Multi-platform recruitment information management system and method based on big data

Abstract

The invention discloses a multi-platform recruitment information management system and method based on big data, and relates to the technical field of recruitment information management.The production operation state is effectively reflected through indexes such as sorting speed and calibration response, an AR simulation test is used for replacing a written certificate, more visual and operable talent qualification authentication is achieved, and the efficiency of recruitment information management is improved. The defects of information isolation, subjective evaluation and untimely verification in traditional authentication are overcome; the dynamic capability evaluation model and the elastic team formation strategy generator work cooperatively, position skills are matched according to actual production requirements, the personnel combination proportion is dynamically adjusted, and the cost and the production progress are considered, so that the problems of recruitment information fragmentation, data lag, skill evaluation deviation and the like in the background are effectively solved, and the recruitment quality is improved. And the scientificity and the accuracy of recruitment and training decision making are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of recruitment information management, and in particular to a multi-platform recruitment information management system and method based on big data. Background Art

[0002] In the current recruitment management system, when facing the employment demands of high concurrency, strong specialization, and short cycle, due to the excessive reliance on the rigid threshold of certificate authentication in the traditional keyword matching-based screening mechanism, such as setting the requirement of holding the HACCP certificate as a hard condition, a large number of skilled workers with practical experience but without certificates will be mis-screened. The deeper contradiction of this phenomenon lies in the fragmentation of data value. The behavioral data accumulated by each recruitment platform and the internal production data of enterprises, such as historical employment quality evaluation, are in an isolated state; the recruitment system can accurately match explicit labels such as academic qualifications and certificates, but it cannot screen out the high-value information of candidates in certain aspects, resulting in the fact that the employed certificate holders actually cannot adapt to the actual production line rhythm;

[0003] The distortion of this ability evaluation system directly triggers a chain reaction. To fill the personnel gap, enterprises have to adopt strategies of poaching at high prices and hiring with lowered standards, falling into a vicious cycle. Moreover, the interference of the production line caused by temporary training will cause hidden losses;

[0004] It can be seen that most of the current recruitment management solutions simplify the talent value into a combination of several static labels, ignoring the decomposability of skill elements, the transferability of experience, and the dynamic adaptability of person-job matching. When sudden demands occur, such solutions cannot effectively identify the real ability, nor can they predict potential risks through data fusion. Eventually, enterprises are forced to make difficult choices under the triple pressures of high cost, low efficiency, and high risk. This systemic failure is particularly prominent in highly volatile industries such as fresh food processing and cross-border e-commerce, becoming the key bottleneck restricting enterprises' agile response to the market. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] The present invention provides a multi-platform recruitment information management system and method based on big data to solve the problem that in the current multi-platform recruitment information management solutions, most of them simplify the talent value into a combination of several static labels, ignoring the decomposability of skill elements, the transferability of experience, and the dynamic adaptability of person-job matching. When sudden demands occur, such solutions cannot effectively identify the real ability, nor can they predict potential risks through data fusion.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a multi-platform recruitment information management system based on big data, including a data collection module, a data processing module, and a job matching module, and further including:

[0009] A multi-source data fusion engine for integrating structured resume data from recruitment platforms, operation log data from production management systems, and real-time verification data from third-party skill certification platforms;

[0010] A dynamic ability assessment model that extracts potential skill characteristics of candidates based on an unstructured data parser, where the potential skill characteristics include the recognition result of the equipment operation trajectory pattern and the simulation score of the emergency response scenario;

[0011] An elastic teaming strategy generator that automatically generates a multi-dimensional skill combination plan according to the process decomposition map of the order production line, which at least includes the ratio parameters of core certification positions, trainable positions, and experience transfer positions.

[0012] As a preferred solution of the multi-platform recruitment information management system based on big data according to the present invention, wherein: the multi-source data fusion engine includes:

[0013] A cross-platform certificate verification unit that accesses the HACCP certification database and performs validity verification, and synchronously compares the operation assessment records of the certificate holder in the past 6 months during the verification;

[0014] A production behavior conversion unit that converts the Internet of Things sensor data of food processing equipment into skill assessment indicators, including the standard deviation of sorting speed and the equipment calibration response time;

[0015] A hidden skill mining unit that analyzes the work-related video content in the candidate's third-party skill certification platform and extracts the feature vector of tool use proficiency.

[0016] As a preferred solution of the multi-platform recruitment information management system based on big data according to the present invention, wherein: in the production behavior conversion unit, the step of converting the Internet of Things sensor data of food processing equipment into skill assessment indicators includes:

[0017] Calculating the average value of the sorting speed, and the calculation formula is:

[0018]

[0019] where μ represents the average value of the sorting speed, N represents the total number of data collections, that is, the number of continuously collected sorting speed data, i represents the data index, and the value range is from 1 to N, x i represents the i-th collected sorting speed data;

[0020] Constructing a sorting speed standard deviation index based on the average value, and the formula is:

[0021]

[0022] Among them, σ represents the standard deviation of the sorting speed, N represents the total number of data acquisitions, i represents the data index, and x i represents the sorting speed data collected at the i-th time, and μ represents the average value of the sorting speed;

[0023] For the equipment calibration response time, the response duration is calculated for each calibration event by the following formula:

[0024] Among them, represents the i1-th calibration response time, represents the completion time of the i1-th calibration event, represents the start time of the i1-th calibration event;

[0025] Combining the response durations of all calibration events, the average calibration response time is obtained. The formula is:

[0026]

[0027] Among them, T c represents the average calibration response time, M represents the total number of calibration events, i2 represents the event index, represents the i1-th calibration response time.

[0028] As a preferred solution of the multi-platform recruitment information management system based on big data according to the present invention, wherein: the dynamic ability evaluation model includes:

[0029] A detachable authentication adaptation module that splits the complete qualification authentication into N independent verification sub-skill units, N≥3, and each sub-skill unit corresponds to a specific process node on the production line;

[0030] An experience migration degree calculation module that constructs a cross-position skill conversion matrix based on historical employment data and calculates the probability value of non-certified personnel meeting the position requirements through targeted training;

[0031] A real-time decay warning module that dynamically updates the skill effective coefficient by analyzing the last 3 simulation operation data of the certificate holder.

[0032] As a preferred solution of the multi-platform recruitment information management system based on big data according to the present invention, wherein: the detachable authentication adaptation module performs the following operations:

[0033] a) Establish an authentication element mapping relationship table, and map the clauses of the HACCP authentication to specific operation nodes on the production line;

[0034] b) Set alternative ability proof rules for each operation node, including:

[0035] Those without a certificate but with operation records of more than the preset hours on similar equipment are regarded as equivalent qualifications;

[0036] Achieving a set-level score in the AR simulation test can replace the requirement for a written certificate.

[0037] As an optimal solution of the multi-platform recruitment information management system based on big data described in the present invention, wherein: in the detachable authentication adaptation module, the method of achieving a set-level score in the AR simulation test to replace the requirement for a written certificate includes: score calculation, normalization processing, and threshold judgment;

[0038] The AR test adopts multiple skill evaluations and gives the original score for each skill dimension. Suppose the AR test includes k items, and the original scores of each item are respectively recorded as s j , j = 1, 2, …, k, where s j represents the original score of the jth AR test item, and k represents the number of AR test items;

[0039] On this basis, the weighted sum method is used to calculate the comprehensive score, and the formula is:

[0040]

[0041] where s raw represents the comprehensive original test score of the AR simulation, and w j represents the weight coefficient of the jth test item, reflecting the contribution of this item to the overall score;

[0042] Since the value ranges of the scores of each item may be different, a linear normalization function is introduced to standardize each score, and the normalization formula is:

[0043] where s′ j represents the normalized score of the jth test item, represents the minimum possible score of the jth test item, represents the maximum possible score of the jth test item;

[0044] Substitute the normalized scores into the comprehensive score formula to form the normalized comprehensive score s:

[0045] where s represents the normalized comprehensive score;

[0046] Set the threshold γ as the certification standard. When the comprehensive normalized score satisfies s ≥ γ, it is regarded as passing the certification test, where γ represents the set-level score threshold for judging whether the certification is up to standard.

[0047] As a preferred solution of the multi-platform recruitment information management system based on big data according to the present invention, wherein: the flexible team formation strategy generator includes:

[0048] A process capability requirement parser, which automatically identifies key control points according to the order product specification and generates a skill requirement heat map;

[0049] A hybrid team formation optimization algorithm, which matches the plasticity skill improvement direction for each non-certified person on the premise of meeting the requirement of the certification rate of core positions;

[0050] A dynamic cost constraint module, which combines the raw material price fluctuation curve and the order delivery deadline to adjust the combination ratio of personnel with different skill levels in real time.

[0051] As a preferred solution of the multi-platform recruitment information management system based on big data according to the present invention, wherein: in the dynamic cost constraint module, the unit cost of personnel at each level, the raw material price fluctuation and the urgency degree of the order delivery deadline are introduced, and the Softmax function is used to dynamically allocate the proportion of personnel at each skill level. The combination ratio is defined as:

[0052]

[0053] Wherein, p o represents the combination ratio of personnel at skill level o, r represents the total number of skill levels, λ represents the sensitivity control factor for ratio adjustment, c o represents the unit cost of personnel at skill level o, α represents the weight coefficient of the impact of raw material price fluctuation on cost, C m represents the raw material price fluctuation coefficient, β represents the weight coefficient of the impact of order urgency on cost pressure, T d represents the remaining delivery time limit of the order, and the smaller this time limit value is, the more urgent the order delivery is.

[0054] Second, the present invention provides a multi-platform recruitment information management method based on big data, including,

[0055] Step S1, constructing an industry feature enhanced database, integrating the historical production anomaly records, equipment operation manuals and industry safety specification texts of the target enterprise;

[0056] Step S2, deploying dynamic skill radar scanning, capturing the actual operation pictures of candidates through the video analysis interface, and extracting the tool holding angle stability and abnormal recognition reaction time indexes;

[0057] Step S3, generating an adaptive training path, and outputting the shortest cycle compliance training plan according to the process bottleneck points of the current production line and the skill gap map of the candidates;

[0058] Step S4, implement a hierarchical access mechanism, divide the production line into a core control area, an auxiliary operation area, and a trainable area, and dynamically allocate the working areas of personnel with different skill levels.

[0059] As a preferred solution of the multi-platform recruitment information management method based on big data described in the present invention, wherein: the generation of the adaptive training path in step S3 includes:

[0060] Establish a skill unit association map, define the prerequisite relationships and the shortest training intervals between sub-skills;

[0061] Develop an augmented reality training scenario library, including a device failure simulation module and a sudden situation stress test module;

[0062] Deploy a production capacity loss prediction model to seek an optimal balance point between training intensity and production progress.

[0063] The beneficial effects of the present invention are as follows: The present invention effectively reflects the production operation status through indicators such as sorting speed and calibration response, and uses AR simulation tests to replace written certificates to achieve more intuitive and operable talent qualification certification, making up for the shortcomings of information isolation, subjective evaluation, and untimely verification in traditional certification; The dynamic ability evaluation model and the flexible teaming strategy generator work together to match the job skills according to the actual production requirements, dynamically adjust the personnel combination ratio, taking into account costs and production progress, thereby effectively resolving problems such as fragmented recruitment information, data lag, and skill evaluation deviation in the background, and improving the scientificity and accuracy of recruitment and training decisions. Description of the Drawings

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0065] Figure 1 It is a schematic framework diagram of the multi-platform recruitment information management system in Embodiment 1.

[0066] Figure 2 It is a schematic flow diagram of the multi-platform recruitment information management method in Embodiment 1. Detailed Embodiments

[0067] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention with reference to the drawings in the specification.

[0068] In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways than those specifically described herein. Those skilled in the art can make similar generalizations without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0069] Secondly, as used herein, an "embodiment" or "embodiments" refers to specific features, structures, or characteristics that may be included in at least one implementation of the present invention. The phrase "in an embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an isolated or alternative embodiment that is mutually exclusive of other embodiments.

[0070] Embodiment 1, referring to Figure 1 and Figure 2 , this embodiment provides a multi-platform recruitment information management system based on big data, including a data acquisition module, a data processing module, and a job matching module, and further including:

[0071] A multi-source data fusion engine for integrating structured resume data from recruitment platforms, operation log data from production management systems, and real-time verification data from third-party skill certification platforms;

[0072] The multi-source data fusion engine includes:

[0073] A cross-platform certificate verification unit that accesses the HACCP certification database and performs validity verification, and synchronously compares the operation assessment records of the certificate holder in the past 6 months during the verification;

[0074] A production behavior conversion unit that converts the Internet of Things sensor data of food processing equipment into skill assessment indicators, including the standard deviation of sorting speed and the equipment calibration response time;

[0075] A latent skill mining unit that analyzes the work-related video content in the candidate's third-party skill certification platform and extracts the feature vector of tool usage proficiency;

[0076] In the production behavior conversion unit, the steps of converting the Internet of Things sensor data of food processing equipment into skill assessment indicators include:

[0077] Calculating the average value of the sorting speed, and the calculation formula is:

[0078]

[0079] where μ represents the average value of the sorting speed, N represents the total number of data acquisitions, that is, the number of continuously acquired sorting speed data, i represents the data index, and the value range is from 1 to N, and x i represents the i-th acquired sorting speed data;

[0080] Construct a standard deviation index of sorting speed based on the average value, and the formula is:

[0081]

[0082] Among them, σ represents the standard deviation of sorting speed, N represents the total number of data acquisitions, i represents the data index, and x i represents the sorting speed data collected for the i-th time, and μ represents the average value of sorting speed;

[0083] For the equipment calibration response time, the response duration is calculated for each calibration event through the following formula:

[0084] Among them, represents the i1-th calibration response time, represents the completion time of the i1-th calibration event, represents the start time of the i1-th calibration event;

[0085] Integrate the response durations of all calibration events to obtain the average calibration response time, and the formula is:

[0086]

[0087] Among them, T c represents the average calibration response time, M represents the total number of calibration events, i2 represents the event index, represents the i1-th calibration response time;

[0088] Specifically, through the processing of the Internet of Things sensor data of food processing equipment, the original data is converted into a skill evaluation index describing the operation behavior. The data processing method calculates the average value and standard deviation in statistics for the sorting speed based on the dynamic information collected by the sensor, reflecting the smooth operation of the equipment. At the same time, through the time truncation calculation of the calibration event, the response ability of the equipment is revealed; the production operation behavior is expressed by quantitative indicators;

[0089] The dynamic ability evaluation model extracts the potential skill characteristics of candidates based on an unstructured data parser. The potential skill characteristics include the recognition result of the equipment operation trajectory pattern and the simulation score of the emergency response scenario;

[0090] The dynamic ability evaluation model includes:

[0091] A detachable authentication adaptation module that splits the complete qualification authentication into N independent verification sub-skill units, N≥3, and each sub-skill unit corresponds to a specific process node on the production line;

[0092] An experience migration degree calculation module that constructs a cross-position skill conversion matrix based on historical employment data and calculates the probability value of non-certified personnel meeting the position requirements through targeted training;

[0093] The real-time decay warning module dynamically updates the skill effectiveness coefficient by analyzing the licensee's recent three simulation operation data.

[0094] The detachable authentication adaptation module performs the following operations:

[0095] a) Establish a mapping relationship table of authentication elements, mapping the clauses of HACCP certification to specific operation nodes on the production line.

[0096] b) Set alternative ability proof rules for each operation node, including:

[0097] Those without a license but with more than a preset number of hours of operation records for similar equipment are regarded as equivalent qualifications.

[0098] Achieving a set-level score in the AR simulation test can replace the requirement of a written certificate.

[0099] In the detachable authentication adaptation module, the method of achieving a set-level score in the AR simulation test to replace the requirement of a written certificate includes: score calculation, normalization processing, and threshold judgment.

[0100] The AR test uses multiple skill evaluations to give the original score for each skill dimension. Suppose the AR test contains k items, and the original scores of each item are respectively recorded as s j , j = 1, 2, …, k, where s j represents the original score of the j-th AR test item, and k represents the number of AR test items.

[0101] On this basis, the weighted sum method is used to calculate the comprehensive score, and the formula is:

[0102]

[0103] where s raw represents the comprehensive original AR simulation test score, and w j represents the weight coefficient of the j-th test item, reflecting the contribution of this item to the overall score.

[0104] Since the value ranges of the scores of each item may vary, a linear normalization function is introduced to standardize each score, and the normalization formula is:

[0105] where s′ j represents the normalized score of the j-th test item, represents the minimum possible score of the j-th test item, represents the maximum possible score of the j-th test item.

[0106] Substitute the normalized scores into the comprehensive score formula to form the normalized comprehensive score s:

[0107] where s represents the normalized comprehensive score;

[0108] Set the threshold γ as the certification standard. When the comprehensive normalized score satisfies s ≥ γ, it is regarded as passing the certification test, where γ represents the set-level scoring threshold for judging whether the certification meets the standard;

[0109] Specifically, the original scores of multiple AR test items are integrated into a comprehensive score through weighted summation, reflecting the importance of each skill dimension in the overall ability evaluation. After introducing the normalization process, the influence that may be caused by the difference in value ranges of different test items is effectively alleviated; the set threshold is used to judge whether the comprehensive score meets the certification requirements, providing an intuitive reflection of the actual operation performance of the operator;

[0110] The flexible teaming strategy generator automatically generates a multi-dimensional skill combination plan according to the process decomposition map of the order production line, which at least includes the ratio parameters of core certification positions, trainable positions, and experience transfer positions;

[0111] The flexible teaming strategy generator includes:

[0112] The process ability requirement parser automatically identifies key control points according to the order product specification and generates a skill requirement heat map;

[0113] The hybrid teaming optimization algorithm matches the plastic skill improvement direction for each non-certified person on the premise of meeting the requirement of the core position certification rate;

[0114] The dynamic cost constraint module combines the raw material price fluctuation curve and the order delivery time limit to adjust the combination ratio of personnel with different skill levels in real time;

[0115] In the dynamic cost constraint module, the unit cost of personnel at each level, the raw material price fluctuation, and the urgency of the order delivery time limit are introduced, and the Softmax function is used to dynamically allocate the proportion of personnel at each skill level. The combination ratio is defined as:

[0116]

[0117] where, p o represents the combination ratio of personnel at skill level o, r represents the total number of skill levels, λ represents the sensitivity control factor for ratio adjustment, c o represents the unit cost of personnel at skill level o, α represents the weight coefficient of the influence of raw material price fluctuation on cost, C m represents the raw material price fluctuation coefficient, β represents the weight coefficient of the influence of order urgency on cost pressure, T dIndicates the remaining delivery time limit of the order. The smaller the time limit value, the more urgent the order delivery.

[0118] Specifically, the cost factor and the order time limit are introduced into the dynamic adjustment of the personnel combination ratio here. The softmax function is used to achieve continuous adjustment of the ratio. Considering the differences in the unit cost of personnel, under the combined action of raw material price fluctuations and order delivery urgency, the combination ratio of skilled personnel corresponding to higher costs or urgent orders will be relatively reduced, while the ratio of skill levels with competitive advantages will be correspondingly increased. By updating relevant parameters in real time, the model can adapt to market dynamic changes and optimize the balance between production costs and delivery timeliness of the system.

[0119] This embodiment also provides a management method for the above-mentioned multi-platform recruitment information management system based on big data, including: Step S1, constructing an industry feature enhanced database, integrating the historical production anomaly records, equipment operation manuals and industry safety specification texts of target enterprises;

[0120] Step S2, deploying dynamic skill radar scanning, capturing the actual operation pictures of candidates through the video analysis interface, and extracting indicators such as the stability of the tool holding angle and the abnormal recognition reaction time of them;

[0121] Step S3, generating an adaptive training path, and outputting the shortest-cycle compliance training plan according to the process bottleneck points of the current production line and the skill gap map of candidates;

[0122] Step S4, implementing a hierarchical access mechanism, dividing the production line into a core control area, an auxiliary operation area and a trainable area, and dynamically allocating the working areas of personnel with different skill levels;

[0123] The generation of the adaptive training path in Step S3 includes:

[0124] Establishing a skill unit association map, defining the prerequisite relationships and the shortest training intervals between sub-skills;

[0125] Developing an augmented reality training scenario library, including an equipment failure simulation module and a sudden situation stress test module;

[0126] Deploying a production capacity loss prediction model to seek the optimal balance point between training intensity and production progress;

[0127] In summary, the detachable skill certification system, dynamic ability migration evaluation model and flexible production teaming strategy constructed by the present invention effectively break the impossible triangle of quality, cost and timeliness in the seasonal order scenario; different from the rigid screening logic of traditional systems, the present invention realizes the refined management of skill elements and the dynamic adaptation of production resources, and is particularly suitable for fields with strict requirements for operation standardization and employment flexibility such as fresh food processing and export food.

[0128] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A multi-platform recruitment information management system based on big data, comprising a data acquisition module, a data processing module, and a job matching module, characterized in that, It further includes: A multi-source data fusion engine for integrating structured resume data from recruitment platforms, operation log data from production management systems, and real-time verification data from third-party skill certification platforms; A dynamic ability assessment model that extracts potential skill characteristics of candidates based on an unstructured data parser, where the potential skill characteristics include the recognition result of the equipment operation trajectory pattern and the simulation score of the emergency response scenario; A flexible team formation strategy generator that automatically generates a multi-dimensional skill combination plan according to the process decomposition map of the order production line, which at least includes the ratio parameters of core certified positions, trainable positions, and experience transfer positions.

2. The multi-platform recruitment information management system based on big data according to claim 1, characterized in that: The multi-source data fusion engine includes: A cross-platform certificate verification unit that accesses the HACCP certification database and performs validity verification, and synchronously compares the operation assessment records of the certificate holder in the past 6 months during the verification; A production behavior conversion unit that converts the IoT sensor data of food processing equipment into skill assessment indicators, including the standard deviation of sorting speed and the equipment calibration response time; A hidden skill mining unit that analyzes the work-related video content in the candidate's third-party skill certification platform and extracts the feature vector of tool usage proficiency.

3. The multi-platform recruitment information management system based on big data according to claim 2, characterized in that: In the production behavior conversion unit, the step of converting the IoT sensor data of food processing equipment into skill assessment indicators includes: Calculating the average value of the sorting speed, and the calculation formula is: Among them, μ represents the average value of the sorting speed, N represents the total number of data acquisitions, that is, the number of sorting speed data continuously acquired, i represents the data index, and its value range is from 1 to N, and x i represents the i-th acquired sorting speed data; Constructing a standard deviation index of sorting speed based on the average value, and the formula is: Among them, σ represents the standard deviation of the sorting speed, N represents the total number of data acquisitions, i represents the data index, and x i represents the sorting speed data acquired in the i-th time, and μ represents the average value of the sorting speed; For the equipment calibration response time, the response duration is calculated by the following formula for each calibration event: Among them, represents the response time of the i1-th calibration, represents the completion time of the i1-th calibration event, represents the start time of the i1-th calibration event; Combining the response durations of all calibration events to obtain the average calibration response time, and the formula is: Among them, T c represents the average calibration response time, M represents the total number of calibration events, i2 represents the event index, represents the i1-th calibration response time.

4. The multi-platform recruitment information management system based on big data according to claim 1, characterized in that: The dynamic ability assessment model includes: A decomposable certification adaptation module that decomposes the complete qualification certification into N independent verification sub-skill units, N≥3, and each sub-skill unit corresponds to a specific process node on the production line; An experience transfer degree calculation module that constructs a cross-position skill conversion matrix based on historical employment data and calculates the probability value of non-certified personnel meeting the position requirements through targeted training; A real-time decay warning module that dynamically updates the skill effective coefficient by analyzing the candidate's last 3 simulation operation data.

5. The multi-platform recruitment information management system based on big data according to claim 4, characterized in that: The decomposable certification adaptation module performs the following operations: a) Establish a mapping relationship table of certification elements, and map the clauses of the HACCP certification to specific operation nodes on the production line; b) Set alternative ability proof rules for each operation node, including: Those without a certificate but with more than a preset number of hours of operation records of the same type of equipment are regarded as equivalent qualifications; Passing the AR simulation test and reaching the set-level score can replace the written certificate requirement.

6. The multi-platform recruitment information management system based on big data according to claim 5, characterized in that: In the decomposable certification adaptation module, the method of replacing the written certificate requirement by passing the AR simulation test and reaching the set-level score includes: score calculation, normalization processing, and threshold judgment; The AR test uses multiple skills evaluation to give the original scores for each skill dimension. Suppose the AR test contains k items, and the original scores of each item are respectively denoted as s j , j = 1, 2, …, k, where s j represents the original score of the j-th AR test item, and k represents the number of AR test items; On this basis, the weighted sum method is used to calculate the comprehensive score, and the formula is: Among them, s raw represents the comprehensive AR simulation of the original test score, and w j represents the weight coefficient of the j-th test item, reflecting the contribution of this item to the overall score; Since the value ranges of the scores of each item may vary, a linear normalization function is introduced to standardize each score, and the normalization formula is: where s′ j represents the normalized score of the j-th test item, represents the minimum possible score of the j-th test item, represents the maximum possible score of the j-th test item; Substitute the normalized score into the comprehensive score formula to form the normalized comprehensive score s: where s represents the normalized comprehensive score; Set the threshold γ as the authentication standard. When the comprehensive normalized score satisfies s≥γ, it is considered to pass the authentication test, where γ represents the set grading threshold for judging whether the authentication is up to standard.

7. The multi-platform recruitment information management system based on big data according to claim 1, characterized in that: The elastic teaming strategy generator includes: A process capability requirement analyzer that automatically identifies key control points according to the order product specification and generates a heat map of skill requirements; A hybrid teaming optimization algorithm that matches the plasticity skill improvement direction for each uncertified person on the premise of meeting the requirement of the certification rate of core positions; A dynamic cost constraint module that combines the raw material price fluctuation curve and the order delivery deadline to adjust the combination ratio of personnel with different skill levels in real time.

8. The multi-platform recruitment information management system based on big data according to claim 7, characterized in that: In the dynamic cost constraint module, the unit cost of personnel at each level, the raw material price fluctuation, and the urgency of the order delivery deadline are introduced, and the Softmax function is used to dynamically allocate the proportion of personnel at each skill level. The combination ratio is defined as: Among them, p o represents the combined ratio of personnel with skill level o, r represents the total number of skill levels, λ represents the sensitivity control factor for ratio adjustment, c o represents the unit cost of personnel with skill level o, α represents the weight coefficient of the impact of raw material price fluctuations on cost, C m represents the raw material price fluctuation coefficient, β represents the weight coefficient of the impact of order urgency on cost pressure, T d represents the remaining delivery time limit of the order. The smaller this time limit value is, the more urgent the order delivery is.

9. A multi-platform recruitment information management method based on big data, based on the multi-platform recruitment information management system according to any one of claims 1 to 8, characterized in that, Including: Step S1: Construct an industry feature enhanced database by integrating the historical production anomaly records, equipment operation manuals, and industry safety specification texts of the target enterprise; Step S2: Deploy dynamic skill radar scanning, capture the actual operation pictures of candidates through the video analysis interface, and extract the indicators of the stability of the tool holding angle and the abnormal recognition reaction time; Step S3: Generate an adaptive training path, and output the shortest cycle compliance training plan according to the process bottleneck points of the current production line and the skill gap map of the candidates; Step S4: Implement a hierarchical access mechanism, divide the production line into a core control area, an auxiliary operation area, and a trainable area, and dynamically allocate the working areas of personnel with different skill levels.

10. A method for managing recruitment information across multiple platforms based on big data as described in claim 9, characterized in that: The generation of the adaptive training path described in Step S3 includes: Establish a skill unit association map, define the prerequisite relationship and the shortest training interval between sub-skills; Develop an augmented reality training scenario library, including an equipment failure simulation module and a sudden situation stress test module; Deploy a production capacity loss prediction model to seek the optimal balance point between the training intensity and the production progress.

Images