Method and device for analyzing user data in recruitment service, equipment and medium

Abstract

The invention relates to a method for analyzing user data in recruitment service. The method comprises the following steps: acquiring recruitment data of a target user; calculating an active score of the target user according to one or more of resume processing data, position release data and position interaction data in the recruitment behavior data; calculating an income score of the target user according to a handshake score and a handshake rate coefficient in the recruitment position data; calculating a consumption score of the target user according to the actual consumption cost progress and the predicted consumption cost progress in the recruitment payment data; and determining the health degree of the target user according to the active score, the income score and the consumption score, wherein the health degree is used for analyzing the service quality of the recruitment service platform to the user. According to the method, multiple data sources including the recruitment behavior data, the recruitment position data and the recruitment payment data are combined, so that the dimension of the data is greatly enriched. According to the method, the health degree of the user can be calculated more accurately, personalized services are provided, and the user experience is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of recruitment services, and in particular to a method, device, electronic device and storage medium for analyzing user data in recruitment services. Background Art

[0002] In the modern business environment, customer relationship management (CRM) systems are crucial for enterprises because they can help enterprises analyze and evaluate customer health. Customer health is a key indicator for enterprises to evaluate service quality and formulate market strategies. An accurate customer health analysis can enable enterprises to identify problems in a timely manner and take corresponding measures, thereby improving customer retention and enhancing the market competitiveness of enterprises.

[0003] However, when analyzing customer health, existing CRM systems have the problem of single analysis data, which leads to limitations in the analyzed health. In addition, due to the lack of comprehensive data analysis, the customer health generated by existing CRM systems is often not accurate enough. Due to the lack of accurate health indicators, it is impossible to objectively evaluate the service quality of the service platform to users, resulting in user dissatisfaction. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for analyzing user data in a recruitment service, which are used to solve at least one technical problem.

[0005] An embodiment of the present application provides a method for analyzing user data in a recruitment service, including: obtaining recruitment data of a target user, the recruitment data including at least recruitment behavior data, recruitment position data, and recruitment payment data; calculating an active score of the target user according to one or more of resume processing data, position posting data, and position interaction data in the recruitment behavior data, the active score being used to indicate the user's activity level; calculating an income score of the target user according to a handshake score and a handshake rate coefficient in the recruitment position data, the income score being used to indicate the income performance of the user posting a position in a paid manner, the handshake score being obtained by the amount of handshakes of the target user posting a position in a paid manner, and the handshake rate coefficient being obtained by the handshake rate of the target user posting a position in a paid manner; calculating a consumption score of the target user according to an actual consumption cost progress and an estimated consumption cost progress in the recruitment payment data, the consumption score being used to indicate the user's consumption trend; determining the health of the target user according to the active score, the income score, and the consumption score, the health being used to analyze the service quality of the recruitment service platform to the user.

[0006] According to the analysis method described above, a job posting score is calculated based on the job posting data, and the job posting score is determined based on the average number of recruiting positions per capita and a newly posted job coefficient. The average number of recruiting positions per capita is determined based on the number of newly posted positions and the number of account IDs of the newly posted positions in a first time period, and the newly posted job coefficient is determined based on the number of newly posted positions in a first cycle and the number of newly posted positions in a second cycle, and the first cycle is smaller than the second cycle.

[0007] The analysis method as described above calculates the target user's profit score based on the handshake score and the handshake rate coefficient in the recruitment position data, including: comparing the target user's handshake volume with the industry average handshake volume to determine the handshake score, the handshake volume is the handshake volume of the target user posting positions in a paid manner in the second time period, and the industry average handshake volume is the average handshake volume of all users posting positions in a paid manner in the second time period; determining the handshake rate coefficient based on the handshake rate of the target user posting positions in a paid manner in the second time period, the handshake rate is proportional to the handshake rate coefficient; determining the target user's profit score based on the product of the handshake score and the handshake rate coefficient.

[0008] The analysis method as described above calculates the consumption score of the target user based on the actual consumption progress and the expected consumption progress in the recruitment payment data, including: calculating the actual consumption progress based on the ratio of the first fee to the second fee, the first fee being the fee consumed by the used service opportunity, and the second fee being the total fee for purchasing the service opportunity within the validity period; determining the expected consumption progress based on the difference between the current date and the end date of the validity period; and determining the consumption score based on the size of the actual consumption progress and the expected consumption progress.

[0009] The analysis method as described above calculates a resume processing score based on the resume processing data, and the resume processing score is determined based on the resume processing rate of the target user in the third time period and the resume processing rate of the region where the target user is located in the third time period.

[0010] The analysis method as described above calculates a job interaction score based on the job interaction data, and the job interaction score is determined based on the sum of the number of chats initiated and resume downloads by the target user in the fourth time period and the sum of the number of chats initiated and resume downloads in the region where the target user is located in the fourth time period.

[0011] The analysis method as described above further includes: determining a competition score based on the number of job posts posted by the target user in the job posting data and the number of new job posts posted by the target user on other recruitment platforms, wherein the competition score is used to judge the degree of dependence of the user on the recruitment platform.

[0012] According to another aspect of the present application, a device for analyzing user data in a recruitment service is provided, comprising: an acquisition module, for acquiring recruitment data of a target user, wherein the recruitment data comprises at least recruitment behavior data, recruitment position data and recruitment payment data; a first calculation module, for calculating an active score of the target user according to one or more of resume processing data, position posting data and position interaction data in the recruitment behavior data, wherein the active score is used to indicate the user's activity level; a second calculation module, for calculating an income score of the target user according to a handshake score and a handshake rate coefficient in the recruitment position data, wherein the income score is used to indicate the income performance of the user posting a position in a paid manner, the handshake score is obtained by the handshake amount of the target user posting a position in a paid manner, and the handshake rate coefficient is obtained by the handshake rate of the target user posting a position in a paid manner; a third calculation module, for calculating a consumption score of the target user according to the actual consumption cost progress and the expected consumption cost progress in the recruitment payment data, wherein the consumption score is used to indicate the user's consumption trend; a health determination module, for determining the health of the target user according to the active score, the income score and the consumption score, wherein the health is used to analyze the service quality of the recruitment service platform to the user.

[0013] According to another aspect of the present application, an electronic device is provided, which includes a processor and a memory, wherein a computer program instruction set is stored in the memory, and when the processor executes the computer program instruction set in the memory, the method for analyzing user data in the recruitment service as described above is implemented.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, wherein a computer program instruction set is stored on the computer-readable storage medium, and when the computer program instruction set is executed by a processor, the method for analyzing user data in a recruitment service as described above is implemented.

[0015] In the above method, by combining multiple data sources, including recruitment behavior data, recruitment position data, and recruitment payment data, the data dimensions are greatly enriched. The richness and comprehensiveness of this data helps to more comprehensively understand the user's recruitment activities, thereby providing deeper analysis and insights. Furthermore, by comprehensively analyzing multiple data, this method can more accurately calculate the user's health. This accuracy helps the recruitment service platform to more effectively identify user needs, provide personalized services, and optimize the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The preferred embodiments of the present invention will be further described in detail below with reference to the accompanying drawings, wherein:

[0017] Figure 1 It is a flow chart of a method for analyzing user data in a recruitment service according to an embodiment of the present application.

[0018] Figure 2 This is a flow chart of the method for calculating the revenue score in step S130.

[0019] Figure 3 This is a flow chart of the method for calculating the revenue score in step S140.

[0020] Figure 4 This is a schematic diagram of the structure of a user health nameplate according to an embodiment of the present application.

[0021] Figure 5 It is a schematic diagram of the structure of a device for analyzing user data in a recruitment service according to an embodiment of the present application.

[0022] Figure 6 It is a schematic diagram of the hardware structure principle of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] In the following detailed description, reference may be made to the various specification drawings that are part of the present application and are used to illustrate specific embodiments of the present application. In the accompanying drawings, similar reference numerals describe substantially similar components in different figures. The various specific embodiments of the present application are described below in sufficient detail so that a person of ordinary skill in the art with relevant knowledge and skills in the art can implement the technical solutions of the present application. It should be understood that other embodiments may also be used or structural, logical or electrical changes may be made to the embodiments of the present application.

[0025] The following is a brief description of the concepts and technical terms that may be involved in the embodiments of the present application.

[0026] The handshake volume refers to the number of interactions between job seekers and corporate recruitment representatives on online recruitment platforms. For example, when a job seeker sends his / her job application intention to a company, and the company views the job application intention and invites the job seeker for an interview or collects the job seeker's resume, the handshake volume increases by 1.

[0027] Handshake rate: It is an indicator to measure recruitment efficiency. It refers to the proportion of successful contacts between job seekers and recruiters within a certain period of time, that is, the ratio of the number of handshakes to the number of contact resumes.

[0028] Resume processing rate: Resume processing rate refers to the ratio of the number of resumes received by the employer and the corresponding decision-making within a specific time frame. "Processing" here means evaluating the resume at least once, which includes: making an "interested" evaluation on the resume, inviting the applicant for an interview, and making an "unsuitable" evaluation on the resume.

[0029] Figure 1 FIG. 1 is a flow chart of a method for analyzing user data in a recruitment service according to an embodiment of the present application. Figure 1 As shown, the method includes:

[0030] Step S110, obtaining recruitment data of the target user, wherein the recruitment data at least includes: recruitment behavior data, recruitment position data and recruitment payment data;

[0031] Step S120, calculating the activity score of the target user according to one or more of the resume processing data, the job posting data and the job interaction data in the recruitment behavior data, wherein the activity score is used to indicate the activity level of the user;

[0032] Step S130, calculating the target user's profit score according to the handshake score and the handshake rate coefficient in the job position data, wherein the profit score is used to represent the profit performance of the user posting the job position in a paid manner, the handshake score is obtained by the handshake amount of the target user posting the job position in a paid manner, and the handshake rate coefficient is obtained by the handshake rate of the target user posting the job position in a paid manner;

[0033] Step S140, calculating the consumption score of the target user according to the actual consumption progress and the estimated consumption progress in the recruitment payment data, wherein the consumption score is used to represent the consumption trend of the user;

[0034] Step S150, determining the health of the target user according to the activity score, the income score and the consumption score, wherein the health is used to analyze the service quality of the recruitment service platform to the user.

[0035] In step S110, the recruitment data of the target user is obtained through the background user recruitment database of the recruitment service platform. Recruitment behavior data includes resume processing data, job posting data and job interaction data of users on the platform. Resume processing data involves behavioral data such as users' viewing, screening, responding, inviting interviews and evaluating their resumes, and the evaluation includes "interested" and "unsuitable"; job posting data includes job information posted by users, job update frequency and other data; job interaction data records the communication and interaction between users and other users, such as initiating chats, downloading resumes, and telephone communication. Recruitment job data includes handshake volume and handshake rate data for user-posted jobs. Recruitment payment data involves users' payment behavior on the platform, including payment amount, payment method, payment time, etc.

[0036] In step S120, resume processing data is used to indicate the user's enthusiasm for processing resumes, and job posting data is used to indicate the user's enthusiasm for posting jobs, thereby reflecting the user's urgency in recruiting personnel. Job interaction data is used to indicate the user's enthusiasm for communicating with job seekers. The active score can be calculated in a variety of ways. For example, a weighted average can be performed based on indicators such as the user's resume processing speed, job posting frequency, and job interaction frequency. The resume processing speed can be calculated based on the number of resumes processed by the user per unit time; the job posting frequency can be calculated based on the number of jobs posted by the user per unit time; and the job interaction frequency can be calculated based on the number of interactions the user has with other users per unit time. Through the comprehensive evaluation of these indicators, an active score reflecting the user's activity level can be obtained.

[0037] According to another embodiment of the present application, the activity score of the target user is calculated based on one or more of the resume processing data, job posting data, job interaction data, and account login data in the recruitment behavior data. The account login data is used to indicate the number of days the account ID is logged in within a specific time period. By adding the account login data, the user's activity score can be calculated more accurately.

[0038] In step S130, the handshake score refers to the handshake volume of the user posting a job in a paid manner, which is an absolute value score, reflecting the effectiveness of the user posting the job. The handshake rate coefficient refers to a coefficient obtained by the user based on the handshake rate of the posting of the job in a paid manner, which is a weight coefficient, reflecting the efficiency of the user posting the job. The profit score can be calculated using the following formula:

[0039] Profit score = handshake score × handshake rate coefficient;

[0040] The formula combines the handshake score and the handshake rate coefficient to comprehensively evaluate the effectiveness of users posting positions through paid methods. Recruitment service platforms can evaluate and improve service quality based on users' profit scores. For example, the platform can improve users' profit scores by providing more accurate recommendations, improving the user interface, or adding interactive functions; or formulate different marketing strategies based on users' profit scores.

[0041] In step S140, the actual consumption cost progress refers to the speed at which the user actually consumes the cost on the platform, reflecting the user's consumption speed. The expected consumption cost progress refers to the speed at which the user is expected to consume the cost on the platform, reflecting the user's consumption plan. The consumption score can be calculated using the following formula: consumption score = actual consumption cost progress / expected consumption cost progress. In this way, a consumption score reflecting the user's consumption trend can be obtained.

[0042] In step S150, the health degree can be calculated using the following formula: health degree = w1×activity score + w2×income score + w3×consumption score, where w1, w2, and w3 are the weights of activity score, income score, and consumption score, respectively, and can be adjusted according to actual conditions. For example, w1, w2, and w3 are 50%, 30%, and 20%, respectively. In this way, a health degree that reflects the service quality of the recruitment service platform to users can be obtained.

[0043] In the above method, by combining multiple data sources, including recruitment behavior data, recruitment position data, and recruitment payment data, the data dimensions are greatly enriched. In particular, user behavior data, such as resume processing, job posting, and job interaction, provide direct indicators of user activity and engagement. The richness and comprehensiveness of this data helps to more fully understand users' recruitment activities, thereby providing deeper analysis and insights.

[0044] Furthermore, by comprehensively analyzing multiple data, this method can more accurately calculate the health of users. The combination of activity score, income score and consumption score takes into account the user's behavior on the platform, recruitment effect and consumption trend. These factors work together to provide a more comprehensive and accurate assessment of the user's health. This accuracy helps recruitment service platforms more effectively identify user needs, provide personalized services, and optimize user experience.

[0045] According to an embodiment of the present application, different levels are divided according to the specific numerical value of health, and different levels display lights of different colors. Among them, the higher the health, the higher the service quality of the service platform, the higher the user's service satisfaction with the service platform, and the more it indicates that the user is a high-value, high-quality user.

[0046] In this way, the recruitment service platform can provide personalized services and suggestions based on the user's health level to enhance the user experience and improve the service quality. The grading and lighting scheme is shown in Table 1 below:

[0047] Table 1

[0048] grade Health score Score range Judgement Light A 100 [75～100] Green Light B 75 [40～75) Yellow Light C 50 [25～40) red light D 25 (0～25) red light

[0049] Similarly, activity scores, income scores, consumption scores and other data can be rated according to the size of the values, thereby helping the service platform to quickly obtain information.

[0050] According to one embodiment of the present application, a job posting score is calculated based on job posting data, and the job posting score is determined based on the average number of recruiting positions per capita and a newly posted position coefficient, wherein the average number of recruiting positions per capita is determined based on the number of newly posted positions and the number of account IDs of newly posted positions in a first time period, and the newly posted position coefficient is determined based on the number of newly posted positions in a first cycle and the number of newly posted positions in a second cycle, wherein the first cycle is smaller than the second cycle.

[0051] First, determine the number of positions available per capita based on the number of new job postings and the number of account IDs that posted the new jobs in the first time period. This can be done by dividing the number of new job postings in the first time period by the number of account IDs that posted the new jobs. For example, if there are 100 new job postings in three months, and these jobs are posted by 5 different accounts, the number of positions available per capita is 20.

[0052] Secondly, the new job posting coefficient is determined based on the number of new job postings in the first period and the number of new job postings in the second period. The first period is smaller than the second period to ensure that the new job posting coefficient can reflect the recent trend of job postings. For example, if there are 50 new job postings in the first period (such as 90 days) and 150 new job postings in the second period (such as 365 days), the new job posting coefficient is 50 / 150=0.33.

[0053] Finally, determine the job posting score based on the average number of positions being recruited and the coefficient of newly released positions. For example, if the average number of positions being recruited is 20 and the coefficient of newly released positions is 0.33, the job posting score is 20*0.33=6.6. Alternatively, use the scoring method to assign different scores based on the numerical values ​​of the number of positions being recruited and the coefficient of newly released positions. For example, if the average number of positions being recruited is 20, 100 points are assigned, and the coefficient of newly released positions is 0.33, 1 is assigned, and the final job posting score is 100×1=100, and the release level is a. The specific assignment scheme is shown in Table 2 below:

[0054] Table 2

[0055]

[0056] According to one embodiment of the present application, a resume processing score is calculated based on the resume processing data, and the resume processing score is determined based on the resume processing rate of the target user in the third time period and the resume processing rate of the region where the target user is located in the third time period.

[0057] First, the resume processing rate of the target user is calculated based on the resume processing data of the target user in the third time period. The calculation formula of the resume processing rate is: the number of resumes processed in the third time period / the number of resumes submitted in the third time period*100%. Among them, the number of resumes processed in the third time period is the number of resumes marked as interested A, interested B, invited for interview A or unsuitable among the resumes submitted in the third time period. The number of resumes submitted in the third time period is the number of resumes submitted in the third time period. Among them, the third time period is 3-15 days.

[0058] Secondly, according to the resume processing data of the target user's area in the third time period, the resume processing rate (market processing rate) is calculated. The resume processing rate of the target user's area in the third time period can be calculated by obtaining the resume processing volume and resume delivery volume in the target user's area in the third time period.

[0059] Finally, the resume processing score is determined based on the resume processing rate of the target user in the third time period and the resume processing rate of the target user's region in the third time period. For example, if the resume processing rate of the target user is 30% and the resume processing rate of the market is 25%, it can be considered that the resume processing efficiency of the target user is higher than the average level, and thus a higher resume processing score is given.

[0060] The specific scheme for determining different levels based on resume processing scores is shown in Table 3 below:

[0061] Table 3

[0062]

[0063]

[0064] According to one embodiment of the present application, a job interaction score is calculated based on the job interaction data, and the job interaction score is determined based on the sum of the number of chats initiated and resume downloads by the target user in a fourth time period (referred to as the number of chats + the number of downloads) and the sum of the number of chats initiated and resume downloads in the region where the target user is located in the fourth time period (referred to as X).

[0065] The number of initiated chats is the number of active chat sessions of the user, and the number of downloaded resumes includes the sum of the number of resume downloads and telephone communications. The job interaction score and job interaction level are determined according to the following Table 4. The fourth time period is 1-3 months. The region where the target user is located can be divided into prefecture-level administrative regions (such as Shanghai).

[0066] Table 4

[0067]

[0068] According to one embodiment of the present application, the account login score is calculated based on the account login data, and the account login score is determined based on the cumulative number of active days of the user in the fifth time period and the number of account IDs of the user. Specifically, the cumulative number of active days of the user in the fifth time period is divided by the number of account IDs of the user to obtain the average login value of each account in the fifth time period. The fifth time period is 1-3 months. The account login score and account login level are determined using the following Table 5.

[0069] Table 5

[0070]

[0071] According to one embodiment of the present application, the active score is determined based on the weighted sum of the job posting score, resume processing score, job interaction score and account login score. For example: active score = q1 × resume processing score + q2 × job posting score + q3 × job interaction score + q4 × account login score, where q1, q2, q3 and q4 are the weights of the resume processing score, job posting score, job interaction score and account login score, respectively, and can be adjusted according to actual conditions. For example, q1, q2, q3 and q4 are 40%, 30%, 20% and 10% respectively.

[0072] Figure 2 is a flow chart of the method for calculating the revenue score in step S130. Figure 2 As shown, the method includes:

[0073] Step S131, comparing the target user's handshake volume with the industry average handshake volume to determine a handshake score, wherein the handshake volume is the average handshake volume of multiple positions posted by the target user in a paid manner in the second time period, and the industry average handshake volume is the average handshake volume of all users posting positions in a paid manner in the second time period or the average handshake volume of all users posting positions in a paid manner in the second time period;

[0074] Step S132, determining a handshake rate coefficient according to the handshake rate of target users posting positions in a paid manner within the second time period, wherein the handshake rate is proportional to the handshake rate coefficient;

[0075] Step S133: determining the target user's revenue score according to the product of the handshake score and the handshake rate coefficient.

[0076] In step S131, the user's handshake volume is the number of handshakes for the positions posted by the user in a paid manner during the second time period. The handshake volume is the number of consensus reached between job seekers and recruiters. The industry handshake volume is the number of handshakes in the same industry as the user. For example, if the user is recruiting for a position in the IT industry, the industry handshake volume is the average handshake volume of all users in the IT industry.

[0077] In step S132, the handshake rate is calculated as follows: handshake rate = handshake volume in the second time period / number of valid positions posted in the second time period. The handshake rate is proportional to the handshake rate coefficient, that is, the higher the handshake rate, the higher the handshake rate coefficient.

[0078] In step S133, the calculation formula of the profit score is: profit score = handshake score (absolute value score) * handshake rate coefficient (weight coefficient).

[0079] The handshake score and handshake rate are determined using the scoring scheme shown in Table 6 below, and then the revenue score is determined:

[0080] Table 6

[0081]

[0082] This application calculates the revenue score by referring to the handshake score and handshake rate coefficient of the user under the payment method, which can comprehensively evaluate the revenue of the paying user in the recruitment service. This helps the recruitment service platform understand the needs and expectations of users, provide better services, and improve the platform's competitiveness in the market and user satisfaction.

[0083] Figure 3 is a flow chart of the method for calculating the revenue score in step S140. Figure 3 As shown, the method includes:

[0084] Step S141, calculating the actual cost consumption progress according to the ratio of the first cost to the second cost, wherein the first cost is the cost consumed by the used service opportunity, and the second cost is the total cost of purchasing the service opportunity within the validity period;

[0085] Step S142, determining the estimated consumption cost progress according to the difference between the current date and the expiration date of the validity period;

[0086] Step S143, determining the consumption score based on the actual consumption cost progress and the estimated consumption cost progress.

[0087] In step S141, the first fee is determined based on the cost of the used service opportunity. For example, if the member purchases a recruitment service of 1,000 yuan and has used 500 yuan, the first fee is 500 yuan. The second fee is determined based on the total cost of the service opportunity purchased during the validity period. For example, if the member purchases a 1,000 yuan Worry-Free service, the second fee is 1,000 yuan. The actual cost consumption progress is calculated based on the ratio of the first fee to the second fee. The calculation formula for the actual cost consumption progress is: actual cost consumption progress = first fee / second fee*100%.

[0088] In step S142, the estimated consumption cost progress is determined according to the difference between the current date and the expiration date of the validity period. The calculation formula of the estimated consumption cost progress is: estimated consumption cost progress = (expiration date of the validity period - current date) / 365 * 100%.

[0089] In step S143, the consumption score is determined according to the actual consumption progress and the estimated consumption progress. For example, if the actual consumption progress is 60% and the estimated consumption progress is 50%, it can be considered that the member's consumption progress is higher than expected, and a higher consumption score is given.

[0090] The consumption score and consumption level are determined by using the relationship between the actual consumption cost progress and the estimated consumption cost progress in Table 7 below:

[0091] Table 7

[0092]

[0093] According to one embodiment of the present application, a competition score is determined based on the number of job posts posted by the target user in the job recruitment data and the number of new job posts posted by the target user on other recruitment platforms. The competition score is used to judge the degree of user dependence on the recruitment platform.

[0094] The number of posted positions refers to positions that are open and not deleted. The number of new positions posted by target users on other recruitment platforms can be obtained through crawler technology or other data collection methods. The formula for calculating the competition score is: competition score = number of valid positions under the member / total number of competing position data * 100%. The competition level of the target user can be determined based on the size of the competition score.

[0095] According to one embodiment of the present application, the supply and demand score is calculated based on the average number of job postings in the sixth time period of the target user's job posting data and the average number of job postings in the sixth time period of the target user's region, and supply and demand are graded based on the supply and demand score. The supply and demand score can help the recruitment service platform understand the market demand for the user's job postings. Among them, the average number of job postings is

[0096] The sixth time period is 5-15 days.

[0097] According to one embodiment of the present application, a method for dividing users into different levels according to different investment amounts or asset sizes. This stratification is usually used in membership organizations or other organizations involving investment and asset management in order to better understand and serve customer groups with different investment levels. For example, investment stratification is performed based on the user's invested assets in the past 365 days. K50 refers to members whose invested assets have reached 50,000 units in the past 365 days, K10 refers to members whose invested assets have reached 10,000 units, and so on, where "K" represents thousand (i.e., thousand units of currency). NA may represent members who have no invested assets or whose invested asset data is unclear.

[0098] Figure 4 FIG. 1 is a schematic diagram of a user health nameplate structure according to an embodiment of the present application. Figure 4 As shown, the user's region (city), membership expiration time, investment stratification, competition level, supply and demand level, health score, activity level, income level and consumption level are grouped together. Among them, the competition level, supply and demand level, activity level, income level and consumption level are represented by capital letters A, B, C and D.

[0099] The health nameplate collects key information about users, such as investment stratification, competition level, supply and demand level, etc. This information not only focuses on the customer's transaction data, but also comprehensively analyzes the customer's usage behavior and interaction to generate a more comprehensive health report. Based on the information in the health nameplate, the service platform operation team can quickly understand various information about users, such as user needs, satisfaction, loyalty, etc., so that the service platform can adjust service plans, renewal strategies or other marketing strategies in a timely manner. Based on the information on the health nameplate, the recruitment service platform can provide more personalized services, such as providing different market analysis reports or recruitment suggestions for users with different competition levels.

[0100] For example, using the health score in the health plate, generate the corresponding renewal strategy:

[0101] Green light (75-100 points): priority for contract renewal and preferential policies;

[0102] Yellow light (40-75 points): follow up on user usage and provide technical support;

[0103] Red light (0-40 points): Focus on one-to-one customer care.

[0104] The generated renewal strategy is then assigned to the corresponding staff, and an execution deadline and feedback mechanism are set.

[0105] Finally, the execution feedback module tracks the execution of the renewal strategy, collects feedback from staff, and returns the feedback information to the system for optimization.

[0106] In the above renewal strategy, this application generates a personalized renewal strategy based on the customer's health score to improve the strategy's pertinence and effectiveness; in addition, the execution feedback module tracks the execution of the renewal strategy and performs dynamic optimization to improve the strategy's execution effect.

[0107] Figure 5 FIG. 1 is a schematic diagram of a structure of a device for analyzing user data in a recruitment service according to an embodiment of the present application. Figure 5 As shown, the analysis device 100 includes:

[0108] An acquisition module 110 is used to acquire recruitment data of a target user from a user recruitment database, wherein the recruitment data at least includes: recruitment behavior data, recruitment position data and recruitment payment data;

[0109] A first calculation module 120, configured to calculate an activity score of a target user according to one or more of resume processing data, job posting data, and job interaction data in the recruitment behavior data, wherein the activity score is used to indicate the activity level of the user;

[0110] The second calculation module 130 is used to calculate the target user's profit score according to the handshake score and the handshake rate coefficient in the job recruitment data, wherein the profit score is used to represent the profit performance of the user posting the job in a paid manner, the handshake score is obtained by the handshake amount of the target user posting the job in a paid manner, and the handshake rate coefficient is obtained by the handshake rate of the target user posting the job in a paid manner;

[0111] The third calculation module 140 is used to calculate the consumption score of the target user according to the actual consumption progress and the estimated consumption progress in the recruitment payment data, and the consumption score is used to represent the consumption trend of the user;

[0112] The health determination module 150 is used to determine the health of the target user according to the activity score, the income score and the consumption score. The health is used to analyze the service quality of the recruitment service platform to the user.

[0113] Figure 6 1 is a schematic diagram of the hardware structure principle of an electronic device according to an embodiment of the present invention. The electronic device can be implemented as a server or other various terminal devices, such as a desktop personal computer, a tablet computer, a laptop computer, a mobile phone, etc., including a processor 601 and a memory 602. The memory 602 stores a program instruction set. When the processor 601 executes the program instruction set on the memory 602, any of the aforementioned recommendation information generation methods is implemented.

[0114] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0115] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0116] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the recommendation information generation method provided by the present invention.

[0117] In one example, the electronic device may further include a communication interface 603 and a bus 604. The processor 601, the memory 602, and the communication interface 603 are connected via the bus 604 and communicate with each other.

[0118] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiment of the present invention.

[0119] Bus 604 includes hardware, software or both, and the components of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 604 may include one or more buses. Although the embodiment of the present invention describes and shows a specific bus, the present invention considers any suitable bus or interconnection.

[0120] The present invention also provides a computer-readable storage medium having computer program instructions stored thereon, and the computer program instructions can be executed by a processor to implement any of the recommendation information generation methods in the aforementioned embodiments. The computer-readable storage medium can be any medium that can tangibly contain or store computer-executable instructions for use by or in combination with an instruction execution system, device, and apparatus. The storage medium can be a transient computer-readable storage medium or a non-transient computer-readable storage medium. Non-transient computer-readable storage media may include, but are not limited to, magnetic storage devices, optical storage devices, and / or semiconductor storage devices. Examples of such storage devices include, for example, magnetic disks, optical disks based on CD, DVD, or Blu-ray technology, and persistent solid-state memories such as flash memory, solid-state drives, and the like.

[0121] The present invention also provides a computer program product, which includes a set of computer program instructions, and when the set of computer program instructions is executed by a processor, any one of the methods for generating recommendation information in the aforementioned embodiments is implemented. The computer program product includes but is not limited to application installation packages published on websites and application stores, application plug-ins, and small programs that can be run in certain applications.

[0122] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0123] The above embodiments are only used to illustrate the present invention, but not to limit the present invention. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the scope of the present invention. Therefore, all equivalent technical solutions should also fall within the scope of the present invention.

Claims

1. A method for analyzing user data in a recruitment service, characterized in that: include: Acquire recruitment data of target users, wherein the recruitment data at least includes: recruitment behavior data, recruitment position data and recruitment payment data; Calculate the activity score of the target user according to one or more of the resume processing data, job posting data and job interaction data in the recruitment behavior data, where the activity score is used to indicate the activity level of the user; Calculate the target user's profit score based on the handshake score and handshake rate coefficient in the job posting data, where the profit score is used to represent the profit performance of the user posting jobs in a paid manner, the handshake score is obtained by the number of handshakes of the target user posting jobs in a paid manner, and the handshake rate coefficient is obtained by the handshake rate of the target user posting jobs in a paid manner; Calculate the consumption score of the target user based on the actual consumption progress and the estimated consumption progress in the recruitment payment data, and the consumption score is used to represent the consumption trend of the user; The health of the target user is determined based on the activity score, income score and consumption score, and the health is used to analyze the service quality of the recruitment service platform to the user.

2. The analysis method according to claim 1, characterized in that A job posting score is calculated based on the job posting data, and the job posting score is determined based on the average number of recruiting jobs and a newly posted job coefficient. The average number of recruiting jobs is determined based on the number of newly posted jobs and the number of account IDs of newly posted jobs in a first time period, and the newly posted job coefficient is determined based on the number of newly posted jobs in a first period and the number of newly posted jobs in a second period, and the first period is smaller than the second period.

3. The analysis method according to claim 1, characterized in that The target user's profit score is calculated based on the handshake score and handshake rate coefficient in the job recruitment data, including: Comparing the target user's handshake volume with the industry average handshake volume to determine a handshake score, wherein the handshake volume is the number of handshakes of the target user who posted positions in a paid manner during the second time period, and the industry average handshake volume is the average number of handshakes of all users who posted positions in a paid manner during the second time period; Determine a handshake rate coefficient according to the handshake rate of target users posting positions in a paid manner within the second time period, wherein the handshake rate is proportional to the handshake rate coefficient; The revenue score of the target user is determined based on the product of the handshake score and the handshake rate coefficient.

4. The analysis method according to claim 1, characterized in that The consumption score of the target user is calculated based on the actual consumption progress and the estimated consumption progress in the recruitment payment data, including: Calculate the actual cost progress based on the ratio of the first cost to the second cost, where the first cost is the cost consumed by the used service opportunity and the second cost is the total cost of purchasing the service opportunity within the validity period; Determine the estimated consumption cost schedule based on the difference between the current date and the expiration date of the validity period; The consumption score is determined by the actual consumption cost progress and the expected consumption cost progress.

5. The analysis method according to claim 1, characterized in that A resume processing score is calculated based on the resume processing data, and the resume processing score is determined based on the resume processing rate of the target user in the third time period and the resume processing rate of the region where the target user is located in the third time period.

6. The analysis method according to claim 1, characterized in that A job interaction score is calculated based on the job interaction data, and the job interaction score is determined based on the sum of the number of chats initiated and resume downloads by the target user in the fourth time period and the sum of the number of chats initiated and resume downloads in the region where the target user is located in the fourth time period.

7. The analysis method according to claim 1, characterized in that Further including: The competition score is determined based on the number of job posts by the target user in the job posting data and the number of new job posts by the target user on other recruitment platforms. The competition score is used to judge the degree of user dependence on this recruitment platform.

8. A device for analyzing user data in a recruitment service, characterized in that: include: An acquisition module, used to acquire recruitment data of a target user, wherein the recruitment data at least includes: recruitment behavior data, recruitment position data and recruitment payment data; A first calculation module, used to calculate the activity score of the target user according to one or more of the resume processing data, the job posting data and the job interaction data in the recruitment behavior data, wherein the activity score is used to indicate the activity level of the user; The second calculation module is used to calculate the target user's profit score according to the handshake score and the handshake rate coefficient in the job recruitment data, wherein the profit score is used to represent the profit performance of the user posting the job in a paid manner, the handshake score is obtained by the handshake amount of the target user posting the job in a paid manner, and the handshake rate coefficient is obtained by the handshake rate of the target user posting the job in a paid manner; The third calculation module is used to calculate the consumption score of the target user according to the actual consumption progress and the estimated consumption progress in the recruitment payment data, and the consumption score is used to represent the consumption trend of the user; The health determination module is used to determine the health of the target user based on the activity score, income score and consumption score. The health is used to analyze the service quality of the recruitment service platform to the user.

9. An electronic device, characterized in that: It includes a processor and a memory, wherein a computer program instruction set is stored in the memory, and when the processor executes the computer program instruction set in the memory, the method for analyzing user data in the recruitment service described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: in, The computer-readable storage medium stores a computer program instruction set, and when the computer program instruction set is executed by a processor, the method for analyzing user data in a recruitment service according to any one of claims 1 to 7 is implemented.

Images