Enterprise key post talent intelligent recommendation method based on knowledge graph

Abstract

The invention relates to an enterprise key post talent intelligent recommendation method based on a knowledge graph. The method comprises the following steps: evaluating personality characteristics of employees based on a big five personality theory; and constructing a double-index portrait system according to the character features and the key post features. And obtaining a relation sample between the character characteristics and enterprise competition, and clustering the relation sample by adopting a clustering algorithm to generate a key post game mechanism. And analyzing the resume information according to the double-index portrait system by using a large language model to obtain a potential key information corpus. And taking the potential key information corpus as knowledge graph data, performing path matching on the knowledge graph data according to a key post game mechanism, and outputting a key post talent recommendation scheme. By adopting the method, the accuracy and efficiency of key post talent recommendation can be improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent human resource management technology, and in particular to an intelligent talent recommendation method for key positions in enterprises based on knowledge graphs. Background Technology

[0002] In the wave of digital transformation, large enterprises are facing the dilemma of "information overload but inefficient talent decision-making": it is difficult to accurately match the personnel in charge with the job requirements, and traditional selection methods that rely on HR experience are no longer able to cope with the urgent staffing needs of sudden projects or key positions, while rarely considering the competitive game between peer companies. This technical method aims to achieve scientific and efficient talent recommendation for key positions during the appointment stage of senior executives or branch general managers, providing quantitative decision support for human resources departments. It is of great significance for optimizing the allocation of corporate talent resources, maximizing the release of human capital efficiency, and enhancing the core competitiveness of enterprises.

[0003] Current personnel and job profiling models are used in local enterprise human resource management, but they do not consider the crucial factor of managerial personality traits in their indicator settings. This method aims to address this issue by designing a managerial personality trait model based on the Big Five personality traits, thereby improving the comprehensiveness and accuracy of personnel profiling and constructing a new indicator system for the profiling model.

[0004] The theory of person-job matching originates from the concept of matching people with organizations. International researchers have analyzed the importance of person-job matching and continuously enriched its models using various methods, such as those based on professional competence models and psychometrics. However, published literature shows limited research on person-job matching based on knowledge graph technology. This study aims to apply knowledge graph-based intelligent recommendation algorithms to the field of human resource management planning in enterprise management. It hopes to leverage the powerful processing capabilities and clear visualization effects of knowledge graphs for unstructured data to contribute to improving enterprises' capabilities in resource allocation and decision support, thereby promoting enterprise informatization and intelligent development. Summary of the Invention

[0005] Therefore, it is necessary to provide a knowledge graph-based intelligent talent recommendation method for key enterprise positions that can improve the intelligence and efficiency of enterprise human resource allocation, addressing the aforementioned technical issues.

[0006] A knowledge graph-based intelligent talent recommendation method for key enterprise positions, the method comprising: Assess employees' personality traits based on the Big Five personality theory.

[0007] A dual-indicator profiling system is constructed based on personality traits and key job characteristics.

[0008] We obtain a sample of the relationship between personality traits and corporate competition, and use a clustering algorithm to cluster the relationship samples to generate a game mechanism for key positions.

[0009] By using a large language model and a dual-indicator profiling system to analyze resume information, a corpus of potential key information is obtained.

[0010] Using a corpus of potential key information as knowledge graph data, path matching is performed on the knowledge graph data based on the game mechanism of key positions, and a talent recommendation scheme for key positions is output.

[0011] The aforementioned knowledge graph-based intelligent talent recommendation method for key enterprise positions, grounded in the Big Five personality theory, transforms core dimensions such as openness and responsibility into quantifiable personality trait indicators. These indicators are then integrated with key characteristics required for the position, such as resilience and collaborative tendencies, to construct a dual-indicator profile system of "personality traits + job characteristics." This system overcomes the limitations of traditional subjective evaluation by achieving precise measurement of personality traits through standardized dimensions. It transforms implicit personality factors into calculable and comparable explicit data, providing a foundation for quantitative matching. Secondly, a closed-loop intelligent mechanism is constructed: first, clustering algorithms are used to cluster samples of the relationship between personality traits and enterprise competition, generating a key position game mechanism with adversarial and suppressive characteristics. This clearly defines the adaptation thresholds and checks and balances of different personality traits in job competition. Then, a large language model is used to deeply analyze resumes, extracting potential key information to form a knowledge graph. Finally, based on the game mechanism, path matching is performed on the knowledge graph to achieve intelligent decision mapping from personality traits to job requirements. This approach, which deeply integrates personality traits into the entire talent assessment process, not only solves the quantitative challenges through a dual-indicator system but also endows the system with dynamic decision-making capabilities through game theory mechanisms and knowledge graphs. It promotes the shift of person-job matching from "experience-based judgment" to "data-driven" approaches, significantly improving the accuracy and efficiency of talent recommendations for key positions and helping enterprises upgrade their human resource allocation intelligently and enhance its effectiveness. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating a knowledge graph-based intelligent talent recommendation method for key enterprise positions in one embodiment. Figure 2 Here is a diagram of the elbow rule in one embodiment; Figure 3 This is an innovative coordinated radar distribution map in one embodiment; Figure 4 This is a radar distribution diagram of a high-voltage independent type in various dimensions in one embodiment; Figure 5 This is a radar distribution diagram of the agile response type in various dimensions in one embodiment; Figure 6 This is a robust and efficient radar distribution map in various dimensions in one embodiment. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0014] In one embodiment, such as Figure 1 As shown, a knowledge graph-based intelligent talent recommendation method for key enterprise positions is provided, including the following steps: Step 102: Assess the employee's personality traits based on the Big Five personality theory.

[0015] Specifically, based on the Big Five personality theory, its five dimensions are mapped onto personality traits, establishing the characteristic dimensions of personality traits: neuroticism, extraversion, openness, agreeableness, and conscientiousness. A 5-point Likert scale (1 = strongly disagree, 2 = disagree, 3 = uncertain, 4 = agree, 5 = strongly agree) was used to design the questionnaire (as shown in Table 1). Items marked "(R)" were back-scored. The questionnaire design primarily focused on behavioral performance in corporate adversarial situations, emphasizing the crucial role of leading subordinates to complete tasks.

[0016] Table 1 Personality Trait Self-Assessment Form

[0017] Step 104: Construct a dual-indicator profile system based on personality traits and key job characteristics.

[0018] Specifically, the personnel profiling model fully considers multiple factors, and the constructed indicator system covers multiple dimensions including basic employee information, work experience, education and training, task experience, research achievements, and personality traits. The job profiling model fully integrates actual work needs, establishing an indicator system comprising seven dimensions: job requirements, professional skills, information literacy, task requirements, task experience, organizational management, and personality traits (competitors). These correspond to the personnel profiling, and each primary indicator is further subdivided into multiple secondary indicators for precise description. A knowledge graph is used to visually present the indicator system, achieving a multi-dimensional and objective description of personnel and positions, providing a solid data foundation for subsequent personnel-job matching decisions. Furthermore, personality traits are incorporated into the indicator system for the first time in the profiling model, fully considering the differences in management philosophy and corporate culture caused by the different personality traits of senior managers in competing companies. This represents the game-theoretic relationship in corporate competition, thereby improving the comprehensiveness and accuracy of the profiling model and providing support for the personnel-job matching algorithm.

[0019] Step 106: Obtain a sample of the relationship between personality traits and corporate competition, and use a clustering algorithm to cluster the relationship samples to generate a game mechanism for key positions.

[0020] Specifically, the questionnaire was distributed, and based on the sample results obtained from the feedback, the reliability of the questionnaire reached an acceptable level through Cronbach's α coefficient test (α=0.81).

[0021] Furthermore, the K-means algorithm is used to cluster personality traits. First, the sum of squared errors (SSE) within clusters corresponding to different k values ​​is calculated, and then an elbow diagram (e.g.) is plotted. Figure 2 As shown in the diagram, the elbow rule diagram clearly shows that the rate of descent decreases significantly when k is 4, indicating that the data should be clustered into 4 categories.

[0022] Furthermore, using the K-means algorithm, four points were randomly selected as centroids. Each data point was assigned to the cluster containing the nearest centroid, and the centroid of each cluster was recalculated. This process was repeated until the centroids no longer changed. Ultimately, four personality trait types were obtained: Innovative and Coordinating, High-Pressure and Autocratic, Agile and Adaptable, and Steady and Efficient (the scores for each dimension are shown in Table 2).

[0023] Table 2. Cluster Center Scores for Personality Trait Types

[0024] Furthermore, the scores for all dimensions of innovative and coordinating senior talents are relatively high, with openness and rigor being the highest. The score distribution for each dimension is shown below. Figure 3 Its core strengths lie in its ability to "break boundaries" and "integrate." Its high openness drives its rapid application of cutting-edge technologies and its adeptness at using unexpected methods; simultaneously, its high rigor ensures the feasibility of innovative solutions, indicating a relatively conservative strategy in confrontations and an emphasis on systemic thinking. Its high agreeableness manifests in excellent teamwork skills, its ability to mediate conflicts and effectively coordinate various resources; however, its high neuroticism also carries the risk of insufficient stress tolerance.

[0025] Highly assertive and autocratic senior professionals possess extremely high neuroticism and low meticulousness. Their score distribution across various dimensions is shown below. Figure 4 In the early stages of a crisis, they demonstrated exceptional control, and their highly neurotic drive for urgency enabled them to issue swift instructions in unexpected situations. Their extroverted nature supported their authoritative image, making them extremely proactive in management. However, their lack of meticulousness could lead to implementation loopholes and unnecessary economic losses.

[0026] Agile and adaptable senior professionals excel at flexible management in dynamic environments. Their score distribution across various dimensions is shown below. Figure 5Their low neuroticism allows them to maintain a stable mindset during prolonged work. Their high openness reflects their willingness to embrace methodological innovation or their belief in the advantages of new approaches, leading them to tend towards a more proactive management style. However, their low rigor may result in uncontrolled progress or inaccurate assessment of the appropriate level of detail.

[0027] Stable and efficient senior professionals possess low neuroticism, low openness, and high rigor. Their score distribution across various dimensions is shown below. Figure 6 This type of highly skilled professional demonstrates exceptional stability and execution in their work; their low neuroticism allows them to maintain emotional stability, effectively cope with pressure, and remain calm and decisive even in the face of unexpected strategic changes. Their high level of meticulousness is reflected in their extreme reliance on standardized processes. Their relatively low openness indicates a limited acceptance of innovative methods, with a preference for proven, mature solutions.

[0028] Furthermore, based on the Big Five personality trait model mentioned above, by analyzing the score differences of different types of senior talents in various dimensions, we can obtain the differences in their decision-making methods, team interactions, and execution plans. We can construct different confrontation and suppression mechanisms to reveal the game mechanism of different personality traits in corporate confrontation and achieve efficient allocation of corporate human resources.

[0029] Furthermore, based on the differences in scores across the five dimensions for different types, a personality trait suppression chain was constructed: Steady and Efficient Type → Innovative and Coordinating Type → High-Pressure and Autocratic Type → Agile and Adaptable Type → Steady and Efficient Type.

[0030] Step 108: Use a large language model to analyze resume information based on a dual-indicator profiling system to obtain a corpus of potential key information.

[0031] Step 110: Using the potential key information corpus as knowledge graph data, perform path matching on the knowledge graph data according to the key position game mechanism, and output a key position talent recommendation scheme.

[0032] The aforementioned knowledge graph-based intelligent talent recommendation method for key enterprise positions, based on the Big Five personality theory, transforms core dimensions such as openness and conscientiousness into quantifiable personality trait indicators. These indicators are then integrated with key characteristics required for the position, such as resilience and collaborative tendencies, to construct a dual-indicator profile system of "personality traits + job characteristics." This system breaks through the limitations of traditional subjective evaluation, achieving precise measurement of personality traits through standardized dimensions. It transforms implicit personality factors into calculable and comparable explicit data, providing a foundation for quantitative matching. Secondly, a closed-loop intelligent mechanism is constructed: first, clustering algorithms are used to cluster samples of the relationship between personality traits and enterprise competition, generating a key position game mechanism with adversarial suppression characteristics, clearly defining the adaptation thresholds and checks and balances of different personality traits in job competition; then, a large language model is used to deeply analyze resumes, extracting potential key information to form a knowledge graph; finally, based on the game mechanism, path matching is performed on the knowledge graph to achieve intelligent decision mapping from personality traits to job requirements. This approach, which deeply integrates personality traits into the entire talent assessment process, not only solves the quantitative challenges through a dual-indicator system but also endows the system with dynamic decision-making capabilities through game theory mechanisms and knowledge graphs. It promotes the shift of person-job matching from "experience-based judgment" to "data-driven" approaches, significantly improving the accuracy and efficiency of talent recommendations for key positions and helping enterprises upgrade their human resource allocation intelligently and enhance its effectiveness.

[0033] In one embodiment, five dimensions of employee personality traits are constructed based on the Big Five personality theory, and a Likert scale is used to design a questionnaire to assess personality traits.

[0034] In one embodiment, the Delphi method is used to determine primary and secondary indicators from objective employee data based on personality traits. These secondary indicators are then fine-tuned according to the key job characteristics of different companies to obtain specific secondary indicators. The Analytic Hierarchy Process (AHP) is used to determine the weights between the primary and secondary indicators, and a dual-indicator profiling system is constructed based on these weights.

[0035] In one embodiment, a sample of the relationship between personality traits and corporate competition is obtained based on the assessment results of personality traits assessed by a questionnaire. The sum of squared errors within the cluster corresponding to different k values ​​of the relationship sample data is calculated to determine the personality trait type based on the drawn elbow diagram. The relationship sample is then clustered according to the personality trait type to generate a key position game mechanism.

[0036] In one embodiment, based on the score differences of the personality trait cluster relationship samples in five dimensions, a personality trait suppression chain is generated as follows: the robust and efficient type suppresses the innovative and coordinated type, the innovative and coordinated type suppresses the high-pressure and autocratic type, the high-pressure and autocratic type suppresses the agile and adaptable type, and the agile and adaptable type suppresses the robust and efficient type, thus obtaining the competitive game mechanism of different personality traits in key positions.

[0037] It's worth noting that the robust and efficient type suppresses the innovative and coordinating type: The robust and efficient type, with its pleasantness and rigor, effectively coordinates team resources, emphasizes execution details and standards, and ensures stable task progress. While the innovative and coordinating type possesses strong innovative capabilities, it may neglect the standardization and stability of execution. The robust and efficient type, on the other hand, can assess the feasibility of innovative solutions and, through meticulous management and stable execution, transforms innovation into tangible results, avoiding chaos caused by excessive innovation. Therefore, it suppresses the innovative and coordinating type in terms of execution stability and risk control.

[0038] Innovative and Coordinating Types Suppress Overbearing and Autocratic Types: The high openness of innovative and coordinating types endows them with combinatorial innovation capabilities, which can break through the rigid patterns caused by the low openness of overbearing and autocratic types. Their high agreeableness-driven team cohesion can dismantle the latter's dependence on individual authority stemming from low agreeableness. When facing overbearing and autocratic types, their neuroticism scores are high, their emotions fluctuate greatly, and they are prone to impulsivity, which may lead to decision-making errors and team instability. In contrast, innovative and coordinating types can respond flexibly with innovative thinking, suppressing overbearing and autocratic types through coordination and calm analysis.

[0039] High-pressure, autocratic types suppress agile, adaptable types: High-pressure, autocratic types score higher on extroversion and neuroticism, possessing strong high-level talent qualities and interpersonal skills, enabling them to make rapid decisions under pressure. Agile, adaptable types, on the other hand, score lower on neuroticism and extroversion, and may appear conservative and hesitant under pressure. High-pressure, autocratic types, with their decisive decisions and strong high-level talent qualities, quickly adjust the team's direction, suppressing the flexibility of agile, adaptable types.

[0040] Agile and adaptable types suppress robust and efficient types: Agile and adaptable types score higher on openness, quickly adapting to new methods, flexibly responding, and adept at using situations to create favorable circumstances. Robust and efficient types, on the other hand, score lower on openness, lack innovative thinking, and tend to favor traditional methods. Agile and adaptable types utilize their ability to quickly adapt and accept new things, flexibly adjusting strategies in changing environments, breaking the conservative patterns of robust and efficient types, thus suppressing their flexibility.

[0041] In one embodiment, a large language model is used to iteratively train the features of related sentences in relational samples based on a dual-index profiling system, generating a corpus of matching relationships between key positions and employees. This corpus is then processed using a word segmentation tool and stored in a new file in the database. A Skip-Gram model is used to retrieve word vectors from the new file's matching corpus and calculate the cosine similarity between each word vector. ; in, For the i-th word vector, For the vector of the j-th word, Let be the cosine similarity between the i-th word vector and the j-th word vector. Based on the cosine similarity, the resume information is parsed to obtain a corpus of potential key information.

[0042] In one embodiment, a corpus of potential key information and preset weight information are input as knowledge graph data. The input query statement is used to perform path matching on the knowledge graph data according to a key position game mechanism. ; in, M For matching degree, R For a set of paths, P As a type of path, p For a path, w 1 represents the path p The weighting of indicators from the first-level position to the current position level. w 2 is the path p The weighting of primary indicators for each position down to specific secondary indicators. To determine the similarity correlation between indicators, w 3 is the path p The weighting of the primary indicator from employee profile to employee persona. w 4 is the path p The weights of primary indicators to specific secondary indicators for employees are assigned. Complete path information is obtained. This complete path information is then exported in JSON format using an export tool. The exported knowledge graph data is parsed to obtain the complete path information between positions and personnel, and a talent recommendation plan for key positions is output.

[0043] It's worth noting that, firstly, through expert interviews, the potential relationships between the secondary indicators of each individual profile and the secondary indicators of which job profiles existed were identified and recorded. Then, based on these identified potential relationships, a large-scale artificial intelligence model was used to generate a large number of statements describing the connections between the indicators. These, combined with work experience and personnel file data, formed a corpus of approximately 50,000 words. Finally, the corpus was preprocessed using the jieba word segmentation tool, including word segmentation, retention of indicator words, and filtering of stop words and punctuation. The processed corpus was then saved to a new file.

[0044] Furthermore, word vectors generated using the Skip-Gram model are used to measure the similarity between words by calculating the cosine similarity between the vectors. For two word vectors... v i and v j The formula for calculating cosine similarity is: ; The similarity correlation score ranges from -1 to 1; a value of 1 indicates that the two vectors are identical, while a value of -1 indicates that the two vectors are completely opposite. Therefore, the closer the correlation score is to 1, the greater the correlation between the two words. The finalized index system and weight information are input into the Neo4j database to build a knowledge graph, providing data support for subsequent matching analysis.

[0045] Furthermore, by inputting a query, all complete path information is retrieved, and the provided export tool is used to export the data into JSON format. The exported JSON file contains the nodes, relationships, and attribute information of the knowledge graph, providing a data foundation for subsequent path search and matching degree calculation. By parsing the JSON-formatted knowledge graph data, all complete paths between personnel and positions can be obtained.

[0046] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0047] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. 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 various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0048] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0049] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A knowledge graph-based intelligent talent recommendation method for key enterprise positions, characterized in that, The method includes: Assess employees' personality traits based on the Big Five personality theory; A dual-indicator profiling system is constructed based on the aforementioned personality traits and key job characteristics; Obtain a sample of the relationship between the personality traits and corporate competition, and use a clustering algorithm to cluster the sample of relationships to generate a game mechanism for key positions; Using a large language model, resume information is analyzed based on the dual-index profiling system to obtain a corpus of potential key information; Using the potential key information corpus as knowledge graph data, path matching is performed on the knowledge graph data according to the key position game mechanism to output a key position talent recommendation scheme.

2. The method according to claim 1, characterized in that, The Big Five personality theory is used to assess employee personality traits, including: Based on the Big Five personality theory, five dimensions of employee personality traits were constructed. A questionnaire was designed using the Likert scale, and the questionnaire was used to evaluate the personality traits.

3. The method according to claim 2, characterized in that, A dual-indicator profiling system is constructed based on the aforementioned personality traits and key job characteristics, including: The Delphi method is used to determine primary and secondary indicators from employees' objective data based on the aforementioned personality traits. The secondary indicators are then fine-tuned according to the key job characteristics of different companies to obtain specific secondary indicators. The weights between the primary indicators and the specific secondary indicators are determined using the analytic hierarchy process (AHP), and a dual-indicator profiling system is constructed based on these weights.

4. The method according to claim 2, characterized in that, Obtain a sample of the relationship between the personality traits and corporate competition, and use a clustering algorithm to cluster the sample of relationships to generate a game mechanism for key positions, including: Based on the evaluation results of the personality traits assessed by the questionnaire, a sample of the relationship between the personality traits and corporate competition is obtained. By calculating the sum of squared intra-cluster errors corresponding to different k values ​​of the data in the relationship sample, the personality trait type is determined according to the drawn elbow diagram. The relationship sample is clustered according to the personality trait type to generate a key position game mechanism.

5. The method according to claim 4, characterized in that, Based on the clustering of the relationship samples according to the personality trait types, a key position game mechanism is generated, including... Based on the score differences of the relationship samples in five dimensions clustered according to the personality trait types, a personality trait suppression chain is generated as follows: the robust and efficient type suppresses the innovative and coordinated type; the innovative and coordinated type suppresses the high-pressure and autocratic type; the high-pressure and autocratic type suppresses the agile and adaptable type; and the agile and adaptable type suppresses the robust and efficient type, thus obtaining the competitive game mechanism of different personality traits in key positions.

6. The method according to any one of claims 1 to 5, characterized in that, Using a large language model to analyze resume information based on the aforementioned dual-index profiling system, a corpus of potential key information is obtained, including: The large language model is used to iteratively train the features of related sentences in the relational samples according to the dual-index profiling system to generate a matching relational corpus of key positions and employees. After the matching relational corpus is processed by a word segmentation tool, it is stored in a new file in the database. The Skip-Gram model is used to retrieve the matching relationship corpus of the new file to generate word vectors, and the cosine similarity between each word vector is calculated: in, For the i-th word vector, For the vector of the j-th word, Let be the cosine similarity between the i-th word vector and the j-th word vector; Based on the cosine similarity analysis of the resume information, a corpus of potential key information is obtained.

7. The method according to claim 6, characterized in that, Using the aforementioned potential key information corpus as knowledge graph data, and performing path matching on the knowledge graph data according to the key position game mechanism to output a key position talent recommendation scheme, the method further includes: The potential key information corpus and preset weight information are input as knowledge graph data. The input query statement is then used to perform path matching on the knowledge graph data based on the key position game mechanism. in, M For matching degree, R For a set of paths, P As a type of path, p For a path, w 1 represents the path p The weighting of indicators from the first-level position to the current position level. w 2 is the path p The weighting of primary indicators for each position down to specific secondary indicators. To determine the similarity correlation between indicators, w 3 is the path p The weighting of the primary indicator from employee profile to employee persona. w 4 is the path p The weighting of primary indicators for employees down to specific secondary indicators; Obtain complete path information; After exporting the complete path information in JSON format using an export tool, the knowledge graph data exported in JSON format is parsed to obtain all complete path information between positions and personnel, and a talent recommendation scheme for key positions is output.

Images