Method, apparatus, electronic device, and medium for generating resume browsing information

Abstract

Embodiments of the present disclosure disclose a method, apparatus, electronic device, and medium for generating resume browsing information. A specific implementation of the method includes: in response to receiving a resume viewing request sent by a user terminal, sending a user identification request to the user terminal; receiving the user identification information sent by the user terminal and storing the user identification information in a user browsing database; sending a resume picture corresponding to the resume viewing request to the user terminal and determining the current time as the first browsing time; in response to receiving a close request sent by the user terminal, determining a resume browsing occupancy ratio and determining the current time as the second browsing time; determining the difference between the second browsing time and the first browsing time as the resume browsing duration; determining the user identification information, the resume browsing occupancy ratio, and the resume browsing duration as resume browsing information and sending the resume browsing information to a management terminal. This implementation can generate resume browsing information.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technologies, and particularly to a method, an apparatus, an electronic device, and a medium for generating resume browsing information. Background Art

[0002] Sending a resume to a user terminal can facilitate the user terminal to view and select a suitable resume. Currently, the common way to send a resume to a user terminal is to print the resume into a paper version or send it to the user terminal in the form of a file, and then send each resume picture that is relatively similar to the current resume picture to the user terminal for the user terminal to view.

[0003] However, the above method usually has the following technical problems:

[0004] First, when sending the resume to the user terminal in the form of a paper version or a file, it is difficult to know the viewing situation of the resume by the user terminal, resulting in difficulty in generating resume browsing information;

[0005] In the process of adopting technical solutions to solve the above technical problem 1, the following problems often occur: when the resume browsing ratio of the current resume picture by the user terminal is relatively low or the resume browsing duration is relatively short, the resume pictures that are relatively similar to the current resume picture do not meet the needs of the user terminal. For these problems, the conventional solution is generally: when the resume browsing ratio included in the resume browsing information is relatively high, use a text similarity matching algorithm to match the resume pictures with a relatively high matching degree with the current resume picture, and then send the resume pictures with a relatively high matching degree to the user terminal. However, the above conventional solution still has the following technical problem 2: since the resume picture includes a large number of feature points, and only the resume browsing ratio is considered without considering the feature points concerned by the user terminal, the matched resume pictures may not meet the needs of the user terminal, resulting in difficulty in sending resume pictures that meet the needs of the user terminal to the user terminal, wasting the viewing time of the user terminal.

[0006] For the above technical problem 2, the conventional solution is generally: use a gaze estimation algorithm to identify the content of the resume picture gazed at by the user terminal, and send resume pictures that meet the needs of the user terminal to the user terminal based on the content concerned by the user terminal. However, the above conventional solution still has the following technical problem 3: the accuracy of the content of the resume picture gazed at by the user terminal identified by the gaze estimation algorithm is relatively low, resulting in a relatively low accuracy of the resume pictures sent to the user terminal, wasting the viewing time of the user terminal.

[0007] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art in this country. Summary of the Invention

[0008] This disclosure is in part for introducing concepts in a brief form, which will be described in detail in the following Detailed Description section. This disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0009] Some embodiments of the present disclosure provide a resume browsing information generation method, apparatus, electronic device, and computer-readable medium to solve one or more of the technical problems mentioned in the above Background section.

[0010] In a first aspect, some embodiments of the present disclosure provide a resume browsing information generation method, which includes: in response to receiving a resume viewing request sent by a user terminal, sending a user identification request to the user terminal; receiving the user identification information sent by the user terminal and storing the user identification information in a user browsing database; sending a resume picture corresponding to the resume viewing request to the user terminal and determining the current time as the first browsing time; in response to receiving a close request sent by the user terminal, determining a resume browsing occupancy ratio and determining the current time as the second browsing time; determining the difference between the second browsing time and the first browsing time as the resume browsing duration; determining the user identification information, the resume browsing occupancy ratio, and the resume browsing duration as resume browsing information and sending the resume browsing information to a management terminal.

[0011] In a second aspect, some embodiments of the present disclosure provide a resume browsing information generation apparatus, which includes: a first sending unit configured to, in response to receiving a resume viewing request sent by a user terminal, send a user identification request to the user terminal; a receiving unit configured to receive the user identification information sent by the user terminal and store the user identification information in a user browsing database; a second sending unit configured to send a resume picture corresponding to the resume viewing request to the user terminal and determine the current time as the first browsing time; a first determining unit configured to, in response to receiving a close request sent by the user terminal, determine a resume browsing occupancy ratio and determine the current time as the second browsing time; a second determining unit configured to determine the difference between the second browsing time and the first browsing time as the resume browsing duration; a third determining unit configured to determine the user identification information, the resume browsing occupancy ratio, and the resume browsing duration as resume browsing information and send the resume browsing information to a management terminal.

[0012] In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device storing one or more programs thereon, which, when executed by the one or more processors, cause the one or more processors to implement the method described in any implementation manner of the first aspect above.

[0013] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium storing a computer program thereon, wherein the program, when executed by a processor, implements the method described in any implementation manner of the first aspect above.

[0014] The above various embodiments of the present disclosure have the following beneficial effects: Through the resume browsing information generation method of some embodiments of the present disclosure, resume browsing information can be generated. Specifically, the reason why it is difficult to generate resume browsing information is that when the resume is sent to the user terminal in the form of a paper version or a file, it is difficult to know the viewing situation of the resume on the user terminal, resulting in difficulty in generating resume browsing information. Based on this, in the resume browsing information generation method of some embodiments of the present disclosure, first, in response to receiving a resume viewing request sent by the user terminal, a user identification request is sent to the above user terminal. Thus, a user identification request can be sent to the user terminal to receive the user identification information sent by the user terminal. Secondly, the user identification information sent by the above user terminal is received and stored in the user browsing database. Thus, the user identification information can be received for subsequent determination of resume browsing information. Then, the resume picture corresponding to the above resume viewing request is sent to the above user terminal, and the current time is determined as the first viewing time. Thus, the resume picture can be sent to the user terminal, and the time when the user terminal starts to view the resume picture can be recorded. Then, in response to receiving the close request sent by the above user terminal, the resume browsing occupancy ratio is determined, and the current time is determined as the second viewing time. Thus, the resume browsing occupancy ratio and the time when the user terminal closes the resume picture can be obtained. After that, the difference between the above second viewing time and the above first viewing time is determined as the resume browsing duration. Thus, the total duration for which the user terminal views the resume picture can be obtained. Finally, the above user identification information, the above resume browsing occupancy ratio, and the above resume browsing duration are determined as resume browsing information, and the above resume browsing information is sent to the management terminal. Thus, resume browsing information can be generated. Therefore, the resume picture can be sent to the user terminal and the viewing situation of the resume picture on the user terminal can be monitored in real time, instead of sending the resume to the user terminal in the form of a paper version or a file, and the viewing situation of the resume picture on the user terminal can be known. Thus, resume browsing information can be generated. Description of the Drawings

[0015] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and that the original and elements are not necessarily drawn to scale.

[0016] Figure 1 is a flowchart of some embodiments of a method for generating resume browsing information according to the present disclosure;

[0017] Figure 2 is a schematic structural diagram of some embodiments of a device for generating resume browsing information according to the present disclosure;

[0018] Figure 3 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. Specific Embodiments

[0019] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some 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 construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes and are not used to limit the protection scope of the present disclosure.

[0020] In addition, it should be noted that for the sake of convenience of description, only the parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order or interdependence relationship of the functions performed by these devices, modules, or units.

[0022] It should be noted that the modifications of "one" and "plural" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0024] The present disclosure will be described in detail below with reference to the drawings and in combination with the embodiments.

[0025] Reference Figure 1, which shows the flow 100 of some embodiments of the resume browsing information generation method according to the present disclosure. The resume browsing information generation method includes the following steps:

[0026] Step 101, in response to receiving a resume viewing request sent by a user terminal, send a user identification request to the user terminal.

[0027] In some embodiments, the execution subject of the resume browsing information generation method (such as a computing device) can, in response to receiving a resume viewing request sent by a user terminal, send a user identification request to the above-mentioned user terminal. Among them, the user terminal can be a terminal that wants to view a resume picture. The resume viewing request can indicate that the user terminal wants to view a resume picture. The resume picture can be a picture representing resume information. The resume information can include, but is not limited to, at least one of the following: resume user identification, resume user basic information, resume user education experience information, resume user work experience information, resume user specialty information, resume user expected position information. The resume user identification can uniquely identify a resume user (the resume user can be a user who wants to apply for a job). The resume user basic information can include, but is not limited to, at least one of the following: name, age, address, mobile phone number, email. The resume user education experience information can include at least one resume user school information. The resume user school information can include, but is not limited to, at least one of the following: school name, major name, academic degree, education start time, and education end time. The resume user work experience information can include, but is not limited to, at least one of the following: supplier name (the company where the resume user has worked), position (the position where the resume user has worked), work start time, and work end time. The resume user specialty information can represent the specialty of the resume user. The resume user expected position information can represent the position expected by the resume user. The user identification request can indicate that it is desired to obtain a user identification. The user identification can uniquely identify a user terminal.

[0028] Step 102, receive the user identification information sent by the user terminal, and store the user identification information in the user browsing database.

[0029] In some embodiments, the above-mentioned execution entity may receive the user identification information sent by the above-mentioned user terminal and store the above-mentioned user identification information in the user browsing database. The user identification information may include, but is not limited to, at least one of the following: user identification, user name, and user mobile phone number. The user browsing database may be a database storing user browsing information. In practice, first, the above-mentioned execution entity may receive the user identification information sent by the user terminal. Then, the above-mentioned execution entity may add the user identification information to the user identification information to store the above-mentioned user identification information in the user browsing database. Here, the user identification information may initially be empty. Among them, in response to receiving the user identification request sent by the above-mentioned execution entity, the user terminal may send the user identification information representing empty to the above-mentioned execution entity. In response to receiving the user identification request sent by the above-mentioned execution entity, the user terminal may also send non-empty user identification information to the above-mentioned execution entity.

[0030] Step 103: Send the resume picture corresponding to the resume viewing request to the user terminal and determine the current time as the first viewing time.

[0031] In some embodiments, the above-mentioned execution entity may send the resume picture corresponding to the above-mentioned resume viewing request to the above-mentioned user terminal and determine the current time as the first viewing time.

[0032] Step 104: In response to receiving the close request sent by the user terminal, determine the resume viewing occupancy ratio and determine the current time as the second viewing time.

[0033] In some embodiments, the above-mentioned execution entity may, in response to receiving the close request sent by the above-mentioned user terminal, determine the resume viewing occupancy ratio and determine the current time as the second viewing time.

[0034] Optionally, before the above-mentioned step of, in response to receiving the close request sent by the above-mentioned user terminal, determining the resume viewing occupancy ratio and determining the current time as the second viewing time, the above-mentioned execution entity may further perform the following steps:

[0035] First step: In response to receiving the first sliding request sent by the above-mentioned user terminal, perform a sliding operation on the resume picture at a preset speed. The preset speed may be to slide the resume picture at a speed of 2 centimeters per second.

[0036] Second step, in response to receiving the second sliding request sent by the above user terminal, send the sliding parameter filling page to the above user terminal to receive the sliding parameter information filled by the above user terminal. Among them, the user terminal clicking the sliding setting button can indicate that the user terminal wants to set the automatic sliding speed. The sliding parameter filling page can be a page that requires the user terminal to fill in the sliding parameter information. The sliding parameter information can include, but is not limited to, at least one of the following: sliding speed.

[0037] Third step, in response to receiving the sliding parameter information sent by the above user terminal, perform a sliding operation based on the above sliding parameter information. In practice, in response to receiving the sliding parameter information sent by the above user terminal, the above execution entity can perform a sliding operation on the resume picture according to the sliding speed included in the above sliding parameter information.

[0038] Fourth step, determine the above sliding parameter information and the current time as the automatic sliding trajectory information.

[0039] Fifth step, store the above automatic sliding trajectory information in the user browsing database. In practice, the above execution entity can add the above automatic sliding trajectory information to the above user identification information to store the above automatic sliding trajectory information in the user browsing database.

[0040] In practice, the above execution entity can determine the browsing occupancy ratio through the following steps:

[0041] First step, in response to determining that the above user terminal performs at least one sliding operation, obtain at least one sliding trajectory information corresponding to the above at least one sliding operation. Among them, the sliding trajectory information in the at least one sliding trajectory information can include, but is not limited to, at least one of the following: sliding time, sliding distance, sliding speed. In practice, in response to determining that the above user terminal performs at least one sliding operation, the above execution entity can obtain at least one sliding trajectory information corresponding to the above at least one sliding operation from the terminal device by means of a wired connection or a wireless connection.

[0042] Second step, store the obtained at least one sliding trajectory information in the user browsing database. In practice, the above execution entity can add the obtained at least one sliding trajectory information to the above user browsing information so as to store the at least one sliding trajectory information in the user browsing database.

[0043] Third step, determine the ratio of the target sliding distance to the resume height as the resume browsing occupancy ratio. Among them, the resume height can be the length of the above resume picture. The target sliding distance can be the largest sliding distance among the at least one sliding distances included in the above user browsing database. Thus, the ratio of the resume picture viewed by the user at the last sliding can be determined as the resume browsing occupancy ratio.

[0044] Step 105, determine the difference between the second browsing time and the first browsing time as the resume browsing duration.

[0045] In some embodiments, the above-mentioned execution entity may determine the difference between the second browsing time and the first browsing time as the resume browsing duration.

[0046] Step 106, determine the user identification information, the resume browsing ratio, and the resume browsing duration as resume browsing information, and send the resume browsing information to the management terminal.

[0047] In some embodiments, the above-mentioned execution entity may determine the user identification information, the resume browsing ratio, and the resume browsing duration as resume browsing information, and send the resume browsing information to the management terminal. Among them, the management terminal may be a terminal for viewing resume browsing information.

[0048] Optionally, the above-mentioned execution entity may further perform the following steps:

[0049] First step, in response to determining that the user identification information meets the preset identification condition, determine the user attribute information corresponding to the user identification information in the user attribute information database as the target attribute information. Among them, the preset identification condition may be that both the user name and the user mobile phone number included in the user identification information are not empty. The user attribute information database may be a database storing user attribute information. The user attribute information may include, but is not limited to, at least one of the following: user name, user mobile phone number, user supplier name, user supplier identification. The user supplier identification may uniquely determine a user supplier (the company where the user is located). In practice, in response to determining that the user identification information meets the preset identification condition, the above-mentioned execution entity may perform the following steps: First, in response to determining that there is user attribute information in the user attribute information database corresponding to the user name and the user mobile phone number included in the user identification information, determine the user attribute information and the user identification included in the user identification information as the target attribute information. Then, in response to determining that there is no user attribute information in the user attribute information database corresponding to the user name and the user mobile phone number included in the user identification information, determine the user identification information as the target attribute information.

[0050] Second step, in response to determining that the user identification information does not meet the above-mentioned preset identification condition, determine the preset attribute information as the target attribute information. Among them, the preset attribute information may be information representing "default user".

[0051] In the third step, store the determined target attribute information and the above resume browsing information in the user browsing database. Among them, the above user browsing database may include user browsing information. The user browsing information may include, but is not limited to, at least one of the following: user identification information, target attribute information, resume browsing information, sliding trajectory information, and sliding browsing information. Among them, the sliding browsing information may include, but is not limited to, at least one of the following: sliding time and sliding position. Here, the sliding time and sliding position may be generated based on the sliding trajectory information. The sliding browsing information may represent that at the sliding time, the resume picture slides to the sliding position.

[0052] Considering the problems of the above conventional solutions, in the face of the above technical problem 2: Since the resume picture includes a large number of feature points, and only based on the resume browsing ratio without considering the feature points concerned by the user terminal, the matched resume picture may not meet the needs of the user terminal, making it difficult to send a resume picture that meets the needs of the user terminal to the user terminal, resulting in a waste of the viewing time of the user terminal. Combining the existing technical status, the following solutions can be decided.

[0053] Optionally, the above execution entity may also perform the following steps:

[0054] In the first step, collect a user feature picture set through a preset collection device. In practice, the above execution entity may collect a user feature picture set of the viewing user within a preset time period through a preset collection device. Here, the preset collection device may be a camera. For example, the preset collection device may be a camera built in the above execution entity. The preset collection device may also be an external camera. Here, the viewing user may be the user using the user terminal. The preset time period may be the time period from when the user terminal starts viewing the resume picture to when the user terminal closes the resume picture. The user feature pictures in the user feature picture set may be user feature pictures corresponding to a time granularity within the preset time period. For example, the time granularity may be: 1 second. The user feature pictures in the user feature picture set may be pictures of the face of the viewing user collected by the preset collection device.

[0055] In the second step, input the above user feature picture set into a pre-trained user browsing position recognition model to obtain user browsing position information. Among them, the pre-trained user browsing position recognition model may be a model pre-trained with the user feature picture set as the input and the user browsing position information as the output. Among them, the above user browsing position information may include, but is not limited to, at least one of the following: user identification, browsing position, and browsing time.

[0056] Step 3: Select the user browsing information corresponding to the above user browsing location information from the above user browsing database as the target user browsing information. In practice, the above execution entity may select the user browsing information that meets the preset selection conditions from the above user browsing database as the target user browsing information. Among them, the preset selection conditions may be that the user identifier included in the user browsing information is the same as the user identifier included in the above user browsing location information, and the sliding time included in the user browsing information is the same as the browsing time included in the above user browsing location information.

[0057] Step 4: Determine the user's concerned information based on the above target user browsing information and the above user browsing location information. In practice, first, the above execution entity may project the browsing location included in the above user browsing location information onto the resume picture where the sliding location included in the above target user browsing information is located to obtain the user's concerned information.

[0058] Step 5: Select an initial resume picture set from the preset resume database. The preset resume database may be a database for storing resume pictures. In practice, the above execution entity may randomly select an initial resume picture set with a preset resume selection quantity from the preset resume database. For example, the preset resume selection quantity may be 30.

[0059] Step 6: For the initial resume picture set, perform the following recommended sub-steps:

[0060] First sub-step: Perform feature extraction processing on each initial resume picture in the initial resume picture set to generate initial resume feature information and obtain an initial resume feature information set. In practice, the above execution entity may perform feature extraction processing on each initial resume picture in the initial resume picture set through a preset feature extraction algorithm to generate initial resume feature information and obtain an initial resume feature information set. For example, the preset feature extraction algorithm may be, but is not limited to: SIFT (Scale-Invariant Feature Transform) algorithm, OCR (Optical Character Recognition) algorithm.

[0061] The second sub-step is to perform a matching process on each initial resume feature information in the initial resume feature information set and the above user's concerned information to generate a feature matching result, and obtain a feature matching result set. In practice, the above-mentioned execution entity can perform a matching process on each initial resume feature information in the initial resume feature information set and the above user's concerned information through a preset feature matching algorithm to generate a feature matching result and obtain a feature matching result set. For example, the preset feature matching algorithm can be, but is not limited to: cosine similarity algorithm, BF (Brute Force) algorithm, NLP (Natural Language Processing) model.

[0062] The third sub-step is to, in response to determining that the number of feature matching results in the feature matching result set that meet the preset feature matching conditions is greater than or equal to the preset feature matching number, determine each feature matching result in the feature matching result set that meets the preset feature matching conditions as the target feature matching result set. Among them, the preset feature matching condition can be: the feature matching result is greater than or equal to the preset feature matching value. For example, the preset feature matching value can be 0.8. The preset feature matching number can be 10.

[0063] The seventh step is to, in response to determining that the number of feature matching results in the feature matching result set that meet the above preset feature matching conditions is less than the above preset feature matching number, select the resume pictures of the preset resume number that meet the preset resume selection conditions from the above preset resume database, add them to the initial resume picture set, and determine the added initial resume picture set as the initial resume picture set for executing the above recommendation step again. Among them, the preset resume selection condition can be: the selected resume pictures are not in the initial resume picture set. For example, the preset resume number can be 10.

[0064] The eighth step is to determine the initial resume picture corresponding to each target feature matching result in the above target feature matching result set as the target resume picture to obtain a target resume picture set.

[0065] The ninth step is to send the above target resume picture set to the above user terminal.

[0066] The optional technical content in step 106 is an inventive point of an embodiment of the present disclosure, which solves the second technical problem mentioned in the background art, "resulting in a waste of the viewing time of the user terminal". The factors that tend to cause confusion in the basic information of transactions are often as follows: Since the resume picture includes a large number of feature points, and only based on the resume browsing ratio without considering the feature points concerned by the user terminal, the matched resume picture may not meet the needs of the user terminal, making it difficult to send a resume picture that meets the needs of the user terminal to the user terminal, resulting in a waste of the viewing time of the user terminal. If the above factors are solved, the effect of reducing the waste of the viewing time of the user terminal can be achieved. To achieve this effect, first, collect the user feature picture set. Thus, the user feature picture set of the user can be collected for subsequent identification of the content concerned by the user. Second, input the above user feature picture set into a pre-trained user browsing position recognition model to obtain user browsing position information. Thus, the position where the user is gazing can be recognized through the user browsing position recognition model. Then, select the user browsing information corresponding to the above user browsing position information from the above user browsing database as the target user browsing information. Immediately afterwards, determine the user concern information based on the above target user browsing information and the above user browsing position information. Thus, the content concerned by the user can be obtained. Then, select an initial resume picture set from the preset resume database. Thus, the initial resume picture set can be selected for subsequent selection of resume pictures that meet the user's needs from the initial resume picture set. Then, for the initial resume picture set, perform the following recommendation steps: First, perform feature extraction processing on each initial resume picture in the initial resume picture set to generate initial resume feature information, obtaining an initial resume feature information set. Thus, the feature information in the initial resume picture can be extracted for subsequent matching with the user concern information. Second, perform matching processing on each initial resume feature information in the initial resume feature information set and the above user concern information to generate a feature matching result, obtaining a feature matching result set. Thus, a feature matching result set corresponding to the initial resume picture set can be obtained. Third, in response to determining that the number of feature matching results that meet the preset feature matching condition in the feature matching result set is greater than or equal to the preset feature matching number, determine each feature matching result that meets the preset feature matching condition in the feature matching result set as the target feature matching result set. Thus, a target feature matching result set that is relatively well matched with the user concern information can be determined. After that, in response to determining that the number of feature matching results that meet the above preset feature matching condition in the feature matching result set is less than the above preset feature matching number, add the resume pictures with the preset resume number that meet the preset resume selection condition selected from the above preset resume database to the initial resume picture set, and determine the added initial resume picture set as the initial resume picture set for re-executing the above recommendation steps.Therefore, when there are few initial resume pictures that meet the user's needs selected from the preset resume database, it is necessary to select initial resume pictures from the preset resume database again. After that, the initial resume pictures corresponding to each target feature matching result in the above target feature matching result set are determined as target resume pictures, and a target resume picture set is obtained. Thus, resume pictures that meet the user's needs can be obtained. Finally, the above target resume picture set is sent to the above user terminal. Thus, resumes that the user may be interested in can be sent to the user terminal for the user terminal to view. Therefore, relatively accurate resume pictures that meet the needs of the user terminal can be sent to the user terminal. Thus, the viewing time of the user terminal can be reduced.

[0067] Considering the problems of the above conventional solutions, in the face of the above technical problem 3: the accuracy of the content of the resume picture gazed at by the user terminal identified by the gaze estimation algorithm is low, resulting in low accuracy of the resume pictures sent to the user terminal, wasting the viewing time of the user terminal. Combining the existing technical situation, the following solution can be decided to be adopted.

[0068] Optionally, the pre-trained user browsing position recognition model can be obtained through the following steps:

[0069] The first step is to obtain a training sample set.

[0070] In some embodiments, the above execution entity can obtain the training sample set from the terminal device through a wired connection or a wireless connection. Among them, the training samples in the above training sample set include: a sample user feature picture set and sample user browsing position information.

[0071] The second step is to determine the initial user browsing position recognition model.

[0072] In some embodiments, the above execution entity can determine the initial user browsing position recognition model. Among them, the above initial user browsing position recognition model can include but is not limited to at least one of the following: an initial matching model, an initial classification model, and an initial recognition model.

[0073] The initial matching model can be a custom model that takes the sample user feature picture as the input and the initial user feature matching picture as the output. The custom model can be divided into three layers:

[0074] The first layer, the face detection layer, is used for: performing face detection processing on the sample user feature image through a preset face detection algorithm to generate an initial face detection image. For example, the preset face detection algorithm can be, but is not limited to: Haar (Haar) cascade detector, MTCNN (Multi-task convolutional neural network), YOLO (You Only Look Once, object detection model). Here, the initial face detection image can determine the position of the face of the viewing user.

[0075] The second layer, the face key point detection layer, is used for: performing face key point detection processing on the initial face detection image through a preset face key point detection algorithm to generate an initial face key point detection image. For example, the preset face key point detection algorithm can be: the facial feature point detection algorithm using the Dlib library and OpenCV (cross-platform computer vision library). Here, the initial face key point detection image can determine the positions of the facial feature points of the viewing user.

[0076] The third layer, the cropping layer, is used for: performing cropping processing on the initial face key point detection image to generate an initial cropped image representing the eyes of the viewing user.

[0077] The fourth layer, the noise reduction layer, is used for: performing noise reduction processing on the initial cropped image through a preset noise reduction algorithm to generate an initial user feature matching image. For example, the preset noise reduction algorithm can be: the Gabor transform algorithm.

[0078] The initial classification model can be a model that takes the initial user feature matching image set as input and outputs the initial user feature classification image group set. Among them, the initial classification model is used for: grouping each initial user feature matching image with the same eye position.

[0079] The initial recognition model can be a model that takes the initial user feature image to be recognized and the sample user feature image set as input and outputs the initial user browsing position information. Here, the initial recognition model is used for: First, project the initial user feature image to be recognized onto the resume image to obtain the initial browsing position. Among them, the initial browsing position can represent the position where the viewing user views the resume image. Then, determine the position of the sample user feature image corresponding to the initial user feature image to be recognized in the sample user feature image set as the target digit. After that, determine the product of the target digit and the above time granularity as the initial browsing time. Finally, determine the initial browsing position and the initial browsing time as the initial user browsing position information.

[0080] The third step is to select training samples from the above training sample set.

[0081] In some embodiments, the above-mentioned execution entity may select training samples from the above-mentioned training sample set. In practice, the above-mentioned execution entity may randomly select training samples from the above-mentioned training sample set.

[0082] Fourth step, input each sample user feature picture in the sample user feature picture set included in the selected training sample into the above-mentioned initial matching model to generate an initial user feature matching picture, and obtain an initial user feature matching picture set.

[0083] In some embodiments, the above-mentioned execution entity may input each sample user feature picture in the sample user feature picture set included in the selected training sample into the above-mentioned initial matching model to generate an initial user feature matching picture, and obtain an initial user feature matching picture set.

[0084] Fifth step, input the above-mentioned initial user feature matching picture set into the above-mentioned initial classification model to obtain an initial user feature classification picture group set.

[0085] In some embodiments, the above-mentioned execution entity may input the above-mentioned initial user feature matching picture set into the above-mentioned initial classification model to obtain an initial user feature classification picture group set.

[0086] Sixth step, select an initial user feature classification picture group that meets the preset classification selection condition from the above-mentioned initial user feature classification picture group set as an initial user feature selection picture group.

[0087] In some embodiments, the above-mentioned execution entity may select an initial user feature classification picture group that meets the preset classification selection condition from the above-mentioned initial user feature classification picture group set as an initial user feature selection picture group. Among them, the preset classification selection condition may be: select the initial user feature classification picture group with the largest number of initial user feature classification pictures included in each initial user feature classification picture group in the initial user feature classification picture group set.

[0088] Seventh step, select an initial user feature selection picture from the above-mentioned initial user feature selection picture group as an initial user feature picture to be recognized.

[0089] In some embodiments, the above-mentioned execution entity may select an initial user feature selection picture from the above-mentioned initial user feature selection picture group as an initial user feature picture to be recognized. In practice, the above-mentioned execution entity may randomly select an initial user feature selection picture from the above-mentioned initial user feature selection picture group as an initial user feature picture to be recognized.

[0090] Eighth step, input the above-mentioned initial user feature picture to be recognized and the sample user feature picture set into the above-mentioned initial recognition model to obtain initial user browsing position information.

[0091] In some embodiments, the above-mentioned execution entity may input the above-mentioned initial user feature picture to be recognized and the sample user feature picture set into the above-mentioned initial recognition model to obtain the initial user browsing position information.

[0092] Step 9: Based on a preset loss function, determine the difference value between the above-mentioned initial user browsing position information and the sample user browsing position information included in the above-mentioned training sample.

[0093] In some embodiments, based on a preset loss function, the above-mentioned execution entity may determine the difference value between the above-mentioned initial user browsing position information and the sample user browsing position information included in the above-mentioned training sample. The preset loss function may be, but is not limited to: mean square error loss function (MSE), hinge loss function, cross-entropy loss function (CrossEntropy), 0-1 loss function, absolute value loss function, log logarithmic loss function, square loss function, exponential loss function, etc.

[0094] Step 10: In response to determining that the above-mentioned difference value is greater than or equal to a preset difference value, adjust the network parameters of the above-mentioned initial user browsing position recognition model.

[0095] In some embodiments, in response to determining that the above-mentioned difference value is greater than or equal to a preset difference value, the above-mentioned execution entity may adjust the network parameters of the above-mentioned initial user browsing position recognition model. For example, the difference between the above-mentioned difference value and the preset difference value can be calculated. On this basis, methods such as backpropagation and stochastic gradient descent are used to transfer the error value forward from the last layer of the model to adjust the parameters of each layer. Of course, according to needs, the method of network freezing (dropout) can also be used to keep the network parameters of some layers unchanged without adjustment, and no limitation is made in this regard. Regarding the setting of the preset difference value, no limitation is made. For example, the preset difference value can be 0.1.

[0096] Optionally, in response to determining that the above-mentioned difference value is less than the preset difference value, determine the above-mentioned initial user browsing position recognition model as the trained user browsing position recognition model.

[0097] In some embodiments, the above-mentioned execution entity may, in response to determining that the above-mentioned difference value is less than the preset difference value, determine the above-mentioned initial user browsing position recognition model as the trained user browsing position recognition model.

[0098] The optional technical content in step 106 is an inventive point of an embodiment of the present disclosure, which solves the third technical problem mentioned in the background art, "resulting in a waste of the viewing time of the user terminal". The factors that are likely to cause confusion in the basic information of the transaction are usually as follows: the accuracy of the content of the resume picture gazed at by the user terminal identified by the gaze estimation algorithm is low, resulting in a low accuracy of the resume picture sent to the user terminal, causing a waste of the viewing time of the user terminal. If the above factors are solved, the effect of reducing the waste of the viewing time of the user terminal can be achieved. To achieve this effect, first, a relatively accurate initial user feature matching picture set can be obtained through the initial matching model. Second, a relatively accurate initial user feature classification picture group set after classifying the initial user feature matching picture set can be obtained through the initial classification model. Then, an initial user feature picture to be recognized can be selected from the initial user feature classification picture group set for input into the initial recognition model. Then, a relatively accurate initial user browsing position information can be recognized through the initial recognition model. Therefore, an initial user browsing position recognition model including the initial matching model, the initial classification model, and the initial recognition model can be trained to obtain a trained user browsing position recognition model, so that relatively accurate user browsing position information can be obtained through the trained user browsing position recognition model. Thus, the content in the resume picture gazed at by the user terminal can be relatively accurately recognized according to the relatively accurate user browsing position information. Therefore, a resume picture that is relatively accurate and meets the needs of the user terminal can be sent to the user terminal. Furthermore, the waste of the viewing time of the user terminal can be reduced.

[0099] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the resume browsing information generation method of some embodiments of the present disclosure, resume browsing information can be generated. Specifically, the reason why it is difficult to generate resume browsing information is that when the resume is sent to the user terminal in paper form or in the form of a file, it is difficult to know the viewing situation of the resume on the user terminal, resulting in difficulty in generating resume browsing information. Based on this, in the resume browsing information generation method of some embodiments of the present disclosure, first, in response to receiving a resume viewing request sent by the user terminal, a user identification request is sent to the above-mentioned user terminal. Thus, a user identification request can be sent to the user terminal to receive the user identification information sent by the user terminal. Secondly, the user identification information sent by the above-mentioned user terminal is received, and the above-mentioned user identification information is stored in the user browsing database. Thus, the user identification information can be received for subsequent determination of resume browsing information. Then, the resume picture corresponding to the above-mentioned resume viewing request is sent to the above-mentioned user terminal, and the current time is determined as the first viewing time. Thus, the resume picture can be sent to the user terminal, and the time when the user terminal starts to view the resume picture can be recorded. Then, in response to receiving the close request sent by the above-mentioned user terminal, the resume browsing occupancy ratio is determined, and the current time is determined as the second viewing time. Thus, the resume browsing occupancy ratio and the time when the user terminal closes the resume picture can be obtained. After that, the difference between the above-mentioned second viewing time and the above-mentioned first viewing time is determined as the resume browsing duration. Thus, the total duration of the user terminal viewing the resume picture can be obtained. Finally, the above-mentioned user identification information, the above-mentioned resume browsing occupancy ratio, and the above-mentioned resume browsing duration are determined as resume browsing information, and the above-mentioned resume browsing information is sent to the management terminal. Thus, resume browsing information can be generated. Therefore, the resume picture can be sent to the user terminal and the viewing situation of the resume picture on the user terminal can be monitored in real time, instead of sending the resume to the user terminal in paper form or in the form of a file, and the viewing situation of the resume picture on the user terminal can be known. Thus, resume browsing information can be generated.

[0100] Further referring to Figure 2 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a resume browsing information generation device. These embodiments of the resume browsing information generation device correspond to Figure 1 the method embodiments shown, and the resume browsing information generation device can be specifically applied to various electronic devices.

[0101] As Figure 2As shown in the figure, the resume browsing information generation device 200 of some embodiments includes: a first sending unit 201, a receiving unit 202, a second sending unit 203, a first determining unit 204, a second determining unit 205, and a third determining unit 206. Among them, the first sending unit 201 is configured to, in response to receiving a resume viewing request sent by a user terminal, send a user identification request to the user terminal; the receiving unit 202 is configured to receive the user identification information sent by the user terminal and store the user identification information in a user browsing database; the second sending unit 203 is configured to send a resume picture corresponding to the resume viewing request to the user terminal and determine the current time as the first browsing time; the first determining unit 204 is configured to, in response to receiving a close request sent by the user terminal, determine a resume browsing occupancy ratio and determine the current time as the second browsing time; the second determining unit 205 is configured to determine the difference between the second browsing time and the first browsing time as the resume browsing duration; the third determining unit 206 is configured to determine the user identification information, the resume browsing occupancy ratio, and the resume browsing duration as resume browsing information and send the resume browsing information to a management terminal.

[0102] It can be understood that the units described in the resume browsing information generation device 200 correspond to the respective steps in the method described with reference to Figure 1 Therefore, the operations, features, and beneficial effects described above for the method also apply to the resume browsing information generation device 200 and the units included therein, and will not be elaborated herein.

[0103] Next, with reference to Figure 3 , which shows a schematic structural diagram of an electronic device (such as a computing device) 300 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present disclosure.

[0104] As Figure 3As shown, the electronic device 300 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 301, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0105] Generally, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 3 an electronic device 300 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had. Figure 3 Each block shown in may represent a device or, as needed, multiple devices.

[0106] Specifically, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such some embodiments, the computer program may be downloaded and installed from a network via the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above functions defined in the methods of some embodiments of the present disclosure are executed.

[0107] It should be noted that the computer-readable media described in some embodiments of the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0108] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed network.

[0109] The above computer-readable medium may be included in the above electronic device; or it may exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the electronic device, the electronic device is caused to: in response to receiving a resume viewing request sent by a user terminal, send a user identification request to the above user terminal; receive the user identification information sent by the above user terminal, and store the above user identification information in a user browsing database; send a resume picture corresponding to the above resume viewing request to the above user terminal, and determine the current time as a first viewing time; in response to receiving a close request sent by the above user terminal, determine a resume viewing occupancy ratio, and determine the current time as a second viewing time; determine the difference between the above second viewing time and the above first viewing time as the resume viewing duration; determine the above user identification information, the above resume viewing occupancy ratio, and the above resume viewing duration as resume viewing information, and send the above resume viewing information to a management terminal.

[0110] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++; and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, executed as a stand-alone software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or, alternatively, may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0111] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a 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 than that marked in the accompanying drawings. For example, two consecutive blocks shown 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, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0112] The units described in some embodiments of the present disclosure can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes a first sending unit, a receiving unit, a second sending unit, a first determining unit, a second determining unit, and a third determining unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the first sending unit can also be described as "the unit that sends a user identification request to the above-mentioned user terminal in response to receiving a resume viewing request sent by the user terminal".

[0113] The functions described above can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0114] The above description is only some preferred embodiments of the present disclosure and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, technical solutions formed by mutually replacing the above features with technical features having similar functions (but not limited to) disclosed in the embodiments of the present disclosure.

Claims

1. A resume browsing information generation method, comprising: In response to receiving a resume viewing request sent by a user terminal, sending a user identification request to the user terminal; Receiving user identification information sent by the user terminal, and storing the user identification information in a user browsing database; Sending a resume picture corresponding to the resume viewing request to the user terminal, and determining the current time as the first browsing time; In response to receiving a closing request sent by the user terminal, determining a resume browsing ratio value, and determining a current time as a second browsing time; Determine the difference between the second browsing time and the first browsing time as the resume browsing time; Determine the user identification information, the resume browsing percentage value and the resume browsing duration as resume browsing information, and send the resume browsing information to a management terminal; Collect user feature picture sets through a preset collection device; Inputting the user feature picture set into a pre-trained user browsing location recognition model to obtain user browsing location information; Selecting user browsing information corresponding to the user browsing location information from the user browsing database as target user browsing information; Determining user-focused information based on the target user browsing information and the user browsing location information; Generate a target resume picture set according to the user's attention information and a preset resume database; Sending the target resume picture set to the user terminal; The pre-trained user browsing location recognition model is obtained by training through the following steps: Obtain a training sample set; Determine an initial user browsing location recognition model, wherein the initial user browsing location recognition model includes: an initial matching model, an initial classification model, and an initial recognition model; Selecting training samples from the training sample set; Inputting each sample user feature picture in the sample user feature picture set included in the selected training sample into the initial matching model to generate an initial user feature matching picture, thereby obtaining an initial user feature matching picture set; Inputting the initial user feature matching picture set into the initial classification model to obtain an initial user feature classification picture group set; Selecting an initial user feature classification picture group that meets a preset classification selection condition from the initial user feature classification picture group set as an initial user feature selection picture group; Selecting an initial user feature selection picture from the initial user feature selection picture group as an initial user feature to-be-recognized picture; Inputting the initial user feature picture to be identified and the sample user feature picture set into the initial recognition model to obtain initial user browsing position information; Determining, based on a preset loss function, a difference value between the initial user browsing location information and the sample user browsing location information included in the training sample; In response to determining that the difference value is greater than or equal to a preset difference value, adjusting a network parameter of the initial user browsing location recognition model; In response to determining that the difference value is less than the preset difference value, the initial user browsing location recognition model is determined as a trained user browsing location recognition model.

2. The method according to claim 1, wherein: Determining the resume browsing ratio includes: In response to determining that the user terminal performs at least one sliding operation, obtaining at least one sliding track information corresponding to the at least one sliding operation, wherein the sliding track information in the at least one sliding track information includes: sliding time, sliding distance, and sliding speed; storing the obtained at least one sliding track information in a user browsing database; The ratio of the target sliding distance to the resume height is determined as the resume browsing ratio, wherein the resume height is the length of the resume picture, and the target sliding distance is the largest sliding distance among at least one sliding distance included in the user browsing database.

3. The method according to claim 1, wherein: The method further comprises: In response to determining that the user identification information satisfies a preset identification condition, determining user attribute information corresponding to the user identification information in a user attribute information database as target attribute information; In response to determining that the user identification information does not satisfy the preset identification condition, determining the preset attribute information as the target attribute information; The determined target attribute information and the resume browsing information are stored in a user browsing database, wherein the user browsing database includes user browsing information, and the user browsing information includes: user identification information, target attribute information, resume browsing information, and sliding track information.

4. The method according to claim 1, wherein: Before determining the resume browsing ratio in response to receiving the closing request sent by the user terminal, and determining the current time as the second browsing time, the method further includes: In response to receiving a first sliding request sent by the user terminal, sliding the resume picture at a preset speed; In response to receiving the second sliding request sent by the user terminal, sending a sliding parameter filling page to the user terminal to receive sliding parameter information filled in by the user terminal; In response to receiving the sliding parameter information sent by the user terminal, performing a sliding operation based on the sliding parameter information; Determine the sliding parameter information and the current time as automatic sliding trajectory information; The automatic sliding track information is stored in a user browsing database.

5. A resume browsing information generating device, comprising: A first sending unit, configured to send a user identification request to the user terminal in response to receiving a resume viewing request sent by the user terminal; a receiving unit, configured to receive the user identification information sent by the user terminal, and store the user identification information in a user browsing database; A second sending unit is configured to send a resume picture corresponding to the resume viewing request to the user terminal, and determine the current time as a first browsing time; A first determining unit is configured to determine a resume browsing ratio value in response to receiving a closing request sent by the user terminal, and determine a current time as a second browsing time; A second determining unit is configured to determine the difference between the second browsing time and the first browsing time as the resume browsing time; A third determining unit is configured to determine the user identification information, the resume browsing ratio value and the resume browsing duration as resume browsing information, and send the resume browsing information to a management terminal; A collection unit, configured to collect a user feature picture set through a preset collection device; An input unit, configured to input the user feature picture set into a pre-trained user browsing position recognition model to obtain user browsing position information; A first selection unit is configured to select user browsing information corresponding to the user browsing location information from the user browsing database as target user browsing information; A fourth determining unit is configured to determine user attention information based on the target user browsing information and the user browsing location information; A generating unit, configured to generate a target resume picture set according to the user concerned information and a preset resume database; A third sending unit is configured to send the target resume picture set to the user terminal; The pre-trained user browsing location recognition model is obtained by training through the following steps: Obtain a training sample set; Determine an initial user browsing location recognition model, wherein the initial user browsing location recognition model includes: an initial matching model, an initial classification model, and an initial recognition model; Selecting training samples from the training sample set; Inputting each sample user feature picture in the sample user feature picture set included in the selected training sample into the initial matching model to generate an initial user feature matching picture, thereby obtaining an initial user feature matching picture set; Inputting the initial user feature matching picture set into the initial classification model to obtain an initial user feature classification picture group set; Selecting an initial user feature classification picture group that meets a preset classification selection condition from the initial user feature classification picture group set as an initial user feature selection picture group; Selecting an initial user feature selection picture from the initial user feature selection picture group as an initial user feature to-be-recognized picture; Inputting the initial user feature picture to be identified and the sample user feature picture set into the initial recognition model to obtain initial user browsing position information; Determining, based on a preset loss function, a difference value between the initial user browsing location information and the sample user browsing location information included in the training sample; In response to determining that the difference value is greater than or equal to a preset difference value, adjusting a network parameter of the initial user browsing location recognition model; In response to determining that the difference value is less than the preset difference value, the initial user browsing location recognition model is determined as a trained user browsing location recognition model.

6. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 4.

7. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images