Work meeting information intelligent management system and method based on knowledge graph

Abstract

The invention discloses an intelligent work information management system and method based on a knowledge graph, and relates to the technical field of work information management.The method comprises the steps that historical data of work members participating in work activities is collected, and entities related to the work activities are recognized through the natural language processing technology; identifying a relationship between entities, and constructing an event chain; constructing a work meeting information knowledge graph; marking start time nodes of work meeting activities in the work meeting member activity information to form a start time node set, and calculating participation intervals of work meeting members; the comprehensive planning efficiency standard reaching condition in the current monitoring period is judged, and an early warning signal is sent out according to the standard reaching condition; analyzing and calculating a calibration planning interval according to unmatched work meeting members; analyzing the true value of the comprehensive planning efficiency in the current monitoring period; and performing calibration processing on the calibration planning interval in the current monitoring period according to the monitoring result. Data support is provided for work meeting decision making, and intelligent management of work meeting information is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of trade union information management, and specifically to a knowledge graph-based intelligent trade union information management system and method. Background Art

[0002] As the representative organization of workers, trade unions bear the important responsibility of safeguarding workers' rights and promoting harmonious labor-capital relations. As union operations become increasingly complex, the demand for union information management is also increasing. Traditional union information management systems are often based on relational databases, which can lead to data silos and difficulty in implementing cross-domain correlation analysis.

[0003] When selecting the time for a union activity, organizers often only refer to the start time of historical activities, ignoring the actual situation of union members. This can easily result in fewer people participating in the activity or cause inconvenience to union members participating in the activity, reducing the participation in union activities, and easily causing waste of resources, which is not conducive to the intelligent management of the union.

[0004] Therefore, the present invention discloses a knowledge graph-based intelligent management system and method for union information to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a knowledge graph-based intelligent management system and method for trade union information to solve the problems raised in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligent management of union information based on knowledge graph, the method comprising the following steps:

[0007] S1: Collect historical data on union members' participation in union activities, clean the collected historical data, perform text preprocessing on the cleaned historical data, define core concepts, attributes, and relationships in the union field, and establish an ontology model for union information management;

[0008] S2: Use natural language processing technology to identify entities related to union activities and perform entity extraction; identify the relationships between entities and build event chains; and construct a union information knowledge graph based on the event chains;

[0009] S3: Analyze the activity information of union members within the monitored union based on the union information knowledge graph, mark the start time nodes of the union activities in the union member activity information to form a set of start time nodes, and calculate the union member participation interval based on the set of start time nodes; determine the comprehensive planning efficiency compliance within the current monitoring period based on the union member participation interval, and issue an early warning signal based on the compliance status;

[0010] S4: Combined with the early warning signal, calculate the calibration planning interval based on the mismatched union members; analyze the true value of the comprehensive planning efficiency within the current monitoring period based on the calibration planning interval; monitor the calibration signal in real time; and calibrate the calibration planning interval within the current monitoring period based on the monitoring results.

[0011] According to the above solution, in S1, the data cleaning includes deduplication, formatting and standardization; the text preprocessing includes word segmentation, part-of-speech tagging and stop word filtering of the original text data;

[0012] Defining the core concepts in the union field involves establishing a hierarchical structure based on the inheritance relationships between the core concepts;

[0013] The core concepts in the field of trade unions include trade unions, union members, labor contracts and trade union activities;

[0014] The inheritance relationship between the core concepts includes parent classes and child classes;

[0015] Defining the attributes of the union domain includes defining the attributes and attribute types of core concepts;

[0016] Attribute types include string, number, and date;

[0017] Defining relationships in the union field involves defining the directionality and multiplicity of relationships;

[0018] The directionality of the relationship includes unidirectional or bidirectional, and the multiplicity of the relationship includes one-to-one, one-to-many and many-to-many;

[0019] Before establishing the ontology model of union information management, it is also necessary to define constraint rules and inference rules; the constraint rules are the constraints between core concepts and relationships; the inference rules are the rules for inferring new knowledge;

[0020] The ontology modeling tool is used to establish the ontology model of trade union information management and perform visualization processing, and the ontology model of trade union information management is filled with instantiated data.

[0021] According to the above scheme, S2 includes the following contents:

[0022] S201: Matching the historical data after text preprocessing with the ontology model of union information management to identify entities related to union activities;

[0023] S202: Utilize named entity recognition tools to extract entities; utilize relationship extraction tools to identify relationships between entities;

[0024] S203: Convert entities and relationships into event chains and use the resource description framework to build a union information knowledge graph.

[0025] This invention combines graph databases and visualization tools to create knowledge graphs that not only enable efficient data management and query, but also support intelligent analysis and decision-making. In the intelligent management of union information, the construction of knowledge graphs will greatly improve the efficiency of information integration and utilization, helping unions achieve intelligent management.

[0026] According to the above solution, S3 includes the following:

[0027] S301: Obtain the activity information of union members in the union to be monitored through the union information knowledge graph. The union member activity information includes union member attributes and attributes of union activities related to the corresponding union members. The union member activity information is recorded as a set A, where A = {A1, A2, ..., A i ,…,A I}; where A i represents the i-th union member information, i∈[1,I]; I represents the number of union member information in the union member activity information set; one union member information corresponds to one union member;

[0028] S302: Based on the union member activity information set, randomly select a union member activity information, and mark the start time node of the union activity with which the corresponding union member has a relationship according to the attributes of the union activity with which the corresponding union member has a relationship; extract the marked start time nodes of the union activities of the same activity type of the i-th union member to form a set denoted as B (i，b) , B (i，b) ={B (i，b) 1, B (i，b) 2,…,B (i，b) c ,…,B (i，b) C}; where B (i，b) c represents the start time node of the cth union activity of the same activity type marked by the i-th union member in the b-th monitoring cycle; c∈[1,C]; C represents the number of start time nodes in the set of start time nodes of the union activity;

[0029] S303: arbitrarily extract a set of start time nodes of union activities of the same activity type that are marked by a union member, calculate the participation interval of the corresponding union member based on the set of start time nodes, and record the participation interval of the i-th union member as TG i ,

[0030]

[0031] Wherein, α represents a proportional coefficient, which is a constant preset by the system, and d represents the total number of monitoring cycles;

[0032] The present invention obtains the activity information of union members in the monitored union through historical data, marks the start time nodes of the corresponding union activities with existing relationships in the union member activity information, and calculates the participation interval of the corresponding union members based on the set of start time nodes. This can effectively reflect the daily participation of union members in union activities and provide data reference for subsequent analysis.

[0033] S304: Obtain the planning interval TP of the corresponding activity type in the current monitoring period. The planning interval is a system preset constant. Determine the matching degree between the current planning interval of the corresponding activity type and the participation interval of the corresponding union member. Calculate the comprehensive planning efficiency based on the matching degree, which is recorded as Efficiency.

[0034]

[0035] Where F() represents the judgment function; if |TP-TG i |≤β1, then F(|TP-TG i |) = 1, indicating the matching of the planning interval of the corresponding activity type and the participation interval of the corresponding union members, where β1 is a system preset constant;

[0036] If |TP-TG i |>β1, then F(|TP-TG i |)=0, indicating a mismatch between the planning interval of the corresponding activity type and the participation interval of the corresponding union members;

[0037] S305: Generate an early warning signal based on the analysis results of S304.

[0038] If Efficiency ≥ β2, it means that the comprehensive planning efficiency in the current monitoring period has reached the standard and no warning signal is issued.

[0039] If 0≤Efficiency<β2, it indicates that the comprehensive planning efficiency in the current monitoring period does not meet the standard and an early warning signal is issued, where β2 is a system preset constant.

[0040] The present invention determines the degree of match between the current planning interval of the corresponding activity type and the participation interval of the corresponding union members, calculates the comprehensive planning efficiency based on the matching degree, determines whether the current comprehensive planning efficiency meets the standard based on the calculation result, and then generates an early warning signal based on the judgment result, providing data reference for subsequent further analysis of whether the comprehensive planning efficiency corresponding to the current calibration planning interval is optimal.

[0041] According to the above scheme, S4 includes the following contents:

[0042] S401: Receive warning signals in real time based on the analysis results in S305. When the system receives the warning signals, it extracts union members whose participation intervals do not match the planned intervals of the corresponding activity types, and calculates and calibrates the planned intervals based on the analysis of the mismatched union members, which is recorded as TGP.

[0043]

[0044] Where θ represents the calibration coefficient, which is selected from the calibration coefficient set in ascending order. The calibration coefficient set is a set of constants preset by the system; G represents the total number of union members whose participation interval does not match the planned interval of the corresponding activity type, g∈[1,G]; TG g represents the participation interval of the g-th union member whose participation interval does not match the planning interval of the corresponding activity type;

[0045] S402: Analyze the actual value of the comprehensive planning efficiency in the current monitoring period according to the calibration planning interval, and record it as Productivity;

[0046]

[0047] Wherein ρ represents the proportional coefficient, which is a system preset constant;

[0048] If |TGP-TG i |≤β1, then F(|TGP-TG i |)=1, if |TGP-TG i |>β1, then F(|TGP-TG i |)=0,

[0049] If |TGP-TG g |≤β1, then F(|TGP-TG g |)=1, if |TGP-TG g |>β1, then F(|TGP-TG g )=0,

[0050] S403: Generate a calibration signal based on the analysis result of S402,

[0051] If Productivity∈[0,β3], it indicates that the comprehensive planning efficiency corresponding to the calibration planning interval in the current monitoring period is optimal, and no calibration signal is issued, where β3 is a system preset constant;

[0052] like [0, β3], it indicates that the comprehensive planning efficiency corresponding to the calibration planning interval in the current monitoring period is not optimal, and a calibration signal is issued;

[0053] S404: Monitor the analysis results in S403 in real time, and receive the calibration signal in real time in combination with the monitoring results; if a calibration signal is received, select the next calibration coefficient in ascending order, and repeat S401-S403 until no calibration signal is issued; if no calibration signal is received, mark the corresponding calibration plan interval with the corresponding union activity and send it to the administrator.

[0054] The present invention calculates the calibration planning interval based on the analysis of mismatched union members, and analyzes the true value of the comprehensive planning efficiency in the current monitoring period based on the calibration planning interval; sends a calibration signal based on whether the comprehensive planning efficiency corresponding to the calibration planning interval in the current monitoring period is optimal, and can further calculate the calibration planning interval, which can more accurately provide data support for union decision-making and realize intelligent management of union information.

[0055] Another aspect of the present application provides a knowledge graph-based intelligent management system for union information, which is applied to the above-mentioned knowledge graph-based intelligent management method for union information. The system includes a union data collection and setting module, a graph construction module, an activity data analysis module, and a planning interval calibration module.

[0056] The union data collection and setting module is used to collect historical data of union members participating in union activities, clean the collected historical data, perform text preprocessing on the cleaned historical data, define the core concepts, attributes and relationships in the union field, and establish an ontology model for union information management;

[0057] The graph construction module is used to use natural language processing technology to identify entities related to union activities and perform entity extraction; identify the relationship between entities and build event chains; and build a union information knowledge graph based on the event chains;

[0058] The activity data analysis module is used to analyze the activity information of union members in the monitored union based on the union information knowledge graph, mark the start time nodes of the union activities in the union member activity information to form a set of start time nodes, and calculate the participation interval of the union members based on the set of start time nodes; determine the comprehensive planning efficiency compliance within the current monitoring period based on the union member participation interval, and issue an early warning signal based on the compliance status;

[0059] The planning interval calibration module is used to combine early warning signals, analyze and calculate the calibration planning interval based on mismatched union members; analyze the true value of the comprehensive planning efficiency within the current monitoring period based on the calibration planning interval; monitor the calibration signal in real time; and calibrate the calibration planning interval within the current monitoring period based on the monitoring results.

[0060] According to the above solution, the union data collection and setting module includes a union data pre-processing unit and an ontology model building unit;

[0061] The union data preprocessing unit is used to collect historical data of union members' participation in union activities, perform data cleaning on the collected historical data, and perform text preprocessing on the cleaned historical data; the data cleaning includes deduplication, formatting, and standardization; the text preprocessing includes word segmentation, part-of-speech tagging, and stop word filtering on the original text data;

[0062] The ontology model building unit is used to define the core concepts, attributes and relationships in the union field and establish an ontology model for union information management; defining the core concepts in the union field includes defining the inheritance relationship between the core concepts; defining the attributes in the union field includes defining the attributes and attribute types of the core concepts; defining the relationships in the union field includes defining the directionality and multiplicity of the relationships;

[0063] Before establishing the ontology model of trade union information management, it is also necessary to define constraint rules and inference rules; the constraint rules are the constraints between core concepts and relationships; the inference rules are the rules for inferring new knowledge; the ontology model of trade union information management is established using ontology modeling tools, and visualization processing is performed to fill the ontology model of trade union information management with instantiated data.

[0064] According to the above solution, the activity data analysis module includes an activity data marking unit, a member participation interval calculation unit and a comprehensive planning efficiency early warning unit;

[0065] The activity data marking unit is used to obtain the activity information of union members in the union to be monitored through the union information knowledge graph, mark the start time nodes of the union activities with which the union member activity information is related, and form a set;

[0066] The member participation interval calculation unit is used to arbitrarily extract a set of start time nodes of union activities of the same activity type that are marked by a union member, and calculate the participation interval of the corresponding union member based on the set of start time nodes;

[0067] The comprehensive planning efficiency warning unit is used to obtain the planning interval of the corresponding activity type in the current monitoring period, determine the matching degree between the current planning interval of the corresponding activity type and the participation interval of the corresponding union members, calculate the comprehensive planning efficiency based on the matching degree, and generate a warning signal based on the comprehensive planning efficiency.

[0068] According to the above solution, the planning interval calibration module includes a calibration planning interval calculation unit and a comprehensive planning efficiency calibration unit;

[0069] The calibration planning interval calculation unit is used to extract union members whose participation intervals do not match the planning intervals of the corresponding activity types when the system receives an early warning signal, and to analyze and calculate the calibration planning interval based on the mismatched union members;

[0070] The comprehensive planning efficiency calibration unit analyzes the true value of the comprehensive planning efficiency in the current monitoring period according to the calibration planning interval, generates a calibration signal according to the true value of the comprehensive planning efficiency, and further calculates the calibration planning interval until no calibration signal is issued.

[0071] Compared with the existing technology, the beneficial effect of the present invention is that the present invention combines graph databases and visualization tools, and the knowledge graph can not only achieve efficient data management and query, but also support intelligent analysis and decision-making. In the intelligent management of union information, the construction of a knowledge graph will greatly improve the efficiency of information integration and utilization, helping unions achieve intelligent management. By obtaining information on union member activities within the monitored union through historical data, marking the start time nodes of union activities with corresponding relationships in the union member activity information, and calculating the corresponding union member's participation interval based on the set of start time nodes, this can effectively reflect the daily participation of union members in union activities and provide data reference for subsequent analysis. By determining the degree of match between the current planning interval of the corresponding activity type and the participation interval of the corresponding union member, the comprehensive planning efficiency is calculated based on the match degree. Based on the calculation result, it is determined whether the current comprehensive planning efficiency meets the standard. Based on the judgment result, an early warning signal is generated, providing data reference for further analysis of whether the comprehensive planning efficiency corresponding to the current calibration planning interval is optimal. By analyzing and calculating the calibration planning interval based on mismatched union members, the actual value of the comprehensive planning efficiency within the current monitoring period is analyzed based on the calibration planning interval. Based on whether the comprehensive planning efficiency corresponding to the calibration planning interval within the current monitoring period is optimal, a calibration signal is issued, which can further calculate the calibration planning interval, providing more accurate data support for union decision-making and realizing intelligent management of union information. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0073] Figure 1 This is a flow chart of a method for intelligent management of union information based on knowledge graphs according to the present invention;

[0074] Figure 2 This is a structural diagram of a knowledge graph-based intelligent management system for trade union information in the present invention. DETAILED DESCRIPTION

[0075] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0076] See also Figure 1 The present invention provides a technical solution: a method for intelligent management of union information based on knowledge graph, which includes the following steps:

[0077] S1: Collect historical data on union members' participation in union activities, clean the collected historical data, perform text preprocessing on the cleaned historical data, define core concepts, attributes, and relationships in the union field, and establish an ontology model for union information management;

[0078] In S1, data cleaning includes deduplication, formatting, and standardization; text preprocessing includes word segmentation, part-of-speech tagging, and stop word filtering of raw text data;

[0079] Defining the core concepts in the union field involves establishing a hierarchical structure based on the inheritance relationships between the core concepts;

[0080] The core concepts in the field of trade unions include trade unions, union members, labor contracts, and union activities;

[0081] The inheritance relationship between core concepts includes parent classes and child classes;

[0082] Defining the attributes of the union domain includes defining the attributes and attribute types of core concepts;

[0083] Attribute types include string, number, and date;

[0084] Defining relationships in the union field involves defining the directionality and multiplicity of relationships;

[0085] The directionality of a relationship includes unidirectional or bidirectional, and the multiplicity of a relationship includes one-to-one, one-to-many, and many-to-many;

[0086] Before establishing the ontology model of union information management, it is also necessary to define constraint rules and inference rules; constraint rules are the constraints between core concepts and relationships; inference rules are the rules for inferring new knowledge;

[0087] The ontology modeling tool is used to establish the ontology model of trade union information management and perform visualization processing, and the ontology model of trade union information management is filled with instantiated data.

[0088] Example 1: In this example, employee is the parent class of union member, and formal union member and temporary union member are subclasses of union member;

[0089] The attributes of union members include name, employee number, joining date, and length of service; the attributes of labor contracts include contract number, signing date, and salary standard; the attributes of union activities include activity name, time, and activity type;

[0090] The joining time is of date type, and the name is of string type;

[0091] Relationships in the union field include affiliation, participation, dependency, and time series relationships;

[0092] Affiliation: "Union employees belong to the union"; Participation: "Union members participate in union activities"; Dependence: "Remuneration is based on the labor contract"; Time series: "A certain training is conducted within a specific time period";

[0093] The relationship between a union and its members is one-to-many, while the relationship between union members participating in union activities is many-to-many.

[0094] The relationship between union members participating in union activities is many-to-many, meaning that one union member can participate in multiple union activities, and multiple union members can participate in one union activity at the same time.

[0095] Binding rules include that a union member can only belong to one union but can attend multiple training courses;

[0096] The inference rule includes that if a union member has completed a certain training course, it can be automatically inferred that the union member has the skills of the course.

[0097] S2: Use natural language processing technology to identify entities related to union activities and perform entity extraction; identify the relationships between entities and build event chains; and construct a union information knowledge graph based on the event chains;

[0098] In S2, the following are included:

[0099] S201: Matching the historical data after text preprocessing with the ontology model of union information management to identify entities related to union activities;

[0100] S202: Utilize named entity recognition tools to extract entities; utilize relationship extraction tools to identify relationships between entities;

[0101] S203: Convert entities and relationships into event chains and use the resource description framework to build a union information knowledge graph.

[0102] S3: Analyze the activity information of union members within the monitored union based on the union information knowledge graph, mark the start time nodes of the union activities in the union member activity information to form a set of start time nodes, and calculate the union member participation interval based on the set of start time nodes; determine the comprehensive planning efficiency compliance within the current monitoring period based on the union member participation interval, and issue an early warning signal based on the compliance status;

[0103] In S3, include the following:

[0104] S301: Obtain the activity information of union members in the union to be monitored through the union information knowledge graph. The union member activity information includes union member attributes and attributes of union activities related to the corresponding union members. The union member activity information is recorded as a set A, where A = {A1, A2, ..., A i ,…,A I}; where A i represents the i-th union member information, i∈[1,I]; I represents the number of union member information in the union member activity information set; one union member information corresponds to one union member;

[0105] S302: Based on the union member activity information set, randomly select a union member activity information, and mark the start time node of the corresponding union activity in the union member activity information according to the attributes of the union activity with which the corresponding union member has a relationship; extract the marked start time nodes of the union activities of the same activity type of the i-th union member to form a set denoted as B (i，b) , B (i，b) ={B (i，b) 1, B (i，b) 2,…,B (i，b) c ,…,B (i，b) C}; where B (i，b) c represents the start time node of the cth union activity of the same activity type marked by the i-th union member in the b-th monitoring cycle; c∈[1,C]; C represents the number of start time nodes in the set of start time nodes of the union activity;

[0106] S303: Randomly extract the start time node set of union activities of the same activity type that are marked by a union member, calculate the participation interval of the corresponding union member based on the start time node set, and record the participation interval of the i-th union member as TG i ,

[0107]

[0108] Wherein, α represents the proportional coefficient, which is a constant preset by the system, and d represents the total number of monitoring cycles;

[0109] S304: Obtain the planning interval TP of the corresponding activity type in the current monitoring period. The planning interval is a system preset constant. Determine the matching degree between the current planning interval of the corresponding activity type and the participation interval of the corresponding union member. Calculate the comprehensive planning efficiency based on the matching degree, which is recorded as Efficiency.

[0110]

[0111] Where F() represents the judgment function; if |TP-TG i |≤β1, then F(|TP-TG i |) = 1, indicating the matching of the planning interval of the corresponding activity type and the participation interval of the corresponding union members, where β1 is a system preset constant;

[0112] If |TP-TG i |>β1, then F(|TP-TG i |)=0, indicating a mismatch between the planning interval of the corresponding activity type and the participation interval of the corresponding union members;

[0113] S305: Generate an early warning signal based on the analysis results of S304.

[0114] If Efficiency ≥ β2, it means that the comprehensive planning efficiency in the current monitoring period has reached the standard and no warning signal is issued.

[0115] If 0≤Efficiency<β2, it indicates that the comprehensive planning efficiency in the current monitoring period does not meet the standard and an early warning signal is issued, where β2 is a system preset constant.

[0116] S4: Combined with the early warning signal, calculate the calibration planning interval based on the mismatched union members; analyze the true value of the comprehensive planning efficiency within the current monitoring period based on the calibration planning interval; monitor the calibration signal in real time; and calibrate the calibration planning interval within the current monitoring period based on the monitoring results.

[0117] In S4, include the following:

[0118] S401: Receive warning signals in real time based on the analysis results in S305. When the system receives the warning signals, it extracts union members whose participation intervals do not match the planned intervals of the corresponding activity types, and calculates and calibrates the planned intervals based on the analysis of the mismatched union members, which is recorded as TGP.

[0119]

[0120] Where θ represents the calibration coefficient, which is selected from the calibration coefficient set in ascending order. The calibration coefficient set is a set of constants preset by the system. G represents the total number of union members whose participation interval does not match the planned interval of the corresponding activity type, g∈[1,G]; TG g represents the participation interval of the g-th union member whose participation interval does not match the planning interval of the corresponding activity type;

[0121] S402: Analyze the actual value of the comprehensive planning efficiency in the current monitoring period according to the calibration planning interval, and record it as Productivity;

[0122]

[0123] Where ρ represents the proportional coefficient, which is a system preset constant;

[0124] If |TGP-TG i |≤β1, then F(|TGP-TG i |)=1, if |TGP-TG i |>β1, then F(|TGP-TG i |)=0,

[0125] If |TGP-TG g |≤β1, then F(|TGP-TG g |)=1, if |TGP-TG g |>β1, then F(|TGP-TG g )=0,

[0126] S403: Generate a calibration signal based on the analysis result of S402,

[0127] If Productivity∈[0,β3], it indicates that the comprehensive planning efficiency corresponding to the calibration planning interval in the current monitoring period is optimal, and no calibration signal is issued, where β3 is a system preset constant;

[0128] like [0, β3], it indicates that the comprehensive planning efficiency corresponding to the calibration planning interval in the current monitoring period is not optimal, and a calibration signal is issued;

[0129] S404: Monitor the analysis results in S403 in real time, and receive the calibration signal in real time in combination with the monitoring results; if a calibration signal is received, select the next calibration coefficient in ascending order, and repeat S401-S403 until no calibration signal is issued; if no calibration signal is received, mark the corresponding calibration plan interval with the corresponding union activity and send it to the administrator.

[0130] See also Figure 2, the present invention provides a technical solution: a union information intelligent management system based on knowledge graph, the system includes a union data collection and setting module, a graph construction module, an activity data analysis module and a planning interval calibration module;

[0131] The union data collection and setting module is used to collect historical data on union members' participation in union activities, clean the collected historical data, perform text preprocessing on the cleaned historical data, define the core concepts, attributes and relationships in the union field, and establish an ontology model for union information management;

[0132] The graph construction module is used to use natural language processing technology to identify entities related to union activities and perform entity extraction; identify the relationships between entities and build event chains; and construct a union information knowledge graph based on the event chains;

[0133] The activity data analysis module is used to analyze the activity information of union members in the monitored union based on the union information knowledge graph, mark the start time nodes of union activities in the union member activity information, form a set of start time nodes, and calculate the participation interval of union members based on the set of start time nodes; based on the participation interval of union members, determine the comprehensive planning efficiency compliance within the current monitoring period and issue early warning signals based on the compliance status;

[0134] The planning interval calibration module is used to combine early warning signals and calculate the calibration planning interval based on the mismatched union members; analyze the true value of the comprehensive planning efficiency within the current monitoring period based on the calibration planning interval; monitor the calibration signal in real time; and calibrate the calibration planning interval within the current monitoring period based on the monitoring results.

[0135] According to the above scheme, the union data collection and setting module includes a union data pre-processing unit and an ontology model building unit;

[0136] The union data preprocessing unit is used to collect historical data on union members' participation in union activities, clean the collected historical data, and perform text preprocessing on the cleaned historical data. Data cleaning includes deduplication, formatting, and standardization. Text preprocessing includes word segmentation, part-of-speech tagging, and stop word filtering on the original text data.

[0137] The ontology model building unit is used to define the core concepts, attributes and relationships in the union field and establish the ontology model for union information management; defining the core concepts in the union field includes defining the inheritance relationship between core concepts; defining the attributes in the union field includes defining the attributes and attribute types of core concepts; defining the relationships in the union field includes defining the directionality and multiplicity of relationships;

[0138] Before establishing the ontology model of trade union information management, it is also necessary to define constraint rules and inference rules; constraint rules are the constraints between core concepts and relationships; inference rules are the rules for inferring new knowledge; the ontology model of trade union information management is established using ontology modeling tools, and visualization is performed to fill the ontology model of trade union information management with instantiated data.

[0139] According to the above scheme, the activity data analysis module includes an activity data marking unit, a member participation interval calculation unit, and a comprehensive planning efficiency early warning unit;

[0140] The activity data marking unit is used to obtain the activity information of union members in the union to be monitored through the union information knowledge graph, mark the start time nodes of the corresponding union activities with existing relationships in the union member activity information, and form a set;

[0141] The member participation interval calculation unit is used to arbitrarily extract a set of start time nodes of union activities of the same activity type that are marked by a union member, and calculate the participation interval of the corresponding union member based on the set of start time nodes;

[0142] The comprehensive planning efficiency early warning unit is used to obtain the planning interval of the corresponding activity type in the current monitoring period, determine the matching degree between the current planning interval of the corresponding activity type and the participation interval of the corresponding union members, calculate the comprehensive planning efficiency based on the matching degree, and generate an early warning signal based on the comprehensive planning efficiency.

[0143] According to the above scheme, the planning interval calibration module includes a calibration planning interval calculation unit and a comprehensive planning efficiency calibration unit;

[0144] The calibration planning interval calculation unit is used to extract the union members whose participation interval does not match the planning interval of the corresponding activity type when the system receives the early warning signal, and calculate the calibration planning interval based on the analysis of the mismatched union members;

[0145] The comprehensive planning efficiency calibration unit analyzes the true value of the comprehensive planning efficiency in the current monitoring period according to the calibration planning interval, generates a calibration signal according to the true value of the comprehensive planning efficiency, and further calculates the calibration planning interval until no calibration signal is issued.

[0146] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0147] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for intelligent management of union information based on knowledge graph, characterized in that: The method comprises the following steps: S1: Collect historical data on union members' participation in union activities, clean the collected historical data, perform text preprocessing on the cleaned historical data, define core concepts, attributes, and relationships in the union field, and establish an ontology model for union information management; S2: Use natural language processing technology to identify entities related to union activities and perform entity extraction; identify the relationships between entities and build event chains; and construct a union information knowledge graph based on the event chains; S3: Analyze the activity information of union members within the monitored union based on the union information knowledge graph, mark the start time nodes of the union activities in the union member activity information to form a set of start time nodes, and calculate the union member participation interval based on the set of start time nodes; determine the comprehensive planning efficiency compliance within the current monitoring period based on the union member participation interval, and issue an early warning signal based on the compliance status; S4: Combined with the early warning signals, the calibration planning interval is calculated based on the mismatched union members; based on the calibration planning interval, the actual value of the comprehensive planning efficiency in the current monitoring period is analyzed; Monitor the calibration signal in real time; perform calibration processing on the calibration plan interval within the current monitoring cycle based on the monitoring results.

2. The method for intelligent management of union information based on knowledge graph according to claim 1 is characterized by: In S1, the data cleaning includes deduplication, formatting and standardization; the text preprocessing includes word segmentation, part-of-speech tagging and stop word filtering of the original text data; Defining the core concepts in the union field involves establishing a hierarchical structure based on the inheritance relationships between the core concepts; The core concepts in the field of trade unions include trade unions, union members, labor contracts and trade union activities; The inheritance relationship between the core concepts includes parent classes and child classes; Defining the attributes of the union domain includes defining the attributes and attribute types of core concepts; Attribute types include string, number, and date; Defining relationships in the union field involves defining the directionality and multiplicity of relationships; The directionality of the relationship includes unidirectional or bidirectional, and the multiplicity of the relationship includes one-to-one, one-to-many and many-to-many; Before establishing the ontology model of union information management, it is also necessary to define constraint rules and inference rules; the constraint rules are the constraints between core concepts and relationships; the inference rules are the rules for inferring new knowledge; The ontology modeling tool is used to establish the ontology model of trade union information management and perform visualization processing, and the ontology model of trade union information management is filled with instantiated data.

3. The method for intelligent management of union information based on knowledge graph according to claim 2 is characterized by: In S2, the following are included: S201: Matching the historical data after text preprocessing with the ontology model of union information management to identify entities related to union activities; S202: Utilize named entity recognition tools to extract entities; utilize relationship extraction tools to identify relationships between entities; S203: Convert entities and relationships into event chains and use the resource description framework to build a union information knowledge graph.

4. The method for intelligent management of union information based on knowledge graph according to claim 3 is characterized by: In S3, include the following: S301: Obtain the activity information of union members in the union to be monitored through the union information knowledge graph. The union member activity information includes union member attributes and attributes of union activities related to the corresponding union members. The union member activity information is recorded as a set A, where A = {A1, A2, ..., A i ,…,A I }; where A i represents the i-th union member information, i∈[1,I]; I represents the number of union member information in the union member activity information set; one union member information corresponds to one union member; S302: Based on the union member activity information set, randomly select a piece of union member activity information, and mark the start time node of the union activity to which the corresponding union member is associated according to the attributes of the union activity to which the corresponding union member is associated; Extract the marked start time nodes of the union activities of the same activity type of the i-th union member to form a set denoted as B (i，b) , B (i，b) ={B (i，b) 1, B (i，b) 2,…,B (i，b) c ,…,B (i，b) C }; where B (i，b) c represents the start time node of the cth union activity of the same activity type marked by the i-th union member in the b-th monitoring period; c∈[1, C]; C represents the number of start time nodes in the start time node set of the union activity; S303: arbitrarily extract a set of start time nodes of union activities of the same activity type that are marked by a union member, calculate the participation interval of the corresponding union member based on the set of start time nodes, and record the participation interval of the i-th union member as TG i , Wherein, α represents a proportional coefficient, which is a constant preset by the system, and d represents the total number of monitoring cycles; S304: Obtain the planning interval TP of the corresponding activity type in the current monitoring period. The planning interval is a system preset constant. Determine the matching degree between the current planning interval of the corresponding activity type and the participation interval of the corresponding union member. Calculate the comprehensive planning efficiency based on the matching degree, which is recorded as Efficiency. Where F() represents the judgment function; if |TP-TG i |≤β1, then F(|TP-TG i |) = 1, indicating the matching of the planning interval of the corresponding activity type and the participation interval of the corresponding union members, where β1 is a system preset constant; If |TP-TG i |>β1, then F(|TP-TG i |)=0, indicating a mismatch between the planning interval of the corresponding activity type and the participation interval of the corresponding union members; S305: Generate an early warning signal based on the analysis results of S304. If Efficiency ≥ β2, it means that the comprehensive planning efficiency in the current monitoring period has reached the standard and no warning signal is issued. If 0≤Efficiency<β2, it indicates that the comprehensive planning efficiency in the current monitoring period does not meet the standard and an early warning signal is issued, where β2 is a system preset constant.

5. The method for intelligent management of union information based on knowledge graph according to claim 4 is characterized by: In S4, include the following: S401: Receive warning signals in real time based on the analysis results in S305. When the system receives the warning signals, it extracts union members whose participation intervals do not match the planned intervals of the corresponding activity types, and calculates and calibrates the planned intervals based on the analysis of the mismatched union members, which is recorded as TGP. Where θ represents the calibration coefficient, which is selected from the calibration coefficient set in ascending order. The calibration coefficient set is a set of constants preset by the system; G represents the total number of union members whose participation interval does not match the planned interval of the corresponding activity type, g∈[1,G]; TG g represents the participation interval of the g-th union member whose participation interval does not match the planning interval of the corresponding activity type; S402: Analyze the actual value of the comprehensive planning efficiency in the current monitoring period according to the calibration planning interval, and record it as Productivity; Wherein ρ represents the proportional coefficient, which is a system preset constant; If |TGP-TG i |≤β1, then F(|TGP-TG i |)=1, if |TGP-TG i |>β1, then F(|TGP-TG i |)=0, If |TGP-TG g |≤β1, then F(|TGP-TG g |)=1, if |TGP-TG g |>β1, then F(|TGP-TG g )=0, S403: Generate a calibration signal based on the analysis result of S402, If Productivity∈[0,β3], it indicates that the comprehensive planning efficiency corresponding to the calibration planning interval in the current monitoring period is optimal, and no calibration signal is issued, where β3 is a system preset constant; like This indicates that the comprehensive planning efficiency corresponding to the calibration planning interval in the current monitoring period is not optimal, and a calibration signal is issued; S404: Monitor the analysis results in S403 in real time, and receive the calibration signal in real time in combination with the monitoring results; if a calibration signal is received, select the next calibration coefficient in ascending order, and repeat S401-S403 until no calibration signal is issued; if no calibration signal is received, mark the corresponding calibration plan interval with the corresponding union activity and send it to the administrator.

6. A knowledge graph-based intelligent management system for union information, wherein the system is applied to the knowledge graph-based intelligent management method for union information according to any one of claims 1 to 5, and is characterized in that: The system includes a union data collection and setting module, a map construction module, an activity data analysis module, and a planning interval calibration module; The union data collection and setting module is used to collect historical data of union members participating in union activities, clean the collected historical data, perform text preprocessing on the cleaned historical data, define the core concepts, attributes and relationships in the union field, and establish an ontology model for union information management; The graph construction module is used to use natural language processing technology to identify entities related to union activities and perform entity extraction; identify the relationship between entities and construct event chains; Construct a union information knowledge graph based on the event chain; The activity data analysis module is used to analyze the activity information of union members in the monitored union based on the union information knowledge graph, mark the start time nodes of the union activities in the union member activity information to form a set of start time nodes, and calculate the participation interval of the union members based on the set of start time nodes; determine the comprehensive planning efficiency compliance within the current monitoring period based on the union member participation interval, and issue an early warning signal based on the compliance status; The planning interval calibration module is used to combine the early warning signal and calculate the calibration planning interval according to the mismatched union members; based on the calibration planning interval, analyze the actual value of the comprehensive planning efficiency in the current monitoring period; Monitor the calibration signal in real time; perform calibration processing on the calibration plan interval within the current monitoring cycle based on the monitoring results.

7. The knowledge graph-based intelligent management system for union information according to claim 6 is characterized by: The union data collection and setting module includes a union data pre-processing unit and an ontology model building unit; The union data preprocessing unit is used to collect historical data of union members' participation in union activities, perform data cleaning on the collected historical data, and perform text preprocessing on the cleaned historical data; the data cleaning includes deduplication, formatting, and standardization; the text preprocessing includes word segmentation, part-of-speech tagging, and stop word filtering on the original text data; The ontology model building unit is used to define the core concepts, attributes and relationships in the union field and establish an ontology model for union information management; defining the core concepts in the union field includes defining the inheritance relationship between the core concepts; defining the attributes in the union field includes defining the attributes and attribute types of the core concepts; defining the relationships in the union field includes defining the directionality and multiplicity of the relationships; Before establishing the ontology model of trade union information management, it is also necessary to define constraint rules and inference rules; the constraint rules are the constraints between core concepts and relationships; the inference rules are the rules for inferring new knowledge; the ontology model of trade union information management is established using ontology modeling tools, and visualization processing is performed to fill the ontology model of trade union information management with instantiated data.

8. The knowledge graph-based intelligent management system for union information according to claim 6 is characterized by: The activity data analysis module includes an activity data marking unit, a member participation interval calculation unit and a comprehensive planning efficiency early warning unit; The activity data marking unit is used to obtain the activity information of union members in the union to be monitored through the union information knowledge graph, mark the start time nodes of the union activities with which the union member activity information is related, and form a set; The member participation interval calculation unit is used to arbitrarily extract a set of start time nodes of union activities of the same activity type that are marked by a union member, and calculate the participation interval of the corresponding union member based on the set of start time nodes; The comprehensive planning efficiency warning unit is used to obtain the planning interval of the corresponding activity type in the current monitoring period, determine the matching degree between the current planning interval of the corresponding activity type and the participation interval of the corresponding union members, calculate the comprehensive planning efficiency based on the matching degree, and generate a warning signal based on the comprehensive planning efficiency.

9. The knowledge graph-based intelligent management system for union information according to claim 6 is characterized by: The planning interval calibration module includes a calibration planning interval calculation unit and a comprehensive planning efficiency calibration unit; The calibration planning interval calculation unit is used to extract union members whose participation intervals do not match the planning intervals of the corresponding activity types when the system receives an early warning signal, and to analyze and calculate the calibration planning interval based on the unmatched union members; The comprehensive planning efficiency calibration unit analyzes the true value of the comprehensive planning efficiency in the current monitoring period according to the calibration planning interval, generates a calibration signal according to the true value of the comprehensive planning efficiency, and further calculates the calibration planning interval until no calibration signal is issued.

Images