User protocol-based employment service outsourcing intelligent management method and system

Abstract

The invention relates to the technical field of employment service outsourcing, in particular to an employment service outsourcing intelligent management method and system based on a user protocol. According to the method, the target knowledge graph is constructed and the updated association vector is generated according to the association relationship, so that the selection of outsourcing personnel is more accurate, the optimal outsourcing personnel can be dynamically matched based on specific business requirements of an enterprise, the adaptation degree of the outsourcing personnel is improved, and through the training of the weighted association vector and the standard matching prediction model, the accuracy of the outsourcing personnel is improved. The system can better cope with different business requirements, continuously optimize the matching recommendation effect of outsourcing personnel, has relatively strong self-learning and optimization capabilities, enhances the long-term adaptability of the system, can meet the existing business requirements by establishing the knowledge graph, updating the association vector and optimizing the matching prediction model, and also can meet the requirements of the outsourcing personnel. And the system can be expanded and adjusted according to specific requirements of different fields or industries, and has relatively high system adaptability and flexibility.

Description

Technical Field

[0001] The present invention relates to the technical field of labor service outsourcing, and particularly to an intelligent management method and system for labor service outsourcing based on user agreements. Background Art

[0002] With the continuous optimization of enterprise operation models, labor outsourcing has become an important resource allocation strategy in modern enterprise management. By entrusting non-core business to professional personnel of third-party suppliers, enterprises can effectively reduce operation costs, improve business execution efficiency, and concentrate resources on cultivating core competitiveness.

[0003] In the existing outsourcing model, enterprises usually establish cooperation with multiple suppliers. After the suppliers undertake the business, they assign their affiliated business personnel to perform specific tasks. However, there are significant limitations in this model. The enterprise's option to select outsourcing personnel is essentially restricted by the supplier's assignment mechanism, and it is difficult to directly match the optimal candidates dynamically according to specific business requirements. Summary of the Invention

[0004] The main object of the present invention is to provide an intelligent management method for labor service outsourcing based on user agreements, aiming to solve the technical problems in the prior art.

[0005] The present invention proposes an intelligent management method for labor service outsourcing based on user agreements, including: Obtaining outsourcing personnel data, and constructing a target knowledge graph according to the outsourcing personnel data, wherein the target knowledge graph includes multiple outsourcing personnel nodes and multiple outsourcing personnel associated nodes corresponding to each outsourcing personnel node; Obtaining corresponding association relationships according to each of the outsourcing personnel nodes and outsourcing personnel associated nodes; Generating updated association vectors between multiple outsourcing personnel associated nodes that have an association relationship with the outsourcing personnel nodes according to the target knowledge graph; Determining the actual weights between each outsourcing personnel node and multiple outsourcing personnel associated nodes according to the association relationships, and adding each actual weight to the corresponding updated association vector to obtain corresponding weighted association vectors; Training a preset matching prediction model according to multiple weighted association vectors to obtain a standard matching prediction model; Obtaining a query request, and inputting the query request into the job matching prediction model for outsourcing personnel recommendation.

[0006] Preferably, before the step of generating updated association vectors between multiple outsourcing personnel associated nodes that have an association relationship with the outsourcing personnel nodes according to the target knowledge graph, it includes: Obtain M initial node groups corresponding to each of the outsourced personnel nodes from the target knowledge graph, where the Nth initial node group includes N - 1 feature nodes associated with the outsourced personnel node, N is a positive integer and N ∈ [1, M]; Obtain the specified time, and remove the feature nodes that do not belong to the specified time from the M initial node groups corresponding to the outsourced personnel nodes, to obtain M updated node groups; Obtain feature vectors according to the feature nodes, and perform fusion processing on the feature vectors of all feature nodes in each updated node group according to the outsourced personnel node, to obtain a fusion vector.

[0007] Preferably, the step of generating an updated association vector between multiple outsourced personnel association nodes associated with the outsourced personnel node according to the target knowledge graph includes: Obtain historical outsourced personnel data and current outsourced personnel data according to the outsourced personnel data, and construct a first target knowledge graph according to the historical outsourced personnel data; Generate a first association fusion vector between multiple outsourced personnel association nodes associated with the outsourced personnel node according to the first target knowledge graph; Construct a second target knowledge graph according to the current outsourced personnel data; Generate a second association fusion vector between multiple outsourced personnel association nodes associated with the outsourced personnel node according to the second target knowledge graph; Replace the first association fusion vector in the first target knowledge graph according to each of the second association fusion vectors, to obtain a corresponding updated association vector.

[0008] Preferably, the step of replacing the first association fusion vector in the first target knowledge graph according to the second association fusion vector to obtain a corresponding updated association vector includes: Obtain multiple first entities and second entities in the first target knowledge graph and the second target knowledge graph, and obtain corresponding first relationships and second relationships according to each of the first entities and second entities; Obtain corresponding entity similarities according to each of the first entities and second entities; Obtain corresponding relationship similarities according to each of the first relationships and second relationships, and obtain corresponding entity correlations according to each of the relationship similarities and entity similarities; Obtain a total similarity according to multiple entity correlations, and obtain a difference degree between the first association fusion vector and the second association fusion vector according to the total similarity; If the difference degree is greater than a preset threshold, mark the first association fusion vector; If the difference degree is less than a preset threshold, the first associated fusion vector in the first target knowledge graph is replaced by the second associated fusion vector to obtain an updated associated vector.

[0009] Preferably, the step of inputting the query request into the job matching prediction model for recommending outsourcing personnel includes: Obtain request information according to the query request, and extract multiple requirement elements in the request information, where the requirement elements are mapped to outsourcing personnel associated nodes in the target knowledge graph; Input each of the requirement elements into the job matching prediction model to obtain an actual associated fusion vector corresponding to each of the requirement elements; Obtain corresponding association matching degrees according to each of the actual associated fusion vectors and the updated associated vector, and sort the multiple association matching degrees to obtain a matching degree sorting table; Select the outsourcing personnel associated node corresponding to the association matching degree ranked first in the matching degree sorting table as the recommended associated node; Obtain a corresponding outsourcing personnel node according to the recommended associated node, and recommend the outsourcing personnel node to the user.

[0010] Preferably, after the step of obtaining a corresponding outsourcing personnel node according to the recommended associated node and recommending the outsourcing personnel node to the user, it further includes: Obtain a feedback result of the recommendation of the outsourcing personnel node to the user, and determine whether the feedback result reaches a preset expected value; If the feedback result reaches the preset expected value, it is determined that the result of this recommendation meets the standard; If the feedback result does not reach the preset expected value, return to the step of selecting the outsourcing personnel associated node corresponding to the association matching degree ranked first in the matching degree sorting table; Select the outsourcing personnel associated node corresponding to the association matching degree ranked second as the recommended associated node again until the feedback result reaches the preset expected value.

[0011] This application also provides an intelligent management system for labor service outsourcing based on user agreements, including: A construction module, configured to obtain outsourcing personnel data and construct a target knowledge graph according to the outsourcing personnel data, where the target knowledge graph includes multiple outsourcing personnel nodes and multiple outsourcing personnel associated nodes corresponding to each outsourcing personnel node; An acquisition module, configured to obtain corresponding association relationships according to each of the outsourcing personnel nodes and the outsourcing personnel associated nodes; A generation module, configured to generate updated association vectors between multiple outsourcing personnel association nodes that have an association relationship with the outsourcing personnel nodes according to the target knowledge graph; A determination module, configured to determine the actual weight between each outsourcing personnel node and multiple outsourcing personnel association nodes according to the association relationship, and add each actual weight to the corresponding updated association vector to obtain a corresponding weighted association vector; A training module, configured to train a preset matching prediction model according to multiple weighted association vectors to obtain a standard matching prediction model; A recommendation module, configured to obtain a query request and input the query request into the job matching prediction model for outsourcing personnel recommendation.

[0012] Preferably, the generation module includes: A first construction unit, configured to obtain historical outsourcing personnel data and current outsourcing personnel data according to the outsourcing personnel data, and construct a first target knowledge graph according to the historical outsourcing personnel data; A first generation unit, configured to generate a first association fusion vector between multiple outsourcing personnel association nodes that have an association relationship with the outsourcing personnel nodes according to the first target knowledge graph; A second construction unit, configured to construct a second target knowledge graph according to the current outsourcing personnel data; A second generation unit, configured to generate a second association fusion vector between multiple outsourcing personnel association nodes that have an association relationship with the outsourcing personnel nodes according to the second target knowledge graph; A replacement unit, configured to replace the first association fusion vector in the first target knowledge graph with each second association fusion vector to obtain a corresponding updated association vector.

[0013] The present invention also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above intelligent management method for labor service outsourcing based on user agreements are implemented.

[0014] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above intelligent management method for labor service outsourcing based on user agreements are implemented.

[0015] The beneficial effects of the present invention are as follows: the present invention makes the selection of outsourced personnel more accurate by constructing a target knowledge graph and generating an updated association vector based on the association relationship, and can dynamically match the optimal outsourced personnel based on the specific business needs of the enterprise, thereby improving the adaptability of the outsourced personnel and avoiding the limitations of the traditional supplier assignment mechanism. Through the intelligent management system, the enterprise can select outsourced personnel more flexibly and efficiently, avoiding dependence on the supplier's single assignment mechanism, so as to better adjust personnel allocation according to business needs, improve resource utilization efficiency, directly control the selection of outsourced personnel, reduce uncertainty and information asymmetry in outsourcing services, ensure a high degree of fit between outsourced personnel and enterprise needs, and thus improve the overall quality of outsourcing services. Through the training of weighted association vectors and standard matching prediction models, the system can better It can better respond to different business needs, continuously optimize the matching and recommendation effects of outsourced personnel, has strong self-learning and optimization capabilities, and enhances the long-term adaptability of the system. The automated outsourced personnel recommendation system greatly reduces the time and energy costs of enterprises in selecting outsourced personnel and improves decision-making efficiency. With the assistance of intelligent algorithms, enterprises can make more scientific and reasonable outsourced personnel selection decisions and promote the digital transformation of enterprise management methods. By establishing knowledge graphs, updating association vectors and optimizing matching prediction models, it can not only meet existing business needs, but also expand and adjust according to the specific requirements of different fields or industries. It has strong system adaptability and flexibility, effectively solving the limitations of the supplier assignment mechanism in the traditional outsourcing model, and improving the efficiency and quality of outsourcing management through intelligent management and precise personnel matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Schematic diagram of a method flow according to an embodiment of the present invention.

[0017] Figure 2 FIG. 1 is a schematic diagram of a system structure according to an embodiment of the present invention.

[0018] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of the present application.

[0019] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0021] like Figure 1 As shown, the present application provides an intelligent management method for outsourcing employment services based on user agreements, including: S1. Obtain the data of outsourced personnel, and construct a target knowledge graph according to the data of outsourced personnel. Among them, the target knowledge graph includes multiple outsourced personnel nodes and multiple outsourced personnel associated nodes corresponding to each outsourced personnel node; S2. Obtain the corresponding association relationships according to each of the outsourced personnel nodes and the outsourced personnel associated nodes; S3. Generate updated association vectors between multiple outsourced personnel associated nodes that have an association relationship with the outsourced personnel nodes according to the target knowledge graph; S4. Determine the actual weights between each outsourced personnel node and multiple outsourced personnel associated nodes according to the association relationships, and add each actual weight to the corresponding updated association vector to obtain the corresponding weighted association vector; S5. Train a preset matching prediction model according to multiple weighted association vectors to obtain a standard matching prediction model; S6. Obtain a query request, and input the query request into the job matching prediction model for the recommendation of outsourced personnel.

[0022] As described in the above steps S1 - S6, the present invention obtains the data of outsourced personnel and constructs a target knowledge graph according to the data of outsourced personnel. Among them, the target knowledge graph includes multiple outsourced personnel nodes and multiple outsourced personnel associated nodes corresponding to each outsourced personnel node. By obtaining the data of outsourced personnel, multi-dimensional information related to outsourced personnel, such as skills, work experience, performance, etc., can be obtained. By collecting and analyzing various data of outsourced personnel, the accuracy and practicability of the knowledge graph can be ensured. By comprehensively collecting data, a basis for subsequent intelligent matching is provided, avoiding a single and static personnel selection method. Obtaining the data of outsourced personnel is the basic step of the whole process, providing necessary data support for the subsequent construction of the knowledge graph and the generation of the matching prediction model. Constructing the target knowledge graph can associate outsourced personnel with their associated nodes, which can more clearly present the relationship between outsourced personnel and business requirements. By establishing the relationship between outsourced personnel and their associated nodes, multi-dimensional characteristics of outsourced personnel (such as skills, experience, etc.) can be revealed, thus providing valuable information for intelligent recommendation and dynamic matching. The establishment of the relationship between outsourced personnel nodes and associated nodes can comprehensively reflect the capabilities and work backgrounds of outsourced personnel, avoiding the limitations of traditional static screening methods. Most of the existing technologies rely on manual judgment or simple empirical rules and cannot systematically perform intelligent matching between outsourced personnel and business requirements. Through the construction of the knowledge graph, automated and data-driven matching can be achieved; Obtain the corresponding association relationships through each outsourcer node and outsourcer association node. By obtaining the relationships between the outsourcer nodes and the association nodes, the degree of association between the capabilities of the outsourcers and the tasks can be accurately depicted. Through the detailed association relationships, it is possible to identify which outsourcers are more suitable for specific task requirements. The association relationships can be automatically extracted through data mining or machine learning algorithms without manual intervention, reducing human errors and biases. Through the clear association relationships, this kind of mismatch can be eliminated and the accuracy of selection can be improved. The acquisition of the association relationships is closely related to the construction of the knowledge graph, which provides an important basis for the subsequent generation of updated association vectors and weighted association vectors; Generate an updated association vector between multiple outsourcer association nodes that have an association relationship with the outsourcer node through the target knowledge graph. The generated updated association vector can dynamically reflect the relationship changes between the outsourcer and the association nodes, making the selection of outsourcers more flexible and accurate. To achieve more intelligent matching, the association relationships may change at different time points. By generating the updated association vector, this kind of change can be reflected in real time to ensure the timeliness and accuracy of the recommendation results. The generated updated association vector can be refined to the specific matching situation of each outsourcer node, optimizing the resource allocation. Different from the static matching method of the prior art, the present invention can more flexibly and accurately perform personnel matching according to actual needs by dynamically updating the association relationship vector. The generated updated association vector provides a basis for dynamic adjustment for the subsequent generation of weighted association vectors; Determine the actual weights between each outsourcer node and multiple outsourcer association nodes through the association relationships, and add each actual weight to the corresponding updated association vector to obtain the corresponding weighted association vector. By calculating the actual weights and generating the weighted association vector, the true degree of association between each outsourcer node and its association nodes can be accurately reflected, avoiding the problem of "equalization". The calculation of the weights can weight the association relationships according to factors such as the actual capabilities and experience of the outsourcers, making the matching results more in line with actual needs. By assigning different weights, the matching algorithm can be optimized to select the most suitable outsourcers, avoiding simple recommendations based solely on equal weights. Traditional outsourcer selection usually ignores individual differences and fails to accurately reflect the actual capabilities of each outsourcer. Through the weighting mechanism, more detailed personalized recommendations can be achieved. The generation of the weighted association vector is a further optimization of the updated association vector, making the selection of outsourcers more accurate; The standard matching prediction model is obtained by training a preset matching prediction model with multiple weighted association vectors. Training the matching prediction model can perform automated and accurate recommendations based on the relationship between outsourced personnel and tasks. By training the matching prediction model, historical data, association relationships, and weighted vectors can be effectively utilized to construct an intelligent matching system with powerful prediction capabilities. Through training with machine learning algorithms, effective matching patterns can be automatically extracted from the data without relying on manual experience. The selection of outsourced personnel in the prior art usually relies on manual rules or static models, lacking adaptability and intelligence. The present invention can greatly improve the accuracy and efficiency of selection through an intelligent prediction model. By training the model, efficient matching with query requests can be achieved; By obtaining a query request and inputting the query request into the job matching prediction model for recommending outsourced personnel, through inputting the query request and making recommendations for outsourced personnel, the system can dynamically respond to the needs of enterprises, provide personalized and accurate recommendations for outsourced personnel to enterprises. By responding to the query request, real-time matching and recommendation can be achieved, and the selection of outsourced personnel can be adjusted in a timely manner according to changes in the needs of enterprises. The query request can reflect the current specific needs of enterprises, and the outsourced personnel recommended by the system according to the model can ensure the efficient completion of tasks. Traditional methods often cannot perform dynamic personnel recommendations according to specific business needs. The present invention can respond to changes in a timely manner through an intelligent model and provide personnel recommendations that better meet the needs. The acquisition of the query request is closely related to the previous steps, and finally, a recommendation result is generated through the model to achieve accurate matching. The present invention can achieve intelligent dynamic matching of outsourced personnel, thus solving the problem that enterprises are restricted in the selection of outsourced personnel in the existing outsourcing mode, optimizing the selection mechanism of outsourced personnel, and making the matching between outsourced personnel and task requirements more accurate, flexible, and efficient. Through the relevance modeling and update based on the knowledge graph, and the training of the intelligent matching prediction model, the present invention greatly improves the automation degree of outsourced personnel selection and the accuracy of personalized recommendations, having significant technical advantages and innovativeness.

[0023] In one embodiment, before step S3 of generating an updated association vector between multiple outsourced personnel association nodes having an association relationship with an outsourced personnel node according to the target knowledge graph, it includes: S31. Obtain M initial node groups corresponding to the outsourced personnel node from the target knowledge graph according to each outsourced personnel node, where the Nth initial node group includes N - 1 feature nodes having an association relationship with the outsourced personnel node, N is a positive integer and N ∈ [1, M]; S32. Obtain a specified time, and remove the feature nodes that do not belong to the specified time from the M initial node groups corresponding to the outsourced personnel node to obtain M updated node groups; S33. Obtain a feature vector according to the feature node, and perform a fusion process on the feature vectors of all feature nodes in each updated node group according to the outsourcer node to obtain a fusion vector.

[0024] As described in the above steps S31 - S33, the present invention obtains M initial node groups corresponding to the outsourcer node from the target knowledge graph through each outsourcer node. Among them, the Nth initial node group includes N - 1 feature nodes having an associated relationship with the outsourcer node. By extracting feature nodes related to the outsourcer from the knowledge graph, relevant information such as the capabilities, experience, and historical tasks of the outsourcer can be accurately described, and a complete portrait of the outsourcer can be constructed. In this way, the enterprise can make a selection based on the real background data of the outsourcer, thereby avoiding artificial deviation or insufficient judgment. In the traditional outsourcing model, the selection of outsourcers by the enterprise is limited by the assignment of the supplier, which often fails to meet the dynamic nature of business requirements. By dynamically obtaining the feature nodes of the outsourcer, more detailed information can be provided for the subsequent matching process, enhancing the flexibility and adaptability of the selection. When obtaining the M initial node groups, the feature nodes in each initial node group can cover the relevance between the outsourcer and the task, and can provide accurate feature inputs for selection and matching. Based on the node association of the graph, the suitability of the outsourcer can be evaluated more comprehensively and dynamically. In the prior art, the selection of outsourcers mainly relies on the static assignment of the supplier, lacking a dynamic evaluation mechanism based on the knowledge graph. The present invention can highly fit the selection of outsourcers with specific business requirements, thereby improving the accuracy and matching degree of the selection, laying a foundation for subsequent time screening and feature vector fusion, providing preliminary feature data of the outsourcer, providing basic information of the outsourcer through the associated feature nodes, and providing key inputs for data update and fusion in the subsequent steps; By obtaining the specified time and removing the feature nodes that do not belong to the specified time from the M initial node groups corresponding to the outsourced personnel nodes, M updated node groups are obtained. By setting the time filtering condition, it can ensure that the feature information of each outsourced personnel is the latest and most relevant within a specific time range, avoiding interference from outdated or irrelevant information in decision-making. The capabilities and adaptabilities of outsourced personnel may change over time. For example, outsourced personnel may participate in different projects, accumulate new experiences, or have job changes. The present invention can ensure that the system selects the most relevant and latest information of outsourced personnel for the current requirements, thereby improving the accuracy of matching. The time screening parameter ensures the timeliness of the selected feature nodes by defining the time range of the feature nodes, effectively avoiding the outdated evaluation of the capabilities of outsourced personnel and ensuring a more accurate match between business requirements and outsourced personnel. Traditional evaluations of outsourced personnel usually ignore the factor of time, which may lead to the selected information no longer meeting the current requirements. By introducing a time filtering mechanism, this defect is avoided, making the selection process more precise. The initial node groups obtained in the first step are screened to obtain the latest node data related to a specific time period, providing high-quality data input for subsequent feature vector processing; Feature vectors are obtained through feature nodes. The acquisition of feature vectors can convert the actual meaning of each feature node into a data format that can be processed by a computer, and then perform subsequent data analysis and fusion. Feature vectors can accurately represent the capabilities, experiences, etc. of outsourced personnel, with highly dataized and quantifiable characteristics, facilitating subsequent analysis. Converting feature nodes into feature vectors is the basis for subsequent machine learning and data analysis, which can convert complex node data into processable numerical information, thus facilitating the effective fusion and matching of the system. In the present invention, the feature information of outsourced personnel can be converted into numerical vectors, facilitating the calculation and matching of the system, effectively reducing the deviation of manual operations, and more accurately quantifying the characteristics of outsourced personnel. Traditional evaluations of outsourced personnel rely on manual or static rule judgments, lacking in-depth quantitative analysis of the characteristics of outsourced personnel. Through feature vectorization processing, the present invention can provide higher precision and more comprehensive data support for the matching of outsourced personnel; Fuse the feature vectors of all feature nodes in each updated node group according to the outsourced personnel nodes. The fusion of feature vectors can integrate the information of multiple feature nodes, thereby obtaining a more representative vector to comprehensively express the comprehensive ability of outsourced personnel. This kind of fusion processing can improve the evaluation accuracy of the system for outsourced personnel, ensure that multi-dimensional information is comprehensively considered. Different feature nodes may reflect the abilities of outsourced personnel from different perspectives. By fusing multiple feature vectors, a more comprehensive and information-rich vector can be obtained, enhancing the accuracy of matching and multi-dimensional consideration. By fusing the feature vectors of different feature nodes, the performance and adaptability of outsourced personnel in different dimensions can be better captured, avoiding the limitations that may be brought by single-dimensional evaluation. In the prior art, the evaluation of outsourced personnel may only rely on a single dimension or a simple scoring method, lacking the ability to comprehensively consider multi-dimensional factors. However, through the fusion processing of the present invention, a more comprehensive evaluation of outsourced personnel can be carried out, thereby improving the matching effect. This method is the core part of the entire process. By fusing feature vectors, the comprehensive evaluation result of outsourced personnel is finally obtained, integrating the work results of the first three steps (initial node acquisition, time screening, feature vector transformation) to provide core data support for the final matching of outsourced personnel. By gradually analyzing the beneficial effects of the above steps, overall, the present invention can effectively solve the limitations in the existing outsourcing mode by dynamically obtaining the feature nodes of outsourced personnel, introducing a time screening mechanism, feature vectorization, and fusion processing, improving the flexibility, accuracy, and adaptability of the selection of outsourced personnel.

[0025] In one embodiment, the step S3 of generating an updated association vector between multiple outsourcing personnel association nodes associated with the outsourcing personnel node according to the target knowledge graph includes: S34. Obtain historical outsourcing personnel data and current outsourcing personnel data according to the outsourcing personnel data, and construct a first target knowledge graph according to the historical outsourcing personnel data; S35. Generate a first association fusion vector between multiple outsourcing personnel association nodes associated with the outsourcing personnel node according to the first target knowledge graph; S36. Construct a second target knowledge graph according to the current outsourcing personnel data; S37. Generate a second association fusion vector between multiple outsourcing personnel association nodes associated with the outsourcing personnel node according to the second target knowledge graph; S38. Replace the first association fusion vector in the first target knowledge graph with each second association fusion vector to obtain the corresponding updated association vector.

[0026] As described in the above steps S34 - S38, the present invention obtains historical and current outsourced personnel data through external personnel data. By obtaining historical and current outsourced personnel data, the system can conduct more comprehensive data analysis and personnel matching. It not only provides multi-dimensional information about outsourced personnel but also allows for a comprehensive assessment of their historical performance, helping to uncover more valuable data patterns of outsourced personnel. By combining historical and current data, the system can better understand aspects such as the work ability, historical task performance, task completion status, and work efficiency of outsourced personnel, providing a more accurate basis for personnel selection. Existing technologies often rely solely on the current outsourced personnel information provided by outsourcing companies while ignoring the historical data of outsourced personnel. Historical data can provide more in-depth analysis, such as judging the performance and adaptability of outsourced personnel in similar tasks. This can prevent enterprises from making wrong decisions due to incomplete or inaccurate information. This step provides the data source basis, providing data support for subsequent construction of the target knowledge graph, generation of associated fusion vectors, and update of associated vectors, and is the data input link in the entire process; Construct a first target knowledge graph based on the historical outsourced personnel data. The construction of the first target knowledge graph transforms the data of outsourced personnel into structured information, which can reveal the relevance between outsourced personnel. Through the first target knowledge graph, enterprises can more clearly see the similarities, complementarities, etc. between different outsourced personnel, which is crucial for subsequent personnel matching and optimization. The first target knowledge graph can construct the relationships and characteristics between outsourced personnel based on historical data. The construction of the first target knowledge graph provides basic data support for subsequent data processing and analysis, and can discover the potential abilities and matching values of personnel through the relationships between nodes. Existing technologies usually lack in-depth correlation analysis of outsourced personnel and cannot display the multi-dimensional relationships between outsourced personnel through a graph. Compared with traditional personnel screening methods, the graph method can more intuitively display the potential of outsourced personnel and provide more selection bases for enterprises. This step is the core of the entire process. Constructing the first target knowledge graph provides a structured information basis for subsequent steps such as generation of associated fusion vectors and update of associated vectors, ensuring the accuracy and effectiveness of subsequent steps; Generate a first associated fusion vector among multiple outsourcer associated nodes that have an associated relationship with the outsourcer node through the first target knowledge graph. By generating the first associated fusion vector, the relationship between the outsourcer and other associated nodes (such as other outsourcers or tasks) can be quantified to form a vector representation. This vectorized method makes subsequent calculations and analyses more efficient and accurate. The first associated fusion vector can focus on the actual working relationships, skill requirements, task coordination, etc. among outsourcers, avoiding simple manual screening, reducing subjective biases, and improving the matching efficiency. Traditional technologies mostly rely on manual evaluation or screening based on simple conditions, while the present invention avoids manual errors through the generation of associated vectors, enhancing the accuracy and objectivity of outsourcer selection. Generating the first associated fusion vector is for dynamic matching of outsourcers by comparing and updating the associated vectors in subsequent steps, making the selection of outsourcers more in line with the actual needs of the enterprise; Construct a second target knowledge graph based on the current outsourcer data. The second target knowledge graph, based on the current outsourcer data, can reflect the performance of the outsourcer in the current environment, task matching situations, etc. The second target knowledge graph, based on the current outsourcer data, can reflect the changes and adaptability of the outsourcer in real time. By constructing the second target knowledge graph, the enterprise can obtain a precise response to real-time task requirements. Existing technologies usually lack dynamic analysis based on the current performance of outsourcers. The present invention can dynamically respond to the actual situation of outsourcers and provide real-time optimization support through the construction of the second target knowledge graph. The construction of the second target knowledge graph corresponds to the first target knowledge graph, providing a new basis for the update of the subsequent associated fusion vector. By comparing historical and current data, the outsourcer selection strategy can be dynamically adjusted to improve the matching accuracy; Generate a second associated fusion vector among multiple outsourcer associated nodes that have an associated relationship with the outsourcer node through the second target knowledge graph. The second associated fusion vector is generated based on the second target knowledge graph, which means that this vector can accurately reflect the adaptation situation and potential capabilities of the current outsourcer in actual tasks, contributing to more dynamic adjustment of personnel matching. Through the second associated fusion vector, the enterprise can obtain personnel recommendations that are more in line with the current task requirements. The second associated fusion vector can reflect the actual working associations among personnel, avoiding the lag problems that may occur in traditional methods. Traditional outsourcer matching methods usually cannot respond to changes in task requirements in real time, while the present invention can perform precise matching in a short time through the generation of the second associated fusion vector, enhancing the utilization efficiency of outsourcers. The generation of the second associated fusion vector directly supports the update of the vector in the first target knowledge graph. By replacing the vector in the first target knowledge graph with the second associated fusion vector, the update and dynamic adjustment of the knowledge graph are ensured, making subsequent personnel matching more precise and flexible; By replacing the first associated fusion vector in the first target knowledge graph with each second associated fusion vector, the corresponding updated associated vector is obtained. By replacing the first associated fusion vector in the first target knowledge graph with the second associated fusion vector, the dynamic update of the knowledge graph can be realized, thereby improving the real-time performance and accuracy of personnel matching. The updated graph can more accurately reflect the current status and task requirements of outsourced personnel. Replacing and updating the associated vector enables the knowledge graph to continuously self-optimize, enhancing the flexibility and accuracy of outsourced personnel selection. The graphs in traditional methods are usually static and cannot be quickly updated according to the latest data. Through the dynamic update of the associated vector in the present invention, the knowledge graph can flexibly respond to changes in outsourced personnel, ensuring that the matching results are more in line with real-time requirements. This step is the comprehensive application and optimization of the foregoing steps, ensuring that the finally generated knowledge graph can accurately reflect the matching situation between the current task requirements and outsourced personnel, and providing the enterprise with the optimal personnel selection strategy.

[0027] In one embodiment, the step S38 of obtaining the corresponding updated associated vector by replacing the first associated fusion vector in the first target knowledge graph with the second associated fusion vector includes: S381. Obtain a plurality of first entities and second entities in the first target knowledge graph and the second target knowledge graph, and obtain the corresponding first relationship and second relationship according to each of the first entities and second entities; S382. Calculate and obtain the corresponding entity similarity according to each of the first entities and second entities through cosine similarity; S383. Calculate and obtain the corresponding relationship similarity according to each of the first relationship and second relationship through cosine similarity, and calculate and obtain the corresponding entity correlation according to the weighted sum of each relationship similarity and entity similarity; S384. Obtain the total similarity according to a plurality of the entity correlations, and obtain the difference degree between the first associated fusion vector and the second associated fusion vector according to the total similarity (the sum of the difference degree and the total similarity is 1); If the difference degree is greater than a preset threshold, mark the first associated fusion vector; If the difference degree is less than the preset threshold, replace the first associated fusion vector in the first target knowledge graph with the second associated fusion vector to obtain the updated associated vector.

[0028] As described in the above steps S381 - S384, the present invention obtains multiple first entities and second entities in the first target knowledge graph and the second target knowledge graph. By obtaining multiple entities, it can comprehensively and systematically compare and analyze the information in different target knowledge graphs, providing richer background information. Entities in different graphs can reflect data characteristics in different fields or different systems, providing multi - dimensional data sources for subsequent analysis. It can ensure obtaining meaningful entity data in multi - dimensional graphs, laying a foundation for subsequent similarity calculation and entity relevance analysis. By selecting multiple entities, it can ensure the comprehensiveness of calculation, avoid missing important data, and at the same time ensure the depth and breadth of comparison. Existing technologies often focus on entities in a single graph, lacking cross - graph entity comparison and being difficult to comprehensively reflect the relevance between different fields. This method makes up for the deficiencies of existing technologies through cross - graph entity selection. The acquisition of entities is the basis of the whole process, and the subsequent calculation of relationship similarity, entity similarity and relevance is based on this. By ensuring the accurate acquisition of entities, the accuracy of subsequent analysis can be improved; And obtain corresponding first relationships and second relationships according to each first entity and second entity. By clarifying the relationships between the first entity and the second entity, their internal connections can be deeply explored, which helps to accurately conduct similarity analysis. By extracting the upstream - downstream relationships, dependency relationships, etc. between entities, it helps to conduct detailed comparison and analysis in subsequent steps, ensuring the integrity of relationship information. It is the link connecting entity to entity. By obtaining the corresponding relationships, the connections between entities can be deeply understood, providing more detailed parameters for similarity calculation. Obtaining the corresponding relationships helps to avoid incorrect matching or overly general similarity evaluation, improving the accuracy of calculation. In traditional knowledge graph analysis, the subtle relationship differences between entities may be ignored, resulting in inaccurate analysis results. This method improves the comparability and analysis depth of graph data by clarifying relationships, is closely related to the first step, and the obtained relationship data is the basis for subsequent similarity calculation and relevance evaluation. Relationship information can further refine the entity - to - entity similarity calculation process; The corresponding entity similarity is obtained through each first entity and second entity. Through the quantitative evaluation of entity similarity, it provides a numerical basis for subsequent correlation analysis, avoiding subjective errors. The evaluation of entity similarity can reveal potential connections between different fields, providing data support for optimizing decisions. The similarity evaluation can intuitively reflect the similarity degree between entities, providing a quantitative basis for relevance judgment. By introducing the calculation of similarity, it avoids the uncertainty of manual intervention and judgment. Entity similarity provides a measurable standard, enabling systematic comparison of different entities and reflecting the potential associations in the graph. Traditional methods often neglect the subtle similarity evaluation across graphs and domains, easily leading to underestimation or overestimation of relevance. Through this step, the similarity between different entities can be calculated and compared more accurately. This step is closely related to the previous entity acquisition and relationship analysis, providing an important basis for subsequent relevance evaluation and the update of fusion vectors; The corresponding relationship similarity is obtained through each first relationship and second relationship. The evaluation of relationship similarity makes the analysis more detailed, enabling quantification of the strength of similar relationships in different graphs and further optimizing the effect of knowledge fusion. Relationship similarity can help determine whether two relationships are similar in function and structure, which is a key factor in relationship matching. By calculating relationship similarity, it ensures that the subsequent knowledge fusion process is more accurate. The quantification of similarity can avoid ambiguity and improve the accuracy of the system in dealing with complex relationships. Existing methods usually neglect the impact of relationship matching on the overall analysis, while this method improves the efficiency and accuracy of graph integration by accurately evaluating relationship similarity, closely cooperating with entity similarity analysis. Through relationship similarity, the similarity matching is further optimized, providing a basis for subsequent adjustment of fusion vectors and calculation of difference degrees; The corresponding entity relevance is obtained according to each relationship similarity and entity similarity. Combining relationship similarity with entity similarity can comprehensively consider the influence of two dimensions, more comprehensively evaluating the relevance between entities. By combining the similarities of entities and relationships, the associations between entities in the graph can be described more accurately, thereby improving the quality of subsequent processing. Combining similarities from multiple dimensions can comprehensively consider the influence of different factors on entity relevance, enhancing the comprehensiveness of the analysis. Existing technologies may handle entities and relationships independently, resulting in one-sided analysis. The combined processing of this method ensures full consideration of multi-dimensional data, improving the accuracy and adaptability of the system. This is a key step in combining the similarities of the previous two dimensions (entities and relationships), providing a basis for subsequent total similarity calculation; Obtain the overall similarity through the relevance of multiple entities. The calculation of the overall similarity can comprehensively evaluate the similarity between multiple entities, providing a global perspective for further decision-making. By aggregating the relevance of multiple entities, the one-sidedness of local analysis can be avoided, ensuring the accuracy of the overall judgment. Through the aggregation of the relevance of multiple entities, a more comprehensive similarity measure can be obtained, avoiding the deviation caused by isolated similarity calculations. Traditional methods often focus on individual comparisons and lack a unified evaluation on the whole. Through this method, information from different sources can be more effectively integrated. This method is an extension of the previous entity relevance calculation, and the overall and effectiveness of the overall similarity calculation are improved by using the aggregation method; Obtain the difference degree between the first associated fusion vector and the second associated fusion vector according to the overall similarity. By calculating the difference degree, the differences between the two fusion vectors can be quantified, providing a basis for further decision-making. The calculation of the difference degree can reveal the differences between the two fusion vectors, helping to judge whether the fusion vectors need to be replaced or adjusted, improving the flexibility of the system, and providing an intuitive difference degree evaluation to avoid blindly replacing or marking vectors. In the prior art, the lack of quantitative evaluation of vector differences makes it impossible to accurately judge when the vectors need to be updated, while this step can provide a reasonable basis for adjustment. The calculation of the difference degree depends on the evaluation of the overall similarity, ensuring that the judgment basis for replacement or marking has sufficient logical support; If the difference degree is greater than the preset threshold, mark the first associated fusion vector. If the difference degree is less than the preset threshold, replace the first associated fusion vector in the first target knowledge graph with the second associated fusion vector to obtain an updated associated vector. Through intelligent judgment using the preset threshold, the vector fusion result can be automatically adjusted, reducing the need for manual intervention. Through threshold setting, it can be intelligently judged whether to replace or mark the vector according to the difference degree, thereby improving the dynamic adaptability and accuracy of the system. The preset threshold provides a flexible adjustment mechanism that can be customized according to actual needs, enhancing the versatility and adjustability of the method. The prior art usually lacks an automatic adjustment mechanism and relies on manual decision-making, while this step improves the automation and adaptability of the system through intelligent processing. According to the difference degree judgment, it is further determined whether to replace or mark, which is closely related to the previous similarity calculation and overall similarity evaluation, providing the system with dynamic update capabilities.

[0029] In one embodiment, the step S6 of inputting the query request into the work matching prediction model for recommending outsourcing personnel includes: S61. Obtain request information according to the query request, and extract multiple requirement elements from the request information, where the requirement elements are mapped to the outsourcing personnel association nodes in the target knowledge graph; S62. Input each of the said requirement elements into the job matching prediction model to obtain the actual associated fusion vector corresponding to each of the said requirement elements; S63. Calculate and obtain the corresponding association matching degree through cosine similarity based on each of the said actual associated fusion vectors and the updated association vector, and sort the multiple association matching degrees to obtain a matching degree ranking list; S64. Select the outsourcing personnel association node corresponding to the association matching degree ranked first from the said matching degree ranking list as the recommended association node; S65. Obtain the corresponding outsourcing personnel node according to the said recommended association node, and recommend to the user according to the said outsourcing personnel node.

[0030] As described in the above steps S61 - S65, the present invention obtains request information through a query request. By obtaining the request information, it can ensure that the system can obtain the specific requirements of users or enterprises in real time, providing accurate basic data for the analysis of subsequent steps. By querying the request information, it can flexibly adapt to different demand scenarios, avoiding a single preset data input method, improving the universality and scalability of the system, and being closely related to the subsequent extraction of requirement elements and the input of the matching model. It ensures that the subsequent requirement elements can be effectively mapped and processed based on accurate data, and extracts multiple requirement elements from the request information. Among them, the requirement elements are mapped to the outsourcing personnel association nodes in the target knowledge graph. Extracting multiple requirement elements from the request information helps to understand user requirements more meticulously, not limited to a single requirement, improving the accuracy of requirement analysis. User requirements often include multiple aspects. Extracting multiple requirement elements can ensure that all dimensions of the requirements are comprehensively captured, avoiding ignoring some details. In the existing outsourcing mode, requirements are usually simplified to a single dimension and cannot effectively handle complex multi-dimensional requirements. However, the present invention can better match suitable candidates by extracting multiple requirement elements. The extracted requirement elements will be mapped to the outsourcing personnel nodes in the target knowledge graph and become the input of the subsequent job matching prediction model, ensuring that the subsequent steps can be effectively matched based on comprehensive requirements. By mapping the requirement elements to the outsourcing personnel association nodes in the target knowledge graph, intelligent matching can be achieved, and the associated relationships in the graph can be used to efficiently screen out the personnel matching the requirements. The knowledge graph can effectively integrate various business knowledge and personnel information, making the matching between requirements and outsourcing personnel more accurate. After the requirement elements are mapped to the knowledge graph, it provides data support for the subsequent job matching prediction model and promotes the subsequent calculation of the association matching degree; By inputting each requirement element into the job matching prediction model, the actual associated fusion vector corresponding to each requirement element is obtained. Using the job matching prediction model can dynamically judge the matching degree between the requirement element and the outsourced personnel based on historical data and algorithm prediction, thereby improving the accuracy and reliability of the matching. With the support of the prediction model, manual intervention can be reduced and the matching efficiency can be improved. The prediction model can optimize the matching strategy according to the changing requirements and market conditions. Existing technologies usually rely on static rules or manual judgment and cannot make dynamic adjustments according to the changing requirements. However, with the help of the algorithm, the job matching prediction model significantly improves the flexibility and adaptability. The output of the job matching prediction model is the actual associated fusion vector, which provides the basic data support for the subsequent calculation of the associated matching degree. The generated actual associated fusion vector is the synthesis result of multi-dimensional data, which can accurately reflect the matching situation between the requirement element and the outsourced personnel, avoiding the limitations of a single dimension. By integrating multiple feature information, the matching relationship between the requirement and the outsourced personnel can be considered more comprehensively, improving the accuracy of the matching result. Traditional methods cannot perform multi-dimensional fusion matching and usually rely on manual screening or simple rules. The actual associated fusion vector can express the matching degree between the requirement and the personnel more comprehensively. The actual associated fusion vector is closely related to the subsequent calculation of the associated matching degree and is an important input data for determining the final matching degree; The corresponding associated matching degree is obtained through each actual associated fusion vector and the updated associated vector. By calculating the associated matching degree, the fit degree between the requirement element and the outsourced personnel can be quantified, providing a scientific basis for decision-making and avoiding the deviation caused by subjective judgment. By introducing the updated associated vector, the matching strategy can be dynamically adjusted and optimized according to the actual situation, making the matching process more flexible and accurate. Existing technologies often use static matching algorithms and lack the ability of dynamic adjustment. By introducing the updated associated vector, it can be flexibly adjusted according to the new requirements and external changes. The calculation of the matching degree provides the basis for the subsequent sorting and recommendation steps, ensuring that the finally recommended outsourced personnel best meet the user's needs; Sort multiple association matching degrees to obtain a matching degree sorting table. By selecting the outsourcer association node corresponding to the first-ranked association matching degree from the matching degree sorting table as the recommended association node, the most suitable outsourcer can be quickly found through sorting, avoiding the subjective deviation in the manual screening process, making the recommendation result more objective and fair. Sorting can arrange all candidate personnel according to the matching degree priority, thus effectively screening out the best matching candidate, improving the efficiency and accuracy of the recommendation. The selection of the recommended association node ensures that the finally recommended outsourcer best meets the user's needs, thereby improving the quality of outsourcer selection, reducing unnecessary matching and adjustment. By selecting the first-ranked matching degree in the sorting, the relevance of the recommendation can be maximized, avoiding the selection of personnel with a poor matching degree. In the prior art, the selection of outsourcers mostly depends on the established rules or personnel assignment of the supplier, while the present invention makes recommendations completely based on requirements and matching degrees, with higher freedom and accuracy. The recommended association node is a key step in subsequently obtaining the outsourcer node, ensuring that the final selection of the outsourcer meets the actual requirements; Obtain the corresponding outsourcer node based on the recommended association node, and recommend to the user according to the outsourcer node. Through the finally selected outsourcer node, provide accurate personnel recommendation to help the user quickly find the most suitable outsourcer. Through the finally obtained outsourcer node, it can be ensured that the personnel given by the recommendation system is the best choice obtained according to the comprehensive matching degree algorithm, improving the efficiency and quality of the outsourcer. In the traditional technology, the selection of outsourcers is often restricted by the supplier, while the present invention can get rid of this limitation and provide more efficient personnel recommendation. The final outsourcer recommendation is the result of the whole process, reflecting the effectiveness and accuracy of the previous steps such as data processing and matching prediction. The technical solution of the present invention can effectively solve the limitations in the existing outsourcing mode, provide a dynamic matching mechanism based on requirements, avoid the limitations of supplier assignment in the traditional method, and improve the accuracy and flexibility of outsourcer selection.

[0031] In one embodiment, after the step S6 of obtaining the corresponding outsourcer node according to the recommended association node and recommending to the user according to the outsourcer node, it further includes: S66. Obtain the feedback result of the recommendation to the user based on the outsourcer node, and judge whether the feedback result reaches a preset expected value; If the feedback result reaches the preset expected value, determine that the result of this recommendation meets the standard; If the feedback result does not reach the preset expected value, return to the step of selecting the outsourcer association node corresponding to the first-ranked association matching degree from the matching degree sorting table; S67. Select the outsourcing staff association node corresponding to the second-ranked association matching degree and re-use it as the recommended association node until the feedback result reaches the preset expected value.

[0032] As described in the above steps S66 - S67, the present invention obtains the feedback result of the recommendation to the user through the outsourcing staff node. By obtaining the recommendation feedback result of the outsourcing staff node to the user, the information of the matching degree with the actual needs of the user can be obtained in real time, which provides a data basis for the subsequent adjustment of the recommendation result, ensures that each recommendation can meet the user's needs as much as possible, and thus can ensure dynamic adjustment according to the actual feedback between the outsourcing staff node and the user. Instead of relying on a static recommendation system, the recommendation result is optimized according to the real feedback of the user. The feedback result is a dynamically obtained parameter, which can be adjusted in real time according to different user groups and business types, reducing the dependence on manual work and improving the adaptability and flexibility of the system. In the prior art, the recommendation may only rely on system calculation or algorithm matching, and may not take into account the actual user feedback. However, the present invention can fundamentally improve the recommendation system by obtaining the feedback in a timely manner, making it more in line with the actual needs. Judge whether the feedback result reaches the preset expected value. If the feedback result reaches the preset expected value, it is determined that the result of this recommendation meets the standard. By comparing with the preset expected value, the quality of each recommendation is ensured to meet the standard, avoiding meaningless recommendations that waste user and system resources, and ensuring the controllability of the effect during the recommendation process. If the feedback of the recommendation does not reach the preset expected value, the system will further optimize the recommendation to avoid user dissatisfaction or mis-matching situations. The preset expected value is a standard set according to historical data and business requirements, ensuring that each recommendation is within a reasonable effect range and improving the accuracy of the recommendation. In the prior art, there may be no clear effect judgment mechanism, and it is easy to have problems with uneven recommendation effects. However, the present invention makes the recommendation more accurate through the clear setting of the expected value. This step directly determines whether to continue to execute the subsequent steps, and whether the feedback result meets the standard directly affects whether the recommendation needs to be optimized and adjusted. If the feedback result does not meet the preset expected value, return to the step of selecting the outsourcing personnel association node corresponding to the first associated matching degree in the matching degree ranking table. By selecting the outsourcing personnel association node corresponding to the second associated matching degree as the recommended association node again until the feedback result meets the preset expected value. Through the fallback selection mechanism of the matching degree ranking table, the system can quickly make a secondary recommendation based on outsourcing personnel with a higher matching degree, minimizing the occurrence of incorrect recommendations. When the feedback result does not meet the expectation, this design provides a fallback mechanism that can automatically select outsourcing personnel with a higher matching degree for a new recommendation, avoiding manual intervention and improving the matching efficiency. The matching degree ranking table ensures that each recommendation is based on the optimal matching degree ranking through multi-dimensional analysis of outsourcing personnel, and can be continuously optimized in a data-driven manner. By dynamically adjusting the ranking of recommended personnel, it ensures that each adjustment is based on the best matching degree, continuously improving the accuracy and effectiveness of the recommendation. By sequentially selecting outsourcing personnel with a higher matching degree ranking, the recommendation process has sufficient flexibility, and each adjustment can effectively improve the success rate of the recommendation, avoiding excessive ineffective recommendations. During each fallback process, the matching degree ranking table can be adjusted according to the real-time feedback result to ensure that each recommendation better meets the user's needs than the previous round of recommendation, avoiding manual repetitive operations. Compared with the existing outsourcing model, the present invention provides a more efficient way of dynamic personnel adjustment, breaking through the limitation of fixed assignment of outsourcing personnel by suppliers, enhancing the flexibility of enterprises in personnel selection, gradually adjusting the recommended personnel to best meet the user's needs, reducing the risk of mismatch, and improving the overall work efficiency and user satisfaction.

[0033] As Figure 2 shown, the present application also provides an intelligent management system for labor service outsourcing based on a user agreement, including: A construction module for obtaining outsourcing personnel data and constructing a target knowledge graph according to the outsourcing personnel data, where the target knowledge graph includes a plurality of outsourcing personnel nodes and a plurality of outsourcing personnel association nodes corresponding to each outsourcing personnel node; An acquisition module for obtaining corresponding association relationships according to each of the outsourcing personnel nodes and outsourcing personnel association nodes; A generation module for generating updated association vectors between a plurality of the outsourcing personnel association nodes having an association relationship with the outsourcing personnel nodes according to the target knowledge graph; A determination module for determining the actual weight between each outsourcing personnel node and a plurality of outsourcing personnel association nodes according to the association relationship and adding each actual weight to the corresponding updated association vector to obtain a corresponding weighted association vector; A training module for training a preset matching prediction model according to a plurality of the weighted association vectors to obtain a standard matching prediction model; A recommendation module for obtaining a query request and inputting the query request into a job matching prediction model for recommending outsourcing personnel.

[0034] In one embodiment, the generation module includes: A first construction unit for obtaining historical outsourcing personnel data and current outsourcing personnel data according to the outsourcing personnel data, and constructing a first target knowledge graph according to the historical outsourcing personnel data; A first generation unit for generating a first association fusion vector between a plurality of the outsourcing personnel association nodes having an association relationship with the outsourcing personnel node according to the first target knowledge graph; A second construction unit for constructing a second target knowledge graph according to the current outsourcing personnel data; A second generation unit for generating a second association fusion vector between a plurality of the outsourcing personnel association nodes having an association relationship with the outsourcing personnel node according to the second target knowledge graph; A replacement unit for replacing the first association fusion vector in the first target knowledge graph according to each of the second association fusion vectors to obtain a corresponding updated association vector.

[0035] It should be noted that each module and unit in the intelligent management system for labor service outsourcing based on the user agreement corresponds one by one to the steps in the intelligent management method for labor service outsourcing based on the user agreement.

[0036] As Figure 3 shown, the present application also provides a computer device, which may be a server, and its internal structure may be as Figure 3 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all data required for the process of the intelligent management method for labor service outsourcing based on the user agreement. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the intelligent management method for labor service outsourcing based on the user agreement.

[0037] Those skilled in the art can understand that Figure 3 the structure shown in

[0038] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements any one of the above-mentioned intelligent management methods for labor service outsourcing based on user agreements.

[0039] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in the present application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0040] It should be noted that in this article, the terms "including", "comprising", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, apparatus, article, or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, apparatus, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, apparatus, article, or method including that element.

[0041] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. An intelligent management method for labor service outsourcing based on user agreements, characterized in that, Including: Obtain data of outsourced personnel, and construct a target knowledge graph according to the data of outsourced personnel, where the target knowledge graph includes a plurality of outsourced personnel nodes and a plurality of outsourced personnel associated nodes corresponding to each outsourced personnel node; Obtain the corresponding association relationships according to each of the outsourced personnel nodes and the outsourced personnel associated nodes; Generate an updated association vector between a plurality of the outsourced personnel associated nodes that have an association relationship with the outsourced personnel nodes according to the target knowledge graph; Determine the actual weight between each outsourced personnel node and a plurality of outsourced personnel associated nodes according to the association relationship, and add each actual weight to the corresponding updated association vector to obtain a corresponding weighted association vector; Train a preset matching prediction model according to a plurality of the weighted association vectors to obtain a standard matching prediction model; Obtain a query request, and input the query request into the job matching prediction model for recommending outsourced personnel.

2. The intelligent management method for labor service outsourcing based on user agreement according to claim 1, characterized in that Before the step of generating an updated association vector between a plurality of the outsourced personnel associated nodes that have an association relationship with the outsourced personnel nodes according to the target knowledge graph, it includes: Obtain M initial node groups corresponding to the outsourced personnel node from the target knowledge graph according to each outsourced personnel node, where the Nth initial node group includes N - 1 feature nodes that have an association relationship with the outsourced personnel node, N is a positive integer and N ∈ [1, M]; Obtain a specified time, and remove the feature nodes that do not belong to the specified time from the M initial node groups corresponding to the outsourced personnel node to obtain M updated node groups; Obtain feature vectors according to the feature nodes, and perform fusion processing on the feature vectors of all the feature nodes in each updated node group according to the outsourced personnel node to obtain a fusion vector.

3. The intelligent management method for labor service outsourcing based on user agreement according to claim 1, characterized in that, The step of generating an updated association vector between a plurality of the outsourced personnel associated nodes that have an association relationship with the outsourced personnel nodes according to the target knowledge graph includes: Obtain historical outsourced personnel data and current outsourced personnel data according to the data of outsourced personnel, and construct a first target knowledge graph according to the historical outsourced personnel data; Generate a first association fusion vector between a plurality of the outsourced personnel associated nodes that have an association relationship with the outsourced personnel nodes according to the first target knowledge graph; Construct a second target knowledge graph according to the current outsourced personnel data; Generate a second association fusion vector between a plurality of the outsourced personnel associated nodes that have an association relationship with the outsourced personnel nodes according to the second target knowledge graph; Replace the first association fusion vector in the first target knowledge graph according to each second association fusion vector to obtain a corresponding updated association vector.

4. The intelligent management method for labor service outsourcing based on user agreement according to claim 3, characterized in that, The step of replacing the first association fusion vector in the first target knowledge graph according to the second association fusion vector to obtain a corresponding updated association vector includes: Obtain a plurality of first entities and second entities in the first target knowledge graph and the second target knowledge graph, and obtain corresponding first relationships and second relationships according to each of the first entities and second entities; Obtain the corresponding entity similarity according to each of the first entities and second entities; Obtain the corresponding relationship similarity according to each of the first relationships and the second relationships, and obtain the corresponding entity relevance according to each of the relationship similarities and entity similarities; Obtain the total similarity according to multiple entity relevances, and obtain the difference degree between the first associated fusion vector and the second associated fusion vector according to the total similarity; If the difference degree is greater than a preset threshold, mark the first associated fusion vector; If the difference degree is less than a preset threshold, replace the first associated fusion vector in the first target knowledge graph with the second associated fusion vector to obtain an updated associated vector.

5. The intelligent management method for labor service outsourcing based on user agreement according to claim 1, characterized in that, The step of inputting the query request into the job matching prediction model for recommending outsourcing personnel includes: Obtain request information according to the query request, and extract multiple requirement elements in the request information, where the requirement elements are mapped to the outsourcing personnel associated nodes in the target knowledge graph; Input each of the requirement elements into the job matching prediction model to obtain the actual associated fusion vector corresponding to each of the requirement elements; Obtain the corresponding associated matching degree according to each of the actual associated fusion vectors and the updated associated vector, and sort multiple associated matching degrees to obtain a matching degree ranking table; Select the outsourcing personnel associated node corresponding to the associated matching degree ranked first in the matching degree ranking table as the recommended associated node; Obtain the corresponding outsourcing personnel node according to the recommended associated node, and recommend to the user according to the outsourcing personnel node.

6. The intelligent management method for labor service outsourcing based on user agreement according to claim 5, characterized in that, After the step of obtaining the corresponding outsourcing personnel node according to the recommended associated node and recommending to the user according to the outsourcing personnel node, it further includes: Obtain the feedback result of the recommendation of the outsourcing personnel node to the user, and determine whether the feedback result reaches a preset expected value; If the feedback result reaches the preset expected value, determine that the result of this recommendation meets the standard; If the feedback result does not reach the preset expected value, return to the step of selecting the outsourcing personnel associated node corresponding to the associated matching degree ranked first in the matching degree ranking table; Select the outsourcing personnel associated node corresponding to the second ranked associated matching degree as the recommended associated node again until the feedback result reaches the preset expected value.

7. An intelligent management system for labor service outsourcing based on user agreements, characterized in that, It includes: A construction module for obtaining outsourcing personnel data and constructing a target knowledge graph according to the outsourcing personnel data, where the target knowledge graph includes multiple outsourcing personnel nodes and multiple outsourcing personnel associated nodes corresponding to each outsourcing personnel node; An acquisition module for obtaining the corresponding association relationship according to each of the outsourcing personnel nodes and the outsourcing personnel associated nodes; A generation module for generating an updated associated vector between multiple outsourcing personnel associated nodes having an association relationship with the outsourcing personnel node according to the target knowledge graph; A determination module for determining the actual weight between each outsourcing personnel node and multiple outsourcing personnel associated nodes according to the association relationship, and adding each actual weight to the corresponding updated associated vector to obtain the corresponding weighted associated vector; A training module for training a preset matching prediction model according to multiple weighted associated vectors to obtain a standard matching prediction model; A recommendation module for obtaining a query request and inputting the query request into a work matching prediction model for recommending outsourcing personnel.

8. The intelligent management system for labor service outsourcing based on user agreement according to claim 7, characterized in that, The generation module includes: A first construction unit for obtaining historical outsourcing personnel data and current outsourcing personnel data according to the outsourcing personnel data, and constructing a first target knowledge graph according to the historical outsourcing personnel data; A first generation unit for generating a first association fusion vector between a plurality of the outsourcing personnel association nodes having an association relationship with the outsourcing personnel node according to the first target knowledge graph; A second construction unit for constructing a second target knowledge graph according to the current outsourcing personnel data; A second generation unit for generating a second association fusion vector between a plurality of the outsourcing personnel association nodes having an association relationship with the outsourcing personnel node according to the second target knowledge graph; A replacement unit for replacing the first association fusion vector in the first target knowledge graph according to each of the second association fusion vectors to obtain a corresponding updated association vector.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images