Talent policy matching method and system based on knowledge graph

Abstract

The invention discloses a talent policy matching method and system based on a knowledge graph. The method comprises the following steps: acquiring talent policy information of a preset area; sorting and disassembling talent policies in a preset area to obtain a plurality of sub-policies, performing tagging processing on the sub-policies, and drawing a policy knowledge graph; constructing talent questionnaire information fields according to the sub-policies based on a preset matching rule; obtaining questionnaire filling information of the user side for the talent questionnaire information field; constructing a talent information knowledge graph according to the questionnaire filling information; matching the policy knowledge graph with the talent information knowledge graph to obtain an adaptive policy; and sending the adaptive policy to a user side for display. Through the big data technology, the labor work cost of talent policy matching is reduced, and the work efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically, to a talent policy matching method and system based on knowledge graph. Background Art

[0002] Talent is the driving force for corporate and urban development. More and more new talent policies are constantly being proposed, bringing pressure to the talent policy matching work. Therefore, the old model can no longer accurately match new policy information for talents, causing inconvenience to talents.

[0003] Therefore, the prior art has defects and needs to be improved urgently. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to provide a talent policy matching method and system based on knowledge graph, which can reduce the human work cost of talent policy matching and improve work efficiency.

[0005] The first aspect of the present invention provides a talent policy matching method based on a knowledge graph, comprising:

[0006] Obtain talent policy information for a preset area;

[0007] Sort out and disassemble the talent policies of the preset regions to obtain multiple sub-policies, label the sub-policies, and draw a policy knowledge map;

[0008] Based on the preset matching rules and sub-policies, the talent questionnaire information fields are constructed;

[0009] Obtain the questionnaire filling information of the talent questionnaire information field on the user side;

[0010] Build a talent information knowledge graph based on the information filled in the questionnaire;

[0011] Match the policy knowledge graph with the talent information knowledge graph to obtain the appropriate policy;

[0012] The adapted policy is sent to the user terminal for display.

[0013] In this solution, the steps of constructing the talent questionnaire information field according to the sub-policy specifically include:

[0014] Extract label features from sub-policies;

[0015] According to the label features in the sub-policy, the preset question-answer knowledge base is searched to obtain the questionnaire questions corresponding to the label features;

[0016] Based on the preset review end, the questionnaire questions corresponding to the label features are reviewed. If the review is approved, the questionnaire questions corresponding to the label features are set as sub-questionnaire information fields;

[0017] The sub-questionnaire information fields are combined to obtain the talent questionnaire information field.

[0018] This plan also includes:

[0019] Number the sub-policies to obtain the sub-policy number values;

[0020] According to the number value of the sub-policy, the sub-questionnaire information field of the sub-policy is numbered to obtain the number value of the corresponding sub-questionnaire information field, and the number value of the corresponding sub-policy is associated with the number value of the sub-questionnaire information field to obtain the sub-policy and sub-questionnaire information field with the associated number value;

[0021] The associated number value is stored in the sub-policy and sub-questionnaire information fields.

[0022] In this solution, the step of numbering the sub-policies specifically includes:

[0023] Set the sub-policy number using the preset numbering rules;

[0024] Obtain the feature requirements of the sub-policy and the probability value of the label features that meet the corresponding sub-policy in the historical questionnaire filling information;

[0025] Sort the label features of the sub-policies from large to small according to the corresponding probability values, and determine the sub-number of the label features corresponding to the sub-policy;

[0026] Set the sub-policy number to the parent number of the tag feature;

[0027] The tag features are numbered according to the parent number of the corresponding tag feature and the child number of the tag feature.

[0028] In this solution, the steps of matching the policy knowledge graph with the talent information knowledge graph to obtain a matching policy specifically include:

[0029] Divide the policy knowledge graph according to different policies to obtain multiple sub-policy knowledge graphs;

[0030] Match the sub-policy knowledge graph with the talent information knowledge graph to obtain a matching sub-score;

[0031] If the matching sub-score is greater than or equal to the preset score threshold of the corresponding sub-policy, the sub-policy of the sub-policy knowledge graph corresponding to the matching sub-score is set as the corresponding policy;

[0032] Determine the corresponding sub-policy level according to whether the matching sub-score falls within a first preset score interval of the corresponding sub-policy;

[0033] Sent to the user end for display according to the adapted policy and corresponding sub-policy level.

[0034] This plan also includes:

[0035] According to the sub-policy, query the preset weight coefficient table to obtain the weight coefficient corresponding to the sub-policy;

[0036] Multiply the weight coefficient corresponding to the sub-policy by the corresponding matching sub-score to obtain the weight score of the corresponding sub-policy;

[0037] Add up the weighted scores of all sub-policies to get a comprehensive score;

[0038] According to whether the comprehensive score falls into the second preset score range of the corresponding policy, the corresponding comprehensive score level is determined;

[0039] Determine the appropriate comprehensive policy level based on the comprehensive score level;

[0040] The adapted comprehensive policy and the corresponding comprehensive policy level are sent to the user terminal for display.

[0041] In this solution, the step of matching the sub-policy knowledge graph with the talent information knowledge graph specifically includes:

[0042] Extract questionnaire filling information from the talent information knowledge graph;

[0043] According to the questionnaire filling information in the talent information knowledge graph, the questionnaire question filling data and the number value of the sub-questionnaire information field corresponding to the location of the questionnaire question filling data are obtained;

[0044] According to the number value of the sub-questionnaire information field where the data corresponding to the questionnaire question is located, determine the number value of the sub-policy that matches it;

[0045] Determine the sub-policy that matches it according to the number value of the sub-policy that matches it;

[0046] The label features in the matching sub-policy are matched with the corresponding questionnaire question filling data in the order of the numbers to determine whether the corresponding questionnaire question filling data conforms to the label features in the matching sub-policy.

[0047] The second aspect of the present invention provides a talent policy matching system based on knowledge graph, including:

[0048] Policy input module, policy arrangement module, policy knowledge map module, talent questionnaire module, questionnaire filling module, filled information arrangement module, talent knowledge map module and output module;

[0049] The policy input module is used to input talent policies and review and determine talent policies;

[0050] The policy arrangement module is used to sort out and disassemble the talent policy to obtain the sorted talent policy information;

[0051] The policy knowledge graph module is used to construct a policy knowledge graph based on the sorted talent policy data;

[0052] The talent questionnaire module is used to construct talent questionnaire information fields based on the sorted talent policy information;

[0053] The questionnaire filling module is used for the user to log in and fill in the questionnaire, obtain the questionnaire filling information, and review the questionnaire filling information;

[0054] The filled-in data sorting module is used to sort the filled-in information of the questionnaire to obtain sorted filled-in data;

[0055] The talent knowledge graph module is used to construct a talent knowledge graph based on the sorted filled-in data;

[0056] The output module is used to output the corresponding policy.

[0057] In this solution, the questionnaire filling module includes: a user login unit, a questionnaire filling unit and a questionnaire review unit;

[0058] The user login unit is used for user-side account registration, login, logout, modification and verification;

[0059] The questionnaire filling unit is used for the user to fill in the talent questionnaire information and obtain the questionnaire filling information;

[0060] The questionnaire review unit is used to review the questionnaire filling information and delete the questionnaire filling information that does not meet the specifications or is wrong.

[0061] In this solution, the output module includes: a score output unit, a score verification unit, a policy output unit, a policy verification unit and an appeal unit;

[0062] The score output unit is used to output the matching sub-score or the comprehensive score;

[0063] The score verification unit is used for the user end to check and verify the matching sub-score or the comprehensive score;

[0064] The policy output unit is used to output the corresponding policy;

[0065] The policy verification unit is used for the user end to check and verify the adapted policy;

[0066] The appeal unit is used for the user to appeal the questioned matching sub-scores, comprehensive scores and corresponding policies.

[0067] The present invention discloses a talent policy matching method and system based on knowledge graph, which reduces the human work cost of talent policy matching and improves work efficiency through big data technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A flow chart of a talent policy matching method based on knowledge graph of the present invention is shown;

[0069] Figure 2 A block diagram of a talent policy matching system based on knowledge graph of the present invention is shown. DETAILED DESCRIPTION

[0070] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0071] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0072] Figure 1 A flow chart of a talent policy matching method based on knowledge graph of the present invention is shown.

[0073] S101, obtaining talent policy information of a preset area;

[0074] S102, sorting out and disassembling the talent policies of the preset regions to obtain multiple sub-policies, labeling the sub-policies, and drawing a policy knowledge map;

[0075] S103, constructing talent questionnaire information fields based on preset matching rules and sub-policies;

[0076] S104, obtaining the questionnaire filling information of the talent questionnaire information field from the user end;

[0077] S105, constructing a talent information knowledge graph based on the information filled in the questionnaire;

[0078] S106, matching the policy knowledge graph with the talent information knowledge graph to obtain a matching policy;

[0079] S107, sending the adapted policy to the user terminal for display.

[0080] According to an embodiment of the present invention, the talent policies in each region may be different. Therefore, the talent policies have geographical restrictions. There may be many talent policies in each region at the same time. Each policy is set as a sub-policy, and the sub-policy includes label features such as policy type, issuance time, and policy validity period. If the corresponding sub-policy is a sub-policy that can independently implement talent subsidies, for example, if the sub-policy is met, the subsidy amount can be received, then the name of the corresponding sub-policy is used as a node, and the label feature of the corresponding sub-policy is used as an edge to construct a sub-policy knowledge graph of the corresponding sub-policy; if the corresponding sub-policy is not a sub-policy that can independently implement talent subsidies, then the policy that can implement talent subsidies only when multiple sub-policies are met at the same time is set as a comprehensive policy, and the comprehensive policy is composed of multiple sub-policies. The sub-policy knowledge graphs of multiple sub-policies are combined to obtain a comprehensive policy knowledge graph; the sub-policy knowledge graphs of all sub-policies are combined to obtain a policy knowledge graph.

[0081] According to an embodiment of the present invention, the step of constructing a talent questionnaire information field according to the sub-policy specifically includes:

[0082] Extract label features from sub-policies;

[0083] According to the label features in the sub-policy, the preset question-answer knowledge base is searched to obtain the questionnaire questions corresponding to the label features;

[0084] Based on the preset review end, the questionnaire questions corresponding to the label features are reviewed. If the review is approved, the questionnaire questions corresponding to the label features are set as sub-questionnaire information fields;

[0085] The sub-questionnaire information fields are combined to obtain the talent questionnaire information field.

[0086] It should be noted that the preset question-and-answer knowledge base stores various label features and corresponding questionnaire questions. For example, if the label feature is the policy validity period, the corresponding questionnaire question is a time question. The questionnaire question corresponding to the label feature is reviewed by the preset review end. If it meets the requirements, it is agreed, and the questionnaire question corresponding to the label feature is set as the sub-questionnaire information field; if the questionnaire question corresponding to the label feature does not meet the requirements, it is disagreed, and the questionnaire question corresponding to the label feature is revised.

[0087] According to an embodiment of the present invention, it also includes:

[0088] Number the sub-policies to obtain the sub-policy number values;

[0089] According to the number value of the sub-policy, the sub-questionnaire information field of the sub-policy is numbered to obtain the number value of the corresponding sub-questionnaire information field, and the number value of the corresponding sub-policy is associated with the number value of the sub-questionnaire information field to obtain the sub-policy and sub-questionnaire information field with the associated number value;

[0090] The associated number value is stored in the sub-policy and sub-questionnaire information fields.

[0091] It should be noted that both the sub-policy and the sub-questionnaire information end of the sub-policy are numbered to facilitate the targeted matching of the policy knowledge graph and the talent information knowledge graph in the later stage, so as to reduce the matching calculation amount. For example, if the sub-policy is numbered A, and the sub-questionnaire information field of the sub-policy is numbered as a, targeted matching can be achieved through number matching.

[0092] According to an embodiment of the present invention, the step of numbering the sub-policies specifically includes:

[0093] Set the sub-policy number using the preset numbering rules;

[0094] Obtain the feature requirements of the sub-policy and the probability value of the label features that meet the corresponding sub-policy in the historical questionnaire filling information;

[0095] Sort the label features of the sub-policies from large to small according to the corresponding probability values, and determine the sub-number of the label features corresponding to the sub-policy;

[0096] Set the sub-policy number to the parent number of the tag feature;

[0097] The tag features are numbered according to the parent number of the corresponding tag feature and the child number of the tag feature.

[0098] It should be noted that the numbering of the sub-policies includes numbering the label features in the sub-policies. For example, if the sub-policy is numbered A and one of the label features has a sub-number of 2, the number value of the corresponding label feature is A-2.

[0099] According to an embodiment of the present invention, the step of matching the policy knowledge graph with the talent information knowledge graph to obtain a matching policy specifically includes:

[0100] Divide the policy knowledge graph according to different policies to obtain multiple sub-policy knowledge graphs;

[0101] Match the sub-policy knowledge graph with the talent information knowledge graph to obtain a matching sub-score;

[0102] If the matching sub-score is greater than or equal to the preset score threshold of the corresponding sub-policy, the sub-policy of the sub-policy knowledge graph corresponding to the matching sub-score is set as the corresponding policy;

[0103] Determine the corresponding sub-policy level according to whether the matching sub-score falls within a first preset score interval of the corresponding sub-policy;

[0104] Sent to the user end for display according to the adapted policy and corresponding sub-policy level.

[0105] It should be noted that when a sub-policy is a separate sub-policy that can implement talent subsidies, a score threshold for the corresponding sub-policy is set. If the matching sub-score is greater than or equal to the preset score threshold of the corresponding sub-policy, it means that the corresponding user terminal meets the corresponding talent policy, and the corresponding sub-policy level is determined based on the first preset score range in which the matching sub-score falls. The higher the corresponding matching sub-score, the higher the corresponding sub-policy level, and the higher the amount of talent policy subsidy that the corresponding user terminal can get.

[0106] According to an embodiment of the present invention, it also includes:

[0107] According to the sub-policy, query the preset weight coefficient table to obtain the weight coefficient corresponding to the sub-policy;

[0108] Multiply the weight coefficient corresponding to the sub-policy by the corresponding matching sub-score to obtain the weight score of the corresponding sub-policy;

[0109] Add up the weighted scores of all sub-policies to get a comprehensive score;

[0110] According to whether the comprehensive score falls into the second preset score range of the corresponding policy, the corresponding comprehensive score level is determined;

[0111] Determine the appropriate comprehensive policy level based on the comprehensive score level;

[0112] The adapted comprehensive policy and the corresponding comprehensive policy level are sent to the user terminal for display.

[0113] It should be noted that the comprehensive score is calculated by the matching sub-scores of each sub-policy in the comprehensive policy. For example, the comprehensive policy includes two sub-policies A and B, and the weight coefficients of the two sub-policies are 1 and 0.5 respectively. If the matching sub-scores corresponding to sub-policies A and B are both 10, then the comprehensive score of the corresponding comprehensive policy is 10*1+10*0.5=15, wherein the higher the comprehensive score, the higher the corresponding comprehensive score level, and the higher the talent policy subsidy obtained by the corresponding user end. For example, the second preset score intervals are (0, 10], (10, 15], (15, 20]... wherein the second preset score interval (0, 10] corresponds to the first level of the comprehensive policy, the second preset score interval (10, 15] corresponds to the second level of the comprehensive policy, and the second preset score interval (15, 20] corresponds to the third level of the comprehensive policy.

[0114] According to an embodiment of the present invention, the step of matching the sub-policy knowledge graph with the talent information knowledge graph specifically includes:

[0115] Extract questionnaire filling information from the talent information knowledge graph;

[0116] According to the questionnaire filling information in the talent information knowledge graph, the questionnaire question filling data and the number value of the sub-questionnaire information field corresponding to the location of the questionnaire question filling data are obtained;

[0117] According to the number value of the sub-questionnaire information field where the data corresponding to the questionnaire question is located, determine the number value of the sub-policy that matches it;

[0118] Determine the sub-policy that matches it according to the number value of the sub-policy that matches it;

[0119] The label features in the matching sub-policy are matched with the corresponding questionnaire question filling data in the order of the numbers to determine whether the corresponding questionnaire question filling data conforms to the label features in the matching sub-policy.

[0120] It should be noted that the sub-policy knowledge graph and the sub-questionnaire information fields are matched in a targeted manner through the associated number value to reduce the matching calculation, and the score is set for the label feature in each sub-policy. If the information filled in the corresponding questionnaire question meets the label feature in the matching sub-policy, the score set for the corresponding label feature is recorded. For example, the label feature is whether to settle down, and the score set in the corresponding label feature is 5 points. If the user terminal agrees to settle down, the corresponding user terminal will increase 5 points in the sub-policy; if the user terminal does not agree to settle down, the corresponding user terminal will not increase the score in the label feature.

[0121] According to an embodiment of the present invention, it also includes:

[0122] Obtain information on opposing policies;

[0123] Extract policy hierarchies from opposing policy information;

[0124] According to the policy level in the opposing policy information, determine the preferential subsidies for the policy level under the corresponding policy;

[0125] Compare and analyze the corresponding preferential subsidies, determine the best preferential subsidy, and mark it;

[0126] All preferential subsidies in the opposing policies are sent to the user end, and the best discount is marked and displayed.

[0127] It should be noted that the opposing policies cannot coexist normally. For example, sub-policy A and sub-policy C cannot be enjoyed at the same time. If the user terminal selects sub-policy A, he cannot select sub-policy C. In this case, the corresponding sub-policy A and sub-policy C are set as opposing policies. The opposing policies include: opposing sub-policies, opposing comprehensive policies, opposing sub-policies and comprehensive policies; the policy level includes sub-policy level and comprehensive policy level. Different policy levels correspond to different preferential subsidies. For example, preferential subsidies include subsidy amount, help with settlement, purchase qualification, etc. The preferential subsidies are sorted according to the user terminal's wishes. For example, the purchase qualification is placed in the first place. If all preferential subsidies in the policy include the purchase qualification, the purchase qualification will be marked and displayed; further, the user terminal can also query the preferential subsidies to determine the label characteristics that the corresponding user terminal needs to meet, so as to make targeted self-adjustments.

[0128] Figure 2 A block diagram of a talent policy matching system based on knowledge graph of the present invention is shown.

[0129] like Figure 2 As shown, the second aspect of the present invention provides a talent policy matching system based on knowledge graph, including:

[0130] Policy input module, policy arrangement module, policy knowledge map module, talent questionnaire module, questionnaire filling module, filled information arrangement module, talent knowledge map module and output module;

[0131] The policy input module is used to input talent policies and review and determine talent policies;

[0132] The policy arrangement module is used to sort out and disassemble the talent policy to obtain the sorted talent policy information;

[0133] The policy knowledge graph module is used to construct a policy knowledge graph based on the sorted talent policy data;

[0134] The talent questionnaire module is used to construct talent questionnaire information fields based on the sorted talent policy information;

[0135] The questionnaire filling module is used for the user to log in and fill in the questionnaire, obtain the questionnaire filling information, and review the questionnaire filling information;

[0136] The filled-in data sorting module is used to sort the filled-in information of the questionnaire to obtain sorted filled-in data;

[0137] The talent knowledge graph module is used to construct a talent knowledge graph based on the sorted filled-in data;

[0138] The output module is used to output the corresponding policy.

[0139] According to an embodiment of the present invention, the policy input module includes a policy input unit and a policy review unit. The talent policy is input into the policy input unit, and then the policy review unit reviews and determines the input talent policy. Then, the talent policy after review and determination is sorted and disassembled according to the policy sorting module to obtain sorted talent policy information. The sorted talent policy information includes the name of the sub-policy, the label features of the sub-policy, etc. The sorted talent policy information is sent to the policy knowledge graph module and the talent questionnaire module respectively. The talent questionnaire module presets a question and answer knowledge base. The questionnaire questions are determined through label features and the preset question and answer knowledge base, and the talent questionnaire information field is constructed.

[0140] According to an embodiment of the present invention, the questionnaire filling module includes: a user login unit, a questionnaire filling unit and a questionnaire review unit;

[0141] The user login unit is used for user-side account registration, login, logout, modification and verification;

[0142] The questionnaire filling unit is used for the user to fill in the talent questionnaire information and obtain the questionnaire filling information;

[0143] The questionnaire review unit is used to review the questionnaire filling information and delete the questionnaire filling information that does not meet the specifications or is wrong.

[0144] It should be noted that the user terminal logs in to the system through the user login unit. After the identity of the user terminal is verified, it is allowed to enter the questionnaire filling unit. The user terminal fills in the talent questionnaire information in the questionnaire filling unit, and the unfilled positions are set as blank.

[0145] According to an embodiment of the present invention, the output module includes: a score output unit, a score verification unit, a policy output unit, a policy verification unit and an appeal unit;

[0146] The score output unit is used to output the matching sub-score or the comprehensive score;

[0147] The score verification unit is used for the user end to check and verify the matching sub-score or the comprehensive score;

[0148] The policy output unit is used to output the corresponding policy;

[0149] The policy verification unit is used for the user end to check and verify the adapted policy;

[0150] The appeal unit is used for the user to appeal the questioned matching sub-scores, comprehensive scores and corresponding policies.

[0151] It should be noted that the matching sub-score or comprehensive score is output through the score output unit. If the user terminal has doubts about the matching sub-score or comprehensive score, the user terminal can check and verify the calculation process of the output matching sub-score or comprehensive score through the score verification unit. If there are still doubts or there are matching calculation errors, the user terminal can make a score appeal through the appeal unit. In addition, the corresponding policy is output through the policy output unit. If the user terminal has doubts about the output corresponding policy, the user terminal can check and verify the corresponding policy through the policy verification unit. The policy verification unit includes data information such as label features of the corresponding corresponding policy for the user terminal to review. If the user terminal still has doubts about the corresponding policy or the policy matching is wrong, the user terminal can make a policy appeal through the appeal unit.

[0152] The present invention discloses a talent policy matching method and system based on knowledge graph, wherein the method includes: obtaining talent policy information of a preset area; combing and disassembling the talent policy of the preset area to obtain multiple sub-policies, labeling the sub-policies, and drawing a policy knowledge graph; constructing a talent questionnaire information field according to the sub-policies based on preset matching rules; obtaining the questionnaire filling information of the talent questionnaire information field from the user end; constructing a talent information knowledge graph according to the questionnaire filling information; matching the policy knowledge graph with the talent information knowledge graph to obtain a matching policy; and sending the matching policy to the user end for display. The present invention reduces the human work cost of talent policy matching and improves work efficiency through big data technology.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0154] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0155] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0156] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0157] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A talent policy matching method based on knowledge graph, characterized in that: include: Obtain talent policy information for a preset area; Sort out and disassemble the talent policies of the preset regions to obtain multiple sub-policies, label the sub-policies, and draw a policy knowledge map; Based on the preset matching rules and sub-policies, the talent questionnaire information fields are constructed; Obtain the questionnaire filling information of the talent questionnaire information field on the user side; Build a talent information knowledge graph based on the information filled in the questionnaire; Match the policy knowledge graph with the talent information knowledge graph to obtain the appropriate policy; The adapted policy is sent to the user terminal for display.

2. According to claim 1, a talent policy matching method based on knowledge graph is characterized in that: The step of constructing the talent questionnaire information field according to the sub-policy specifically includes: Extract label features from sub-policies; According to the label features in the sub-policy, the preset question-answer knowledge base is searched to obtain the questionnaire questions corresponding to the label features; Based on the preset review end, the questionnaire questions corresponding to the label features are reviewed. If the review is approved, the questionnaire questions corresponding to the label features are set as sub-questionnaire information fields; The sub-questionnaire information fields are combined to obtain the talent questionnaire information field.

3. According to claim 2, a talent policy matching method based on knowledge graph is characterized in that: Also includes: Number the sub-policies to obtain the sub-policy number values; According to the number value of the sub-policy, the sub-questionnaire information field of the sub-policy is numbered to obtain the number value of the corresponding sub-questionnaire information field, and the number value of the corresponding sub-policy is associated with the number value of the sub-questionnaire information field to obtain the sub-policy and sub-questionnaire information field with the associated number value; The associated number value is stored in the sub-policy and sub-questionnaire information fields.

4. According to claim 3, a talent policy matching method based on knowledge graph is characterized in that: The step of numbering the sub-policies specifically includes: Set the sub-policy number using the preset numbering rules; Obtain the feature requirements of the sub-policy and the probability value of the label features that meet the corresponding sub-policy in the historical questionnaire filling information; Sort the label features of the sub-policies from large to small according to the corresponding probability values, and determine the sub-number of the label features corresponding to the sub-policy; Set the sub-policy number to the parent number of the tag feature; The tag features are numbered according to the parent number of the corresponding tag feature and the child number of the tag feature.

5. According to claim 1, a talent policy matching method based on knowledge graph is characterized in that: The step of matching the policy knowledge graph with the talent information knowledge graph to obtain a matching policy specifically includes: Divide the policy knowledge graph according to different policies to obtain multiple sub-policy knowledge graphs; Match the sub-policy knowledge graph with the talent information knowledge graph to obtain a matching sub-score; If the matching sub-score is greater than or equal to the preset score threshold of the corresponding sub-policy, the sub-policy of the sub-policy knowledge graph corresponding to the matching sub-score is set as the corresponding policy; Determine the corresponding sub-policy level according to whether the matching sub-score falls within a first preset score interval of the corresponding sub-policy; Sent to the user end for display according to the adapted policy and corresponding sub-policy level.

6. A talent policy matching method based on knowledge graph according to claim 5, characterized in that: Also includes: According to the sub-policy, query the preset weight coefficient table to obtain the weight coefficient corresponding to the sub-policy; Multiply the weight coefficient corresponding to the sub-policy by the corresponding matching sub-score to obtain the weight score of the corresponding sub-policy; Add up the weighted scores of all sub-policies to get a comprehensive score; According to whether the comprehensive score falls into the second preset score range of the corresponding policy, the corresponding comprehensive score level is determined; Determine the appropriate comprehensive policy level based on the comprehensive score level; The adapted comprehensive policy and the corresponding comprehensive policy level are sent to the user terminal for display.

7. According to claim 5, a talent policy matching method based on knowledge graph is characterized in that: The step of matching the sub-policy knowledge graph with the talent information knowledge graph specifically includes: Extract questionnaire filling information from the talent information knowledge graph; According to the questionnaire filling information in the talent information knowledge graph, the questionnaire question filling data and the number value of the sub-questionnaire information field corresponding to the location of the questionnaire question filling data are obtained; According to the number value of the sub-questionnaire information field where the data corresponding to the questionnaire question is located, determine the number value of the sub-policy that matches it; Determine the sub-policy that matches it according to the number value of the sub-policy that matches it; The label features in the matching sub-policy are matched with the corresponding questionnaire question filling data in the order of the numbers to determine whether the corresponding questionnaire question filling data conforms to the label features in the matching sub-policy.

8. A talent policy matching system based on knowledge graph, characterized in that: include: Policy input module, policy arrangement module, policy knowledge map module, talent questionnaire module, questionnaire filling module, filled information arrangement module, talent knowledge map module and output module; The policy input module is used to input talent policies and review and determine talent policies; The policy arrangement module is used to sort out and disassemble the talent policy to obtain the organized talent policy information; The policy knowledge graph module is used to construct a policy knowledge graph based on the sorted talent policy data; The talent questionnaire module is used to construct talent questionnaire information fields based on the sorted talent policy information; The questionnaire filling module is used for the user to log in and fill in the questionnaire, obtain the questionnaire filling information, and review the questionnaire filling information; The filled-in data sorting module is used to sort the filled-in information of the questionnaire to obtain sorted filled-in data; The talent knowledge graph module is used to construct a talent knowledge graph based on the sorted filled-in data; The output module is used to output the corresponding policy.

9. According to claim 8, a talent policy matching system based on knowledge graph is characterized in that: The questionnaire filling module includes: a user login unit, a questionnaire filling unit and a questionnaire review unit; The user login unit is used for user-side account registration, login, logout, modification and verification; The questionnaire filling unit is used for the user to fill in the talent questionnaire information and obtain the questionnaire filling information; The questionnaire review unit is used to review the questionnaire filling information and delete the questionnaire filling information that does not meet the specifications or is wrong.

10. A talent policy matching system based on knowledge graph according to claim 8, characterized in that: The output module includes: a score output unit, a score verification unit, a policy output unit, a policy verification unit and an appeal unit; The score output unit is used to output the matching sub-score or the comprehensive score; The score verification unit is used for the user end to check and verify the matching sub-score or the comprehensive score; The policy output unit is used to output the corresponding policy; The policy verification unit is used for the user end to check and verify the adapted policy; The appeal unit is used for the user to appeal the questioned matching sub-scores, comprehensive scores and corresponding policies.

Images