Multi-dimensional cooperative processing volunteer service work management system and method

Abstract

The invention provides a multi-dimensional co-processing volunteer service work management system and method, and the method comprises the steps: carrying out the fusion and alignment of multi-source heterogeneous data of the multi-dimensional entities of volunteers, volunteer activities, favorites and organizations, and obtaining a volunteer service knowledge graph; determining a matching preference coefficient between the volunteer and the volunteer activity through the volunteer service knowledge graph; determining a multi-dimensional decision function of volunteer service management based on a multi-dimensional evaluation matrix among a plurality of hierarchical structures of volunteer activities, volunteers, recipients and organizations; and determining a cooperative scheduling strategy of volunteer service work based on the matching preference coefficient and the multi-dimensional decision function, and performing dynamic matching and resource cooperative scheduling on the volunteer, the volunteer activity and the helper through the cooperative scheduling strategy. By adopting the scheme of the application, the dynamic collaborative scheduling of the participants and the resources can be realized by integrating the deep semantic association among the participants of the multi-source heterogeneous data mining voluntary service and constructing a multi-dimensional evaluation decision system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of resource collaborative scheduling, and more particularly to a multi-dimensional collaborative processing volunteer service work management system and method. BACKGROUND

[0002] With the continuous development of social public welfare, volunteer service has widely covered community support, emergency support, cultural dissemination and other fields. The number of participants (volunteers, volunteer activities, recipients, and organization units) and the complexity of service scenarios have significantly increased, and the service data generated (such as volunteer skill certificates, activity holding time periods, recipient demand descriptions, and organization unit resource lists) presents a multi-source heterogeneous characteristic. Efficient volunteer service management needs to achieve accurate matching between multiple subjects, dynamic resource allocation, and service efficiency optimization to cope with the regular service needs and emergency response needs of sudden service, and to improve the pertinence of volunteer service, resource utilization rate, and recipient satisfaction, which has become the core direction of promoting the standardization and intelligent development of the volunteer service field.

[0003] Currently, volunteer service management mainly relies on traditional information registration systems or manual matching modes. Although some optimization schemes introduce simple data association functions (such as matching activities according to volunteer skills), there are still significant technical limitations: first, the information of volunteers, activities, recipients, and other participants is stored in a scattered manner, making it difficult to form a unified knowledge carrier, which leads to the inability to explore deep associations between participants (such as the adaptability of volunteer historical service quality to current activity needs); second, matching decisions mainly rely on a single dimension (such as skill matching), ignoring key factors such as interest preferences and organization resource coordination capabilities, resulting in low matching accuracy; third, the evaluation system has a single dimension, and a scientific multi-level weight calculation model has not been established, making the development of scheduling strategies lack objective quantitative basis; fourth, the dynamic scheduling capability is insufficient, and it is difficult to adjust the matching scheme according to real-time data (such as temporary time conflicts of volunteers and changes in activity resource consumption), which may lead to problems such as resource waste and delayed response to recipient demand. Therefore, how to integrate multi-source heterogeneous data to explore deep semantic associations between volunteer service participants and build a multi-dimensional evaluation and decision-making system to achieve dynamic collaborative scheduling of participants and resources has become a difficult problem in the industry. SUMMARY

[0004] The present application provides a multi-dimensional collaborative processing volunteer service work management system and method, which can integrate multi-source heterogeneous data to explore deep semantic associations between volunteer service participants and build a multi-dimensional evaluation and decision-making system to achieve dynamic collaborative scheduling of participants and resources.

[0005] In a first aspect, the present application provides a multi-dimensional collaborative processing volunteer service work management method, comprising: construct a heterogeneous information network of multi-dimensional entities of volunteers, volunteer activities, recipients and organization units, and then fuse and align multi-source heterogeneous data in the heterogeneous information network to obtain a volunteer service knowledge graph; perform semantic embedding of entity nodes in the volunteer service knowledge graph based on a predefined meta-path set and path constraints to obtain semantic correlation strength between multi-dimensional entities, and then determine a matching preference coefficient between volunteers and volunteer activities according to all semantic correlation strengths; establish a multi-dimensional evaluation matrix between hierarchical structures of volunteer activities, volunteers, recipients and organization units, and then determine a combination weight of each hierarchical structure factor with respect to a total hierarchical structure based on the multi-dimensional evaluation matrix, and determine a multi-dimensional decision function of volunteer service management according to all combination weights; determine a collaborative scheduling strategy for volunteer service work based on the matching preference coefficient and the multi-dimensional decision function, and then dynamically match and collaboratively schedule volunteers, volunteer activities and recipients through the collaborative scheduling strategy.

[0006] In some embodiments, the multi-source heterogeneous data in the heterogeneous information network is fused and aligned to obtain a volunteer service knowledge graph, specifically including: standardize the multi-source heterogeneous data in the heterogeneous information network to obtain multi-source data with unified data format; perform entity disambiguation based on the multi-source data to generate a volunteer entity set; combine entity attributes in the heterogeneous information network to fuse entities in the volunteer entity set based on semantic correlation to obtain a plurality of entity relationship chains; generate a volunteer service knowledge graph based on all entity relationship chains.

[0007] In some embodiments, the semantic embedding of entity nodes in the volunteer service knowledge graph based on a predefined meta-path set and path constraints to obtain semantic correlation strength between multi-dimensional entities specifically includes: determine a predefined meta-path set; map entity nodes in the volunteer service knowledge graph to a low-dimensional vector space based on the meta-path set for entity semantic embedding to obtain entity semantic features; determine semantic correlation strength between multi-dimensional entities in the volunteer service knowledge graph according to the entity semantic features.

[0008] In some embodiments, the matching preference coefficient between volunteers and volunteer activities according to all semantic correlation strengths specifically includes: determine the strength type of each semantic correlation strength; construct a comparison judgment matrix based on the strength type of each semantic correlation strength; determine a matching preference coefficient between the volunteer and the volunteer activity based on all semantic correlation strengths and the comparison judgment matrix.

[0009] In some embodiments, establishing a multi-dimensional evaluation matrix between the volunteer activity, the volunteer, the recipient, and the organizational unit hierarchy specifically includes: building a hierarchy system of the volunteer service management on the volunteer activity, the volunteer, the recipient, and the organizational unit; determining evaluation indexes of each criterion layer in the hierarchy system; generating a judgment matrix of different dimensional criterion layers and the whole criterion layer according to all evaluation indexes; testing and integrating all judgment matrices to obtain a multi-dimensional evaluation matrix between the volunteer activity, the volunteer, the recipient, and the organizational unit hierarchy.

[0010] In some embodiments, determining a combined weight of each hierarchy factor relative to the total hierarchy based on the multi-dimensional evaluation matrix specifically includes: determining a single hierarchy weight of each hierarchy factor in the hierarchy system based on the multi-dimensional evaluation matrix; determining an initial combined weight of each hierarchy factor relative to the total hierarchy according to the single hierarchy weight of all hierarchy factors; performing overall consistency verification on all initial combined weights to obtain the combined weight of each hierarchy factor relative to the total hierarchy.

[0011] In some embodiments, determining a collaborative scheduling strategy of the volunteer service work based on the matching preference coefficient and the multi-dimensional decision function specifically includes: filtering out a combination of the volunteer and the volunteer activity as a candidate object of collaborative scheduling through the matching preference coefficient; substituting volunteer service scheduling strategies corresponding to all candidate objects into the multi-dimensional decision function to calculate a comprehensive decision value of each volunteer service scheduling strategy; prioritizing each volunteer service scheduling strategy according to all comprehensive decision values to obtain a collaborative scheduling strategy of the volunteer service work.

[0012] In a second aspect, the present application provides a multi-dimensional collaborative processing volunteer service work management system, comprising: a collection module configured to build a heterogeneous information network of multi-dimensional entities of volunteers, volunteer activities, recipients, and organizational units, and then fuse and align multi-source heterogeneous data in the heterogeneous information network to obtain a volunteer service knowledge graph; The processing module is configured to perform path constraint-based semantic embedding on entity nodes in the volunteer service knowledge graph through a predefined set of meta-paths, to obtain semantic correlation strengths between multi-dimensional entities, and to determine a matching preference coefficient between volunteers and volunteer activities according to all the semantic correlation strengths. The processing module is configured to establish a multi-dimensional evaluation matrix between volunteer activities, volunteers, beneficiaries, and organizational unit hierarchies, to determine combined weights of each hierarchical factor relative to a total hierarchy based on the multi-dimensional evaluation matrix, and to determine a multi-dimensional decision function for volunteer service management according to all the combined weights. The execution module is configured to determine a collaborative scheduling strategy for volunteer service work based on the matching preference coefficient and the multi-dimensional decision function, and to perform dynamic matching and resource collaborative scheduling of volunteers, volunteer activities, and beneficiaries through the collaborative scheduling strategy.

[0013] In a third aspect, the present application provides a computer device, which comprises a memory and a processor, the memory stores a code, and the processor is configured to acquire the code and execute the multi-dimensional collaborative processing volunteer service work management method described above.

[0014] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the multi-dimensional collaborative processing volunteer service work management method described above.

[0015] The technical scheme provided by the embodiments of the present application has the following beneficial effects: In the multi-dimensional collaborative processing volunteer service work management system and method provided by the present application, a multi-dimensional entity heterogeneous information network of volunteers, volunteer activities, beneficiaries, and organizational units is first constructed, and then multi-source heterogeneous data in the heterogeneous information network is fused and aligned to obtain a volunteer service knowledge graph. Path constraint-based semantic embedding is performed on entity nodes in the volunteer service knowledge graph through a predefined set of meta-paths to obtain semantic correlation strengths between multi-dimensional entities, and then a matching preference coefficient between volunteers and volunteer activities is determined according to all the semantic correlation strengths. A multi-dimensional evaluation matrix between volunteer activities, volunteers, beneficiaries, and organizational unit hierarchies is established, and then combined weights of each hierarchical factor relative to a total hierarchy are determined based on the multi-dimensional evaluation matrix, and a multi-dimensional decision function for volunteer service management is determined according to all the combined weights. A collaborative scheduling strategy for volunteer service work is determined based on the matching preference coefficient and the multi-dimensional decision function, and then dynamic matching and resource collaborative scheduling of volunteers, volunteer activities, and beneficiaries are performed through the collaborative scheduling strategy.

[0016] It can be seen that, by the cooperative scheduling strategy, the volunteers, volunteer activities and the assisted are dynamically matched and resource is cooperatively scheduled; first, the determination of the volunteer service knowledge graph can obtain a graph structure knowledge carrier for storing the volunteer service participating subjects and their attributes and the semantic association between the participating subjects, the determination of the volunteer service knowledge graph solves the problem of lack of effective fusion alignment of multi-source heterogeneous data in the prior art, realizes the association and penetration of the information of four core subjects of volunteers, volunteer activities, assisted and organization units, provides a unified structured knowledge carrier for all subsequent data processing and decision steps of the scheme, avoids the information missing problem caused by a single data source, and breaks through the limitations of unquantized entity semantic association and single dimension matching in the prior art, and provides data support for accurately calculating the semantic association strength and matching preference coefficient; then, the determination of the matching preference coefficient can obtain an index set of the quantitative matching degree of the volunteers and the volunteer activities, the determination of the matching preference coefficient can accurately represent the matching priority between the volunteers and the volunteer activities, breaks through the limitations of subjective matching decision and lack of objective quantitative support in the prior art, and provides a core quantitative basis for subsequent determination of the volunteer service cooperative scheduling strategy, and improves the scientificity and accuracy of the matching decision; then, the determination of the multi-dimensional decision function can obtain the final function of the quantitative volunteer service scheduling scheme comprehensive decision value, the determination of the multi-dimensional decision function integrates the multi-subject evaluation indexes with the combination weight of the four criteria of volunteer activity effectiveness, volunteer service capability, assisted demand adaptation and organization unit planning capability as the core coefficient, and through the linear weighting logic of coefficient x each dimension normalized score, the multi-dimensional and multi-subject evaluation information is converted into unified calculation logic, solves the problems of single dimension of the evaluation system and lack of multi-subject and multi-dimensional quantitative support for the scheduling strategy in the prior art, upgrades the scheduling strategy evaluation from single index judgment to multi-dimensional comprehensive measurement, ensures that the strategy can consider the whole-dimensional demand of activity efficiency, volunteer adaptation, assisted satisfaction and organization planning, and avoids the overall resource waste caused by local optimization; finally, the cooperative scheduling strategy of the volunteer service work is determined based on the matching preference coefficient and the multi-dimensional decision function; in summary, based on the above scheme, the multi-source heterogeneous data can be integrated to mine the deep semantic association between the volunteer service participating subjects and construct a multi-dimensional evaluation decision system to realize the dynamic cooperative scheduling of the participating subjects and the resources. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is an exemplary flowchart of a multi-dimensional cooperative processing volunteer service work management method according to some embodiments of the present application; Figure 2 is an exemplary flowchart of determining a volunteer service knowledge graph according to some embodiments of the present application; Figure 3 is an operation flowchart of determining a combination weight according to some embodiments of the present application; Figure 4is a structural schematic diagram of a multi-dimensional collaborative processing volunteer service work management system according to some embodiments of the present application; Figure 5 is an internal structure diagram of a computer device implementing a multi-dimensional collaborative processing volunteer service work management method according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in combination with the drawings of the specification and specific embodiments.

[0019] Reference Figure 1 The figure is an exemplary flowchart of a multi-dimensional collaborative processing volunteer service work management method according to some embodiments of the present application, which mainly includes the following steps: In step 101, a multi-dimensional entity heterogeneous information network of volunteers, volunteer activities, beneficiaries and organization units is constructed, and then multi-source heterogeneous data in the heterogeneous information network is fused and aligned to obtain a volunteer service knowledge graph.

[0020] It should be noted that in the present application, the heterogeneous information network is a data processing network that defines the semantic structure of various participating subjects in volunteer service data and mines deep information. In the present scheme, by constructing a heterogeneous information network containing multi-dimensional entities such as volunteers, volunteer activities, beneficiaries and service evaluation and their semantic associations, a precise and intelligent matching basis for college volunteer services can be provided, precise matching of volunteers and volunteer activities can be achieved, and problems such as repeated service for beneficiaries and uneven distribution of volunteer service can be avoided, helping to achieve the goal of multi-state service and precise service object matching. In specific implementation, the construction of the multi-dimensional entity heterogeneous information network of volunteers, volunteer activities, beneficiaries and organization units can be implemented in the following manner, i.e., the core data of volunteer services can be extracted from the database of the volunteer service work management system, including the basic information, hobbies, skills mastered and historical volunteer service records of volunteers, the activity content, time period and required skills of volunteer activities, the service condition and service evaluation of beneficiaries, and the basic information, resource list and jurisdiction of organization units. Then, the attribute definition of the four types of entities of volunteers, volunteer activities, beneficiaries and organization units and the semantic relationship between entities are determined by referring to existing heterogeneous information network construction methods (such as the meta-path-based heterogeneous information network construction method), including the participation and being participated relationship between volunteers and volunteer activities, the service and being served relationship between volunteer activities and beneficiaries, the mastered and being mastered relationship between volunteers and skills, and the belonging and being belonged relationship between volunteers and hobbies, etc. Finally, a heterogeneous information network containing multi-dimensional entities, entity attributes and semantic associations is formed.

[0021] In some embodiments, with reference to Figure 2FIG. 1 is an exemplary flow chart for determining a volunteer service knowledge graph according to some embodiments of the present application. The present application can use the following steps to achieve the fusion and alignment of multi-source heterogeneous data in the heterogeneous information network to obtain a volunteer service knowledge graph: In step 1011, the multi-source heterogeneous data in the heterogeneous information network is standardized to obtain multi-source data with uniform data format. In step 1012, entity disambiguation is performed based on the multi-source data to generate a set of volunteer entities. In step 1013, the entities in the set of volunteer entities are semantically associated and fused in combination with the entity attributes in the heterogeneous information network to obtain a plurality of entity relationship chains. In step 1014, a volunteer service knowledge graph is generated based on all the entity relationship chains.

[0022] In a specific implementation, the multi-source heterogeneous data in the heterogeneous information network can be standardized to obtain multi-source data with uniform data format using the following method, i.e., obtaining multi-source heterogeneous data composed of four types of data, i.e., volunteers, volunteer activities, beneficiaries, and organizational units, in the heterogeneous information network, and using existing data standardization techniques to map the text attributes of the multi-source data (such as service skills: first aid) to structured codes (such as “first aid → SK-001”), to uniformly convert numerical attributes (such as service duration: 150 minutes) to hour units (such as “150 minutes → 2.5 hours”), and to normalize regional attributes (such as “XX area XX community”) using a two-level identification of “area code + community code”, and output multi-source heterogeneous data with uniform format. The multi-source heterogeneous data is a data set with different data formats and types but carrying key information of volunteer services. The multi-source data is a data set carrying key information of volunteer services with uniform format and data type, which can provide comprehensive basic data for subsequent data fusion and alignment and knowledge graph construction, and avoid information missing problems caused by a single data source. The data standardization techniques can include dictionary mapping and coding techniques, unit uniform conversion techniques, and two-level identification normalization techniques.

[0023] In a specific implementation, the entity disambiguation based on the multi-source data and the generation of the volunteer entity set can be implemented in the following manner: first, taking "name + student ID" as the exclusive identifier of a volunteer and "activity code + holding period" as the exclusive identifier of a volunteer activity, and based on the exclusive identifiers of the volunteers and the volunteer activities, the suspected duplicate entities in the multi-source data are preliminarily screened, then a path similarity algorithm is called to calculate the semantic similarity of the suspected duplicate entities, and the suspected duplicate entities with a similarity greater than or equal to 0.9 are determined as duplicate entities and removed, and finally the de-duplicated volunteer entity set is output; wherein the volunteer entity set is a set of key participating subjects in the volunteer service process, including uniquely identified volunteers, volunteer activities, beneficiaries and organizational units, the volunteer entity set can eliminate the duplication and redundancy of entities, ensure the accuracy of subsequent semantic association fusion and matching analysis, and lay an entity foundation for accurate association construction.

[0024] In a specific implementation, the semantic association fusion of the entities in the volunteer entity set in combination with the entity attributes in the heterogeneous information network can be implemented in the following manner: the semantic association construction method is used to establish four types of semantic associations of "volunteer-master-service skill", "volunteer-participate-volunteer activity", "volunteer activity-service-beneficiary" and "organizational unit-unified-volunteer activity" according to the volunteer entity set and the entity attributes (such as "service skill" of a volunteer and "required skill" of a volunteer activity) in the heterogeneous information network with reference to the pre-defined core association types of volunteer service, and simultaneously associate the dynamic attributes (such as "service score" of a beneficiary and "resource consumption" of a volunteer activity) in the heterogeneous information network to the corresponding relationship links to form a structured entity relationship chain such as "volunteer-participate (service duration 2.5 hours)-volunteer activity-service (score 4.8)-beneficiary", thereby obtaining a plurality of entity relationship chains; wherein the entity relationship chain is a structured link that serially connects the semantic associations between volunteer service entities, the entity relationship chain can clearly present the logical associations between entities, provide structured association support for the volunteer service knowledge graph, and assist in subsequent semantic embedding and association strength calculation.

[0025] It should be noted that in the present application, the volunteer service knowledge graph is a graph structure knowledge carrier that stores the participating subjects of volunteer service and their attributes and the semantic associations between the participating subjects, the volunteer service knowledge graph can integrate the knowledge in the field of volunteer service, provide comprehensive knowledge support for the accurate matching of volunteers and volunteer activities, the establishment of a multi-dimensional evaluation matrix and the formulation of a collaborative scheduling strategy, and improve the accuracy and efficiency of the management of university volunteer service.

[0026] In a specific implementation, the generation of the volunteer service knowledge graph based on all entity relationship chains can be implemented in the following manner, i.e., all entities in the entity relationship chains can be defined as entity nodes, entity attributes can be defined as node attributes, semantic associations can be defined as edges between nodes, and all entity relationship chains can be imported into a graph database in the structure of "node-edge-attribute" by using existing graph database construction technology (such as Neo4j), and a daily incremental synchronization + emergency data real-time synchronization update mechanism can be set to update the newly added data on the same day and handle emergency activities and volunteer adjustments, so as to finally output a volunteer service knowledge graph with complete entities, attributes and association relationships.

[0027] In step 102, the entity nodes in the volunteer service knowledge graph are subjected to path constraint-based semantic embedding through a predefined meta-path set, so as to obtain the semantic association strength between multi-dimensional entities, and then determine the matching preference coefficient between volunteers and volunteer activities according to all the semantic association strengths.

[0028] In some embodiments, the path constraint-based semantic embedding of the entity nodes in the volunteer service knowledge graph through a predefined meta-path set to obtain the semantic association strength between multi-dimensional entities can be implemented in the following steps: determine a predefined meta-path set; map the entity nodes in the volunteer service knowledge graph to a low-dimensional vector space based on the meta-path set for entity semantic embedding, to obtain entity semantic features; determine the semantic association strength between multi-dimensional entities in the volunteer service knowledge graph according to the entity semantic features.

[0029] It should be noted that, in the present application, the meta-path set is a combination of entity connection paths predefined for core scenarios such as skill matching and historical service adaptation in the process of volunteer service management, which contains the unique identifier, entity order, adaptation scenario and association type description of each meta-path. The meta-path set can accurately reflect the key semantic association between entities, provide clear path constraints for entity semantic embedding, ensure that the embedding direction meets the precise matching requirements of college volunteer services, and avoid semantic deviation from the core scenarios.

[0030] In a specific implementation, the predefined set of meta-paths can be determined based on the entity types and the fixed association logic between entities in the volunteer service knowledge graph, combined with the core scene requirements of the volunteer service precise matching (such as skill adaptation, historical service reference, interest association, etc.) to obtain the predefined set of meta-paths, that is, the effective association types between entities in the volunteer service knowledge graph can be sorted out to exclude irrelevant associations (such as “volunteer-irrelevant resource-volunteer activity”), the meta-path “volunteer-service skill-volunteer activity” is defined for the skill matching scene, the meta-path “volunteer-participation-volunteer activity-service-recipient” is defined for the historical service adaptation scene, and the meta-path “volunteer-interest label-volunteer activity” is defined for the interest assistance scene, thereby outputting the structured set of meta-paths.

[0031] In a specific implementation, the entity nodes in the volunteer service knowledge graph can be mapped into a low-dimensional vector space based on the set of meta-paths for entity semantic embedding to obtain entity semantic features, which can be achieved in the following way: first, for each meta-path in the set of meta-paths, the number of associated instances of the entity nodes in the volunteer service knowledge graph under the meta-path is counted, for example, the number of instances of “volunteer A-service skill-volunteer activity B”, and the semantic similarity between each two entity nodes in the volunteer service knowledge graph under the meta-path is calculated using a path similarity algorithm, that is, the semantic similarity is equal to the number of instances between the two entities that meet the meta-path divided by the sum of the number of instances that meet the meta-path for each of the two entities, thereby generating a semantic similarity matrix under the path according to the semantic similarity between all entity nodes. The semantic similarity matrix under each meta-path in the set of meta-paths can be obtained through the above steps; then, the semantic similarity matrices of all meta-paths are mapped into a low-dimensional vector space for integration using existing dimension reduction techniques (such as principal component analysis dimension reduction technique) so that the distance between entity nodes in the vector space is positively correlated with the semantic similarity, and the matrix composed of the integrated low-dimensional vectors is used as the entity semantic features; wherein the entity semantic features are low-dimensional vector features representing the semantic connotation of the entity in the volunteer service knowledge graph, which can convert the abstract semantic association of the entity into specific numerical values, provide an operable quantitative basis for subsequent calculation of semantic association strength, and solve the problem of difficult direct measurement of semantics.

[0032] In a specific implementation, the determination of the semantic association strength between the multi-dimensional entities in the volunteer service knowledge graph according to the entity semantic features can be implemented in the following manner: first, for each two entity nodes in the volunteer service knowledge graph, the semantic association strength between the two entity nodes can be calculated based on the entity semantic vectors of the two entity nodes in the entity semantic features, that is, the ratio of the dot product of the two entity semantic vectors to the product of the lengths of the two entity semantic vectors. Through the above steps, the semantic association strength between each two entity nodes in the volunteer service knowledge graph can be obtained, and thus the semantic association strength between the multi-dimensional entities in the volunteer service knowledge graph can be obtained.

[0033] It should be noted that in the present application, the semantic association strength is a quantitative index reflecting the closeness of the semantic association between the multi-dimensional entities in the volunteer service knowledge graph. The semantic association strength can accurately quantify the adaptability between entities, provide core data support for subsequent determination of the matching preference coefficient between volunteers and volunteer activities, and improve the scientificity of the matching decision.

[0034] In some embodiments, the determination of the matching preference coefficient between volunteers and volunteer activities according to all the semantic association strengths can be implemented in the following steps: determining the strength type of each semantic association strength; constructing a comparison judgment matrix based on the strength type of each semantic association strength; determining the matching preference coefficient between volunteers and volunteer activities based on all the semantic association strengths and the comparison judgment matrix.

[0035] In a specific implementation, the determination of the strength type of each semantic association strength can be implemented in the following manner: the semantic association strength between the entities corresponding to the meta-path of “volunteer-service skill-volunteer activity” can be defined as skill adaptation type semantic association strength according to the entity association records under each meta-path in the meta-path set, reflecting the matching degree of volunteer skills and activity requirements; the semantic association strength between the entities corresponding to the meta-path of “volunteer-participation-volunteer activity-service-recipient” can be defined as historical service type semantic association strength, reflecting the adaptability of the volunteer's past service and the current activity; and the semantic association strength between the entities corresponding to the meta-path of “volunteer-interest label-volunteer activity” can be defined as interest matching type semantic association strength, which can assist in improving the personalization of matching, so as to clearly determine the strength type of each semantic association strength. The strength type is a category classified according to the core role of the semantic association strength according to the matching requirements of university volunteer service, including skill adaptation type, historical service type, and interest matching type. The strength type can clearly determine the functional positioning of different semantic association strengths in the matching decision, and provide clear classification basis for subsequent construction of the comparison judgment matrix and allocation of weights.

[0036] In a specific implementation, the construction of the comparison judgment matrix based on the strength types of the respective semantic association strengths can be achieved in the following manner: the ratio scale technique in the analytic hierarchy process can be used to invite multiple volunteer service management experts (e.g., 5) to compare the importance of the three types of strength according to the three types of semantic association strengths that have been determined and the pre-set core objectives of the volunteer service matching (e.g., skill priority, historical reference, interest assistance) to generate a preliminary comparison judgment matrix, calculate the consistency index of the preliminary comparison judgment matrix, i.e., (the maximum eigenvalue of the matrix - the order of the matrix) ÷ (the order of the matrix - 1), and refer to the random consistency index table of the analytic hierarchy process to determine the random consistency index of the judgment matrix, then calculate the consistency ratio of the judgment matrix, i.e., the consistency index divided by the random consistency index, if the consistency ratio is less than 0.1, it is determined that the preliminary comparison judgment matrix is valid, otherwise, the volunteer service management experts are invited to adjust the scores again until the preliminary comparison judgment matrix passes the consistency test, and then the preliminary comparison judgment matrix that passes the consistency test is used as the comparison judgment matrix; wherein the comparison judgment matrix is a quantitative matrix that converts the subjective judgments of volunteer service management experts into objective values, which can provide a structured tool for scientifically determining the adaptation weights of the respective strength types and avoid the randomness of weight allocation.

[0037] In a specific implementation, the determination of the matching preference coefficients between the volunteers and the volunteer activities based on all the semantic association strengths and the comparison judgment matrix can be achieved in the following manner: first, the geometric mean of each row element of the comparison judgment matrix is calculated using the square root method in the analytic hierarchy process, and all the geometric means are normalized to the interval [0, 1] to obtain the adaptation weights of the three types of strength, for example, the adaptation weight of the skill adaptation type is 0.5, the adaptation weight of the historical service type is 0.3, and the adaptation weight of the interest matching type is 0.2; then, the matching coefficients of each volunteer and volunteer activity are calculated according to all the semantic association strengths and normalized to the interval [0, 1], i.e., the matching coefficient of volunteer i and volunteer activity j = the adaptation weight of the skill adaptation type × the skill adaptation type semantic association strength between volunteer i and volunteer activity j + the adaptation weight of the historical service type × the historical service type semantic association strength between volunteer i and volunteer activity j + the adaptation weight of the interest matching type × the interest matching type semantic association strength between volunteer i and volunteer activity j; finally, the set of matching coefficients of all volunteer-volunteer activity combinations is used as the matching preference coefficients between the volunteers and the volunteer activities.

[0038] It should be noted that in this application, the matching preference coefficients are a set of indicators that quantify the adaptation degree of volunteers and volunteer activities, which can accurately represent the matching priority between volunteers and volunteer activities and provide a core quantitative basis for subsequent determination of volunteer service coordination scheduling strategies, thereby improving the scientificity and accuracy of the matching decision.

[0039] In step 103, a multi-dimensional evaluation matrix between the hierarchical structures of the volunteer activities, volunteers, recipients and organization units is established, and then the combined weights of each hierarchical structure factor relative to the total hierarchical structure are determined based on the multi-dimensional evaluation matrix, and a multi-dimensional decision function of the volunteer service management is determined according to all the combined weights.

[0040] In some embodiments, the multi-dimensional evaluation matrix between the hierarchical structures of the volunteer activities, volunteers, recipients and organization units can be established by the following steps: A hierarchical structure system of the volunteer service management on the volunteer activities, volunteers, recipients and organization units is constructed; Evaluation indexes of each criterion layer in the hierarchical structure system are determined; A judgment matrix of different dimension criterion layers and the whole criterion layers is generated according to all the evaluation indexes; All the judgment matrices are tested and integrated to obtain the multi-dimensional evaluation matrix between the hierarchical structures of the volunteer activities, volunteers, recipients and organization units.

[0041] It should be noted that in this application, the hierarchical structure system is a hierarchical framework built according to the target layer, criterion layer and evaluation index layer according to the goal of improving the efficiency of university volunteer service management. The hierarchical structure system can clearly define the subordinate relationship and evaluation logic of each level in the volunteer service management, and provide a structured basis for subsequent evaluation index determination and judgment matrix construction.

[0042] In specific implementation, the hierarchical structure system of the volunteer service management on the volunteer activities, volunteers, recipients and organization units can be constructed by the following method, that is, the hierarchical division technology of the analytic hierarchy process can be used to construct the hierarchical structure system of the volunteer service management, that is, the preset optimization target of the volunteer service management is obtained, and the target layer is defined as the optimization target of the volunteer service management to clearly define the overall optimization direction. The criterion layer is refined into different dimensions according to the volunteer service participants, including the volunteer activity efficiency criterion layer, the volunteer service ability criterion layer, the recipient demand adaptation criterion layer and the organization unit overall planning ability criterion layer. The evaluation index layer is associated with the core evaluation direction of each criterion layer, for example, the volunteer activity efficiency criterion layer is associated with the demand matching degree and the resource utilization rate, and the hierarchical logical correlation is demonstrated by the volunteer service management experts to ensure the clear subordinate relationship of each level, thereby obtaining the hierarchical structure system of the volunteer service management on the volunteer activities, volunteers, recipients and organization units.

[0043] In a specific implementation, the evaluation indexes of each criterion layer in the hierarchical system can be determined in the following manner: based on the existing volunteer service evaluation system and existing operation data, the evaluation indexes of different dimension criterion layers in the hierarchical system can be determined based on the principle of "quantifiable and strong correlation", for example, the activity demand matching degree (i.e., the matching rate of activity content and assistance demand), resource utilization efficiency (i.e., the ratio of material / human input to service output), and time period matching rationality (i.e., the matching rate of activity time period and volunteer idle time period) are selected as the three indexes of the volunteer activity effectiveness criterion layer, the skill compliance rate (i.e., the proportion of volunteers with the required skills), service time length stability (i.e., the deviation rate of actual service time length and committed time length), and historical service good evaluation rate (i.e., the proportion of past assistance evaluators with a rating of 4 stars or above) are selected as the three indexes of the volunteer service capability criterion layer, the demand response time efficiency (i.e., the time length from demand submission to service start), service satisfaction (i.e., the average rating of service by assistance recipients), and demand repeated solution rate (i.e., the proportion of the same demand requiring multiple services) are selected as the three indexes of the assistance recipient demand adaptation criterion layer, and the resource scheduling efficiency (i.e., the time length of material allocation), emergency response speed (i.e., the service start time length for sudden demand), and incentive mechanism perfection degree (i.e., the coverage proportion of volunteer incentive measures) are selected as the three indexes of the organization unit coordination capability criterion layer; wherein, the evaluation index refers to the quantifiable evaluation item of different dimension criterion layers in the hierarchical system on the demand of volunteer service management, which can convert the abstract criterion layer dimension into a specific measurable index, providing practical basis for subsequent judgment matrix construction and evaluation quantization.

[0044] In a specific implementation, the judgment matrix of different dimension criterion layers and the overall criterion layer can be generated based on all evaluation indexes in the following manner: the proportion scaling method of the analytic hierarchy process is used to invite multiple volunteer service management experts (e.g., 5) to compare the importance of the four dimensions of the criterion layer to generate the judgment matrix of the overall criterion layer; at the same time, for different dimension criterion layers, volunteer service management experts are invited to compare the importance of the evaluation indexes under the criterion layer to generate the judgment matrix of the corresponding dimension criterion layer, thereby obtaining the judgment matrix of each dimension criterion layer; wherein, the judgment matrix is a quantization matrix constructed by volunteer service management experts comparing the importance of the criterion layer dimension or the evaluation indexes under different dimension criterion layers, which can convert the subjective judgment of volunteer service management experts into objective values, providing tool support for scientific calculation of index weight and avoiding evaluation subjectivity.

[0045] It should be noted that in the present application, the multi-dimensional evaluation matrix is a multi-dimensional judgment matrix for evaluating the importance of the index under the management hierarchy of volunteer service. The multi-dimensional evaluation matrix can help the system integrate the multi-subject and multi-dimensional evaluation information of volunteer service, and provide complete and reliable evaluation data support for subsequent determination of combination weight and construction of multi-dimensional decision function. In specific implementation, the consistency of all judgment matrices is tested and integrated to obtain the multi-dimensional evaluation matrix between the multiple hierarchical structures of volunteer activities, volunteers, recipients and organization units, which can be realized in the following manner, that is: first, for each judgment matrix, the consistency index of the judgment matrix is calculated, that is: (the maximum eigenvalue of the matrix-the order of the matrix) ÷ (the order of the matrix-1), and the random consistency index of the judgment matrix is determined by referring to the random consistency index table of the analytic hierarchy process, then the consistency ratio of the judgment matrix is calculated, that is: the consistency index divided by the random consistency index, if the consistency ratio is less than 0.1, the matrix is determined to pass the test, if the consistency ratio is greater than or equal to 0.1, the volunteer service management experts are invited to adjust the score again, and the test is repeated until all judgment matrices pass the test; then, the existing matrix integration method (such as hierarchical matrix correlation integration method) is used to integrate the overall judgment matrix of the criterion layer and the judgment matrix of each dimension criterion layer that pass the test to form a multi-dimensional evaluation matrix containing hierarchical structure, judgment matrix and verification result.

[0046] In some embodiments, with reference to Figure 3 The figure is an operation flow chart for determining combination weight according to some embodiments of the present application, and in the present application, the determination of the combination weight of each hierarchical factor relative to the total hierarchical structure based on the multi-dimensional evaluation matrix can be realized in the following steps: Determine the single hierarchical weight of each hierarchical factor in the hierarchical system based on the multi-dimensional evaluation matrix; Determine the initial combination weight of each hierarchical factor relative to the total hierarchical structure according to the single hierarchical weight of all hierarchical factors; Integrate the overall consistency of all initial combination weights to obtain the combination weight of each hierarchical factor relative to the total hierarchical structure.

[0047] In a specific implementation, the single-level weight of each hierarchical factor in the hierarchical system can be determined based on the multi-dimensional evaluation matrix in the following manner: for the judgment matrix of each dimension criterion layer in the multi-dimensional evaluation matrix, the geometric mean of each row element in the judgment matrix is calculated, and the geometric mean of each row element is divided by the sum of all geometric means to obtain the single-level weight of each hierarchical factor of the criterion layer (i.e., the evaluation index of the criterion layer, such as the volunteer service ability and the skill compliance rate). The single-level weight refers to the quantitative value of the importance of the hierarchical factor of the criterion layer in the hierarchical system. The single-level weight can provide a basic quantitative basis for subsequent overall weight synthesis, and can clarify the relative importance of the factors in a single level to avoid confusion in the calculation of the weight between levels.

[0048] In a specific implementation, the initial combined weight of each hierarchical factor relative to the overall hierarchy can be determined based on the single-level weight of all hierarchical factors in the following manner: first, for the judgment matrix of the criterion layer as a whole in the multi-dimensional evaluation matrix, the geometric mean of each row element in the judgment matrix is calculated, and the geometric mean of each row element is divided by the sum of all geometric means to obtain the single-level weight of each dimension criterion layer. Then, for each hierarchical factor, the single-level weight of the hierarchical factor is multiplied by the single-level weight of the dimension criterion layer corresponding to the hierarchical factor to obtain the initial combined weight of the hierarchical factor relative to the overall hierarchy. Through the above steps, the initial combined weight of each hierarchical factor relative to the overall hierarchy can be obtained. The initial combined weight refers to the initial quantitative value of the importance of the hierarchical factor of the criterion layer relative to the overall hierarchy in the hierarchical system. The initial combined weight preliminarily integrates the weight information of each level to form the approximate importance proportion of the factors of the criterion layer, and provides a weight basis to be verified for subsequent consistency verification.

[0049] In a specific implementation, the overall consistency of all initial combination weights is verified, and the combination weight of each hierarchical factor relative to the total hierarchy can be implemented in the following manner, that is, the initial combination weight of each hierarchical factor is multiplied by the consistency ratio of the corresponding judgment matrix of the hierarchical factor to obtain the consistency ratio of the initial combination weight, and the sum of the consistency ratios of all initial combination weights is taken as the overall consistency ratio. If the overall consistency ratio is greater than or equal to 0.1, the weight deviation analysis is entered. For each initial combination weight, the deviation of the initial combination weight is calculated, that is, the difference between the initial combination weight and the average value of all initial combination weights ÷ the average value of all initial combination weights. If the deviation exceeds 5%, the initial combination weight is determined to be an abnormal value. The judgment matrix corresponding to the abnormal value is traced back to recalculate the single-level weight, and the modified single-level weight is used to synthesize a new initial combination weight again. Through the above steps, the weight deviation analysis of each initial combination weight can be performed. The verification is repeated until there is no abnormal value and the overall consistency ratio is less than 0.1. The modified initial combination weight of all is taken as the combination weight of each hierarchical factor relative to the total hierarchy.

[0050] It should be noted that in the present application, the combination weight refers to the final importance quantification value of the criterion layer hierarchical factor relative to the total hierarchy after the overall consistency verification of the hierarchical structure system. This combination weight can ensure that the weight has scientific effectiveness, provides a core quantification coefficient for constructing a volunteer service multi-dimensional decision function, accurately matching volunteers and volunteer activities, and supports the scientific formulation of collaborative scheduling strategies.

[0051] In some embodiments, the multi-dimensional decision function for volunteer service management according to all combination weights can be implemented in the following steps: All combination weights are taken as the coefficients of each dimension of the criterion layer to establish a function basic framework. The function basic framework is subjected to effectiveness verification to obtain a multi-dimensional decision function for volunteer service management.

[0052] In a specific implementation, the function basic framework can be established by using the following method: all the combination weights are used as the coefficients of each dimension of the criterion layer. The function basic framework can be established by using the linear weighting model of the analytic hierarchy process, that is, the sum of the combination weights of all the hierarchical structure factors in each core dimension is used as the coefficient of the corresponding core dimension. At the same time, the variable is defined as the normalized score of the volunteer service scheduling scheme (such as priority scheduling and resource balance scheduling) in each dimension of the criterion layer. Thus, the function basic framework is obtained, that is, the comprehensive decision value of the volunteer service scheduling scheme = volunteer activity effectiveness coefficient x volunteer activity effectiveness score + volunteer service capacity coefficient x volunteer service capacity score + recipient demand adaptation coefficient x recipient demand adaptation score + organizational unit planning capacity coefficient x organizational unit planning capacity score. The function basic framework is a linear weighted preliminary function structure established by the normalized score of the scheduling scheme in each criterion of the volunteer service management volunteer activity effectiveness, volunteer service capacity, recipient demand adaptation, and organizational unit planning capacity. The function basic framework can clearly determine the core components of the multi-dimensional decision function, including coefficients, variables, and logical expressions, and provides a standardized basic framework for subsequent effectiveness verification and function optimization, avoiding logical confusion in function construction.

[0053] In a specific implementation, the function basic framework is verified for effectiveness, and the multi-dimensional decision function of volunteer service management can be implemented by using the following method: the function basic framework is verified for effectiveness by using the technical solution of Pearson correlation coefficient analysis and historical data backtracking verification, that is, the scheduling scheme records of multiple volunteer activities, the scores of each scheduling scheme in different dimension criterion layers, and actual management effectiveness data (including recipient satisfaction mean, resource utilization efficiency, and volunteer matching precision) in the last three years are input. The scores of the scheduling scheme in the volunteer service historical operation data are substituted into the function basic framework to calculate the comprehensive decision value, and the correlation coefficient between the comprehensive decision value and the actual management effectiveness data is calculated by using the Pearson correlation coefficient formula. If the correlation coefficient is less than a preset threshold (such as 0.85), the consistency of the combination weights or the rationality of the evaluation score quantization (such as correcting the abnormal “demand response timeliness” score) is checked back, and the correlation coefficient is calculated again until the correlation coefficient is greater than or equal to the preset threshold. Finally, the multi-dimensional decision function of volunteer service management that passes the verification is output.

[0054] It should be noted that in the present application, the multi-dimensional decision function is the final function for quantifying the comprehensive decision value of the volunteer service scheduling scheme, which can integrate multi-dimensional evaluation information, objectively quantify the advantages and disadvantages of different scheduling schemes, provide a scientific basis for the selection of volunteer service collaborative scheduling strategy, and effectively improve the accuracy and efficiency of university volunteer service management decision-making.

[0055] In step 104, the collaborative scheduling strategy of the volunteer service work is determined based on the matching preference coefficient and the multi-dimensional decision function, and then the volunteers, volunteer activities and beneficiaries are dynamically matched and resource collaboratively scheduled through the collaborative scheduling strategy.

[0056] In some embodiments, determining the collaborative scheduling strategy of the volunteer service work based on the matching preference coefficient and the multi-dimensional decision function can be implemented by the following steps: Filtering the combination of volunteers and volunteer activities as candidate objects for collaborative scheduling through the matching preference coefficient; Substituting the volunteer service scheduling strategy corresponding to all candidate objects into the multi-dimensional decision function to calculate the comprehensive decision value of each volunteer service scheduling strategy; According to all the comprehensive decision values, the priority of each volunteer service scheduling strategy is sorted to obtain the collaborative scheduling strategy of the volunteer service work.

[0057] In specific implementation, filtering the combination of volunteers and volunteer activities as candidate objects for collaborative scheduling through the matching preference coefficient can be implemented in the following way, that is, first, the adaptability threshold (such as 0.2) can be set according to the demand of university volunteer service scene; then, all combinations of volunteers and volunteer activities are traversed, the matching coefficients of each combination are extracted in the matching preference coefficient, the combinations whose matching coefficients are less than the adaptability threshold are excluded, and the combinations whose matching coefficients are greater than or equal to the adaptability threshold are reserved as candidate objects for volunteer service collaborative scheduling; wherein, the candidate object is the precise adaptation combination of volunteers and volunteer activities after the matching preference coefficient threshold screening, which can exclude low adaptation and no execution condition combinations for subsequent scheduling strategy calculation, reduce invalid calculation amount, and provide high-quality basic objects for collaborative scheduling.

[0058] In a specific implementation, the comprehensive decision value of each volunteer service scheduling strategy can be calculated by substituting the volunteer service scheduling strategies corresponding to all candidate objects into the multi-dimensional decision function in the following manner: the candidate object-scene adaptive scheduling strategy generation method is used to generate volunteer service scheduling strategies corresponding to all candidate objects. For each volunteer service scheduling strategy, the normalized scores of the volunteer service scheduling strategy in each dimension criterion layer are determined based on historical operation data, and the normalized scores of each dimension criterion layer are substituted into the multi-dimensional decision function to calculate the comprehensive decision value of the scheduling strategy. Through the above steps, the comprehensive decision value of each volunteer service scheduling strategy can be obtained. The comprehensive decision value is a numerical value quantifying the comprehensive performance of the volunteer service scheduling strategy in the adaptability, efficiency and resource utilization dimensions. The higher the comprehensive decision value, the better the comprehensive performance of the volunteer service scheduling in the adaptability, efficiency and resource utilization dimensions. The comprehensive decision value can convert the abstract strategy advantages and disadvantages into comparable objective data, providing a core quantitative basis for scheduling strategy priority ranking.

[0059] In a specific implementation, the priority ranking of each volunteer service scheduling strategy according to all comprehensive decision values to obtain the collaborative scheduling strategy of volunteer service work can be achieved in the following manner: the scheduling strategy descending order sorting algorithm is used to sort all volunteer service scheduling strategies in descending order of comprehensive decision value, and the sequence obtained after sorting is used as the collaborative scheduling strategy of volunteer service work.

[0060] It should be noted that in this application, the collaborative scheduling strategy is a feasible strategy that combines the execution priority, the matching relationship between volunteers and volunteer activities, the resource allocation scheme and the emergency plan in the volunteer service scene. The collaborative scheduling strategy can integrate the matching preferences of volunteers and volunteer activities and the multi-dimensional evaluation of volunteer activities to ensure the optimal adaptability, efficiency and resource allocation of volunteer services, and improve the management and execution efficiency.

[0061] In a specific implementation, the dynamic matching and resource collaborative scheduling of volunteers, volunteer activities and beneficiaries through the collaborative scheduling strategy can be achieved in the following manner: the intelligent resource allocation algorithm is used to carry out dynamic matching and resource scheduling based on the collaborative scheduling strategy, that is, according to the explicit resource allocation scheme in the collaborative scheduling strategy, real-time inventory data, volunteer distribution location, the principle of near-range resource priority allocation for emergency activities and balanced distribution for regular activities, the optimal material allocation path and personnel collection time node are calculated and output, and real-time execution feedback data (such as material delivery status and volunteer on-site status) is received. If there is a deviation (such as material delay), the scheduling scheme is adjusted based on the collaborative scheduling strategy to ensure efficient implementation of dynamic matching and resource scheduling, and improve the execution accuracy and resource utilization rate of volunteer services.

[0062] In addition, another aspect of the present application, in some embodiments, the present application provides a multi-dimensional collaborative processing of volunteer service work management system, reference Figure 4 The figure is a structural schematic diagram of a multi-dimensional collaborative processing of volunteer service work management system 400 according to some embodiments of the present application, which includes a collection module 401, a processing module 402 and an execution module 403, which are described as follows: The collection module 401 is mainly used for constructing a multi-dimensional heterogeneous information network of volunteers, volunteer activities, beneficiaries and organizational units in the present application, and then fusing and aligning multi-source heterogeneous data in the heterogeneous information network to obtain a volunteer service knowledge graph; The processing module 402 is mainly used for performing semantic embedding of entity nodes in the volunteer service knowledge graph based on path constraints through a predefined meta-path set in the present application, obtaining semantic correlation strength between multi-dimensional entities, and then determining a matching preference coefficient between volunteers and volunteer activities according to all semantic correlation strengths; It should be noted that the processing module 402 is also used for establishing a multi-dimensional evaluation matrix between volunteer activities, volunteers, beneficiaries and organizational unit hierarchies in the present application, and then determining a combination weight of each hierarchy factor with respect to the total hierarchy based on the multi-dimensional evaluation matrix, and determining a multi-dimensional decision function of volunteer service management according to all combination weights; The execution module 403 is mainly used for determining a collaborative scheduling strategy of volunteer service work based on the matching preference coefficient and the multi-dimensional decision function in the present application, and then dynamically matching and resource collaborative scheduling volunteers, volunteer activities and beneficiaries through the collaborative scheduling strategy.

[0063] The above-mentioned modules of the multi-dimensional collaborative processing of volunteer service work management system can be realized by software, hardware and their combinations in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned modules.

[0064] In addition, in one embodiment, the present application provides a computer device which can be a server, and its internal structure diagram can be as follows: Figure 5As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the multi-dimensional collaborative processing volunteer service work management method data. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program can implement a multi-dimensional collaborative processing volunteer service work management method when executed by the processor.

[0065] Those skilled in the art can understand that, Figure 5 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0066] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above multi-dimensional collaborative processing volunteer service work management method embodiments.

[0067] In one embodiment, a computer readable storage medium is provided, storing a computer program, which is executed by a processor to implement the steps in the above multi-dimensional collaborative processing volunteer service work management method embodiments.

[0068] In one embodiment, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in the above multi-dimensional collaborative processing volunteer service work management method embodiments.

[0069] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0070] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0071] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A multi-dimensional collaborative management method for volunteer service work, characterized in that, Includes the following steps: A heterogeneous information network of multi-dimensional entities, including volunteers, volunteer activities, beneficiaries, and organizing units, is constructed. Then, the multi-source heterogeneous data in the heterogeneous information network are fused and aligned to obtain a volunteer service knowledge graph. By performing path-constrained semantic embedding on entity nodes in the volunteer service knowledge graph through a predefined set of meta-paths, the semantic association strength between multi-dimensional entities is obtained, and then the matching preference coefficient between volunteers and volunteer activities is determined based on all semantic association strengths. Establish a multidimensional evaluation matrix among the hierarchical structure of volunteer activities, volunteers, beneficiaries and organizing units, and then determine the combined weight of each hierarchical factor relative to the overall hierarchical structure based on the multidimensional evaluation matrix. Determine the multidimensional decision function for volunteer service management based on all the combined weights. Based on the matching preference coefficient and the multidimensional decision function, a collaborative scheduling strategy for volunteer service work is determined, and then the collaborative scheduling strategy is used to dynamically match and coordinate resources for volunteers, volunteer activities and beneficiaries.

2. The method as described in claim 1, characterized in that, The process of fusing and aligning multi-source heterogeneous data in the heterogeneous information network to obtain a volunteer service knowledge graph specifically includes: Standardize the multi-source heterogeneous data in the heterogeneous information network to obtain multi-source data with a unified data format; Based on the multi-source data, entity disambiguation is performed to generate a volunteer entity set; By combining entity attributes in heterogeneous information networks, semantic association fusion is performed on entities in the volunteer entity set to obtain multiple entity relationship chains; A volunteer service knowledge graph is generated based on all entity relationship chains.

3. The method as described in claim 1, characterized in that, By performing path-constrained semantic embedding on entity nodes in the volunteer service knowledge graph using a predefined set of meta-paths, the semantic association strength between multi-dimensional entities is obtained, specifically including: Determine the predefined set of metapaths; Based on the meta-path set, entity nodes in the volunteer service knowledge graph are mapped to a low-dimensional vector space for entity semantic embedding to obtain entity semantic features. The semantic association strength between multi-dimensional entities in the volunteer service knowledge graph is determined based on the semantic features of the entities.

4. The method as described in claim 1, characterized in that, The matching preference coefficient between volunteers and volunteer activities is determined based on the strength of all semantic associations, specifically including: Determine the strength type of each semantic association; A comparison judgment matrix is ​​constructed based on the strength type of each semantic association strength; The matching preference coefficient between volunteers and volunteer activities is determined based on all semantic association strengths and the comparison judgment matrix.

5. The method as described in claim 1, characterized in that, Establishing a multi-dimensional evaluation matrix among the hierarchical structure of volunteer activities, volunteers, beneficiaries, and organizing units specifically includes: Construct a hierarchical structure system for volunteer service management across volunteer activities, volunteers, beneficiaries, and organizing units; Determine the evaluation indicators for each criterion layer in the hierarchical structure system; Based on all evaluation indicators, a judgment matrix is ​​generated for different dimensional criterion layers and the criterion layers as a whole. By verifying and integrating all the judgment matrices, a multidimensional evaluation matrix is ​​obtained that represents the multiple levels of volunteer activities, volunteers, beneficiaries, and organizing units.

6. The method as described in claim 1, characterized in that, Determining the combined weights of each hierarchical structural factor relative to the overall hierarchical structure based on the multidimensional evaluation matrix specifically includes: The single-level weights of each hierarchical structural factor in the hierarchical structure system are determined based on the multidimensional evaluation matrix. The initial combined weight of each hierarchical factor relative to the total hierarchical structure is determined based on the single-level weights of all hierarchical factors. Perform overall consistency verification on all initial combination weights to obtain the combination weights of each hierarchical structural factor relative to the total hierarchical structure.

7. The method as described in claim 1, characterized in that, The specific methods for determining the collaborative scheduling strategy for volunteer service work based on the matching preference coefficient and the multidimensional decision function include: The matching preference coefficient is used to filter out combinations of volunteers and volunteer activities as candidates for collaborative scheduling; Substitute the volunteer service scheduling strategies corresponding to all candidate objects into the multidimensional decision function to calculate the comprehensive decision value of each volunteer service scheduling strategy; Based on all the comprehensive decision values, the various volunteer service scheduling strategies are prioritized to obtain the collaborative scheduling strategy for volunteer service work.

8. A multi-dimensional collaborative processing volunteer service work management system, characterized in that, include: The data collection module is used to construct a heterogeneous information network of multi-dimensional entities, including volunteers, volunteer activities, beneficiaries, and organizations, and then to fuse and align the multi-source heterogeneous data in the heterogeneous information network to obtain a volunteer service knowledge graph. The processing module is used to perform path-constrained semantic embedding on entity nodes in the volunteer service knowledge graph through a predefined set of meta-paths to obtain the semantic association strength between multi-dimensional entities, and then determine the matching preference coefficient between volunteers and volunteer activities based on all semantic association strengths. The processing module is used to establish a multi-dimensional evaluation matrix among the hierarchical structure of volunteer activities, volunteers, beneficiaries and organizational units, and then determine the combined weight of each hierarchical factor relative to the overall hierarchical structure based on the multi-dimensional evaluation matrix, and determine the multi-dimensional decision function of volunteer service management based on all the combined weights. The execution module is used to determine the collaborative scheduling strategy for volunteer service work based on the matching preference coefficient and the multidimensional decision function, and then use the collaborative scheduling strategy to dynamically match and coordinate resources for volunteers, volunteer activities and beneficiaries.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the volunteer service work management method with multi-dimensional collaborative processing as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the volunteer service work management method with multi-dimensional collaborative processing as described in any one of claims 1 to 7.

Images