Office Course Recommendation Method, Device, Electronic Device and Medium

Abstract

The present application provides an office course recommendation method, apparatus, electronic device, and computer-readable storage medium. The method includes: obtaining multi-dimensional office data of employees; clustering the multi-dimensional office data by using a preset clustering algorithm, extracting common labels according to the clustering results, and generating an office label set of employees; performing association rule mining on the office label set of employees based on the Apriori algorithm to obtain specific strong association rules; and recommending relevant office courses to employees according to the strong association rules. Compared with the prior art, accurate correlations between various office behavior data of employees themselves can be obtained through the present solution, and on this basis, precise recommendations of office courses are made for employees, helping employees gradually improve office efficiency and creating a closed-loop for improving employee efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a method and device for recommending office courses, an electronic device, and a computer-readable storage medium. Background Art

[0002] Corporate governance generally boils down to the management of its affiliated people, things, and matters. Currently, most of them are based on business data to build visual dashboards, and conduct intelligent analysis on a large amount of business data, and then provide relevant predictions or decision-making suggestions for office courses. Then, employees learn the recommended office courses to improve office efficiency, forming an efficiency improvement closed loop.

[0003] However, there is a lack of relevant analysis of employees' personal office behaviors, and employees have no grasp of their own office behavior preferences in their work. The differences in employees' educational backgrounds, personalities, and various behaviors make diversification prominent. The traditional technology of extracting common factors based on huge business data is no longer applicable to individuals. Intelligent analysis pays more attention to the diversification of behaviors and the personalization of recommendations. However, currently, more is to extract common features based on a large amount of personal data, and judge the quality of individual behaviors based on common features, lacking innovation and theoretical basis, and it is difficult to provide practical suggestions for employees' office courses, thus making it difficult to form an efficiency improvement closed loop. Summary of the Invention

[0004] The purpose of the present application is to provide a method and device for recommending office courses, an electronic device, and a computer-readable storage medium.

[0005] The first aspect of the present application provides a method for recommending office courses, including:

[0006] Obtaining multi-dimensional office data of employees;

[0007] Using a preset clustering algorithm to cluster the multi-dimensional office data, and extracting common labels according to the clustering results to generate an office label set of employees;

[0008] Performing association rule mining on the office label set of employees based on the Apriori algorithm to obtain specific strong association rules;

[0009] Recommending relevant office courses for the employees according to the strong association rules.

[0010] The second aspect of the present application provides an office course recommendation device, including:

[0011] An obtaining module, configured to obtain multi-dimensional office data of employees;

[0012] A label generation module, configured to use a preset clustering algorithm to cluster the multi-dimensional office data, and extract common labels according to the clustering results to generate an office label set of employees;

[0013] A mining module, configured to perform association rule mining on the office label set of the employee based on the Apriori algorithm to obtain specific strong association rules;

[0014] A recommendation module, configured to recommend relevant office courses for the employee according to the strong association rules.

[0015] A third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor runs the computer program, it is configured to implement the method described in the first aspect of the present application.

[0016] A fourth aspect of the present application provides a computer-readable medium, on which computer-readable instructions are stored, and the computer-readable instructions can be executed by a processor to implement the method described in the first aspect of the present application.

[0017] Compared with the prior art, the office course recommendation method, device, electronic device, and medium provided by the present application obtain multi-dimensional office data of employees; use a preset clustering algorithm to cluster the multi-dimensional office data, extract common labels according to the clustering results, and generate an office label set for employees; perform association rule mining on the office label set of employees based on the Apriori algorithm to obtain specific strong association rules; recommend relevant office courses for employees according to the strong association rules. Compared with the prior art, through this solution, the accurate correlation between the various office behavior data of employees themselves can be obtained, and on this basis, accurate recommendations of office courses can be made for employees, helping employees gradually improve office efficiency and creating a closed loop for employee efficiency improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0019] Figure 1 Shows a flowchart of an office course recommendation method provided by some embodiments of the present application;

[0020] Figure 2 Shows a schematic diagram of an office course recommendation device provided by some embodiments of the present application;

[0021] Figure 3 Shows a schematic diagram of an electronic device provided by some embodiments of the present application;

[0022] Figure 4Schematic diagram of a computer-readable storage medium provided by some embodiments of the present application is shown. Detailed implementation manners

[0023] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0024] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the ordinary meanings understood by those skilled in the art to which this application belongs.

[0025] In addition, terms such as "first" and "second" are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0026] An office course recommendation method and device, an electronic device, and a computer-readable medium are provided in an embodiment of the present application, and will be described below with reference to the accompanying drawings.

[0027] Please refer to Figure 1 , which shows a flowchart of an office course recommendation method provided by some embodiments of the present application. As shown in the figure, the office course recommendation method may include the following steps:

[0028] Step S101: Obtain multi-dimensional office data of employees.

[0029] Among them, the multi-dimensional office data may include basic information of employees, office behavior data, and office psychological data; among them, the basic information of employees may include: name, gender, age, occupation, contact information, education background, and native place, etc.; office behavior data (i.e., behavior characteristics) may include: meeting behavior data, email behavior data, audio-visual behavior data, various office software usage data, and desktop office behavior data; office psychological data (i.e., psychological characteristics) includes: whether each office behavior process is fixed, whether the usage time follows a certain rule, and whether more attention is paid to efficiency. According to the above multi-dimensional office data, data such as employees' own office behavior data, the company's overall office behavior data, and employees' comprehensive preference for each office course can be sorted out.

[0030] In this step, office data from different sources of employees is collected in various ways to complete the aggregation and collection of basic office data, that is, to complete the construction of the office data warehouse.

[0031] In some embodiments of the present application, before step S102, the above method further includes: preprocessing the collected multi-dimensional office data of employees, specifically implemented as: cleaning the multi-dimensional office data; classifying non-numerical data to obtain the corresponding grade values of the non-numerical data; using the mean fluctuation substitution method to insert corresponding values for the missing values in the data set.

[0032] Specifically, for the massive office data of employees, first perform data cleaning, and then for non-numerical data, divide it into different grades and assign corresponding data based on different grades, so as to complete the assignment of relevant non-numerical indicators. For the large number of missing values that may appear in all data sets, use the mean fluctuation substitution method to add a number within the range of -N to +N to the mean, avoiding the huge impact on the generation of the decision tree caused by inserting a large number of identical values.

[0033] Step S102: Use a preset clustering algorithm to cluster the multi-dimensional office data, and extract common labels according to the clustering results to generate an office label set for employees.

[0034] In some embodiments of the present application, the above preset clustering algorithm includes the K-means clustering algorithm. Specifically, step S102 can be implemented as: using the K-means clustering algorithm to specify the K value to cluster the multi-dimensional office data to obtain multiple classes.

[0035] The specific implementation solution is as follows:

[0036] For the massive office data, when determining different categories such as meeting behavior data, email behavior data, audio and video behavior data, various office software usage data, and desktop office behavior data, the K-Means algorithm can first select a suitable k value according to the prior experience of the data. If there is no prior knowledge, a suitable k value can be selected through cross-validation.

[0037] After determining the number of k, we need to select k initial centroids. Since a heuristic method is used, the selection of the positions of the k initial centroids has a great impact on the final clustering result and the running time of the algorithm. Therefore, it is necessary to select appropriate k centroids, preferably these centroids should not be too close.

[0038] The input is a sample set D = {x1, x2,... xm}, the number of clusters k for clustering, and the maximum number of iterations N. The output is a cluster partition C = {C1, C2,... Ck}. Randomly select k samples from the data set D as the initial k centroids {μ1, μ2,..., μk}. For n = 1, 2,..., N, calculate the distances between the samples and each centroid vector, classify according to the distances, and then recalculate the new centroids for all the sample points in each classification cluster. If none of the k centroid vectors change, then output the cluster partition C = {C1, C2,... Ck}. Among them, Ck represents a classification in the office data.

[0039] For example, for a large amount of employee office data, based on the distance magnitude between the office data, the sample set is divided into K clusters. In the initial data set, the points within the cluster are made to be as closely connected as possible, while the distances between the clusters are made as large as possible. Assume k = 3. First, randomly select 3 class centroids corresponding to the k classes, and then calculate the distances from all points in all office sample data to these 3 centroids respectively, and label the class of each sample as the class of the centroid with the smallest distance to this sample. After calculating the distances between the sample data and the 3 centroids, the classes of all sample points after the first round of iteration are obtained. Then, for the office data points labeled with different classes, calculate their new centroids respectively, that is, label the class of all points as the class of the centroid with the closest distance and calculate the new centroids. Finally, we get 3 classes of the office data after continuous iteration.

[0040] In practical applications, after using the K - means algorithm to cluster the data, it is usually necessary to verify and evaluate the clustering effect. In this embodiment, an entropy - based class evaluation algorithm is used to evaluate the quality of each class, and the classes with good clustering effects are put into the clustering result; according to the clustering centers of each class in the clustering result, the common labels of this class are extracted as the office labels of the employees, and an office label set of the employees is generated.

[0041] Specifically, the generation of the office label set of employees includes: after the office data warehouse is built, it is necessary to build a data analysis model based on the massive office data. First, use an unsupervised learning algorithm (K - means clustering algorithm) to learn features from the unlabeled data, and divide the massive office data into multiple categories (such as meetings, audio - videos, signed reports, seals, emails, customer service, desktop office software, etc.). In the unsupervised mode, find the point where most of the data aggregates among the data in the same class, and establish a data model that minimizes the distribution of data points and the distance to the neighboring central points. For example, for a certain category, such as emails, the aggregation point where most of the data is distributed, and then obtain the common features of the employees' emails, extract the common label system, form a label set, that is, a label warehouse, and generate a data label system that is more in line with the business.

[0042] Step S103: Perform association rule mining on the office label set of the employee based on the Apriori algorithm to obtain specific strong association rules.

[0043] Specifically, step S103 can be implemented as follows: Divide the office label items in the office label set into different item sets, use the Apriori algorithm to determine the frequent item sets in the item sets. Each frequent item set k can generate 2*(2^k - 1) association rules, and filter out the association rules with a confidence greater than or equal to the minimum confidence as strong association rules.

[0044] Specifically, by integrating data such as the employee's own office behavior data, the company's overall office behavior data, and the employee's comprehensive preference for each office course, data association analysis is carried out to mine the mutual relationships hidden in the data. Relying on a large amount of label data in the ADS layer of the data platform (the label data has been calculated in modules in the ADS layer), for office label items such as meetings, audio and video, signed reports, seals, emails, customer service, and desktop office software usage, use the Apriori algorithm to determine the frequent item sets among them;

[0045] Specifically, the process of using the Apriori algorithm to determine the frequent item sets is as follows:

[0046] Suppose I = {I1, I2, … Im} is a set of m different items, such as the set of office label items like the above-mentioned meetings, audio and video, signed reports, seals, emails, customer service, and desktop office software usage. The elements in the set are called items. The set I of items is called an item set, and an item set with a length of k is called a k-item set. Let the data D related to the task be a set of database transactions, where each transaction T is a set of items, such that Each transaction has an identifier T ID ; Let A be an item set. Transaction T contains A if and only if Then the association rule form is A => B (where And ). There are two important metric values in the association rule metric: support and confidence. For the association rule R: A => B, then:

[0047] 1. Support: It is the ratio of the number of transactions that contain both A and B in the transaction set to the total number of all transactions. Support(A => B) = P(A ∪ B) = count(A ∪ B) / |D|.

[0048] 2. Confidence: It is the ratio of the number of transactions that contain both A and B to the number of transactions that contain A. Confidence(A => B) = P(B|A) = support(A ∪ B) / support(A).

[0049] Continuously iterate to generate new candidate sets, find candidate sets with support greater than or equal to the threshold minsup (minimum support), and thus generate frequent item sets. Each frequent k-item set can generate 2*(2^k - 1) association rules, and filter out association rules with confidence greater than or equal to minconf (minimum confidence) as strong association rules.

[0050] Among them, the minimum support represents the lowest importance of the item set in a statistical sense. The minimum confidence represents the lowest reliability of the association rule. If the support and confidence both reach the minimum support and minimum confidence, then this association rule is a strong association rule. A strong association rule means that if the rule R: X => Y satisfies support(X => Y) >= supmin (minimum support, which is used to measure the lowest importance that the rule needs to meet) and confidence(X => Y) >= confmin (minimum confidence, which represents the lowest reliability that the association rule needs to meet), the association rule X => Y is called a strong association rule; otherwise, the association rule X => Y is called a weak association rule.

[0051] Step S104: Recommend relevant office courses to the employee according to the strong association rules.

[0052] Specifically, step S104 can be implemented as: sort all the obtained strong association rules according to the size of their confidence; recommend relevant office courses to the employee according to the sorting result.

[0053] For the office behaviors with strong associations discovered by the above algorithm, such as the associations found among several office behaviors, and such employees with such association behaviors all have certain characteristics, then extract the office behaviors preferred by the employees for relevant practical course recommendations, effectively improve the playback rate of the recommended courses as much as possible while ensuring that the employees like them, and truly achieve that the employees like them and they are effective, creating a closed loop for improving employee efficiency.

[0054] For example, assume there are the following several strong association rules and their confidence has been given: confidence = 50%; confidence = 80%; confidence = 60%.

[0055] After sorting according to the size of the confidence, recommend the relevant office courses of the strong association rule with confidence = 80% to the employee.

[0056] According to some embodiments of the present application, the above method may further include the following steps:

[0057] Present the above-mentioned strong association rules and the office courses recommended according to the above-mentioned strong association rules to employees in a visual interface form. For example, present them to employees in the form of a Web page, so that employees can obtain more intuitive recommended results.

[0058] Based on this application, employees can intuitively see the change trends of their personal core office data and the time allocation of various office behaviors, which helps employees better allocate their time; employees can view the correlations between their own office behavior data, and in this process, discover the gaps with similar employees and timely identify existing problems.

[0059] The office course recommendation method provided by the embodiments of this application obtains multi-dimensional office data of employees; uses a preset clustering algorithm to cluster the multi-dimensional office data, and extracts common labels according to the clustering results to generate an office label set for employees; performs association rule mining on the office label set of employees based on the Apriori algorithm to obtain specific strong association rules; recommends relevant office courses to employees according to the strong association rules. Compared with the prior art, through this solution, the accurate correlations between the office behavior data of employees themselves can be obtained, and based on this, precise recommendations of office courses can be made for employees, helping employees gradually improve their office efficiency and creating a closed-loop for employees to improve efficiency.

[0060] In the above embodiments, an office course recommendation method is provided. Correspondingly, this application also provides an office course recommendation device. The office course recommendation device provided by the embodiments of this application can implement the above office course recommendation method, and the office course recommendation device can be implemented in a software, hardware, or a combination of software and hardware manner. For example, the office course recommendation device can include integrated or separate functional modules or units to execute the corresponding steps in the above methods. Please refer to Figure 2 which shows a schematic diagram of an office course recommendation device provided by some embodiments of this application. Since the device embodiments are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, refer to the partial description of the method embodiments. The device embodiments described below are only illustrative.

[0061] As Figure 2 shown, the office course recommendation device 10 may include:

[0062] An acquisition module 101, configured to acquire multi-dimensional office data of employees;

[0063] A label generation module 102, configured to use a preset clustering algorithm to cluster the multi-dimensional office data, and extract common labels according to the clustering results to generate an office label set for employees;

[0064] The mining module 103 is used to perform association rule mining on the office label set of the employee based on the Apriori algorithm to obtain specific strong association rules;

[0065] The recommendation module 104 is used to recommend relevant office courses to the employee according to the strong association rules.

[0066] In some embodiments of the embodiments of the present application, the above device 10 further includes:

[0067] The preprocessing module is used to preprocess the multi-dimensional office data of the employee before the label generation module clusters the multi-dimensional office data using a preset clustering algorithm.

[0068] In some embodiments of the embodiments of the present application, the preprocessing module is specifically used for:

[0069] Perform data cleaning on the multi-dimensional office data;

[0070] Perform level division on non-numerical data to obtain the level values corresponding to the non-numerical data;

[0071] Use the mean fluctuation replacement method to insert corresponding numerical values for the missing values in the dataset.

[0072] In some embodiments of the embodiments of the present application, the preset clustering algorithm includes the K-means clustering algorithm.

[0073] Correspondingly, the label generation module 102 is specifically used for:

[0074] Use the K-means clustering algorithm to specify the K value to cluster the multi-dimensional office data to obtain multiple classes;

[0075] Use the class evaluation algorithm based on entropy to evaluate the quality of each class, and put the classes with good clustering effects into the clustering results;

[0076] Extract the common labels of each class in the clustering results as the office labels of the employee, and generate the office label set of the employee.

[0077] In some embodiments of the embodiments of the present application, the mining module 103 is specifically used for:

[0078] For the office label items in the office label set, use the Apriori algorithm to determine the frequent item sets therein. Each frequent item set k can generate 2(2k - 1) association rules, and filter out the association rules with a confidence greater than or equal to the minimum confidence as strong association rules.

[0079] In some embodiments of the embodiments of the present application, the recommendation module 104 is specifically used for:

[0080] Sort all the obtained strong association rules according to the magnitude of their confidence levels;

[0081] Recommend relevant office courses to the employee according to the sorting result.

[0082] In some embodiments of the present application, the multi-dimensional office data includes basic information, office behavior data, and office psychological data; among them,

[0083] The basic information includes: name, gender, age, occupation, contact information, education level, and native place;

[0084] The office behavior data includes: meeting behavior data, email behavior data, audio-video behavior data, various office software usage data, and desktop office behavior data;

[0085] The office psychological data includes: whether each office behavior process is fixed, whether the usage time follows a certain pattern, and whether more attention is paid to efficiency.

[0086] In some embodiments of the present application, the above-mentioned device 10 further includes:

[0087] A display module, configured to present the strong association rules and the office courses recommended according to the strong association rules to the employee in a visual interface form.

[0088] The office course recommendation device 10 provided by the embodiments of the present application has the same inventive concept as the office course recommendation method provided by the foregoing embodiments of the present application and has the same beneficial effects.

[0089] The present application embodiment also provides an electronic device corresponding to the office course recommendation method provided by the foregoing embodiment. The electronic device may be a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the above-mentioned office course recommendation method.

[0090] Please refer to Figure 3 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. As Figure 3 shown, the electronic device 20 includes: a processor 200, a memory 201, a bus 202, and a communication interface 203. The processor 200, the communication interface 203, and the memory 201 are connected through the bus 202; a computer program that can run on the processor 200 is stored in the memory 201, and when the processor 200 runs the computer program, it executes the office course recommendation method provided by any one of the foregoing embodiments of the present application.

[0091] Among them, the memory 201 may include high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is implemented through at least one communication interface 203 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0092] The bus 202 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 201 is used to store programs. After receiving an execution instruction, the processor 200 executes the program. Any implementation manner of the office course recommendation method disclosed in any implementation manner of the foregoing embodiments of the present application can be applied to the processor 200 or implemented by the processor 200.

[0093] The processor 200 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 200 or the instructions in the form of software. The above-mentioned processor 200 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), 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 gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by the hardware decoding processor, or executed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, etc. This storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and combines its hardware to complete the steps of the above method.

[0094] The electronic device provided in the embodiments of the present application and the office course recommendation method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by it.

[0095] The embodiments of the present application also provide a computer-readable storage medium corresponding to the office course recommendation method provided in the foregoing embodiments. Please refer toFigure 4 , which shows that the computer-readable storage medium is an optical disc 30, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the office course recommendation method provided by any of the foregoing embodiments.

[0096] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other optical and magnetic storage media, which will not be elaborated here one by one.

[0097] The computer-readable storage medium provided by the above embodiments of the present application and the office course recommendation method provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0098] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the part of the module, program segment, or code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be covered by the scope of the claims and the specification of the present application.

Claims

1. An office course recommendation method, characterized in that, including: Obtaining multi-dimensional office data of employees; The multi-dimensional office data includes basic information, office behavior data, and office psychological data; The basic information includes: name, gender, age, occupation, contact information, education level, and native place; the office behavior data includes: meeting behavior data, email behavior data, audio-video behavior data, various office software usage data, and desktop office behavior data; the office psychological data includes: whether each office behavior process is fixed, whether the usage time follows a certain pattern, and whether more attention is paid to efficiency; Using a preset clustering algorithm to cluster the multi-dimensional office data, and extracting common labels according to the clustering results to generate an office label set of employees; For the office label items in the office label set, using the Apriori algorithm to determine the frequent item sets therein. Each frequent item set k generates 2*(2k−1) association rules, and screening out the association rules with a confidence level greater than or equal to the minimum confidence level as strong association rules; the office label items refer to the common labels of each category; Recommending relevant office courses to the employees according to the strong association rules; The step of using a preset clustering algorithm to cluster the multi-dimensional office data, and extracting common labels according to the clustering results to generate an office label set of employees includes: Using a preset clustering algorithm to learn features from the multi-dimensional office data, and dividing the multi-dimensional office data into multiple categories; the categories include emails. In an unsupervised mode, finding the aggregation points where most of the email data is distributed, and then obtaining the common features of the employees' emails, so as to extract the common labels of the employees' emails. The common labels of all extracted categories constitute the office label set of employees.

2. The method according to claim 1, characterized in that, Before using the preset clustering algorithm to cluster the multi-dimensional office data, it further includes: Preprocessing the multi-dimensional office data of the employees; The preprocessing includes: Performing data cleaning on the multi-dimensional office data; Performing grade division on non-numerical data to obtain the grade values corresponding to the non-numerical data; Using the mean fluctuation replacement method to insert corresponding numerical values for the missing values in the dataset.

3. The method according to claim 1, characterized in that, The preset clustering algorithm includes the K-means clustering algorithm; The step of using a preset clustering algorithm to cluster the multi-dimensional office data, and extracting common labels according to the clustering results to generate an office label set of employees includes: Using a class evaluation algorithm based on entropy to evaluate the quality of each class, and putting the classes with good clustering effects into the clustering results; Extracting the common labels of each class as the office labels of employees according to the clustering centers of each class in the clustering results to generate an office label set of employees.

4. The method according to claim 1, characterized in that, The step of recommending relevant office courses to the employees according to the strong association rules includes: Sorting all the obtained strong association rules according to the size of their confidence levels; Recommending relevant office courses to the employees according to the sorting results.

5. The method according to claim 1, characterized in that, The method further includes: Presenting the strong association rules and the office courses recommended according to the strong association rules to the employees in a visual interface form.

6. An office course recommendation device, characterized in that, including: An acquisition module for acquiring multi-dimensional office data of employees; The multi-dimensional office data includes basic information, office behavior data, and office psychological data; The basic information includes: name, gender, age, occupation, contact information, education level, and native place; the office behavior data includes: meeting behavior data, email behavior data, audio-video behavior data, various office software usage data, and desktop office behavior data; the office psychological data includes: whether each office behavior process is fixed, whether the usage time follows a certain pattern, and whether more attention is paid to efficiency; A label generation module, configured to cluster the multi-dimensional office data by using a preset clustering algorithm, and extract common labels according to the clustering result to generate an office label set of the employee; A mining module, configured to determine frequent item sets among the office label items in the office label set by using the Apriori algorithm. Each frequent item set k generates 2*(2k−1) association rules, and filters out the association rules with a confidence level greater than or equal to the minimum confidence level as strong association rules; the office label item refers to the common label of each category; A recommendation module, configured to recommend relevant office courses to the employee according to the strong association rules; The label generation module is specifically configured to learn features from the multi-dimensional office data by using a preset clustering algorithm, and divide the multi-dimensional office data into multiple categories; the categories include emails. In an unsupervised mode, find the aggregation point where most of the email data is distributed, and then obtain the common features of the employee's emails, so as to extract the common labels of the employee's emails. The common labels extracted from all categories constitute the office label set of the employee.

7. An electronic device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 5.

8. A computer-readable medium, characterized in that, Computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by the processor to implement the method according to any one of claims 1 to 5.

Images