CN111861055A - Resource scheduling method, device and platform - Google Patents

Resource scheduling method, device and platform Download PDF

Info

Publication number
CN111861055A
CN111861055A CN201910349889.7A CN201910349889A CN111861055A CN 111861055 A CN111861055 A CN 111861055A CN 201910349889 A CN201910349889 A CN 201910349889A CN 111861055 A CN111861055 A CN 111861055A
Authority
CN
China
Prior art keywords
resource
scheduling
event
target event
resources
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910349889.7A
Other languages
Chinese (zh)
Inventor
张柯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201910349889.7A priority Critical patent/CN111861055A/en
Publication of CN111861055A publication Critical patent/CN111861055A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a resource scheduling method, a resource scheduling device and a resource scheduling platform, wherein the method comprises the following steps: the method comprises the steps of firstly obtaining event characteristics of a target event requesting resource scheduling and multi-dimensional resource characteristics of resources in a resource pool, then carrying out resource matching on the target event according to the event characteristics and the multi-dimensional resource characteristics of the resources, and then determining scheduling resources of the target event according to the obtained resource matching degree of the target event and the resources. The technical scheme provided by the invention can improve the efficiency and the rationality of resource scheduling.

Description

Resource scheduling method, device and platform
Technical Field
The invention relates to the technical field of computer networks, in particular to a resource scheduling method, a resource scheduling device and a resource scheduling platform.
Background
Social resources such as police officers, security personnel and mediators are an indispensable part in city management, and the reasonability of resource allocation is an important factor influencing the reasonable and efficient management of cities, so that how to schedule the social resources to ensure the reasonable allocation of the resources is also an important problem to be solved in the city management.
At present, when the social resources need to be scheduled, a manual scheduling mode is mostly adopted, and special workers allocate resources to users according to the resource requirements of the users. For example: after social disputes occur, the user calls the staff, and the staff screens out proper mediators to drive to the site for mediation.
However, the above-mentioned manual resource scheduling method is not efficient enough, and the phenomenon of unreasonable resource allocation is also easy to occur due to the personal level of the staff.
Disclosure of Invention
In view of this, the present invention provides a method, an apparatus, and a platform for resource scheduling, which are used to improve the efficiency and the rationality of resource scheduling.
In order to achieve the above object, in a first aspect, an embodiment of the present invention provides a resource scheduling method, including:
acquiring event characteristics of a target event requesting resource scheduling and multi-dimensional resource characteristics of each resource in a resource pool;
according to the event characteristics and the multi-dimensional resource characteristics of each resource, performing resource matching on the target event to obtain the resource matching degree of the target event and each resource;
and determining the scheduling resources of the target event according to the resource matching degree of the target event and each resource.
As an optional implementation manner in the embodiment of the present invention, performing resource matching on a target event to obtain a resource matching degree between the target event and each resource includes:
and performing resource matching on the target event by adopting a pre-established machine learning model to obtain the resource matching degree of the target event and each resource.
As an optional implementation manner of the embodiment of the present invention, the machine learning model is a linear machine learning model.
As an optional implementation manner of the embodiment of the present invention, determining scheduling resources of a target event according to a resource matching degree between the target event and each resource includes:
determining a resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource, wherein the density scheduling factor of each resource is used for expressing the resource scheduling density distribution of the resource;
and determining scheduling resources of the target event according to the resource matching scores between the target event and the resources.
As an optional implementation manner of the embodiment of the present invention, before determining the resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource, the method further includes:
for each resource, determining a density scheduling factor of the resource according to the proportion of the total number of events which are requested to be scheduled in the target area in the history to the total number of all events which are requested to be scheduled in the history and the proportion of the total number of resources which are currently schedulable in the target area to the total number of all resources which are currently schedulable; the area where the resources are located is divided into a plurality of areas, and the target area is the area where the resources are located.
As an optional implementation manner of the embodiment of the present invention, determining a resource matching score between a target event and each resource according to a resource matching degree between the target event and each resource and a density scheduling factor of each resource includes:
and determining a resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource, and the density scheduling factor and the random factor of each resource, wherein the random factor is any random number generated.
As an optional implementation manner of the embodiment of the present invention, before performing resource matching on a target event by using a pre-established machine learning model, the method further includes:
and establishing a machine learning model according to historical resource scheduling data, wherein the historical resource scheduling data comprises event characteristics of historical scheduling events, multi-dimensional resource characteristics of scheduled resources and resource matching degrees between the scheduled resources and the historical scheduling events.
As an optional implementation manner of the embodiment of the present invention, the event feature includes an event type, and the establishing of the machine learning model according to the historical resource scheduling data includes:
for each type of event, obtaining sample data according to historical resource scheduling data corresponding to the event type;
Establishing a machine learning model corresponding to the event type according to the sample data;
performing resource matching on the target event by adopting a pre-established machine learning model, wherein the resource matching comprises the following steps:
and performing resource matching on the target event by adopting a pre-established machine learning model corresponding to the event type of the target event.
As an optional implementation manner of the embodiment of the present invention, the method further includes:
and updating the machine learning model.
As an optional implementation manner of the embodiment of the present invention, before performing resource matching on a target event according to an event feature and a multidimensional resource feature of each resource, the method further includes:
and performing data cleaning on the resources in the resource pool.
As an optional implementation manner of the embodiment of the present invention, performing data cleaning on resources in a resource pool includes:
filtering out from the resource pool at least one of the following resources: resources whose feature values of the key features do not meet preset requirements, non-schedulable resources, and resources that are in an offline state.
As an optional implementation manner of the embodiment of the present invention, before performing resource matching on a target event according to an event feature and a multidimensional resource feature of each resource, the method further includes:
Performing rule screening on the resources in the resource pool according to a preset screening rule; the screening rules comprise screening rules preset by a system and/or screening rules set by a user.
As an optional implementation manner in this embodiment of the present invention, before obtaining an event feature of a target event requesting resource scheduling and a multidimensional resource feature of each resource in a resource pool, the method further includes:
receiving a resource scheduling request sent by user equipment, and generating an order according to the resource scheduling request, wherein the resource scheduling request is used for requesting to schedule resources for a target event;
after determining the scheduling resources of the target event according to the resource matching degree between the target event and each resource, the method further comprises:
and dispatching the order to the target terminal where the scheduling resource of the target event is located.
As an optional implementation manner of the embodiment of the present invention, the method further includes:
and sending a resource scheduling success message of the target event to the user equipment.
As an optional implementation manner of the embodiment of the present invention, the order includes a service demand location of the target event, and the method further includes:
and sending the real-time position of the target terminal to the user equipment so that the user equipment displays the real-time position of the target terminal to the user.
As an optional implementation manner of the embodiment of the present invention, the multidimensional resource feature of the resource includes: the method further comprises:
receiving evaluation information sent by user equipment after the order is finished;
and updating the skill adequacy length of the scheduling resources according to the evaluation information.
In a second aspect, an embodiment of the present invention provides a resource scheduling apparatus, including:
the system comprises an acquisition module, a resource scheduling module and a resource management module, wherein the acquisition module is used for acquiring the event characteristics of a target event requesting resource scheduling and the multi-dimensional resource characteristics of each resource in a resource pool;
the matching module is used for performing resource matching on the target event according to the event characteristics and the multi-dimensional resource characteristics of each resource to obtain the resource matching degree of the target event and each resource;
and the determining module is used for determining the scheduling resources of the target event according to the resource matching degree of the target event and each resource.
As an optional implementation manner of the embodiment of the present invention, the event feature includes: the service demand position and the multi-dimensional resource characteristics of the resource comprise: resource location and skill excel in length.
As an optional implementation manner of the embodiment of the present invention, the matching module is specifically configured to:
and performing resource matching on the target event by adopting a pre-established machine learning model to obtain the resource matching degree of the target event and each resource.
As an optional implementation manner of the embodiment of the present invention, the machine learning model is a linear machine learning model.
As an optional implementation manner of the embodiment of the present invention, the determining module is specifically configured to:
determining a resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource, wherein the density scheduling factor of each resource is used for expressing the resource scheduling density distribution of the resource;
and determining scheduling resources of the target event according to the resource matching scores between the target event and the resources.
As an optional implementation manner of the embodiment of the present invention, the determining module is further configured to:
before determining the resource matching score between a target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource, for each resource, determining the density scheduling factor of the resource according to the proportion of the total number of events which are requested to be scheduled in a historical target area to the total number of all events which are requested to be scheduled in the historical target area and the proportion of the total number of resources which are currently schedulable in the current schedulable total number of all resources in the target area; the area where the resources are located is divided into a plurality of areas, and the target area is the area where the resources are located.
As an optional implementation manner of the embodiment of the present invention, the determining module is specifically configured to:
and determining a resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource, and the density scheduling factor and the random factor of each resource, wherein the random factor is any random number generated.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
and the establishing module is used for establishing a machine learning model according to historical resource scheduling data before the matching module adopts the pre-established machine learning model to perform resource matching on the target event, wherein the historical resource scheduling data comprises the event characteristics of the historical scheduling event, the multi-dimensional resource characteristics of the scheduled resource and the resource matching degree between the scheduled resource and the historical scheduling event.
As an optional implementation manner of the embodiment of the present invention, the establishing module is specifically configured to:
for each type of event, obtaining sample data according to historical resource scheduling data corresponding to the event type;
establishing a machine learning model corresponding to the event type according to the sample data;
the matching module is specifically configured to:
and performing resource matching on the target event by adopting a pre-established machine learning model corresponding to the event type of the target event.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
and the updating module is used for updating the machine learning model.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
and the data cleaning module is used for cleaning the data of the resources in the resource pool before the matching module performs resource matching on the target event according to the event characteristics and the multi-dimensional resource characteristics of the resources.
As an optional implementation manner of the embodiment of the present invention, the data cleansing module is specifically configured to:
filtering out from the resource pool at least one of the following resources: resources whose feature values of the key features do not meet preset requirements, non-schedulable resources, and resources that are in an offline state.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
the rule screening module is used for carrying out rule screening on the resources in the resource pool according to a preset screening rule before the matching module carries out resource matching on the target event according to the event characteristics and the multi-dimensional resource characteristics of each resource; the screening rules comprise screening rules preset by a system and/or screening rules set by a user.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
A receiving module, configured to receive a resource scheduling request sent by a user equipment before the obtaining module obtains an event feature of a target event requesting resource scheduling and a multidimensional resource feature of each resource in a resource pool, where the resource scheduling request is used to request to schedule a resource for the target event;
the processing module is used for generating an order according to the resource scheduling request;
and the scheduling module is used for dispatching the order to the target terminal where the scheduling resource of the target event is located after the determining module determines the scheduling resource of the target event according to the resource matching degree of the target event and each resource.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
and the sending module is used for sending the resource scheduling success message of the target event to the user equipment.
As an optional implementation manner of the embodiment of the present invention, the order includes a service requirement location of the target event, and the sending module is further configured to:
and sending the real-time position of the target terminal to the user equipment so that the user equipment displays the real-time position of the target terminal to the user.
As an optional implementation manner of the embodiment of the present invention, the multidimensional resource feature of the resource includes: the receiving module is also used for: receiving evaluation information sent by user equipment after the order is finished;
The processing module is further configured to: and updating the skill adequacy length of the scheduling resources according to the evaluation information.
In a third aspect, an embodiment of the present invention provides a resource scheduling platform, including: a memory for storing a computer program and a processor; the processor is configured to perform the method of the first aspect or any of the embodiments of the first aspect when the computer program is invoked.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method according to the first aspect or any embodiment of the first aspect.
According to the resource scheduling method, the resource scheduling device and the resource scheduling platform, the event characteristics of the target event requesting resource scheduling and the multidimensional resource characteristics of each resource in the resource pool are obtained, then the target event is subjected to resource matching according to the event characteristics and the multidimensional resource characteristics of each resource, and the scheduling resources of the target event are determined according to the obtained resource matching degree of the target event and each resource, so that the automatic scheduling of the resources can be realized, and the efficiency and the rationality of resource scheduling can be improved; and when the resources are matched, the resource matching is carried out based on the multi-dimensional resource characteristics of the resources, so that the rationality of resource scheduling can be further improved.
Drawings
Fig. 1 is a flowchart illustrating a resource scheduling method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating another resource scheduling method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a resource scheduling apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a resource scheduling platform according to an embodiment of the present invention.
Detailed Description
Aiming at the technical problems that the current manual resource scheduling mode is not efficient enough and the phenomenon of unreasonable resource allocation is easy to occur, the embodiment of the invention provides a resource scheduling method, a device and a platform, which are used for improving the efficiency and the rationality of resource scheduling.
The resources described in the embodiment of the present invention may include social governance resources such as police officers, security personnel, city management, etc., social service resources such as moderator, community staff, volunteers, etc., and may also include other social resources, which is not particularly limited in this embodiment. In addition, the resource described in this embodiment is a service resource having a spatial location attribute, which may specifically be the human resource described above, or may be an intelligent robot having a service function, and at this time, the intelligent robot may be integrated with the terminal described in this embodiment.
The user equipment in this embodiment may be an electronic device with display, operation, and network access functions, for example, a mobile device such as a mobile phone, a tablet computer, a notebook computer, or an intelligent wearable device, or a fixed device such as a desktop computer or a television with a network access function. The terminal may be an electronic device with display, operation and network access functions, and may be a mobile device such as a mobile phone, a tablet computer, a notebook computer or a smart wearable device.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 1 is a schematic flowchart of a resource scheduling method according to an embodiment of the present invention, and as shown in fig. 1, the method according to this embodiment may include the following steps:
s110, acquiring the event characteristics of the target event requesting resource scheduling and the multi-dimensional resource characteristics of each resource in the resource pool.
Specifically, when a user needs to schedule a resource, the user may send a resource scheduling request to the resource scheduling platform through the user equipment, for example: after social disputes occur, the user can apply for mediation (namely apply for scheduling resources) by scanning the two-dimensional code or logging in a platform and the like; the resource scheduling request can carry event information of an event (namely a target event) needing to request resource scheduling, wherein the event information can be composed of event characteristics, and the resource scheduling platform can extract the event characteristics of the target event from the resource scheduling request after receiving the resource scheduling request; the event characteristics specifically include service demand positions, and also include event categories, event properties, special requirements and the like, where the event properties belong to a broad class, and may be, for example, mediation service events or public security service events; the event category belongs to a subclass of event properties, and may be, for example, a social dispute mediation event or a marital mediation event among mediation service events.
The resource pool comprises people or mechanisms which can be scheduled by a resource scheduling platform, the resource information of each resource can be composed of a plurality of resource characteristics, and the resource scheduling platform can extract the resource characteristics from the resource information. In this embodiment, the resource characteristics may include a resource location and a skill adequacy length, and may further include various characteristics such as adequacy skills, height, weight, age, sex, and position, where the skill adequacy length may be determined based on the historical evaluation of the resource by the user, or may be determined according to other manners, such as a skill assessment result.
And S120, performing resource matching on the target event according to the event characteristics and the multi-dimensional resource characteristics of the resources to obtain the resource matching degree of the target event and the resources.
Specifically, when performing resource matching, a related feature matching algorithm may be adopted to perform resource matching on the target event; in the embodiment, in order to improve the accuracy of the resource matching result, a pre-established machine learning model can be adopted to perform resource matching on the target event; the machine learning model may be various linear or non-linear machine learning models, and in order to facilitate quantification of the resource matching degree, the linear machine learning model may be optionally established, for example: a linear Regression model, a Logistic Regression model, etc., preferably a Logistic Regression (LR) model is used in this embodiment to improve the accuracy of the resource matching degree prediction result.
In this embodiment, before performing resource matching, a machine learning model may be established according to historical resource scheduling data, where the historical resource scheduling data is data of resource scheduling that occurs in history, and may include event features of a historical scheduling event, multidimensional resource features of a scheduled resource, and a resource matching degree between the scheduled resource and the historical scheduling event, where the resource matching degree may be used to indicate whether the resource scheduling is successful or not, and may specifically be, for example, an evaluation value of a user for the resource scheduling.
During specific construction, sample data can be obtained according to historical resource scheduling data, and then a machine learning algorithm (such as an LR algorithm) is adopted for training the sample data to obtain a machine learning model. The input features in the sample data can be determined according to the event features of the historical scheduling events and the multidimensional resource features of the scheduled resources, and the output features in the sample data can be the resource matching degree between the scheduled resources and the historical scheduling events.
After the machine learning model is established, the resource matching degree of the target event and each resource can be predicted through the machine learning model, wherein the input features of the predicted data are determined by a determination method adopted by the input features in the sample data.
For the LR model, model weights (i.e., weights of each feature in the model) are obtained through training, and a quantifiable predicted value, i.e., a resource matching degree, which represents the matching degree of the resource corresponding to the predicted data to the target event can be obtained according to the input features of the predicted data and the model weights.
In this embodiment, when there are multiple event types, sample data may be obtained for each event type according to historical resource scheduling data corresponding to the event type; and then establishing a machine learning model corresponding to the event type according to the sample data. Correspondingly, when the pre-established machine learning model is used for resource matching of the target event, the pre-established machine learning model corresponding to the event type of the target event can be used for resource matching of the target event. For example: for social dispute resolution events, resource scheduling data corresponding to the events in history can be screened out, machine learning models corresponding to the events are established according to the data, and the establishment modes of the machine learning models of other event types are similar; when the resource scheduling platform receives the scheduling of resources (namely, a moderator) needing to be mediated, the resource matching degree of the event and each resource is predicted by adopting a corresponding machine learning model according to the event type (namely, the social dispute mediation event type).
In order to improve the accuracy of the resource matching result, the machine learning model may be updated with the latest historical resource scheduling data in this embodiment. The specific updating process is similar to the establishing process of the machine learning model, and is not described herein again.
In order to improve the efficiency of resource scheduling, in this embodiment, before performing resource matching, data cleaning may be performed on resources in the resource pool, so as to ensure that the resources in the resource pool are all schedulable high-quality resources.
In addition, in order to further improve the efficiency of resource scheduling, in this embodiment, before resource matching is performed, resources in the resource pool may be screened according to a preset screening rule.
The screening rules may include screening rules preset by the system, and in order to improve the user satisfaction, the screening rules may also include screening rules set by the user. For example: the system can preset a resource type screening rule, namely screening out resources corresponding to the resource type and the event type; the user can set a filtering rule such as the age, the gender and/or the distance of the service personnel (i.e. the resources), i.e. the resources with the age, the gender and/or the distance meeting the corresponding rule set by the user are filtered. In addition, the resource scheduling platform may open a rule screening interface for a third party user to set a screening rule, so as to improve the controllability of the scheduled resource, that is, the user setting the screening rule may include a user needing the resource service and the third party user.
And S130, determining the scheduling resources of the target event according to the resource matching degree of the target event and each resource.
After the resource matching degree of the target event and each resource is determined, the scheduling resource of the target event can be determined according to the resource. Specifically, the scheduling resource of the target event may be directly determined according to the resource matching degree, that is, the resource with the highest resource matching degree is determined as the scheduling resource of the target event.
Considering that the probability of occurrence of an event is inconsistent in the whole area, in order to improve the scheduling efficiency, the density distribution factor of resource scheduling needs to be considered, and the probability of occurrence of the event in a certain area is ensured to be consistent with the density of schedulable resources in the area as much as possible, namely, the scheduling resources of the target event are determined according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource.
In specific implementation, a resource matching score between a target event and each resource can be determined according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource; and then determining scheduling resources of the target event according to the resource matching scores between the target event and the resources, wherein the density scheduling factor of each resource is used for expressing the resource scheduling density distribution of the resources.
For each resource, determining a density scheduling factor of the resource according to the proportion of the total number of events which are requested to be scheduled and occur in the target area in the history to the total number of all events which are requested to be scheduled and occur in the history, and the proportion of the total number of resources which are currently schedulable and occur in the target area to the total number of all resources which are currently schedulable.
In order to prevent the "starvation" phenomenon of some low-quality schedulable resources, in this embodiment, a random factor may be added when determining the scheduling resources of the target event, and the random factor may be any random number. By adding the random factor, a small part of negative sample data can be collected so as to provide a higher-quality data reference for a subsequent optimization machine learning model.
In a specific implementation, at least one of a density scheduling factor and a random factor may be added in addition to the resource matching degree between the target event and each resource to determine the scheduling resource of the target event.
After receiving the resource scheduling request, the resource scheduling platform may generate an order according to the resource scheduling request, and then after determining the scheduled resource of the target event, the resource scheduling platform distributes the order to a terminal (referred to as a target terminal) where the scheduled resource of the target event is located, so that a service person can quickly arrive at the site after receiving the order to provide service for the user. The order may include event information (e.g., a service demand location) of the target event and information such as a contact information of the user, so that service personnel can quickly arrive at the site to provide the service.
In addition, the resource scheduling platform can simultaneously send a resource scheduling success message of the target event to the user equipment to prompt the user that the order has been successfully dispatched. The resource scheduling success message can carry information such as resource information and contact information of the scheduled resource, and the user can check the information and contact the scheduled resource through an order on the user equipment.
In order to facilitate the user to know the location of the service staff, in this embodiment, the resource scheduling platform may send the real-time location of the target terminal to the user equipment, so that the user equipment displays the real-time location of the target terminal to the user.
After the order is finished, the user equipment can provide an evaluation interface for the user to evaluate, the evaluation information is sent to the resource scheduling platform after the user evaluation is finished, and after the resource scheduling platform receives the evaluation information sent by the user equipment after the order is finished, the skill adequacy length of the scheduled resource can be updated according to the evaluation information.
According to the resource scheduling method provided by the embodiment, the event characteristics of the target event requesting resource scheduling and the multidimensional resource characteristics of each resource in the resource pool are obtained, then the target event is subjected to resource matching according to the event characteristics and the multidimensional resource characteristics of each resource, and the scheduling resource of the target event is determined according to the obtained resource matching degree of the target event and each resource, so that the automatic scheduling of the resource can be realized, and the efficiency and the rationality of resource scheduling can be improved; and when the resources are matched, the resource matching is carried out based on the multi-dimensional resource characteristics of the resources, so that the rationality of resource scheduling can be further improved.
Fig. 2 is a schematic flowchart of another resource scheduling method according to an embodiment of the present invention, and this embodiment is a specific implementation manner of the embodiment shown in fig. 1. As shown in fig. 2, the method provided by this embodiment may include the following steps:
and S210, for each type of event, establishing a machine learning model corresponding to the event type according to historical resource scheduling data.
The historical resource scheduling data is data of resource scheduling occurring in history, and may include event characteristics of a historical scheduling event, multidimensional resource characteristics of scheduled resources, and resource matching degrees between the scheduled resources and the historical scheduling event.
During specific construction, sample data of the event type can be obtained according to the event type and historical resource scheduling data, and then a machine learning algorithm (such as an LR algorithm) is adopted for training the sample data to obtain a machine learning model corresponding to the event type. The input features in the sample data may be determined according to event features of the historical scheduling events and multidimensional resource features of the scheduled resources, and the input features may specifically be a direct combination of the event features and the multidimensional resource features, or features further determined according to the event features and the multidimensional resource features, for example: the distance between the historical scheduling event and the scheduled resource can be calculated according to the event position in the event characteristic and the resource position in the multi-dimensional resource characteristic, and the distance is used as one of the input characteristics; the input characteristics may be determined in other manners, which is not particularly limited in this embodiment. The output characteristic in the sample data may be a resource matching degree between the scheduled resource and the historical scheduling event, where the resource matching degree may be used to indicate whether the scheduling of the secondary resource is successful or not, and may specifically be, for example, an evaluation value of the user on the scheduling of the secondary resource.
After the machine learning model is established, the resource matching degree of the target event and each resource can be predicted through the machine learning model, wherein the input features of the predicted data are determined by a determination method adopted by the input features in the sample data.
S220, acquiring the event characteristics of the target event requesting resource scheduling and the multi-dimensional resource characteristics of each resource in the resource pool.
This step can refer to the description of step S110 corresponding to the embodiment shown in fig. 1, and is not repeated herein.
And S230, performing data cleaning on the resources in the resource pool.
In particular implementations, at least one of the following resources may be filtered out of the resource pool: resources whose feature values of the key features do not meet preset requirements, non-schedulable resources, and resources that are in an offline state.
The key feature may be determined according to a resource type, and the preset requirement may include, for example: the eigenvalue is not null and/or the eigenvalue is within a preset range, etc. Non-schedulable resources may include, for example, resources that are not in-flight and resources that do not match the event type, etc.
And S240, performing rule screening on the resources in the resource pool according to a preset screening rule.
Specifically, the filtering rule may include a filtering rule preset by the system and/or a filtering rule set by the user.
And S250, according to the event characteristics and the multi-dimensional resource characteristics of each resource, performing resource matching on the target event by adopting a machine learning model corresponding to the event type of the target event to obtain the resource matching degree of the target event and each resource.
Specifically, the input characteristics of the predicted data can be determined according to the event characteristics and the multidimensional resource characteristics of each resource, and the determination method is consistent with the determination method adopted by the input characteristics in the sample data; and then inputting the input characteristics into a machine learning model corresponding to the event type of the target event for prediction to obtain the resource matching degree of the target event and each resource.
And S260, determining the scheduling resources of the target event according to the resource matching degree of the target event and each resource, the density scheduling factor of each resource and the random factor.
Specifically, for each resource, the density scheduling factor of the resource may be determined according to the total number of events that have been requested to be scheduled in the historical target area, the total number of resources that are currently schedulable in the target area, and the total number of resources that are currently schedulable. Specifically, the density scheduling factor may be calculated by using the following formula (1):
Figure BDA0002043588580000131
Wherein, the density represents the density scheduling factor, history, of the resourceareaRepresenting the total number of events, history, in the target area that have been requested to be scheduledtotalRepresenting the total number of events, resources, historically all requests were scheduledareaRepresents the total number of resources, which can be scheduled currently in the target areatotalIndicating the total number of resources that are currently schedulable.
In specific implementation, the resource matching score of the target event and each resource can be determined according to the resource matching degree of the target event and each resource, the density scheduling factor of each resource and the random factor, and then the scheduling resource of the target event can be determined according to the resource matching score of the target event and each resource.
The resource matching score of the target event and each resource can be calculated by adopting the following formula:
scorei＝αmodeli+βdensityi+γrand (2)
wherein, scoreiRepresenting the matching score of the ith resource, and alpha, beta and gamma are hyper parameters, modeliRepresenting the resource matching degree, density, of the target event and the ith resourceiThe density distribution factor of the ith resource is represented, and rand represents a random factor.
And S270, updating the machine learning model.
Specifically, the machine learning model may be updated periodically with the latest historical resource scheduling data.
The resource scheduling method provided by the embodiment can improve the efficiency of resource scheduling through data cleaning and rule screening
Based on the same inventive concept, as an implementation of the foregoing method, an embodiment of the present invention provides a resource scheduling apparatus, where the apparatus embodiment corresponds to the foregoing method embodiment, and for convenience of reading, details in the foregoing method embodiment are not repeated in this apparatus embodiment one by one, but it should be clear that the apparatus in this embodiment can correspondingly implement all the contents in the foregoing method embodiment.
Fig. 3 is a schematic structural diagram of a resource scheduling apparatus according to an embodiment of the present invention, and as shown in fig. 3, the apparatus according to the embodiment includes:
an obtaining module 110, configured to obtain an event feature of a target event requesting resource scheduling and a multidimensional resource feature of each resource in a resource pool;
the matching module 120 is configured to perform resource matching on the target event according to the event characteristics and the multidimensional resource characteristics of each resource, so as to obtain a resource matching degree between the target event and each resource;
the determining module 130 is configured to determine scheduling resources of the target event according to the resource matching degree between the target event and each resource.
Wherein the event characteristics may include: the multi-dimensional resource characteristics of the service demand location, resource may include: resource location and skill excel in length.
As an optional implementation manner of the embodiment of the present invention, the matching module 120 is specifically configured to:
and performing resource matching on the target event by adopting a pre-established machine learning model to obtain the resource matching degree of the target event and each resource.
As an optional implementation manner of the embodiment of the present invention, the machine learning model is a linear machine learning model.
As an optional implementation manner of the embodiment of the present invention, the determining module 130 is specifically configured to:
determining a resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource, wherein the density scheduling factor of each resource is used for expressing the resource scheduling density distribution of the resource;
and determining scheduling resources of the target event according to the resource matching scores between the target event and the resources.
As an optional implementation manner of the embodiment of the present invention, the determining module 130 is further configured to:
before determining the resource matching score between a target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource, for each resource, determining the density scheduling factor of the resource according to the proportion of the total number of events which are requested to be scheduled in a historical target area to the total number of all events which are requested to be scheduled in the historical target area and the proportion of the total number of resources which are currently schedulable in the current schedulable total number of all resources in the target area; the area where the resources are located is divided into a plurality of areas, and the target area is the area where the resources are located.
As an optional implementation manner of the embodiment of the present invention, the determining module 130 is specifically configured to:
and determining a resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource, and the density scheduling factor and the random factor of each resource, wherein the random factor is any random number generated.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
the establishing module 140 is configured to establish a machine learning model according to historical resource scheduling data before the matching module 120 performs resource matching on the target event by using a pre-established machine learning model, where the historical resource scheduling data includes event features of a historical scheduling event, multidimensional resource features of scheduled resources, and a resource matching degree between the scheduled resources and the historical scheduling event.
As an optional implementation manner of the embodiment of the present invention, the establishing module 140 is specifically configured to:
for each type of event, obtaining sample data according to historical resource scheduling data corresponding to the event type;
establishing a machine learning model corresponding to the event type according to the sample data;
the matching module 120 is specifically configured to:
and performing resource matching on the target event by adopting a pre-established machine learning model corresponding to the event type of the target event.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
an update module 150 for updating the machine learning model.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
and the data cleaning module 160 is configured to perform data cleaning on the resources in the resource pool before the matching module 120 performs resource matching on the target event according to the event features and the multidimensional resource features of the resources.
As an optional implementation manner of the embodiment of the present invention, the data cleansing module 160 is specifically configured to:
filtering out from the resource pool at least one of the following resources: resources whose feature values of the key features do not meet preset requirements, non-schedulable resources, and resources that are in an offline state.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
the rule screening module 170 is configured to perform rule screening on the resources in the resource pool according to a preset screening rule before the matching module 120 performs resource matching on the target event according to the event feature and the multidimensional resource feature of each resource; the screening rules comprise screening rules preset by a system and/or screening rules set by a user.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
a receiving module 180, configured to receive a resource scheduling request sent by a user equipment before the obtaining module 110 obtains an event feature of a target event requesting resource scheduling and a multidimensional resource feature of each resource in a resource pool, where the resource scheduling request is used to request to schedule a resource for the target event;
the processing module 190 is configured to generate an order according to the resource scheduling request;
the scheduling module 200 is configured to, after the determining module 130 determines the scheduling resource of the target event according to the resource matching degree between the target event and each resource, dispatch the order to the target terminal where the scheduling resource of the target event is located.
As an optional implementation manner of the embodiment of the present invention, the apparatus further includes:
a sending module 210, configured to send a resource scheduling success message of the target event to the user equipment.
As an optional implementation manner of the embodiment of the present invention, the order includes a service requirement location of the target event, and the sending module 210 is further configured to:
and sending the real-time position of the target terminal to the user equipment so that the user equipment displays the real-time position of the target terminal to the user.
As an optional implementation manner of the embodiment of the present invention, the multidimensional resource feature of the resource includes: the receiving module 180 is also used for: receiving evaluation information sent by user equipment after the order is finished;
The processing module 190 is further configured to: and updating the skill adequacy length of the scheduling resources according to the evaluation information.
The apparatus provided in this embodiment may perform the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
Based on the same inventive concept, the embodiment of the invention also provides a resource scheduling platform. Fig. 4 is a schematic structural diagram of a resource scheduling platform according to an embodiment of the present invention, and as shown in fig. 4, the resource scheduling platform according to the embodiment includes: a memory 210 and a processor 220, the memory 210 for storing computer programs; the processor 220 is adapted to perform the method according to the above-described method embodiments when invoking the computer program.
The resource scheduling platform provided in this embodiment may execute the method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method described in the above method embodiments.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied in the medium.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer readable media include both permanent and non-permanent, removable and non-removable storage media. Storage media may implement information storage by any method or technology, and the information may be computer-readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (19)

1. A method for scheduling resources, comprising:
acquiring event characteristics of a target event requesting resource scheduling and multi-dimensional resource characteristics of each resource in a resource pool;
performing resource matching on the target event according to the event characteristics and the multi-dimensional resource characteristics of each resource to obtain the resource matching degree of the target event and each resource;
and determining the scheduling resources of the target event according to the resource matching degree of the target event and each resource.
2. The method according to claim 1, wherein the performing resource matching on the target event to obtain a resource matching degree between the target event and each resource comprises:
And performing resource matching on the target event by adopting a pre-established machine learning model to obtain the resource matching degree of the target event and each resource.
3. The method of claim 2, wherein the machine learning model is a linear machine learning model.
4. The method of claim 1, wherein the determining the scheduling resource of the target event according to the resource matching degree of the target event and each resource comprises:
determining a resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource, wherein the density scheduling factor of each resource is used for expressing the resource scheduling density distribution of the resource;
and determining scheduling resources of the target event according to the resource matching scores between the target event and the resources.
5. The method according to claim 4, wherein before determining the resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource, the method further comprises:
For each resource, determining a density scheduling factor of the resource according to the proportion of the total number of events which are requested to be scheduled in a historical target area to the total number of all events which are requested to be scheduled in the historical target area and the proportion of the total number of resources which are currently schedulable in the target area to the total number of all resources which are currently schedulable; the area where the resource is located is divided into a plurality of areas, and the target area is the area where the resource is located.
6. The method according to claim 4, wherein the determining the resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource and the density scheduling factor of each resource comprises:
and determining a resource matching score between the target event and each resource according to the resource matching degree between the target event and each resource, the density scheduling factor of each resource and a random factor, wherein the random factor is any generated random number.
7. The method of claim 2, wherein prior to the resource matching the target event using the pre-established machine learning model, the method further comprises:
And establishing the machine learning model according to historical resource scheduling data, wherein the historical resource scheduling data comprises event characteristics of historical scheduling events, multi-dimensional resource characteristics of scheduled resources and resource matching degrees between the scheduled resources and the historical scheduling events.
8. The method of claim 7, wherein the event features comprise event types, and wherein building the machine learning model from historical resource scheduling data comprises:
for each type of event, obtaining sample data according to historical resource scheduling data corresponding to the event type;
establishing a machine learning model corresponding to the event type according to the sample data;
performing resource matching on the target event by using a pre-established machine learning model, including:
and performing resource matching on the target event by adopting a pre-established machine learning model corresponding to the event type of the target event.
9. The method of claim 2, further comprising:
updating the machine learning model.
10. The method of claim 1, wherein prior to the resource matching the target event according to the event features and the multi-dimensional resource features of the resources, the method further comprises:
And performing data cleaning on the resources in the resource pool.
11. The method of claim 10, wherein the data cleansing of the resources in the resource pool comprises:
filtering out from the resource pool at least one of the following resources: resources whose feature values of the key features do not meet preset requirements, non-schedulable resources, and resources that are in an offline state.
12. The method of claim 1, wherein prior to the resource matching the target event according to the event features and the multi-dimensional resource features of the resources, the method further comprises:
performing rule screening on the resources in the resource pool according to a preset screening rule; the screening rules comprise screening rules preset by a system and/or screening rules set by a user.
13. The method according to any one of claims 1-12, wherein before the obtaining the event characteristic of the target event requesting resource scheduling and the multidimensional resource characteristic of each resource in the resource pool, the method further comprises:
receiving a resource scheduling request sent by user equipment, and generating an order according to the resource scheduling request, wherein the resource scheduling request is used for requesting to schedule resources for a target event;
After determining the scheduling resources of the target event according to the resource matching degree between the target event and each resource, the method further includes:
and dispatching the order to a target terminal where the scheduling resource of the target event is located.
14. The method of claim 13, further comprising:
and sending a resource scheduling success message of the target event to the user equipment.
15. The method of claim 13, wherein the order includes a service demand location for the target event, the method further comprising:
and sending the real-time position of the target terminal to the user equipment so that the user equipment displays the real-time position of the target terminal to a user.
16. The method of claim 13, wherein the multidimensional resource characteristics of the resource comprise: the method further comprises:
receiving evaluation information sent by the user equipment after the order is completed;
and updating the skill adequacy length of the scheduling resource according to the evaluation information.
17. A resource scheduling apparatus, comprising:
the system comprises an acquisition module, a resource scheduling module and a resource management module, wherein the acquisition module is used for acquiring the event characteristics of a target event requesting resource scheduling and the multi-dimensional resource characteristics of each resource in a resource pool;
The matching module is used for performing resource matching on the target event according to the event characteristics and the multi-dimensional resource characteristics of each resource to obtain the resource matching degree of the target event and each resource;
and the determining module is used for determining the scheduling resources of the target event according to the resource matching degree of the target event and each resource.
18. A resource scheduling platform, comprising: a memory for storing a computer program and a processor; the processor is adapted to perform the method of any of claims 1-16 when the computer program is invoked.
19. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-16.
CN201910349889.7A 2019-04-28 2019-04-28 Resource scheduling method, device and platform Pending CN111861055A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910349889.7A CN111861055A (en) 2019-04-28 2019-04-28 Resource scheduling method, device and platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910349889.7A CN111861055A (en) 2019-04-28 2019-04-28 Resource scheduling method, device and platform

Publications (1)

Publication Number Publication Date
CN111861055A true CN111861055A (en) 2020-10-30

Family

ID=72964986

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910349889.7A Pending CN111861055A (en) 2019-04-28 2019-04-28 Resource scheduling method, device and platform

Country Status (1)

Country Link
CN (1) CN111861055A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116132214A (en) * 2022-12-30 2023-05-16 中国联合网络通信集团有限公司 Event transmission method, device, equipment and medium based on event bus model

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116132214A (en) * 2022-12-30 2023-05-16 中国联合网络通信集团有限公司 Event transmission method, device, equipment and medium based on event bus model

Similar Documents

Publication Publication Date Title
CN108364085B (en) Takeout delivery time prediction method and device
WO2021120799A1 (en) Anchor information pushing method and apparatus, computer device, and storage medium
US11816727B2 (en) Credit scoring method and server
KR20180081101A (en) Method and apparatus for optimizing user credit score
CN110417607B (en) Flow prediction method, device and equipment
CN108133390A (en) For predicting the method and apparatus of user behavior and computing device
CN113099475A (en) Network quality detection method and device, electronic equipment and readable storage medium
CN107256231B (en) Team member identification device, method and system
CN115203496A (en) Project intelligent prediction and evaluation method and system based on big data and readable storage medium
CN113012336A (en) Queuing reservation method of banking business and device, storage medium and equipment thereof
CN111861055A (en) Resource scheduling method, device and platform
CN109995549B (en) Method and device for evaluating flow value
CN113055423B (en) Policy pushing method, policy execution method, device, equipment and medium
CN116485237A (en) Method, system, equipment and medium for evaluating asset value of power regulation and control data
CN115600818A (en) Multi-dimensional scoring method and device, electronic equipment and storage medium
WO2022062777A1 (en) Data management method, data management apparatus, and storage medium
CN113205391B (en) Historical order matching degree based order dispatching method, electronic equipment and computer readable medium
US20230206028A1 (en) Deep learning models processing time series data
CN116542831B (en) Method and device for processing recruitment data, electronic equipment and storage medium
CN114090854B (en) Intelligent label weight updating method and system based on information entropy and computer equipment
CN117172735A (en) Resource information prediction method, device, computer equipment and storage medium
Wibowo Evaluating and selecting hospital locations using fuzzy multicriteria decision making
CN115690871A (en) Service processing method and device
CN117135027A (en) Fault discovery method, apparatus, device, storage medium, and computer program product
CN116112879A (en) Information pushing method, device, electronic equipment and computer program product

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination