CN114121247A

CN114121247A - Resource scheduling method and device, computer equipment and storage medium

Info

Publication number: CN114121247A
Application number: CN202111436196.5A
Authority: CN
Inventors: 张西
Original assignee: Ping An International Smart City Technology Co Ltd
Current assignee: Shenzhen Ping An Smart Healthcare Technology Co ltd
Priority date: 2021-11-29
Filing date: 2021-11-29
Publication date: 2022-03-01
Anticipated expiration: 2041-11-29
Also published as: CN114121247B

Abstract

The embodiment of the invention provides a resource scheduling method, a resource scheduling device, computer equipment and a storage medium, which relate to the artificial intelligence technology and comprise the following steps: determining whether the target medical resource is a rare medical resource or not according to the resource identifier, and if the target medical resource is the rare medical resource, calling a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource to obtain a first reference resource scheduling scheme; calling a second resource scheduling model to predict a scheduling scheme of the target medical resource according to the resource demand information to obtain a second reference resource scheduling scheme; the target medical resource is scheduled by determining the target resource scheduling scheme based on the first reference resource scheduling scheme and the second reference resource scheduling scheme, so that the efficiency of scheduling the medical resource can be improved. The present application relates to a blockchain technique, such as a scenario in which attribute information of a target medical resource can be written into a blockchain for a first reference resource scheduling scheme of the target medical resource.

Description

Resource scheduling method and device, computer equipment and storage medium

Technical Field

The invention relates to the technical field of computers, in particular to an artificial intelligence technology, and specifically relates to a resource scheduling method, a resource scheduling device, computer equipment and a storage medium.

Background

With the development of society, the increase of population and the improvement of economic conditions, the demand of people on medical health guarantee and the health service quality standard are also improved. Medical resources vary from those in other industries with uncertainty as to when, what, and how much resources a patient is expecting to provide, and will vary due to the needs of different types of patients. In an emergency situation, such as a large car accident, there may be no medical resources needed in the hospital where the patient is located, so that the patient misses the optimal treatment time due to the lack of the rare medical resources, and how to schedule the medical resources becomes a research hotspot.

Disclosure of Invention

The embodiment of the invention provides a resource scheduling method, a resource scheduling device, computer equipment and a storage medium, which can improve the efficiency of scheduling medical resources.

In one aspect, an embodiment of the present invention provides a resource scheduling method, where the method includes:

receiving a medical resource scheduling request, wherein the medical resource scheduling request carries resource demand information and a resource identifier;

determining whether a target medical resource is a rare medical resource according to the resource identifier, wherein the target medical resource is a resource indicated by the resource identifier;

if the medical resource is the rare medical resource, determining attribute information of the target medical resource, wherein the attribute information comprises at least one of the following: resource distribution mode, resource timeliness, resource storage mode and resource treatment effect;

calling a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information to obtain a first reference resource scheduling scheme of the target medical resource;

calling a second resource scheduling model to predict a scheduling scheme of the target medical resource according to the resource demand information to obtain a second reference resource scheduling scheme of the target medical resource;

determining a target resource scheduling scheme for the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme;

scheduling the target medical resource based on the target resource scheduling plan.

In one aspect, an embodiment of the present invention provides a resource scheduling apparatus, where the apparatus includes:

the system comprises a receiving unit, a resource scheduling unit and a resource processing unit, wherein the receiving unit is used for receiving a medical resource scheduling request which carries resource demand information and a resource identifier;

the processing unit is used for determining whether a target medical resource is a rare medical resource according to the resource identifier, wherein the target medical resource is a resource indicated by the resource identifier;

the processing unit is further configured to determine attribute information of the target medical resource if the medical resource is the rare medical resource, where the attribute information includes at least one of: resource distribution mode, resource timeliness, resource storage mode and resource treatment effect;

the processing unit is further configured to call a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource, so as to obtain a first reference resource scheduling scheme of the target medical resource;

the processing unit is further configured to call a second resource scheduling model to predict a scheduling scheme of the target medical resource according to the resource demand information, so as to obtain a second reference resource scheduling scheme of the target medical resource;

the processing unit is further configured to determine a target resource scheduling scheme of the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme;

the processing unit is further configured to schedule the target medical resource based on the target resource scheduling scheme.

In one aspect, an embodiment of the present application provides a computer device, including a processor and a memory, where the processor and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the above-mentioned resource scheduling method.

In one aspect, an embodiment of the present application provides a computer-readable storage medium, where program instructions are stored in the computer-readable storage medium, and when the program instructions are executed, the computer-readable storage medium is used to implement the resource scheduling method described above.

In one aspect, the present application provides a computer program product or a computer program, where the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium, and when the computer instructions are executed by a processor of a computer device, the computer program product or the computer program performs the resource scheduling method described above.

In the embodiment of the application, the computer device can receive the medical resource scheduling request, then determine whether the target medical resource is a rare medical resource according to the resource identifier, and if the target medical resource is the rare medical resource, determine the attribute information of the target medical resource; calling a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource to obtain a first reference resource scheduling scheme of the target medical resource; according to the resource demand information, calling a second resource scheduling model to predict a scheduling scheme of the target medical resource to obtain a second reference resource scheduling scheme of the target medical resource; determining a target resource scheduling scheme of the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme; the target medical resource is then scheduled based on the target resource scheduling scheme. The appropriate target resource scheduling scheme for scheduling the target medical resource is determined according to the attribute information and the resource demand information of the target medical resource, and then the target medical resource is scheduled according to the target resource scheduling scheme, so that the efficiency of scheduling the target medical resource can be greatly improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1a is a schematic structural diagram of a resource scheduling system according to an embodiment of the present invention;

FIG. 1b is a schematic diagram of an architecture of another resource scheduling system according to an embodiment of the present invention;

fig. 2 is a flowchart illustrating a 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 computer device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The embodiment of the application provides a resource scheduling scheme, which mainly utilizes artificial intelligence to acquire and process attribute information of target medical resources and resource demand information of a sick user. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like. The general principle of this resource scheduling scheme is as follows: when a user lacks certain medical resources, the required medical resources can be dispatched from other places (such as other medical institutions). For example, a user may send a medical resource scheduling request to a terminal device where a storage location where the medical resource is stored is located, or the user may send a medical resource scheduling request to a resource scheduling platform that uniformly monitors various types of medical resources; correspondingly, the terminal device or the resource scheduling platform in which the storage location storing the medical resource is located may receive a medical resource scheduling request sent by a user, where the medical resource scheduling request may carry resource demand information and a resource identifier of a diseased user, where the resource identifier may be used to indicate a required target medical resource, and then determine whether the required target medical resource is a rare medical resource, and if it is determined that the target medical resource is a rare medical resource, attribute information of the target medical resource may be obtained, where the attribute information may be resource timeliness of the target medical resource, and for example, the resource timeliness of the target medical resource may be several hours. Then, a suitable resource scheduling scheme for scheduling the target medical resource can be determined according to the attribute information of the target medical resource and the resource demand information of the sick user. According to the attribute information, a first resource scheduling model is called to predict a scheduling scheme of the target medical resource, so that a first reference resource scheduling scheme of the target medical resource is obtained; according to the resource demand information, a second resource scheduling model is called to predict a scheduling scheme of the target medical resource, and a second reference resource scheduling scheme of the target medical resource is obtained; and then selecting the most appropriate resource scheduling scheme from the first reference resource scheduling scheme and the second reference resource scheduling scheme, and scheduling the target medical resource for the user based on the selected resource scheduling scheme, thereby realizing that the required target medical resource can be acquired more quickly in appropriate time or emergency time.

According to the resource scheduling scheme, the target resource scheduling scheme for scheduling the target medical resource is obtained through two dimensions of the attribute of the target medical resource and the resource demand information of the diseased user, so that the most appropriate resource scheduling scheme can be obtained, and the efficiency of scheduling the medical resource is improved by further scheduling the target medical resource through the target resource scheduling scheme.

Based on the above resource scheduling scheme, an embodiment of the present application provides a resource scheduling system, please refer to fig. 1a, the resource scheduling system includes at least two terminal devices 101 and a resource scheduling platform 102, where any terminal device 101 may send a medical resource scheduling request to the resource scheduling platform 102, and the resource scheduling platform 102 may determine a resource scheduling scheme for scheduling a corresponding medical resource based on the medical resource scheduling request sent by any terminal device 101, and schedule the corresponding medical resource based on the resource scheduling scheme. The terminal device 101 and the resource scheduling platform 102 may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein. The resource scheduling platform 102 may be a terminal device or a server. The terminal device may be an intelligent device such as a mobile phone, a tablet computer, a notebook computer, a palm computer, a Mobile Internet Device (MID), a wearable device, and the like. The servers include a plurality of servers (also called nodes), which may be independent physical servers, and may also be cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, Network services, cloud communication, middleware services, domain name services, security services, Content Delivery Networks (CDNs), big data platforms, and artificial intelligence platforms.

In one embodiment, when a user needs a certain medical resource, the user may send a medical resource scheduling request to the resource scheduling platform 102 through the terminal device 101, and then the resource scheduling platform 102, after receiving the medical resource scheduling request sent by the terminal device 101, may determine whether a resource of a target medical resource requested by the medical resource scheduling request is a rare medical resource, and if it is determined that the target medical resource is a rare medical resource, may predict a resource scheduling scheme for scheduling the target medical resource according to attribute information of the target medical resource and resource demand information of the sick user to obtain a target resource scheduling scheme of the target medical resource, and the resource scheduling platform 102 may send the target resource scheduling scheme to another terminal device 101 based on the target resource scheduling scheme, so that after the other terminal device 101 receives the target resource scheduling scheme, and calling the target medical resource stored in the position of the terminal equipment for the user.

It should be noted that fig. 1a merely represents an exemplary system architecture of the resource scheduling system, and does not limit the specific architecture of the resource scheduling system. For example, the number of terminal devices in fig. 1a is 2; but in other embodiments the number of terminal devices may be 3, 5 or even more. As another example, the terminal device 101 and the resource scheduling platform 102 in fig. 1a may both be located outside the blockchain network; however, in other embodiments, the resource scheduling system may also be deployed based on a blockchain network, that is, both the terminal device 101 and the resource scheduling platform 102 may be deployed in the blockchain network, or as shown in fig. 1b, the terminal device 101 is deployed outside the blockchain network, and the resource scheduling platform 102 is deployed inside the blockchain network, and so on. The blockchain mentioned here is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Which is essentially a decentralized database, is a string of blocks of data that are related using cryptographic methods.

Referring to fig. 2, fig. 2 is a schematic flowchart of a resource scheduling method according to an embodiment of the present invention. The resource scheduling method may be executed by a computer device, where the computer device may be the resource scheduling platform 102 in the resource scheduling system, and the resource scheduling method described in this embodiment may include the following steps S201 to S207:

s201, receiving a medical resource scheduling request, wherein the medical resource scheduling request carries resource demand information and a resource identifier.

The medical resource scheduling request can be sent by a first user or a medical platform, and the first user can be a doctor or a sick user; the resource identifier may be used to indicate the target medical resource and the resource requirement information may be used to indicate the urgency of the need for the target medical resource. The resource demand information may include the amount of the target medical resource required by the second user, the time required for the target medical resource, and the like, and the resource demand information may further include an urgency level of the target medical resource required by the second user, which may be associated with a demand time level of the target medical resource, the shorter the demand time is, the higher the urgency level is. The second user may refer to a sick user, for example, when the second user is in an operative stage, the resource demand information may include that the time for which a blood package of a rare blood type of the target medical resource is needed may be 30 minutes, 1 hour, and so on. The target medical resource may be a rare medical resource or a general medical resource. The rare medical resources refer to resources with the quantity of medical resources smaller than a quantity threshold value, or the rare medical resources refer to resources only produced in a certain quantity within a certain time, and can be understood as follows: rare medical resources refer to very rare and precious resources. The rare medical resource may be, for example, a rare drug (viper serum), an organ required for organ transplantation, blood for a rare blood group, or the like. Alternatively, the scarce medical resource may also be a medical specialist or the like in a certain medical field.

In a specific implementation, when the second user needs a certain medical resource within a certain time (e.g., within 1 hour), the first user or the medical platform may send a medical resource scheduling request for the target medical resource to the computer device, and accordingly, the computer device may receive the medical resource scheduling request sent by the first user.

In one embodiment, the medical resource scheduling request carries input operational characteristics of the first user. The input operation features may be features of voice input, keyboard text input strength, text input speed, single-hand input or two-hand input, and the like. In the case of voice input, the voice input by each user is different in tone and tone, so that whether the medical resource scheduling request is sent by the first user himself or herself can be known through the voice input characteristics. The computer device can compare the input operation characteristics of the first user with the recorded historical input operation characteristics to obtain a comparison result, then obtain an input characteristic matching value of the first user based on the comparison result, then obtain an identity verification mode corresponding to the input characteristic value of the first user according to a preset corresponding relation between the input characteristic matching value and the identity verification mode, perform identity verification on the first user by using the identity verification mode corresponding to the input characteristic value of the first user, and execute step S202 after the identity verification of the first user is passed; and if the authentication of the first user is not passed, sending prompt information to the first user, wherein the prompt information is used for indicating that the authentication is not passed. The historical input operation features may be various input operation features left when the first user registers on the computer device, where the registration may be understood as obtaining resource scheduling authority in the computer device in advance, so as to conveniently obtain sending a medical resource scheduling request to the computer device. The authentication mode can be account password authentication, wechat code scanning authentication, dynamic acquisition of an authentication code by a mobile phone and the like. For example, the input operation characteristic of the first user is 20 words per minute of the text input speed, and the historical input operation characteristic of the first user is 20 words per minute. And then comparing the input operation characteristics with the historical operation characteristics to obtain a comparison result of complete matching, acquiring an input characteristic matching value of the first user as 100 according to the complete matching of the comparison result, and determining the input characteristic matching value as account password login by the computer equipment based on the preset corresponding relation between the input characteristic matching value and the identity authentication mode. The first user may then enter an account password, and the computer device may authenticate the first user based on the entered account password. Wherein, the corresponding relationship between the input feature matching value and the authentication mode can be preset. For example, when the input feature matching value is 85-100, the authentication mode is an account password; when the input feature matching value is 70-85, the identity verification mode is WeChat code scanning verification; when the input feature matching value is 55-70, the authentication mode is that a mobile phone authentication code needs to be input; and when the input feature matching value is less than 55, the first user is not considered to be the user himself, the authentication request is directly rejected, and the first user is not allowed to perform subsequent operations.

In an embodiment, the specific implementation manner that the computer device may compare the input operation characteristics of the first user with the recorded historical input operation characteristics to obtain a comparison result, and then obtain the input characteristic matching value of the first user based on the comparison result may be: the computer device may calculate a similarity between the input operation feature of the first user and the recorded historical input operation feature, and search for an input feature matching value corresponding to the calculated similarity from a correspondence between the similarity and the input feature matching value, to obtain an input feature matching value of the first user.

In one embodiment, the number of the input operation features of the first user is multiple, for example, when the first user sends the resource scheduling request, the input operation features may include keyboard text input strength and single-hand input. In this case, the computer device needs to compare a plurality of input operation features with corresponding historical operation features, determine an operation feature value of each input operation feature according to the comparison result, and sum the operation feature values of each input operation feature as an input feature matching value of the first user. For example, the input operation features include single-hand input and keyboard text input strength; and then comparing the two input operation characteristics with the corresponding historical operation characteristics, obtaining an operation characteristic value of 40 input by one hand and an operation characteristic value of 30 keyboard character input force according to a comparison result, and then summing the operation characteristic value of 40 input by one hand and the operation characteristic value of the keyboard character input force to obtain an input characteristic matching value of 70 of the target user.

S202, determining whether the target medical resource is a rare medical resource according to the resource identifier.

The rare medical resource may be a rare drug (viper serum), an organ required for organ transplantation, a rare blood type blood, and the like, and it is understood that the medical resource of which the quantity of the medical resource is less than the quantity threshold in step S201 may all belong to the rare medical resource. In one embodiment, different reference resource identifiers may correspond to different medical resources, for example, reference resource identifier 1 corresponds to a serum resource and reference resource identifier 2 corresponds to a rare blood type blood resource. The computer equipment can determine the target medical resource corresponding to the resource identifier from the corresponding relation between the reference resource identifier and the medical resource; judging whether the target medical resource is a rare medical resource, and executing S203 if the target medical resource is determined to be the rare medical resource; if the target medical resource is determined not to be the rare medical resource, reminding information can be output to the first user, and the reminding information can remind that the target medical resource is not the rare medical resource.

And S203, if the medical resource is a rare medical resource, determining the attribute information of the target medical resource.

The attribute information refers to some resource characteristics of the target medical resource, and the attribute information may include, but is not limited to: resource timeliness, resource treatment effect, resource storage mode and resource distribution mode. The timeliness of the target medical resource refers to the validity period of the target medical resource, for example, a certain medical resource may lose the functional role of the target medical resource after the validity period is possibly 1 hour, i.e., 1 hour. Resource storage means that medical resources may require low temperature storage, dry storage, and the like. The resource distribution method is a method of distributing medical resources. For example, the medical resource is a medical specialist and is distributed by a special vehicle; the medical resource is medicine and can be delivered by a truck.

S204, calling the first resource scheduling model to predict the scheduling scheme of the target medical resource according to the attribute information of the target medical resource to obtain a first reference resource scheduling scheme of the target medical resource. The first reference resource scheduling scheme may include a resource scheduling route, a time required for resource scheduling, a resource storage location, and the like.

In one embodiment, the first resource scheduling model may include a feature extraction layer, an attention mechanism layer, and a fully-connected layer. The feature extraction layer can be used for extracting feature vectors of the attribute information, and the attention mechanism layer can be used for performing attention weight analysis on the attribute information; the specific implementation manner of the computer device that may invoke the first resource scheduling model to predict the scheduling scheme of the target medical resource according to the attribute information of the target medical resource, to obtain the first reference resource scheduling scheme of the target medical resource, where the medical resource scheduling request is sent by the first user, may be: acquiring the position information of a first user, and acquiring the position information of the first user; calling a feature extraction layer in the first resource scheduling model to respectively perform feature extraction on the attribute information and the position information of the target medical resource to obtain an attribute feature vector of the attribute information of the target medical resource and a position feature vector corresponding to the position information; calling an attention mechanism layer in the first resource scheduling model to perform attention analysis on the attribute feature vectors of the attribute information to obtain weight values of the attribute feature vectors; weighting the attribute feature vectors based on the weight values of the attribute feature vectors to obtain weighted features of the attribute information; then calling an attention mechanism layer in the first resource scheduling model to perform attention analysis on the position feature vector to obtain a weight value of the position feature vector; weighting the position characteristic vector based on the weight value of the position characteristic vector to obtain the weighted characteristic of the position information; and then, calling a full connection layer in the first resource scheduling model to analyze the weighted characteristics of the attribute information and the weighted characteristics of the position information to obtain a first reference resource scheduling scheme of the target medical resource. In a specific implementation, the computer device may obtain the location information of the first user by using a GPS (Global Positioning System) Positioning technology or by using instant messaging software in the terminal device where the first user is located. And then, taking the position information of the first user and the attribute information of the target medical resource as the input of a first resource scheduling model, and then calling a feature extraction layer, an attention mechanism layer and a full connection layer in the first resource scheduling model to process the position information and the attribute information of the first user to obtain a target resource scheduling scheme of the target medical resource. Before the first resource scheduling model is called, the model may be trained based on a plurality of samples and the resource scheduling scheme label corresponding to each sample, so as to obtain the first resource scheduling model. In particular, the computer device may obtain a plurality of sample pairs, each sample pair comprising: training resource attributes of the target medical resources, training position information of the user and resource scheduling scheme labels; then, the computer device can call the initial resource scheduling model to predict the scheduling scheme of the target medical resource according to the plurality of sample pairs to obtain the resource scheduling prediction scheme corresponding to each sample pair, and then optimize the initial resource scheduling model based on the resource scheduling prediction scheme and the resource scheduling scheme label corresponding to each sample pair to obtain a first resource scheduling model. The structure of the initial resource scheduling model is the same as that of the first resource scheduling model.

S205, according to the resource demand information, calling a second resource scheduling model to predict a scheduling scheme of the target medical resource, and obtaining a second reference resource scheduling scheme of the target medical resource. The second reference resource scheduling scheme may include a resource scheduling route, a time required for resource scheduling, a resource storage location, and the like.

In particular implementations, the resource requirement information is presented textually, and the computer device can extract relevant information about the location information and the target medical resource from the resource requirement information. In this case, the location information generally exists in the resource requirement information, i.e. the location where the resource requirement information comes from, i.e. the location where the first user is located, can be indicated. And the target medical resource required by the second user, the use time of the target medical resource required and the like are recorded in the resource requirement information, and correspondingly, the associated information with the target medical resource can be the use time, the number of the target medical resources and the like. The computer device may respectively process the position information and the associated information of the target medical resource by using a feature extraction layer in the second resource scheduling model to obtain a feature vector corresponding to the position information and a feature vector corresponding to the associated information of the target medical resource, and call a full connection layer in the second resource scheduling model to analyze and process the associated information of the target medical resource to obtain a second reference resource scheduling scheme of the target medical resource. Wherein the second resource scheduling model may be a simple neural network model. At this time, the second resource scheduling model may be obtained by training a plurality of training sample pairs, where each of the plurality of training sample pairs includes location information, association information of the target medical resource, and a resource scheduling scheme label.

S206, determining a target resource scheduling scheme of the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme.

In a specific implementation, the computer device may compare the first reference resource scheduling scheme with the second resource scheduling scheme, and determine, if it is determined that the first reference resource scheduling scheme is the same as the second reference resource scheduling scheme, a target resource scheduling scheme of the target medical resource using the first reference resource scheduling scheme or the second reference resource scheduling scheme.

In one embodiment, if the computer device determines that the first reference resource scheduling scheme is different from the second reference resource scheduling scheme, in order to determine the most appropriate target resource scheduling scheme, the computer device may obtain road condition information in an area where the first user is located; and determining a target resource scheduling scheme of the target medical resource from the first reference resource scheduling scheme and the second reference resource scheduling scheme according to the road condition information. The road condition information in the area where the first user is located can be determined through a GPS positioning technology or from various maps. The area where the first user is located may be a preset area or an area formed by extending the location where the first user is located to a target distance, for example, an area formed by taking the location where the first user is located as a center of a circle and taking the target distance as a radius, and the area where the first user is located may also be an area formed by taking the location where the first user is located to a storage location where the target medical resource is located.

In one embodiment, the traffic information may include a plurality of road segments and the road segment information for each road segment may indicate a current congestion condition for the road segment. The specific implementation mode of determining the target resource scheduling scheme of the target medical resource from the first reference resource scheduling scheme and the second reference resource scheduling scheme according to the road condition information is as follows: the computer equipment can compare the road section information of each road section with the route information in the first reference resource scheduling scheme to obtain the resource scheduling duration of the first reference resource scheduling scheme; comparing the road section information of each road section with the route information in the second reference resource scheduling scheme to obtain the resource scheduling duration of the second reference resource scheduling scheme; then judging whether the resource scheduling duration of the first reference resource scheduling scheme is longer than the resource scheduling duration of the second reference resource scheduling scheme; if the resource scheduling duration of the first reference resource scheduling scheme is longer than the resource scheduling duration of the second reference resource scheduling scheme, determining the second reference resource scheduling scheme as a target resource scheduling scheme of the target medical resource; and if the resource scheduling duration of the first reference resource scheduling scheme is less than the resource scheduling duration of the second reference resource scheduling scheme, determining the first reference resource scheduling scheme as a target resource scheduling scheme of the target medical resource. The road section information may include the required transit time for passing through the road section, the road section environment and the like, and the route information also includes a plurality of road sections; in specific implementation, the computer device may match the road section information of each road section with the route information in the first reference resource scheduling scheme, overlap the transit time indicated by one or more pieces of matched road section information if one or more pieces of matched road section information matched with the route information of the first reference resource scheduling scheme exist in the road section information of the plurality of road sections, obtain an overlap value, and use the overlap value as the resource scheduling duration of the first reference resource scheduling scheme. The matching here may mean that the link environment and the like are consistent with the corresponding links in the route information (i.e., the route information includes intersections, the link information of the plurality of links also includes intersections, and both are the same intersections). Similarly, the computer device may further match the road section information of each road section with a route in the second reference resource scheduling scheme to obtain a resource scheduling duration of the second reference resource scheduling scheme, and then select, from the first reference resource scheduling scheme and the second reference resource scheduling scheme, the reference resource scheduling scheme with the minimum resource scheduling duration as the target resource scheduling scheme.

In one embodiment, if the computer device determines that the first reference resource scheduling scheme and the second reference resource scheduling scheme are not the same, the computer device scores the first reference resource scheduling scheme and the second reference resource scheduling scheme by using the auxiliary resource attribute of the target medical resource to obtain a score of the first reference resource scheduling scheme and a score of the second reference resource scheduling scheme, wherein the auxiliary resource attribute may include but is not limited to: resource matching degree, resource distribution mode and resource timeliness; if the score of the first reference resource scheduling scheme is greater than the score of the second reference resource scheduling scheme, determining the first reference resource scheduling scheme as a target resource scheduling scheme of the target medical resource; and if the score of the second reference resource scheduling scheme is greater than the score of the first reference resource scheduling scheme, determining the second reference resource scheduling scheme as a target resource scheduling scheme of the target medical resource. In a specific implementation, an auxiliary resource attribute scoring rule may be set, and the computer device may score the first reference resource scheduling scheme according to the auxiliary resource attribute scoring rule. For example, the secondary resource attribute scoring rule is: the resource distribution mode in the resource scheduling scheme is low-temperature special vehicle transportation, the score of the resource scheduling scheme is 90, the score of the resource scheduling scheme is 80 if the resource distribution mode in the resource scheduling scheme is air transportation, and the like; the computer device may then determine a resource distribution manner in the first reference resource scheduling scheme and a resource distribution manner in the second reference resource scheduling scheme, score the first reference resource scheduling scheme according to the auxiliary resource attribute scoring rule based on the resource distribution manner in the first reference resource scheduling scheme to obtain a score of the first reference resource scheduling scheme, and score the second reference resource scheduling scheme according to the auxiliary resource attribute scoring rule based on the resource distribution manner in the second reference resource scheduling scheme to obtain a score of the second reference resource scheduling scheme.

And S207, scheduling the target medical resource based on the target resource scheduling scheme.

In specific implementation, after determining a target resource scheduling scheme for scheduling a target medical resource, the computer device determines a target storage location of the target medical resource in the target resource scheduling scheme, for example, the target storage location is a certain medical institution, a certain warehouse, or the like; when the target medical resource is a treatment plan, the target storage location may be a local space of a certain device, etc.; the computer device may then transmit the target resource scheduling scheme to the terminal device at the target storage location, so that the terminal device at the target storage location schedules the target medical resource to the first user based on the target resource scheduling scheme, or so that the terminal device at the target storage location transmits the target medical resource to the second user based on the target resource scheduling scheme, or so that the terminal device at the target storage location transmits the target medical resource to a medical platform (such as a hospital that needs the target medical resource) based on the target resource scheduling scheme.

In one embodiment, to ensure that the target medical resource is sufficient in the target storage location to account for the lack of target medical resource in subsequent target storage locations. After the computer device schedules the target medical resource for the first user based on the target resource scheduling scheme, the computer device may further count the number of the remaining target medical resources in the target storage location, and determine whether the number of the remaining target medical resources is lower than a preset value, if it is determined that the number of the remaining target medical resources is lower than the preset value, monitor the number of the target medical resources stored in the remaining storage locations except the target storage location, and if it is determined that the number of the target medical resources stored in the other storage locations is greater than the preset value, output a prompt message to the terminal device where the target storage location is located, where the prompt message may be used to instruct the terminal device where the target storage location is located to acquire the target medical resource from the other storage locations, so that the target medical resource in the target storage location is sufficient.

In the embodiment of the application, the computer device may receive a medical resource scheduling request sent by a first user, and then determine whether a target medical resource is a rare medical resource according to a resource identifier; if the medical resource is a rare medical resource, determining attribute information of the target medical resource; calling a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource to obtain a first reference resource scheduling scheme of the target medical resource; according to the resource demand information, calling a second resource scheduling model to predict a scheduling scheme of the target medical resource to obtain a second reference resource scheduling scheme of the target medical resource; determining a target resource scheduling scheme of the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme; the target medical resource is then scheduled based on the target resource scheduling scheme. The method comprises the steps of determining a proper target resource scheduling scheme for scheduling the target medical resource according to the attribute information of the target medical resource and the resource demand information of a user, and scheduling the target medical resource according to the target resource scheduling scheme, so that the efficiency of scheduling the target medical resource can be greatly improved, and the target medical resource can be acquired in time.

Based on the description of the foregoing resource scheduling method embodiment, an embodiment of the present application further discloses a resource scheduling apparatus, which may be a computer program (including program code) running in the foregoing mentioned computer device. The resource scheduling apparatus may perform the method shown in fig. 2. Referring to fig. 3, the resource scheduling apparatus may operate as follows:

a receiving unit 301, configured to receive a medical resource scheduling request, where the medical resource scheduling request carries resource demand information and a resource identifier;

a processing unit 302, configured to determine whether a target medical resource is a rare medical resource according to the resource identifier, where the target medical resource is a resource indicated by the resource identifier;

the processing unit 302 is further configured to determine attribute information of the target medical resource if the medical resource is the rare medical resource, where the attribute information includes at least one of: resource distribution mode, resource timeliness, resource storage mode and resource treatment effect;

the processing unit 302 is further configured to invoke a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource, so as to obtain a first reference resource scheduling scheme of the target medical resource;

the processing unit 302 is further configured to invoke a second resource scheduling model to predict a scheduling scheme of the target medical resource according to the resource demand information, so as to obtain a second reference resource scheduling scheme of the target medical resource;

the processing unit 302 is further configured to determine a target resource scheduling scheme of the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme;

the processing unit 302 is further configured to schedule the target medical resource based on the target resource scheduling scheme.

In an embodiment, the medical resource scheduling request further carries an input operation characteristic of a first user, and the processing unit 302 is further configured to:

comparing the input operation characteristics of the first user with recorded historical input operation characteristics to obtain a comparison result;

obtaining an input feature matching value of the first user according to the comparison result;

acquiring an identity verification mode corresponding to the input feature matching value of the first user according to a preset corresponding relation between the input feature matching value and the identity verification mode;

performing identity authentication on the first user by using an identity authentication mode corresponding to the input feature matching value of the first user;

and after the identity authentication of the first user is passed, executing the step of determining whether the target medical resource is a rare medical resource according to the resource identifier.

In an embodiment, the processing unit 302, when determining the target resource scheduling scheme of the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme, may specifically be configured to:

comparing the first reference resource scheduling scheme with the second reference resource scheduling scheme;

if the first reference resource scheduling scheme is different from the second reference resource scheduling scheme, acquiring road condition information in the area where the target user is located;

and determining a target resource scheduling scheme of the target medical resource from the first reference resource scheduling scheme and the second reference resource scheduling scheme according to the road condition information.

if the first reference resource scheduling scheme is different from the second reference resource scheduling scheme, scoring the first reference resource scheduling scheme and the second reference resource scheduling scheme by using an auxiliary resource attribute of the target medical resource to obtain a score of the first reference resource scheduling scheme and a score of the second reference resource scheduling scheme, wherein the auxiliary resource attribute is at least one of the following: resource distribution mode and resource timeliness;

if the score of the first reference resource scheduling scheme is greater than the score of the second reference resource scheduling scheme, determining the first reference resource scheduling scheme as a target resource scheduling scheme of the target medical resource;

and if the score of the second reference resource scheduling scheme is greater than the score of the first reference resource scheduling scheme, determining the second reference resource scheduling scheme as a target resource scheduling scheme of the target medical resource.

In an embodiment, the medical resource scheduling request is sent by a first user, and when the processing unit 302 invokes a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource to obtain a first reference resource scheduling scheme of the target medical resource, the processing unit may specifically be configured to:

acquiring the position information of the first user;

calling a feature extraction layer in a first resource scheduling model to respectively perform feature extraction on the attribute information and the position information of the target medical resource to obtain an attribute feature vector of the attribute information and a position feature vector corresponding to the position information;

calling an attention mechanism layer in the first resource scheduling model to perform attention analysis on the attribute feature vector of the attribute information to obtain a weight value of the attribute feature vector; weighting the attribute feature vector based on the weight value of the attribute feature vector to obtain the weighted feature of the position attribute information;

calling an attention mechanism layer in the first resource scheduling model to perform attention analysis on the position feature vector to obtain a weight value of the position feature vector; weighting the feature vectors based on the weight values of the position feature vectors to obtain weighted features of the position information;

and calling a full connection layer in the first resource scheduling model to analyze the weighted characteristics of the attribute information and the weighted characteristics of the position information to obtain a first reference resource scheduling scheme of the target medical resource.

In one embodiment, the target resource scheduling scheme includes a target storage location of a target medical resource, and the processing unit 302, after scheduling the target medical resource for the first user based on the target resource scheduling scheme, is further configured to:

counting the number of remaining target medical resources in the target storage location;

if the quantity of the remaining target medical resources is lower than a preset value, monitoring the quantity of the target medical resources stored in other storage positions except the target storage position;

and if the quantity of the target medical resources stored in the other storage positions is larger than a preset value, outputting prompt information to the terminal equipment where the target storage position is located, wherein the prompt information is used for indicating that the target medical resources are obtained from the other storage positions.

In an embodiment, the traffic information includes a plurality of road segments and road segment information of each road segment, and the processing unit 302, when determining the target resource scheduling scheme of the target medical resource from the first reference resource scheduling scheme and the second reference resource scheduling scheme according to the traffic information, may specifically be configured to:

comparing the road section information of each road section with the route information in the first reference resource scheduling scheme to obtain the resource scheduling duration of the first reference resource scheduling scheme;

comparing the road section information of each road section with the route information in the second reference resource scheduling scheme to obtain the resource scheduling duration of the second reference resource scheduling scheme;

judging whether the resource scheduling duration of the first reference resource scheduling scheme is greater than the resource scheduling duration of the second reference resource scheduling scheme;

if not, determining the first reference resource scheduling scheme as a target resource scheduling scheme of the target medical resource;

and if so, determining the second reference resource scheduling scheme as a target resource scheduling scheme of the target medical resource.

It can be understood that each functional unit of the resource scheduling apparatus in this embodiment can be specifically implemented according to the method in the foregoing method embodiment fig. 2, and the specific implementation process thereof can refer to the related description in the foregoing method embodiment fig. 2, which is not described herein again.

Further, please refer to fig. 4, where fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application. The computer device in the corresponding embodiment of fig. 2 may be the computer device shown in fig. 4. As shown in fig. 4, the computer device may include: a processor 401, an input device 402, an output device 403, and a memory 404. The processor 401, the input device 402, the output device 403, and the memory 404 are connected by a bus 405. The memory 404 is used to store a computer program comprising program instructions and the processor 401 is used to execute the program instructions stored by the memory 404.

In the embodiment of the present application, the processor 401 executes the executable program code in the memory 404 to perform the following operations:

calling a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource to obtain a first reference resource scheduling scheme of the target medical resource;

In one embodiment, the medical resource scheduling request further carries an input operation characteristic of a first user, and the processor 401 is further configured to:

In one embodiment, the processor 401, when determining the target resource scheduling scheme of the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme, may specifically be configured to:

In an embodiment, the medical resource scheduling request is sent by a first user, and when the processor 401 invokes a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource to obtain a first reference resource scheduling scheme of the target medical resource, the processor may be specifically configured to:

acquiring the position information of the first user;

calling an attention mechanism layer in the first resource scheduling model to perform attention analysis on the attribute feature vector of the attribute information to obtain a weight value of the attribute feature vector, and performing weighting processing on the attribute feature vector based on the weight value of the attribute feature vector to obtain a weighting feature of the attribute information;

calling an attention mechanism layer in the first resource scheduling model to perform attention analysis on the position feature vector to obtain a weight value of the position feature vector, and performing weighting processing on the position feature vector based on the weight value of the position feature vector to obtain a weighting feature of the position information;

In one embodiment, the target resource scheduling scheme comprises a target storage location of a target medical resource, and the processor 401, after scheduling the target medical resource for the first user based on the target resource scheduling scheme, is further configured to:

In an embodiment, the traffic information includes a plurality of road segments and road segment information of each road segment, and the processor 401, when determining the target resource scheduling scheme of the target medical resource from the first reference resource scheduling scheme and the second reference resource scheduling scheme according to the traffic information, may specifically be configured to:

It should be understood that, in the embodiment of the present Application, the Processor 401 may be a Central Processing Unit (CPU), and the Processor 401 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 404 may include a read-only memory and a random access memory, and provides instructions and data to the processor 401. A portion of the memory 404 may also include non-volatile random access memory.

The input device 402 may include a keyboard or the like and inputs a medical resource scheduling request to the processor 401; the output device 403 may include a display or the like.

In a specific implementation, the processor 401, the input device 402, the output device 403, and the memory 404 described in this embodiment may execute the implementation described in all the embodiments above, and may also execute the implementation described in the apparatus above, which is not described herein again.

A computer-readable storage medium is provided in an embodiment of the present application, and stores a computer program, where the computer program includes program instructions, and the program instructions, when executed by a processor, can perform the steps performed in all the above embodiments.

Embodiments of the present application further provide a computer program product or a computer program, where the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium, and when the computer instructions are executed by a processor of a computer device, the computer instructions perform the methods in all the embodiments described above.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. A method for scheduling resources, comprising:

if the medical resource is the rare medical resource, determining attribute information of the target medical resource; wherein the attribute information includes at least one of: resource distribution mode, resource timeliness, resource storage mode and resource treatment effect;

2. The method of claim 1, wherein the medical resource scheduling request further carries input operational characteristics of a first user, the method further comprising:

3. The method of claim 1, wherein determining a target resource scheduling scheme for the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme comprises:

4. The method of claim 1, wherein determining a target resource scheduling scheme for the target medical resource based on the first reference resource scheduling scheme and the second reference resource scheduling scheme comprises:

5. The method according to claim 1, wherein the medical resource scheduling request is sent by a first user, and the step of calling a first resource scheduling model to predict a scheduling scheme of the target medical resource according to the attribute information of the target medical resource to obtain a first reference resource scheduling scheme of the target medical resource comprises:

acquiring the position information of the first user;

6. The method of claim 1, wherein the target resource scheduling scheme comprises a target storage location for a target medical resource, and wherein after scheduling the target medical resource based on the target resource scheduling scheme, the method further comprises:

7. The method according to claim 3, wherein the traffic information includes a plurality of road segments and road segment information for each road segment, and the determining the target resource scheduling scheme for the target medical resource from the first reference resource scheduling scheme and the second reference resource scheduling scheme according to the traffic information includes:

8. A resource scheduling apparatus, comprising:

9. A computer device comprising a memory for storing a computer program;

a processor invoking said computer program in said memory for performing the resource scheduling method of any one of claims 1 to 7.

10. A computer storage medium storing a computer program comprising program instructions that, when executed by a processor, perform the resource scheduling method of any one of claims 1 to 7.