Deep learning-based talent recommendation method
By using a deep learning-based talent recommendation method, the problems of incomplete data records and low matching accuracy in existing technologies are solved, enabling accurate matching and personalized recommendations of talent and enterprise information.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-25
- Publication Date
- 2026-04-10
AI Technical Summary
Existing talent recommendation methods are not conducive to recording and learning from large amounts of information about talents or companies, resulting in reduced data completeness, accuracy, and matching degree, and a lack of personalized recommendations.
A deep learning-based talent recommendation method is adopted. Users can log in to personal or enterprise user modules through the login module, query information through the search module, record operation actions through the recording module, filter data through the interception module, extract feature data through the feature extraction module, process data through the data classification module, provide accurate matching information through the recommendation matching module, and display the information through the display module. Finally, the optimization and debugging module optimizes the system.
It improves the completeness, accuracy, and matching degree of data, and achieves personalized recommendation effects.
Smart Images
Figure CN121834036A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of talent recommendation, and particularly relates to a talent recommendation method based on deep learning. BACKGROUND
[0002] The talent recommendation method mainly includes a talent recommendation system in a recruitment network, a talent recommendation system algorithm based on a collaborator network, a talent recommendation model based on a project label, and an automatic talent recommendation system based on text classification. The purpose of talent recommendation is to discover and attract outstanding talents suitable for a post, and improve the talent reserve and competitiveness of an enterprise.
[0003] In the prior art, the talent recommendation method is inconvenient for recording and learning a large amount of information about talents or enterprises, thereby reducing the completeness, accuracy and matching degree of data, and lacking personalized feature recommendation. SUMMARY
[0004] The talent recommendation method based on deep learning is proposed to solve the problem that the talent recommendation method in the prior art is inconvenient for recording and learning a large amount of information about talents or enterprises, thereby reducing the completeness, accuracy and matching degree of data, and lacking personalized feature recommendation.
[0005] In order to achieve the above purpose, the present application adopts the following technical scheme:
[0006] The talent recommendation method based on deep learning comprises the following steps:
[0007] S1: a recommendation system is prepared, the recommendation system comprises a server module, the server module is connected with a login module, the login module is connected with an operation and maintenance module, a personal user module and an enterprise user module, the operation and maintenance module, the personal user module and the enterprise user module are connected with a same search module, the search module is connected with a recording module, the recording module is connected with a setting module, the setting module is connected with an interception filtering module, the interception filtering module is connected with a processing module, the processing module is connected with an algorithm analysis module, the algorithm analysis module is connected with an optimization and debugging module, the interception filtering module is connected with a feature extraction module, the feature extraction module is connected with a data acquisition module, the data acquisition module is connected with a data classification module, the data classification module is connected with a recommendation matching module, the recommendation matching module is connected with a display module, the display module is connected with a confirmation module and a cancellation module, and the cancellation module is connected with the optimization and debugging module.
[0008] S2: Individuals or enterprises can log in to the personal user module and enterprise user module through the login module, use the search module to query the information they need, and the recording module can record the operation actions of individuals or enterprises and transmit the recorded data to the interception and filtering module. The interception and filtering module intercepts and filters the recorded data and transmits the processed data to the feature extraction module. The feature extraction module transmits the extracted data to the data analysis module and data classification module for processing.
[0009] S3: The recommendation matching module receives the processed feature data and matches appropriate content based on the feature data to provide more accurate matching recommendation information for individuals or enterprises. The recommendation information is displayed through the display module, and the recommendation information is selected through the cancellation module or confirmation module. The information of the cancelled selection will be fed back to the optimization and debugging module, which will optimize and debug based on the feedback information.
[0010] S4: Operation and maintenance personnel log in to the operation and maintenance module through the login module. Through the settings module, they can customize or set the interception and filtering data. The interception and filtering module transmits the intercepted data information to the processing module for processing. The processed data is then transmitted to the algorithm analysis module. The algorithm analysis module processes the sequence data in the recommendation system and transmits it to the optimization and debugging module. The optimization and debugging module optimizes and debugs the recommendation system based on the processed sequence data.
[0011] Preferably, the setting module includes a custom unit, a regular setting unit, an add unit, and an operation unit. The custom unit is connected to the regular setting unit, the regular setting unit is connected to the add unit, and the add unit is connected to the operation unit.
[0012] Preferably, the feature extraction module includes a data sorting unit, a classification unit, a comparison unit, and an extraction unit. The data sorting unit is connected to the classification unit, the classification unit is connected to the comparison unit, and the comparison unit is connected to the extraction unit.
[0013] Preferably, the setting module is used to configure the interception and filtering module, selectively pass the data recorded by the recording module, set the selection criteria and filtering rules, and transmit the data that meets the filtering rules to the feature extraction module.
[0014] Preferably, the recommendation matching module is used to automatically match and recommend suitable content based on personal or user data information, providing individuals or enterprises with more accurate matching information.
[0015] Preferably, the display module is used to display recommended content, and the confirmation module and the cancellation module can be used to select and confirm or cancel the recommended content.
[0016] Preferably, the processing module is used to receive data that does not meet the filtering rules of the interception and filtering module, process the intercepted data into sequence data and transmit it to the algorithm analysis module, and the algorithm analysis module processes the sequence data and performs debugging.
[0017] Preferably, the recording module is used to record the search, click, and browsing data of individuals or enterprises, and transmits the recorded data to the interception and filtering module through the recording and transmission unit. The interception and filtering module filters and intercepts the data according to the filtering rules.
[0018] Preferably, the optimization and debugging module includes a data receiving unit, a data layering unit, a recording unit, and a debugging unit. The data receiving unit is connected to the data layering unit, the data layering unit is connected to the recording unit, and the recording unit is connected to the debugging unit.
[0019] Preferably, the recording module includes a search recording unit, a click recording unit, a browsing recording unit, and a recording transmission unit, wherein the search recording unit is connected to the click recording unit, the click recording unit is connected to the browsing recording unit, and the browsing recording unit is connected to the recording transmission unit.
[0020] The beneficial effects of the deep learning-based talent recommendation method described in this invention are as follows:
[0021] 1. This solution uses a login module to log in personal or corporate information to the personal user module and corporate user module. The search module allows users to search for the information they need. The recording module can record the actions of individuals or enterprises and transmit the recorded data to the interception and filtering module, which then performs interception and filtering on the recorded data.
[0022] 2. This solution receives the processed feature data through the recommendation matching module, matches appropriate content based on the feature data, and provides more accurate matching recommendation information for individuals or enterprises. The recommendation information is displayed through the display module, and the recommendation information can be selected through the cancellation or confirmation module for personalized recommendations.
[0023] 3. In this solution, maintenance and management personnel can log in to the maintenance module through the login module. Through the settings module, they can customize or configure the intercepted and filtered data. The interception and filtering module transmits the intercepted data to the processing module for processing. The processed data is then transmitted to the algorithm analysis module. The algorithm analysis module processes the sequential data in the recommendation system and transmits it to the optimization and debugging module. The optimization and debugging module optimizes and debugs the recommendation system based on the processed sequential data to achieve the purpose of deep learning.
[0024] This invention facilitates the recording and learning of large amounts of information about talent or enterprises during use, thereby improving the completeness, accuracy, and matching degree of the data, and providing personalized recommendations. Attached Figure Description
[0025] Figure 1 This is a structural block diagram of a deep learning-based talent recommendation method proposed in this invention.
[0026] Figure 2 This is a structural block diagram of the recording module of a talent recommendation method based on deep learning proposed in this invention;
[0027] Figure 3 This is a structural block diagram of the module for setting up a talent recommendation method based on deep learning proposed in this invention;
[0028] Figure 4 This is a structural block diagram of the optimization and debugging module for a deep learning-based talent recommendation method proposed in this invention.
[0029] Figure 5 This is a structural block diagram of the feature extraction module of a deep learning-based talent recommendation method proposed in this invention. Detailed Implementation
[0030] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.
[0031] Example 1
[0032] Reference Figure 1 A talent recommendation method based on deep learning includes the following steps:
[0033] S1: Prepare the recommendation system. The recommendation system includes a server module, which connects to a login module. The login module connects to an operations and maintenance module, a personal user module, and an enterprise user module. These modules are connected to a common search module. The search module connects to a recording module, which in turn connects to a settings module. The settings module connects to an interception and filtering module, which connects to a processing module. The processing module connects to an algorithm analysis module, which in turn connects to an optimization and debugging module. The interception and filtering module connects to a feature extraction module, which in turn connects to a data acquisition module. The data acquisition module connects to a data classification module, which... The block connection includes a recommendation matching module, which in turn connects to a display module. The display module connects to a confirmation module and a cancellation module. The cancellation module connects to an optimization and debugging module. The processing module receives data from the interception and filtering module that does not meet the filtering rules, processes the intercepted data into sequence data, and then transmits it to the algorithm analysis module. The algorithm analysis module processes the sequence data and performs debugging. The recommendation matching module automatically matches and recommends suitable content based on personal or user data, providing individuals or businesses with more accurate matching information. The display module displays the recommended content, and the confirmation and cancellation modules allow users to select, confirm, or cancel the recommended content.
[0034] S2: Individuals or enterprises can log in to the personal user module and enterprise user module through the login module, use the search module to query the information they need, and the recording module can record the operation actions of individuals or enterprises and transmit the recorded data to the interception and filtering module. The interception and filtering module intercepts and filters the recorded data and transmits the processed data to the feature extraction module. The feature extraction module transmits the extracted data to the data analysis module and data classification module for processing.
[0035] S3: The recommendation matching module receives the processed feature data and matches appropriate content based on the feature data to provide more accurate matching recommendation information for individuals or enterprises. The recommendation information is displayed through the display module, and the recommendation information is selected through the cancellation module or confirmation module. The information of the cancelled selection will be fed back to the optimization and debugging module, which will optimize and debug based on the feedback information.
[0036] S4: Operation and maintenance personnel log in to the operation and maintenance module through the login module. Through the settings module, they can customize or set the interception and filtering data. The interception and filtering module transmits the intercepted data information to the processing module for processing. The processed data is then transmitted to the algorithm analysis module. The algorithm analysis module processes the sequence data in the recommendation system and transmits it to the optimization and debugging module. The optimization and debugging module optimizes and debugs the recommendation system based on the processed sequence data.
[0037] ReferenceFigure 2 The recording module includes a search recording unit, a click recording unit, a browsing recording unit, and a recording transmission unit. The search recording unit is connected to the click recording unit, the click recording unit is connected to the browsing recording unit, and the browsing recording unit is connected to the recording transmission unit. The recording module is used to record the search, click, and browsing data of individuals or enterprises, and transmits the recorded data to the interception and filtering module through the recording transmission unit. The interception and filtering module filters and intercepts the data according to the filtering rules.
[0038] Reference Figure 3 The settings module includes a custom unit, a regular settings unit, an add unit, and an operation unit. The custom unit is connected to the regular settings unit, the regular settings unit is connected to the add unit, and the add unit is connected to the operation unit. The settings module is used to configure the interception and filtering module, selectively pass the data recorded by the recording module, set the selection criteria and filtering rules, and transmit the data that meets the filtering rules to the feature extraction module.
[0039] Reference Figure 4 The optimization and debugging module includes a data receiving unit, a data layering unit, a recording unit, and a debugging unit. The data receiving unit is connected to the data layering unit, the data layering unit is connected to the recording unit, and the recording unit is connected to the debugging unit.
[0040] Reference Figure 5 The feature extraction module includes a data sorting unit, a classification unit, a comparison unit, and an extraction unit. The data sorting unit is connected to the classification unit, the classification unit is connected to the comparison unit, and the comparison unit is connected to the extraction unit.
[0041] In this embodiment, during use, individuals or enterprises log in to the personal user module and enterprise user module through the login module, use the search module to query the required information, and can record their actions through the search record unit, click record unit, and browse record unit. The record transmission unit transmits the recorded data to the interception and filtering module, which processes the recorded data according to filtering rules and transmits the data that meets the filtering rules to the feature extraction module. The feature extraction module transmits the extracted data to the data analysis module and data classification module for processing. The recommendation and matching module receives the processed feature data and matches appropriate content based on the feature data to provide individuals or enterprises with more accurate matching recommendations. Recommended information is displayed through the display module, and users can select recommended information through the cancel or confirm module. Cancelled information is fed back to the optimization and debugging module, which optimizes and debugs based on the feedback. Then, maintenance personnel log in to the maintenance module through the login module. Through the custom unit, general settings unit, and add unit, they can customize or configure the interception and filtering data. The interception and filtering module transmits data that does not meet the filtering rules to the processing module for serialization processing. The processed data is then transmitted to the algorithm analysis module, which processes the sequential data in the recommendation system and transmits it to the optimization and debugging module. The optimization and debugging module optimizes and debugs the recommendation system based on the processed sequential data.
[0042] Example 2
[0043] The difference between this embodiment and Embodiment 1 is that the recommendation matching module is connected to an extension module, which includes an input unit, a setting unit, and an execution unit. The input unit is connected to the setting unit, and the setting unit is connected to the execution unit. The input unit and the setting unit can customize the recommended content to further optimize the matching. The execution unit executes the input setting instructions to further ensure the accuracy of the recommended content.
[0044] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.
Claims
1. A talent recommendation method based on deep learning, characterized in that, Includes the following steps: S1: Prepare the recommendation system. The recommendation system includes a server module, which is connected to a login module. The login module is connected to an operations and maintenance module, a personal user module, and an enterprise user module. The operations and maintenance module, personal user module, and enterprise user module are connected to the same search module. The search module is connected to a record module, which is connected to a settings module. The settings module is connected to an interception and filtering module, which is connected to a processing module. The processing module is connected to an algorithm analysis module, which is connected to an optimization and debugging module. The interception and filtering module is connected to a feature extraction module, which is connected to a data collection module. The data collection module is connected to a data classification module, which is connected to a recommendation matching module. The recommendation matching module is connected to a display module, which is connected to a confirmation module and a cancellation module. The cancellation module is connected to the optimization and debugging module. S2: Individuals or enterprises can log in to the personal user module and enterprise user module through the login module, use the search module to query the information they need, and the recording module can record the operation actions of individuals or enterprises and transmit the recorded data to the interception and filtering module. The interception and filtering module intercepts and filters the recorded data and transmits the processed data to the feature extraction module. The feature extraction module transmits the extracted data to the data analysis module and data classification module for processing. S3: The recommendation matching module receives the processed feature data and matches appropriate content based on the feature data to provide more accurate matching recommendation information for individuals or enterprises. The recommendation information is displayed through the display module, and the recommendation information is selected through the cancellation module or confirmation module. The information of the cancelled selection will be fed back to the optimization and debugging module, which will optimize and debug based on the feedback information. S4: Operation and maintenance personnel log in to the operation and maintenance module through the login module. Through the settings module, they can customize or set the interception and filtering data. The interception and filtering module transmits the intercepted data information to the processing module for processing. The processed data is then transmitted to the algorithm analysis module. The algorithm analysis module processes the sequence data in the recommendation system and transmits it to the optimization and debugging module. The optimization and debugging module optimizes and debugs the recommendation system based on the processed sequence data.
2. The talent recommendation method based on deep learning according to claim 1, characterized in that, The recording module includes a search recording unit, a click recording unit, a browsing recording unit, and a recording transmission unit. The search recording unit is connected to the click recording unit, the click recording unit is connected to the browsing recording unit, and the browsing recording unit is connected to the recording transmission unit.
3. The talent recommendation method based on deep learning according to claim 2, characterized in that, The setting module includes a custom unit, a regular setting unit, an add unit, and an operation unit. The custom unit is connected to the regular setting unit, the regular setting unit is connected to the add unit, and the add unit is connected to the operation unit.
4. The talent recommendation method based on deep learning according to claim 3, characterized in that, The optimization and debugging module includes a data receiving unit, a data layering unit, a recording unit, and a debugging unit. The data receiving unit is connected to the data layering unit, the data layering unit is connected to the recording unit, and the recording unit is connected to the debugging unit.
5. The talent recommendation method based on deep learning according to claim 4, characterized in that, The feature extraction module includes a data sorting unit, a classification unit, a comparison unit, and an extraction unit. The data sorting unit is connected to the classification unit, the classification unit is connected to the comparison unit, and the comparison unit is connected to the extraction unit.
6. The talent recommendation method based on deep learning according to claim 5, characterized in that, The recording module is used to record the search, click, and browsing data of individuals or enterprises, and transmits the recorded data to the interception and filtering module through the recording and transmission unit. The interception and filtering module filters and intercepts the data according to the filtering rules.
7. The talent recommendation method based on deep learning according to claim 6, characterized in that, The setting module is used to configure the interception and filtering module, selectively pass the data recorded by the recording module, set the selection criteria and filtering rules, and transmit the data that meets the filtering rules to the feature extraction module.
8. The talent recommendation method based on deep learning according to claim 7, characterized in that, The processing module is used to receive data that does not meet the filtering rules of the interception and filtering module, process the intercepted data into sequence data and transmit it to the algorithm analysis module, which processes the sequence data and performs debugging.
9. The talent recommendation method based on deep learning according to claim 8, characterized in that, The recommendation matching module is used to automatically match and recommend suitable content based on personal or user data information, providing individuals or enterprises with more accurate matching information.
10. A talent recommendation method based on deep learning according to claim 9, characterized in that, The display module is used to display recommended content, and the confirmation and cancellation modules allow users to select and confirm or cancel the recommended content.