the word segmentation results corresponding to the work content sentences;

[0153] Classifying the first work content sentences whose similarity is greater than a preset similarity threshold among the work content sentences as the same representative sentence;

[0154] In the case where the first work content statement includes numbers, the numbers in each of the first work content statements are accumulated to obtain an accumulated result, and the accumulated result is used as the numerical result in the same representative statement.

[0155] In a possible implementation, the work content summary module 304 is specifically used to:

[0156] The department to which the employee belongs is determined, and the category corresponding to the representative sentence is determined according to the title corresponding to the representative sentence and the preset correspondence between the department and the category.

[0157] In a possible implementation, the original work content includes a plurality of sub-work contents; the work content summary module 304 is specifically used to:

[0158] Taking the work content sentences corresponding to the sub-work content of the first week as a benchmark, the work content sentences corresponding to the sub-work content of other weeks are matched with the work content sentences corresponding to the sub-work content of the first week in turn for similarity to obtain the at least one representative sentence.

[0159] In a possible implementation, the work content segmentation module 302 is specifically used to:

[0160] If there is a line break character, the original work content is segmented using the line break character as the first segmentation character;

[0161] If there is a sequence number, the original work content is segmented using the sequence number as a second separator; wherein the sequence numbers are continuous;

[0162] If there is a date, the original work content is segmented using the date as the third separator;

[0163] The original work content is segmented using punctuation marks as fourth separators; wherein the punctuation marks include periods and semicolons.

[0164] In a possible implementation manner, the segmentation sentence determination module 303 is specifically configured to:

[0165] Identify each sequence number in the original work content, and determine at least one sequence number group according to the expression form of each sequence number;

[0166] For each sequence number group, when the sequence number group is nested by other sequence number groups, determining the segmented sentence corresponding to the sequence number group as the work content sentence;

[0167] In the case where the sequence number group is nested with other sequence number groups, the segmented sentence corresponding to the sequence number group is determined as the title sentence.

[0168] Based on the same technical concept, the embodiment of the present disclosure also provides an electronic device. Figure 4 , which is a schematic diagram of the structure of an electronic device 400 provided in an embodiment of the present disclosure, includes a processor 401, a memory 402, and a bus 403. The memory 402 is used to store execution instructions.

[0169] In the disclosed embodiment, the memory 402 is specifically used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 401. That is, when the electronic device 400 is running, the processor 401 communicates with the memory 402 through the bus 403, so that the processor 401 executes the application code stored in the memory 402, and then executes the method described in any of the above embodiments.

[0170] Among them, the memory 402 can be, but is not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.

[0171] Processor 401 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0172] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 400. In other embodiments of the present application, the electronic device 400 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0173] The embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the work content processing method in the above method embodiment are executed.

[0174] The embodiments of the present disclosure also provide a computer program product, including a computer program / instruction. When the computer program / instruction processor is executed, the work content processing method provided in the embodiments of the present disclosure is implemented. For details, please refer to the above method embodiments, which will not be repeated here.

[0175] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0176] The method in the embodiments of the present disclosure may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is downloaded and executed on a computer, the process or function described in the present application is executed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM or other programmable device.

[0177] The computer program or instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it may also be an optical medium, such as a digital video disk; it may also be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0178] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0179] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0181] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0182] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for processing work content, characterized in that: The method comprises: Acquire original work content to be summarized, where the original work content is work content written by employees within a preset time period; Segmenting the original work content to obtain a plurality of segmented sentences corresponding to the original work content; Determining a title sentence and a work content sentence from the plurality of segmented sentences; For the work content statements, aggregating the work content statements to obtain a summary result, wherein the summary result includes at least one representative statement for representing the original work content, and a label and a category corresponding to each representative statement; The segmenting process of the original work content includes: If there is a line break character, the original work content is segmented using the line break character as the first segmentation character; If there is a sequence number, the original work content is segmented using the sequence number as a second separator; wherein the sequence numbers are continuous; If there is a date, the original work content is segmented using the date as the third separator; The original work content is segmented using punctuation marks as the fourth segmentation mark; wherein the punctuation marks include a period and a semicolon; The step of determining a title sentence and a work content sentence from the plurality of segmented sentences includes: Identify each sequence number in the original work content, and determine at least one sequence number group according to the expression form of each sequence number; For each sequence number group, when the sequence number group is nested by other sequence number groups, determining the segmented sentence corresponding to the sequence number group as the work content sentence; In the case where the sequence number group is nested in another sequence number group, determining the segmented sentence corresponding to the sequence number group as the title sentence; The summarizing of the work content statements to obtain a summary result includes: Segment each work content sentence to obtain the segmentation result; Based on the word segmentation results corresponding to each of the work content sentences, the work content sentences are summarized according to similarity to obtain the at least one representative sentence; For each representative sentence, determine the category corresponding to the representative sentence according to the title corresponding to the representative sentence, and determine the label corresponding to the representative sentence according to the word segmentation result of the representative sentence and the correspondence between the preset category and the label; The step of aggregating the work content sentences according to their similarities based on the word segmentation results corresponding to the work content sentences to obtain the at least one representative sentence includes: Determine the similarity between the work content sentences based on the word segmentation results corresponding to the work content sentences; Classifying the first work content sentences whose similarity is greater than a preset similarity threshold among the work content sentences as the same representative sentence; In the case where the first work content statement includes numbers, the numbers in each of the first work content statements are accumulated to obtain an accumulated result, and the accumulated result is used as the numerical result in the same representative statement; The step of determining the category corresponding to the representative sentence according to the title corresponding to the representative sentence includes: The department to which the employee belongs is determined, and the category corresponding to the representative sentence is determined according to the title corresponding to the representative sentence and the preset correspondence between the department and the category.

2. The method according to claim 1, characterized in that The original work content includes a plurality of sub-work contents; each sub-work content is used to represent the work content of the employee in weeks; based on the word segmentation results corresponding to each of the work content sentences, each of the work content sentences is summarized according to similarity to obtain the at least one representative sentence, including: Taking the work content sentences corresponding to the sub-work content of the first week as a benchmark, the work content sentences corresponding to the sub-work content of other weeks are matched with the work content sentences corresponding to the sub-work content of the first week in turn for similarity to obtain the at least one representative sentence.

3. A work content processing device, characterized in that: include: A work content acquisition module is used to acquire original work content to be summarized, where the original work content is work content written by employees within a preset time period; A work content segmentation module, used to segment the original work content to obtain a plurality of segmentation statements corresponding to the original work content; A segmentation sentence determination module, used to determine a title sentence and a work content sentence from the plurality of segmentation sentences; A work content summary module, for summarizing the work content statements to obtain a summary result, wherein the summary result includes at least one representative statement for representing the original work content, and a label and a category corresponding to each representative statement; The work content segmentation module is specifically used for: If there is a line break character, the original work content is segmented using the line break character as the first segmentation character; If there is a sequence number, the original work content is segmented using the sequence number as a second separator; wherein the sequence numbers are continuous; If there is a date, the original work content is segmented using the date as the third separator; The original work content is segmented using punctuation marks as the fourth segmentation mark; wherein the punctuation marks include a period and a semicolon; The segmentation sentence determination module is specifically used for: Identify each sequence number in the original work content, and determine at least one sequence number group according to the expression form of each sequence number; For each sequence number group, when the sequence number group is nested by other sequence number groups, determining the segmented sentence corresponding to the sequence number group as the work content sentence; In the case where the sequence number group is nested in another sequence number group, determining the segmented sentence corresponding to the sequence number group as the title sentence; The work content summary module is specifically used for: Segment each work content sentence to obtain the segmentation result; Based on the word segmentation results corresponding to each of the work content sentences, the work content sentences are summarized according to similarity to obtain the at least one representative sentence; For each representative sentence, determine the category corresponding to the representative sentence according to the title corresponding to the representative sentence, and determine the label corresponding to the representative sentence according to the word segmentation result of the representative sentence and the correspondence between the preset category and the label; The work content summary module is also specifically used for: Determine the similarity between the work content sentences based on the word segmentation results corresponding to the work content sentences; Classifying the first work content sentences whose similarity is greater than a preset similarity threshold among the work content sentences as the same representative sentence; In the case where the first work content statement includes numbers, the numbers in each of the first work content statements are accumulated to obtain an accumulated result, and the accumulated result is used as the numerical result in the same representative statement; The work content summary module is also specifically used for: The department to which the employee belongs is determined, and the category corresponding to the representative sentence is determined according to the title corresponding to the representative sentence and the preset correspondence between the department and the category.

4. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the work content processing method as described in claim 1 or 2 is performed.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the work content processing method as claimed in claim 1 or 2 is executed.

Citation Information

Patent Citations

  • Work log processing method and device

    CN110084536A

  • Text classification method, apparatus and device and storage medium

    CN110597988A

  • Material corpus generation method and device, computer equipment and storage medium

    CN110866107A

  • Work summary generation method and system, electronic equipment and medium

    CN113449105A

  • Method for automatically writing document report

    CN113688606A