CN111612183A - Information processing method, information processing device, electronic equipment and computer readable storage medium - Google Patents

Information processing method, information processing device, electronic equipment and computer readable storage medium Download PDF

Info

Publication number
CN111612183A
CN111612183A CN201910138848.3A CN201910138848A CN111612183A CN 111612183 A CN111612183 A CN 111612183A CN 201910138848 A CN201910138848 A CN 201910138848A CN 111612183 A CN111612183 A CN 111612183A
Authority
CN
China
Prior art keywords
predicted
area
information
region
time period
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
CN201910138848.3A
Other languages
Chinese (zh)
Inventor
何龙
杜龙志
刘澍
王志明
付俊强
余芳
范育峰
李奘
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.)
Beijing Didi Infinity Technology and Development Co Ltd
Original Assignee
Beijing Didi Infinity Technology and Development Co 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 Beijing Didi Infinity Technology and Development Co Ltd filed Critical Beijing Didi Infinity Technology and Development Co Ltd
Priority to CN201910138848.3A priority Critical patent/CN111612183A/en
Publication of CN111612183A publication Critical patent/CN111612183A/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
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • G06Q50/40—

Abstract

The application provides an information processing method, an information processing device, an electronic device and a computer readable storage medium, wherein the method comprises the following steps: dividing the target geographical position range into a plurality of areas to be predicted; clustering the multiple regions to be predicted according to historical order information of the multiple regions to be predicted to obtain at least one clustering region; and for each region to be predicted, determining the service demand information of the region to be predicted in the target time period according to the characteristic information of the region to be predicted in the target time period, the characteristic information of each other region to be predicted in the clustering region to which the region to be predicted belongs in the target time period, and the correlation degree between each other region to be predicted and the region to be predicted. The service demand of the area to be predicted is predicted by comprehensively considering the characteristics of the area to be predicted and the characteristics of other areas to be predicted in the clustering area corresponding to the area to be predicted, so that the accuracy of service demand prediction is improved.

Description

Information processing method, information processing device, electronic equipment and computer readable storage medium
Technical Field
The present application relates to the field of information technology, and in particular, to an information processing method, an information processing apparatus, an electronic device, and a computer-readable storage medium.
Background
With the rapid development of internet mobile communication technology and smart devices, various service applications, such as car-taxi Applications (APPs), have emerged. The user can obtain corresponding service of using a car after the APP input destination of taking a car, when the trip request that the user initiated is received to the platform of using a car, can match the service provider for the user, provides corresponding trip service.
At present, when service resources such as drivers are configured, the service resources are generally configured in advance according to historical travel data of users in a certain area, but the mode often causes the problem of unreasonable resource configuration due to instability of the historical travel data of certain areas.
Disclosure of Invention
In view of the above, an object of the present application is to provide an information processing method, an information processing apparatus, an electronic device, and a computer-readable storage medium, so as to improve accuracy of service demand prediction in an area.
In a first aspect, an embodiment of the present application provides an information processing method, including:
dividing the target geographical position range into a plurality of areas to be predicted;
clustering the multiple regions to be predicted according to historical order information of the multiple regions to be predicted to obtain at least one clustering region;
and for each region to be predicted, determining the service demand information of the region to be predicted in the target time period according to the characteristic information of the region to be predicted in the target time period, the characteristic information of each other region to be predicted in the clustering region to which the region to be predicted belongs in the target time period, and the correlation degree between each other region to be predicted and the region to be predicted.
In some embodiments, after determining the service demand information of the area to be predicted in the future preset time period, the method further includes:
and determining a resource configuration strategy for the area to be predicted according to the service demand information.
In some embodiments, after determining the resource configuration policy for the area to be predicted, the method further includes:
after receiving an access request initiated by a user terminal in the area to be predicted, configuring resources for the user terminal according to a resource configuration strategy corresponding to the area to be predicted; alternatively, the first and second electrodes may be,
when the area to be predicted comprises the historical trip location of the user side according to the historical order information of the user side, resources are allocated for the user side according to a resource allocation strategy corresponding to the area to be predicted.
In some embodiments, the correlation between each of the other regions to be predicted and the region to be predicted is determined according to the following steps:
and determining the correlation degree between each other area to be predicted and the area to be predicted according to the similarity between each other area to be predicted and the area to be predicted on the historical order information and the proximity on the geographical position.
In some embodiments, determining the correlation between each of the other areas to be predicted and the area to be predicted according to the similarity between the other areas to be predicted and the area to be predicted in the historical order information and the proximity in the geographic position includes:
and determining the correlation between each other area to be predicted and the area to be predicted according to the similarity on the historical order information, the proximity on the geographic position between each other area to be predicted and the correlation weight respectively corresponding to the historical order information and the geographic position.
In some embodiments, for each to-be-predicted area, determining the service demand information of the to-be-predicted area in the target time period according to the feature information of the to-be-predicted area in the target time period, the feature information of each other to-be-predicted area in the clustering area to which the to-be-predicted area belongs in the target time period, and the correlation degree between each other to-be-predicted area and the to-be-predicted area, includes:
inputting the characteristic information of the area to be predicted in a future preset time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period and the correlation degree between each other area to be predicted and the area to be predicted into a pre-trained service demand prediction model to obtain the service demand information of the area to be predicted in the future preset time period.
In some embodiments, the service demand prediction model is trained according to the following steps:
constructing a training sample library, wherein the training sample library comprises characteristic information of a plurality of regions to be trained in a historical time period, the correlation degree between each region to be trained and other regions to be trained belonging to the same clustering region, and service requirement information of each region to be trained in the historical time period;
obtaining model input characteristics based on the characteristic information of each to-be-trained area in the historical time period and the correlation degree between each to-be-trained area and other to-be-trained areas belonging to the same clustering area, and training to obtain the service demand prediction model by taking the service demand information of each to-be-trained area in the historical time period as model output characteristics.
In some embodiments, the service demand information includes supply-demand ratio information.
In some embodiments, the characteristic information includes a plurality of:
information of the target event occurred; weather information; historical order information; service provider information capable of providing a service.
In some embodiments, if the target time period is a future preset time period, the weather information includes weather forecast information; and if the target time period is the current preset time period, the weather information comprises the current weather information.
In some embodiments, the plurality of regions to be predicted are clustered according to the following steps:
determining the similarity of any two areas to be predicted on the historical order information based on the historical order information of each area to be predicted;
based on the similarity of any two areas to be predicted on the historical order information, the areas to be predicted corresponding to the similarity larger than the set threshold are divided into the same type.
In a second aspect, an embodiment of the present application provides an information processing apparatus, including:
the dividing module is used for dividing the target geographic position range into a plurality of areas to be predicted;
the clustering module is used for clustering the multiple regions to be predicted according to the historical order information of the multiple regions to be predicted to obtain at least one clustering region;
and the determining module is used for determining the service demand information of the area to be predicted in the target time period according to the characteristic information of the area to be predicted in the target time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the target time period and the correlation degree between each other area to be predicted and the area to be predicted.
In some embodiments, the determining module is further configured to:
after determining the service demand information of the area to be predicted in a future preset time period, determining a resource configuration strategy for the area to be predicted according to the service demand information.
In some embodiments, the determining module is further configured to:
after determining a resource configuration strategy for the area to be predicted, after receiving an access request initiated by a user terminal in the area to be predicted, configuring resources for the user terminal according to the resource configuration strategy corresponding to the area to be predicted; alternatively, the first and second electrodes may be,
when the area to be predicted comprises the historical trip location of the user side according to the historical order information of the user side, resources are allocated for the user side according to a resource allocation strategy corresponding to the area to be predicted.
In some embodiments, the determining module is specifically configured to:
and determining the correlation degree between each other area to be predicted and the area to be predicted according to the similarity between each other area to be predicted and the area to be predicted on the historical order information and the proximity on the geographical position.
In some embodiments, the determining module is specifically configured to:
and determining the correlation between each other area to be predicted and the area to be predicted according to the similarity on the historical order information, the proximity on the geographic position between each other area to be predicted and the correlation weight respectively corresponding to the historical order information and the geographic position.
In some embodiments, the determining module is specifically configured to:
inputting the characteristic information of the area to be predicted in a future preset time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period and the correlation degree between each other area to be predicted and the area to be predicted into a pre-trained service demand prediction model to obtain the service demand information of the area to be predicted in the future preset time period.
In some embodiments, further comprising a training module to:
constructing a training sample library, wherein the training sample library comprises characteristic information of a plurality of regions to be trained in a historical time period, the correlation degree between each region to be trained and other regions to be trained belonging to the same clustering region, and service requirement information of each region to be trained in the historical time period;
obtaining model input characteristics based on the characteristic information of each to-be-trained area in the historical time period and the correlation degree between each to-be-trained area and other to-be-trained areas belonging to the same clustering area, and training to obtain the service demand prediction model by taking the service demand information of each to-be-trained area in the historical time period as model output characteristics.
In some embodiments, the service demand information includes supply-demand ratio information.
In some embodiments, the characteristic information includes a plurality of:
information of the target event occurred; weather information; historical order information; service provider information capable of providing a service.
In some embodiments, if the target time period is a future preset time period, the weather information includes weather forecast information; and if the target time period is the current preset time period, the weather information comprises the current weather information.
In some embodiments, the clustering module is specifically configured to:
determining the similarity of any two areas to be predicted on the historical order information based on the historical order information of each area to be predicted;
based on the similarity of any two areas to be predicted on the historical order information, the areas to be predicted corresponding to the similarity larger than the set threshold are divided into the same type.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when the electronic device runs, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to execute the steps of the information processing method according to the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the information processing method according to the first aspect.
According to the information processing method, the device, the electronic equipment and the computer readable storage medium provided by the embodiment of the application, for a plurality of to-be-predicted areas divided in the target geographic position range, the to-be-predicted areas are clustered according to historical order information, and then for each to-be-predicted area in each clustering area, the service demand information of the to-be-predicted area in the target time period is determined according to the feature information of the to-be-predicted area in the target time period, the feature information of each other to-be-predicted area in the clustering area to which the to-be-predicted area belongs in the target time period and the correlation degree between each other to-be-predicted area and the to-be-predicted area. Therefore, for one region to be predicted, the service requirement of the region to be predicted can be predicted by comprehensively considering the characteristics of the region to be predicted and the characteristics of other regions to be predicted in the clustering region corresponding to the region to be predicted, so that the accuracy of service requirement prediction is improved, and further, based on the predicted service requirement, service resource allocation can be more reasonably carried out.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a flow chart of an information processing method provided by an embodiment of the present application;
fig. 2 shows a flowchart of a method for clustering a region to be predicted according to an embodiment of the present application;
FIG. 3 is a flow chart illustrating a training process of a service demand prediction model provided by an embodiment of the present application;
fig. 4 is a schematic structural diagram illustrating an information processing apparatus according to an embodiment of the present application;
fig. 5 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
In order to enable a person skilled in the art to use the present disclosure, the following embodiments are given in conjunction with a specific application scenario "information processing method". It will be apparent to those skilled in the art that the general principles defined herein may be applied to travel scenarios and also to other scenarios requiring information processing without departing from the spirit and scope of the present application. Although the present application is primarily described in the context of a travel scenario, it should be understood that this is only one exemplary embodiment.
The embodiment of the application can serve a travel service platform, and the travel service platform is used for providing corresponding services for the user according to the received travel service request of the client. The trip service platform may include a plurality of taxi taking systems, such as a taxi taking system, a express taxi taking system, a special taxi taking system, a tailgating taxi taking system, and the like.
The information processing method of the embodiment of the application can be applied to a server of a trip service platform and can also be applied to any other computing equipment with a processing function. In some embodiments, the server or computing device may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein.
In some embodiments, the service requester and the service provider may include mobile devices, tablet computers, laptop computers, or built-in devices in motor vehicles, or the like, or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some embodiments, the smart home devices may include smart lighting devices, control devices for smart electrical devices, smart monitoring devices, smart televisions, smart cameras, or walkie-talkies, or the like, or any combination thereof. In some embodiments, the wearable device may include a smart bracelet, a smart lace, smart glass, a smart helmet, a smart watch, a smart garment, a smart backpack, a smart accessory, and the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, or a point of sale (POS) device, or the like, or any combination thereof. In some embodiments, the virtual reality device and/or the augmented reality device may include a virtual reality helmet, virtual reality glass, a virtual reality patch, an augmented reality helmet, augmented reality glass, an augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device and/or augmented reality device may include various virtual reality products and the like.
The idea of the embodiment of the present application is further described below by taking the service requirement of "taxi taking" as an example.
For some middle and large cities with large areas and large traffic, the cities often include multiple regions, for example, beijing cities include "hai lake region", "sunny region", "east city region", "west city region", "rich platform region", etc., service demand information of each region may not be the same in the same time period, for example, a service request end having a taxi taking demand in a certain time period of some regions is far larger than a service providing end capable of providing service in the region, the regions may need more service providing ends to provide trip service, while a service request end having a taxi taking demand in the time period of other regions is far smaller than a service providing end capable of providing service in the region, the region may need to guide the service request end to improve the taxi taking efficiency by activating the configuration of resources, so if the service demand information of each region of a city can be determined in advance, will play an important role in saving network resources and improving service efficiency. How to more accurately confirm the service requirement information of each area is a key problem, and the idea of the embodiment of the application is further described as follows:
an embodiment of the present application provides an information processing method, as shown in fig. 1, including:
s101, dividing the target geographical position range into a plurality of areas to be predicted.
The target geographical location area may be a good geographical area to be subjected to information statistics, which is defined on a map in advance, and the geographical area may be a city or a part of the city, and then is divided into a plurality of areas to be measured according to a preset rule.
For example, the region to be counted may be divided into a plurality of tightly connected regular polygon regions to form a regular polygon mesh structure, each regular polygon region serves as a region to be predicted, and the region to be predicted may be a regular hexagon region.
S102, clustering the multiple regions to be predicted according to historical order information of the multiple regions to be predicted to obtain at least one clustering region.
After the target geographic position range is divided, a large number of regions to be predicted may be obtained, and in order to improve the processing efficiency, the regions to be predicted may be clustered according to the historical order information.
In one embodiment, as shown in fig. 2, the clustering of the plurality of regions to be predicted may be performed according to the following steps, specifically including the following steps S201 to S202:
s201, based on the historical order information of each area to be predicted, the similarity of any two areas to be predicted on the historical order information is determined.
S202, based on the similarity of any two areas to be predicted on the historical order information, the areas to be predicted corresponding to the similarity larger than the set threshold are divided into the same type.
The historical order information can be used for measuring historical demand information of the area to be predicted about a certain service, such as historical order information of a taxi taking service in the travel field, and can be used for measuring similarity of each area to be predicted in the target geographic position range in the taxi taking service, then the areas to be predicted can be classified according to the similarity, and then the service demand information of each area to be predicted in each clustering area in the target time period can be predicted according to the classification result.
Specifically, the historical order information may include various types of information, such as a total historical order amount of the area to be predicted, the number of service providers of the area to be predicted, the number of calls initiated by the service requester of the area to be predicted, and the like.
In the travel field, the service providing end may be a driver end, the service requesting end may be a passenger end, and the specific form of the service providing end may be a mobile terminal, a tablet computer, a laptop computer, and the like.
Specifically, when the similarity between the areas to be predicted is determined based on the historical order information, the historical order information of each area to be predicted can be converted into the corresponding feature vector according to the various types of information included in the historical order information, and then the similarity between the areas to be predicted is calculated based on the feature vectors of the areas to be predicted, for example, the similarity between any two areas to be predicted on the historical order information can be determined through cosine similarity.
In an embodiment, after the similarity between every two to-be-predicted regions is determined, several to-be-predicted regions can be randomly determined to be central regions of several clustering regions respectively, then the to-be-predicted regions are divided into clustering regions with the similarity exceeding a set threshold value with the central regions respectively according to other to-be-predicted regions, the central regions of the clustering regions are recalculated according to clustering results, all to-be-predicted regions are re-clustered according to new centers, and the step of recalculating the central regions of the clustering regions is repeatedly executed until the clustering results do not change any more, so that clustering of the multiple to-be-predicted regions is completed.
In another embodiment, after determining the similarity between every two regions to be predicted, the related regions to be predicted, the similarity of which is significantly greater than a set threshold, may be divided into the same class, for example, including 10 regions to be predicted, where the similarity between every two of the 1 st region to be predicted, the 3 rd region to be predicted, and the 5 th region to be predicted in historical order information is greater than the set threshold, and then the 1 st region to be predicted, the 3 rd region to be predicted, and the 5 th region to be predicted are divided into first clustering regions; if the similarity of the 2 nd to-be-predicted area, the 4 th to-be-predicted area and the 6 th to-be-predicted area on the historical order information is larger than a set threshold value, dividing the 2 nd to-be-predicted area, the 4 th to-be-predicted area and the 6 th to-be-predicted area into second clustering areas; and if the similarity of the historical order information of the remaining 7 th to-be-predicted region, the 8 th to-be-predicted region, the 9 th to-be-predicted region and the 10 th to-be-predicted region is greater than the set threshold value, dividing the 7 th to-be-predicted region, the 8 th to-be-predicted region, the 9 th to-be-predicted region and the 10 th to-be-predicted region into a third cluster region, and in this case, the situation that the similarity of the to-be-predicted regions among different cluster regions on the historical order information is greater than the set threshold value does not exist.
In another embodiment, the plurality of regions to be predicted may be clustered as follows:
the total score corresponding to the historical order information of each region to be predicted can be determined according to the multiple types of information included in the historical order information, the pre-established mapping relation between each type of information and the score and the weight of each type of information, and then the regions to be predicted belonging to the same gear are divided into one type according to the set corresponding relation between the gear and the total score.
For example, the process of calculating the total score corresponding to the historical order information of the 1 st area to be predicted may be as follows:
taking historical order information comprising the total amount of historical orders, the number of service providing terminals and the number of calls initiated by a service request terminal as an example, firstly, according to a mapping relation between each type of information and a score which is established in advance, determining that the score corresponding to the total amount of the historical orders of the 1 st area to be predicted is 35 points; the score corresponding to the number of the service providers is 20; the score corresponding to the number of calls initiated by the service request terminal is 10 points; and the preset total sum of the historical orders accounts for 60%, the number of the service providing terminals accounts for 20%, and the number of the calls initiated by the service requesting terminal accounts for 20%, and then the total score corresponding to the historical order information of the 1 st area to be predicted can be determined to be 27.
In the same way, the total scores corresponding to the historical order information of all the regions to be predicted can be calculated, and then the regions to be predicted are classified according to the gear positions to which the scores belong.
The clustering methods are only some enumerated clustering methods, and clustering can be performed according to other modes, and are not enumerated here one by one.
S103, for each to-be-predicted area, determining the service demand information of the to-be-predicted area in the target time period according to the feature information of the to-be-predicted area in the target time period, the feature information of each other to-be-predicted area in the clustering area to which the to-be-predicted area belongs in the target time period, and the correlation degree between each other to-be-predicted area and the to-be-predicted area.
The target time period is a time period in which service demand information prediction is to be performed on the area to be predicted, and a time difference between the target time period and the current time may be preset, for example, the target time period is a time period one week after the current time, or a time period set minutes after the current time.
The characteristic information here may include the following various kinds:
information of the target event occurred; weather information; historical order information; service provider information capable of providing a service.
The occurred target event information refers to an event that has a significant influence on a "taxi taking" event, which is to occur in the target time period in the area to be predicted, for example, a concert, a world cup and other events are to be held in the target time period in the area to be predicted, because a large number of people may need to taxi to the area to be predicted or return from the area to be predicted.
If the target time period is a future preset time period, the weather information comprises weather forecast information; and if the target time period is the current preset time period, the weather information comprises the current weather information.
The historical order information is historical order information of a relative target time period, and specifically, in the prediction process, the historical order information may be order information of a set historical period that can be acquired at the current time.
In the "taxi taking" service, the service provider information capable of providing the service refers to the number of drivers, that is, the number of drivers capable of providing taxi taking service for the area to be predicted, and the service provider information of the target time period is similar to the historical order information and can also be the service provider information which can be collected at the current time and is set in the historical time period.
The corresponding relation between the historical order information and the set historical period acquired by the service provider information and the target time period is set in advance, for example, the current time is 12 o ' clock in 1 month and 1 day in 2018, the target time period is 20 o ' clock to 24 o ' clock in 1 month and 1 day in 2018, the set historical period can be 6 o ' clock to 12 o ' clock in 1 month and 1 day in 2018, and thus, the service demand information of a certain time period in the current day of the area to be predicted is predicted; certainly, the current time can be 12 o 'clock in 1 month and 1 day in 2018, the target time period is 12 o' clock in 8 months and 8 days in 1 month and 24 o 'clock in 2018, and the set historical period can be 12 o' clock in 25 months and 25 o 'clock in 2017 and 12 o' clock in 1 month and 1 day in 2018, so that the service demand information one week after the area to be predicted is predicted, the service resource preparation matched with the service demand information can be made in advance by predicting the service demand information of the area to be predicted in advance, and then the service resource is adjusted by determining the service demand information of the area to be predicted in the current day, so that the rationalization of service resource configuration is further improved.
The service demand information includes supply-demand ratio information, and in the field of the 'taxi taking' service, the supply-demand ratio information includes the ratio of the number of drivers who can provide taxi taking service to the number of passengers who need taxi taking.
The correlation here can be understood as the influence degree of each other to-be-predicted region on the to-be-predicted region in the cluster region to which the to-be-predicted region belongs, and the influence degree between each other to-be-predicted region and the to-be-predicted region is considered because the influence degree influences the "taxi taking" service requirement information of the to-be-predicted region, for example, if the to-be-predicted region is "hai lake region" and the "sunny region" belong to the same cluster region, when the "sunny region" is to take a singing meeting of a great star, the taxi taking requirement of the hai lake region is also influenced.
In one embodiment, the correlation between each of the other regions to be predicted and the region to be predicted may be determined according to the following steps:
and determining the correlation degree between each other area to be predicted and the area to be predicted according to the similarity between each other area to be predicted and the area to be predicted on the historical order information and the proximity on the geographical position.
The similarity between each other region to be predicted and the region to be predicted in the historical order information is similar to the above-mentioned method, and is not described herein again.
The proximity in geographic position between each other area to be predicted and the area to be predicted can be determined by:
and determining the distance between each other region to be predicted and the position of the region to be predicted in the ground and the distance interval to which the distance between each other region to be predicted and the region to be predicted belongs.
For example, a first distance interval corresponding to less than or equal to 1 km, a second distance interval corresponding to greater than or equal to 1 km and less than or equal to 5 km, a third distance interval corresponding to greater than 5 km and less than or equal to 10 km, and a fourth distance interval corresponding to greater than 10 km are preset, and when it is determined that the distance between any one area to be predicted and the area to be predicted at the location in the ground is 15 km, it can be determined that the distance interval to which the distance between the any one area to be predicted and the area to be predicted belongs is the fourth distance interval.
The proximity of each other area to be predicted to the area to be predicted on the geographical position may be represented according to a preset score corresponding to each distance interval, for example, if the proximity of two areas to be predicted belonging to the first distance interval on the geographical position is the highest and is 10, the proximity of two areas to be predicted belonging to the first distance interval on the geographical position is 10.
Specifically, the correlation between each of the other areas to be predicted and the area to be predicted is determined according to the similarity between each of the other areas to be predicted and the area to be predicted in the historical order information and the proximity in the geographic position, and may be specifically determined as follows:
and determining the correlation between each other area to be predicted and the area to be predicted according to the similarity on the historical order information and the proximity on the geographical position between each other area to be predicted and the correlation weight respectively corresponding to the historical order information and the geographical position.
For example, the relevance weight corresponding to the historical order information is w1The geographic position corresponds to a relevance weight of w2If the similarity of the ith area to be predicted and the jth area to be predicted on the historical order information is AijThe geographical proximity of the ith area to be predicted and the jth area to be predicted is BijThe correlation degree E between each other region to be predicted and the region to be predictedijDetermined by the following equation (1):
Eij＝w1Aij+w2Bij(1)
before predicting the regions to be predicted of the same clustering region, numbering all the regions to be predicted of the same clustering region, for example, a certain clustering region comprises 5 regions to be predicted, namely, the number is 1-5, and when the current region to be predicted is the 1 st region to be predicted, sequentially calculating the correlation degrees between the 2 nd region to be predicted to the 5 th region to be predicted and the 1 st region to be predicted respectively according to the formula.
Specifically, the above determining, for each to-be-predicted region, the service demand information of the to-be-predicted region in the target time period according to the feature information of the to-be-predicted region in the target time period, the feature information of each other to-be-predicted region in the clustering region to which the to-be-predicted region belongs in the target time period, and the correlation between each other to-be-predicted region and the to-be-predicted region includes:
inputting the characteristic information of the area to be predicted in a future preset time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period and the correlation degree between each other area to be predicted and the area to be predicted into a pre-trained service demand prediction model to obtain the service demand information of the area to be predicted in the future preset time period.
Specifically, when the service demand information of the area to be predicted in the future preset time period is predicted, firstly, the obtained feature information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period and the correlation degree between the feature information and the area to be predicted are obtained, the influence feature information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period on the area to be predicted is obtained, then the feature information of the area to be predicted in the future preset time period and the influence feature information of the other area to be predicted on the area to be predicted are input into the service demand prediction model together, and the service demand information of the area to be predicted in the future preset time period can be obtained. The following is a detailed description of a specific embodiment:
if a certain clustering region comprises 5 regions to be predicted, the number is 1-5, the current region to be predicted is the 1 st region to be predicted, and the correlation degrees between the 2 nd region to be predicted and the 5 th region to be predicted and the 1 st region to be predicted are respectively E12，E13，E14，E15If the feature information of the 1 st prediction region includes: target event information-T occurring at a future preset time period11Weather information-T12Historical order information-T13And service provider information-T capable of providing service14(ii) a The characteristic information of the 2 nd to 5 th regions to be predicted is respectively as follows: target event information-T occurring at a future preset time periodi1Weather information-Ti2Historical order information-Ti3And service provider information-T capable of providing servicei4If i corresponds to the number of the to-be-predicted region, the feature information T of the 1 st to-be-predicted region needs to be obtained when the 1 st to-be-predicted region is predicted11～T14And the influence characteristics of the 2 nd to 5 th regions to be predicted on the 1 st region to be predictedInformation E12·Ti1～E15·Ti1And jointly inputting the service demand prediction model, wherein i is 2,3,4 and 5, so that the service demand information of the 1 st area to be predicted in a future preset time period can be obtained.
Therefore, for one region to be predicted, the service requirement of the region to be predicted can be predicted by comprehensively considering the characteristics of the region to be predicted and the characteristics of other regions to be predicted in the clustering region corresponding to the region to be predicted, so that the accuracy of service requirement prediction is improved, and further, based on the predicted service requirement, service resource allocation can be more reasonably carried out.
Of course, in order to further improve the accuracy of service demand prediction, the feature information input into the service demand prediction model is data subjected to corresponding feature engineering processing, such as deleting obviously wrong data, supplementing missing values, and normalizing some data.
For the aforementioned service demand prediction model, which is used to predict the service demand information of a certain area according to the characteristic information, as shown in fig. 3, the service demand prediction model may be specifically trained according to the following steps S301 to S302:
s301, a training sample library is constructed, wherein the training sample library comprises feature information of a plurality of regions to be trained in a historical time period, the correlation degree between each region to be trained and other regions to be trained belonging to the same clustering region, and service requirement information of each region to be trained in the historical time period.
Before a training sample library is constructed, at least one target geographical position is divided into a plurality of areas to be trained, clustering is carried out on the plurality of areas to be trained according to historical order information of the plurality of areas to be trained to obtain at least one clustering area, each clustering area can be used as a sample library, and each area to be trained in the clustering areas is used as a sample; of course, a plurality of clustering regions may be used as a sample library, and each region to be trained in the clustering regions is used as a sample.
The determination process of the correlation degree between each region to be predicted and other regions to be predicted belonging to the same clustering region is similar to that of the above-mentioned regions to be predicted in the same clustering region, and the determination process is not specifically described herein.
It should be noted that, several sets of time difference relationships between the historical order information and the set historical period adopted by the service provider information in the feature information and the historical time period may be set, so that the service demand information of the area to be predicted may be predicted dynamically in the prediction process.
S302, obtaining model input characteristics based on characteristic information of each to-be-trained area in a historical time period and the correlation degree between each to-be-trained area and other to-be-trained areas belonging to the same clustering area, and training to obtain a service demand prediction model by taking service demand information of each to-be-trained area in the historical time period as model output characteristics.
In the model training process, in order to improve the accuracy of the service demand prediction model, corresponding feature engineering processing, such as deleting error data, supplementing missing values, normalizing some data, and the like, is generally performed on feature information of each to-be-trained area in a historical time period.
The number of the model input features and the number of the regions to be trained correspond to each other, for example, if there are 1000 regions to be trained in total in the training sample library, there are 1000 model input features corresponding to each model input feature, each model input feature includes feature information of the region to be trained in the historical time period, and each of the other regions to be trained in the clustering region to which the region to be trained belongs affects the feature information of the region to be trained in the historical time period, wherein the determination process of the affecting feature information is detailed in the above prediction process, and is not described again here.
And inputting the obtained model input characteristics and the model output characteristics into a preselected learning model for training to obtain a service demand prediction model.
The learning model may be one or a combination of a classification tree model, a logistic regression model, and a neural network model, which are not specifically described herein.
After obtaining the service demand prediction model and predicting the service demand information of the area to be predicted based on the service demand prediction model, the information processing method further includes:
and determining a resource configuration strategy for the area to be predicted according to the service demand information.
After the ratio of the number of drivers capable of providing taxi taking service in the target time period of the area to be predicted to the number of passengers needing taxi taking is obtained, the resource allocation strategy to be applied to the passengers needing taxi taking in the area to be predicted can be determined according to the ratio.
The resource allocation policy determined here includes resource allocation of the number of service providers for the area to be predicted, that is, allocation of the number of drivers, for example, when the number of drivers in the area is insufficient, the number of drivers can be scheduled from other areas, and resource allocation of the service requester for the area to be predicted, for example, includes distributing red packets, placing vouchers for taxi and the like to the service requester, and the following is described with an example of resource allocation for the service requester:
for example, if the ratio of the number of drivers that can provide taxi taking service in the target time period to the number of passengers that need taxi taking is relatively large, or the number of drivers that can provide taxi taking service in the target time period is much larger than the number of passengers that need taxi taking, it may be determined that the resource allocation policy of the area to be predicted is as follows: issuing a greater amount of taxi-taking voucher to more potential passengers; if the ratio of the number of drivers capable of providing taxi taking service in the target time period of the predicted area to be predicted to the number of passengers needing taxi taking is slightly smaller, or the number of drivers capable of providing taxi taking service in the target time period of the predicted area to be predicted to be slightly larger than the number of passengers needing taxi taking, the resource allocation policy of the area to be predicted can be determined as follows: issuing smaller-amount taxi-taking voucher to fewer potential passengers; if the number of drivers capable of providing taxi taking service in the target time period of the area to be predicted is less than the number of passengers needing taxi taking, the resource allocation strategy of the area to be predicted can be determined as follows: no ticket is issued to potential passengers.
Specifically, after determining the resource configuration policy for the area to be predicted, the method further includes:
and after receiving an access request initiated by a user terminal in the area to be predicted, configuring resources for the user terminal according to a resource configuration strategy corresponding to the area to be predicted.
In the travel field, the user terminal may include a driver terminal or a passenger terminal, and the resource configuration performed for the passenger terminal is described as an example:
when a passenger terminal logs in a taxi-taking service system in a region to be predicted after receiving, allocating resources to the passenger terminal according to the resource allocation strategy corresponding to the region to be predicted, for example, when the supply of the region to be predicted is far larger than the demand of the region to be predicted, allocating a taxi-taking voucher with a larger amount to the passenger terminal; if the predicted area is slightly larger than the required value, a smaller taxi-taking voucher can be distributed to the passenger end; if the predicted area is equal to or less than the demand, the passenger end is not allocated with the ticket.
Or when the area to be predicted comprises the historical trip location of the user side according to the historical order information of the user side, configuring resources for the user side according to the resource configuration strategy corresponding to the area to be predicted.
Similarly, here, an example of resource allocation performed for the passenger side is described:
whether the area to be predicted comprises the historical travel place of the passenger side or not can be detected according to the historical order information of the passenger side, if yes, resources can be allocated for the passenger side according to the determined resource allocation strategy corresponding to the area to be predicted, for example, the family address of the passenger or a company in the area to be predicted exists in the historical order information of the passenger, namely, certain geographic positions in the areas to be predicted exist, even if the passenger side does not log in a taxi taking service system in the area to be predicted, the resources can be allocated for the passenger side, the probability that the passenger selects 'taxi taking' to go to the area to be predicted is improved, and service utilization rate is improved.
In addition, in the embodiment of the present application, the service requirement information of the area a to be predicted 7 days later in the future may be determined, then the resource configuration policy of the area a to be predicted is determined one week earlier, the resource configuration is performed on the user side according to the resource configuration policy, then the service requirement information of the area a to be predicted is re-predicted based on the feature information of the current day after 7 days later, finally, the change of the service requirement information of the area a to be predicted may be determined based on the service requirement information predicted 7 days earlier and the service requirement information predicted in the current day, so as to adjust the resource configuration policy determined in advance, the adjusted resource configuration policy may be used as the current resource configuration policy of the area a to be predicted, and the following description will be made by taking the example of resource configuration performed on the passenger side:
for example, the current date is 1/2018, the service demand information of the determined area a to be predicted in 1/8/2018 is far greater than the demand, the resource allocation strategy determined for the area a to be predicted is to allocate 10 yuan of vehicle-driving voucher in 1/8/2018 to each potential passenger end, and distribute the 10 yuan of voucher to the potential passenger ends in advance; however, if the weather condition changes when the day 1, 8 and 2018 is reached, the service demand information of the area a to be predicted which is re-determined is slightly increased, the originally determined resource configuration strategy needs to be adjusted, resource configuration is performed on the potential passenger sides on the same day according to the adjusted resource configuration strategy, for example, 2 yuan of taxi-taking voucher is allocated to each potential passenger side, then 2 yuan of taxi-taking voucher is distributed to the potential passenger sides on the same day, and the situation that the supply amount is far larger than the demand is determined in advance to be slightly increased than the demand is determined, so that the resource configuration strategy also changes with the amount of the originally determined taxi-taking voucher.
Based on the above embodiments, the present application also provides an information processing apparatus, and the implementation of the following various apparatuses can refer to the implementation of the method, and repeated details are not repeated.
An embodiment of the present application provides an information processing apparatus 400, as shown in fig. 4, including:
the dividing module 401 may be configured to divide the target geographic location range into a plurality of areas to be predicted.
The clustering module 402 may be configured to cluster the multiple regions to be predicted according to historical order information of the multiple regions to be predicted, so as to obtain at least one clustered region.
The determining module 403 may be configured to, for each to-be-predicted region, determine the service demand information of the to-be-predicted region in the target time period according to the feature information of the to-be-predicted region in the target time period, the feature information of each other to-be-predicted region in the clustering region to which the to-be-predicted region belongs in the target time period, and the correlation between each other to-be-predicted region and the to-be-predicted region.
In an embodiment, the determining module 403 may be further configured to:
and after determining the service demand information of the area to be predicted in a future preset time period, determining a resource allocation strategy for the area to be predicted according to the service demand information.
In an embodiment, the determining module 403 may be further configured to:
after determining a resource configuration strategy for a region to be predicted, after receiving an access request initiated by a user terminal in the region to be predicted, configuring resources for the user terminal according to the resource configuration strategy corresponding to the region to be predicted; alternatively, the first and second electrodes may be,
and when the area to be predicted comprises the historical trip location of the user side according to the historical order information of the user side, configuring resources for the user side according to a resource configuration strategy corresponding to the area to be predicted.
In an embodiment, the determining module 403 may be specifically configured to:
and determining the correlation degree between each other area to be predicted and the area to be predicted according to the similarity between each other area to be predicted and the area to be predicted on the historical order information and the proximity on the geographical position.
In an embodiment, the determining module 403 may be specifically configured to:
and determining the correlation between each other area to be predicted and the area to be predicted according to the similarity on the historical order information and the proximity on the geographical position between each other area to be predicted and the correlation weight respectively corresponding to the historical order information and the geographical position.
In an embodiment, the determining module 403 may be specifically configured to:
inputting the characteristic information of the area to be predicted in a future preset time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period and the correlation degree between each other area to be predicted and the area to be predicted into a pre-trained service demand prediction model to obtain the service demand information of the area to be predicted in the future preset time period.
In one embodiment, further comprising a training module 404, the training module 404 may be configured to:
and constructing a training sample library, wherein the training sample library comprises the characteristic information of a plurality of regions to be trained in a first historical time period, the correlation degree between each region to be predicted and other regions to be predicted belonging to the same clustering region and the service demand information of each region to be predicted in a second historical time period.
Obtaining model input characteristics based on the characteristic information of each to-be-trained region in the first historical time period and the correlation degree between each to-be-predicted region and other to-be-predicted regions belonging to the same clustering region, and training to obtain a service demand prediction model by taking the service demand information of each to-be-predicted region in the second historical time period as model output characteristics.
In one embodiment, the service demand information includes supply-demand ratio information.
In one embodiment, the characteristic information includes a plurality of:
information of the target event occurred; weather information; historical order information; service provider information capable of providing a service.
In one embodiment, the weather information includes weather forecast information if the target time period is a future preset time period; and if the target time period is the current preset time period, the weather information comprises the current weather information.
In an embodiment, the clustering module 402 is specifically configured to:
and determining the similarity of any two areas to be predicted on the historical order information based on the historical order information of each area to be predicted.
Based on the similarity of any two areas to be predicted on the historical order information, the areas to be predicted corresponding to the similarity larger than the set threshold are divided into the same type.
The modules may be connected or in communication with each other via a wired or wireless connection. The wired connection may include a metal cable, an optical cable, a hybrid cable, etc., or any combination thereof. The wireless connection may comprise a connection over a LAN, WAN, bluetooth, ZigBee, NFC, or the like, or any combination thereof. Two or more modules may be combined into a single module, and any one module may be divided into two or more units.
The embodiment of the present application further provides an electronic device 500, where the electronic device 500 may be a general-purpose computer or a special-purpose computer, and both of them may be used to implement the service selection prediction method of the present application. Although only a single computer is shown, for convenience, the functions described herein may be implemented in a distributed fashion across multiple similar platforms to balance processing loads.
As shown in fig. 5, the electronic device 500 may include a network port 501 connected to a network, one or more processors 502 for executing program instructions, a communication bus 503, and a storage medium 504 of different forms, such as a disk, ROM, or RAM, or any combination thereof. Illustratively, the computer platform may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application may be implemented in accordance with these program instructions. The electronic device 500 also includes an Input/Output (I/O) interface 505 between the computer and other Input/Output devices (e.g., keyboard, display screen).
For ease of illustration, only one processor is depicted in the electronic device 500. However, it should be noted that the electronic device 500 in the present application may also comprise a plurality of processors, and thus the steps performed by one processor described in the present application may also be performed by a plurality of processors in combination or individually. For example, if the processor of the electronic device 500 executes steps a and B, it should be understood that steps a and B may also be executed by two different processors together or separately in one processor. For example, a first processor performs step a and a second processor performs step B, or the first processor and the second processor perform steps a and B together.
Taking a processor as an example, the processor 502 executes the following program instructions stored in the storage medium 504:
and dividing the target geographical position range into a plurality of areas to be predicted.
And clustering the multiple regions to be predicted according to the historical order information of the multiple regions to be predicted to obtain at least one clustering region.
And for each region to be predicted, determining the service demand information of the region to be predicted in the target time period according to the characteristic information of the region to be predicted in the target time period, the characteristic information of each other region to be predicted in the clustering region to which the region to be predicted belongs in the target time period, and the correlation degree between each other region to be predicted and the region to be predicted.
In one embodiment, the program instructions executed by the processor 502 further include:
and after determining the service demand information of the area to be predicted in a future preset time period, determining a resource allocation strategy for the area to be predicted according to the service demand information.
In one embodiment, the program instructions executed by the processor 502 further include:
after determining a resource configuration strategy for a region to be predicted, after receiving an access request initiated by a user terminal in the region to be predicted, configuring resources for the user terminal according to the resource configuration strategy corresponding to the region to be predicted; alternatively, the first and second electrodes may be,
and when the area to be predicted comprises the historical trip location of the user side according to the historical order information of the user side, configuring resources for the user side according to a resource configuration strategy corresponding to the area to be predicted.
In one embodiment, the program instructions executed by the processor 502 specifically include:
and determining the correlation degree between each other area to be predicted and the area to be predicted according to the similarity between each other area to be predicted and the area to be predicted on the historical order information and the proximity on the geographical position.
In one embodiment, the program instructions executed by the processor 502 specifically include:
and determining the correlation between each other area to be predicted and the area to be predicted according to the similarity on the historical order information and the proximity on the geographical position between each other area to be predicted and the correlation weight respectively corresponding to the historical order information and the geographical position.
In one embodiment, the program instructions executed by the processor 502 specifically include:
inputting the characteristic information of the area to be predicted in a future preset time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period and the correlation degree between each other area to be predicted and the area to be predicted into a pre-trained service demand prediction model to obtain the service demand information of the area to be predicted in the future preset time period.
In one embodiment, the program instructions executed by the processor 502 further include:
constructing a training sample library, wherein the training sample library comprises characteristic information of a plurality of regions to be trained in a historical time period, the correlation between each region to be predicted and other regions to be predicted belonging to the same clustering region and service demand information of each region to be predicted in the historical time period;
obtaining model input characteristics based on the characteristic information of each to-be-trained area in a historical time period and the correlation degree between each to-be-predicted area and other to-be-predicted areas belonging to the same clustering area, and training to obtain a service demand prediction model by taking the service demand information of each to-be-predicted area in the historical time period as model output characteristics.
The service demand information includes supply-demand ratio information.
The characteristic information includes the following various:
information of the target event occurred; weather information; historical order information; service provider information capable of providing a service.
If the target time period is a future preset time period, the weather information comprises weather forecast information; and if the target time period is the current preset time period, the weather information comprises the current weather information.
Clustering a plurality of regions to be predicted according to the following steps:
and determining the similarity of any two areas to be predicted on the historical order information based on the historical order information of each area to be predicted.
Based on the similarity of any two areas to be predicted on the historical order information, the areas to be predicted corresponding to the similarity larger than the set threshold are divided into the same type.
Corresponding to the information processing methods in fig. 1 to 3, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to perform the steps of the information processing method.
Specifically, the computer-readable storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, and the like, and when a computer program on the storage medium is executed, the information processing method can be executed, so that the problem of low utilization rate of service resources at present is solved.
Based on the same technical concept, embodiments of the present application further provide a computer program product, which includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute steps of the information processing method, and specific implementation may refer to the above method embodiments, and will not be described herein again.
According to the information processing method, the device, the electronic equipment and the computer readable storage medium provided by the embodiment of the application, for a plurality of to-be-predicted areas divided in the target geographic position range, the to-be-predicted areas are clustered according to historical order information, and then for each to-be-predicted area in each clustering area, the service demand information of the to-be-predicted area in the target time period is determined according to the feature information of the to-be-predicted area in the target time period, the feature information of each other to-be-predicted area in the clustering area to which the to-be-predicted area belongs in the target time period and the correlation degree between each other to-be-predicted area and the to-be-predicted area. Therefore, for one region to be predicted, the service requirement of the region to be predicted can be predicted by comprehensively considering the characteristics of the region to be predicted and the characteristics of other regions to be predicted in the clustering region corresponding to the region to be predicted, so that the accuracy of service requirement prediction is improved, and further, based on the predicted service requirement, service resource allocation can be more reasonably carried out.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (24)

1. An information processing method characterized by comprising:
dividing the target geographical position range into a plurality of areas to be predicted;
clustering the multiple regions to be predicted according to historical order information of the multiple regions to be predicted to obtain at least one clustering region;
and for each region to be predicted, determining the service demand information of the region to be predicted in the target time period according to the characteristic information of the region to be predicted in the target time period, the characteristic information of each other region to be predicted in the clustering region to which the region to be predicted belongs in the target time period, and the correlation degree between each other region to be predicted and the region to be predicted.
2. The method of claim 1, wherein after determining the service requirement information of the area to be predicted in a future preset time period, further comprising:
and determining a resource configuration strategy for the area to be predicted according to the service demand information.
3. The method according to claim 2, wherein after determining the resource allocation policy for the area to be predicted, further comprising:
after receiving an access request initiated by a user terminal in the area to be predicted, configuring resources for the user terminal according to a resource configuration strategy corresponding to the area to be predicted; alternatively, the first and second electrodes may be,
when the area to be predicted comprises the historical trip location of the user side according to the historical order information of the user side, resources are allocated for the user side according to a resource allocation strategy corresponding to the area to be predicted.
4. A method according to any one of claims 1 to 3, wherein the degree of correlation between each of said other regions to be predicted and the region to be predicted is determined according to the following steps:
and determining the correlation degree between each other area to be predicted and the area to be predicted according to the similarity between each other area to be predicted and the area to be predicted on the historical order information and the proximity on the geographical position.
5. The method of claim 4, wherein determining the correlation between each of the other areas to be predicted and the area to be predicted according to the similarity between the other areas to be predicted and the area to be predicted in historical order information and the proximity in the geographic position comprises:
and determining the correlation between each other area to be predicted and the area to be predicted according to the similarity on the historical order information, the proximity on the geographic position between each other area to be predicted and the correlation weight respectively corresponding to the historical order information and the geographic position.
6. The method according to claim 1, wherein for each region to be predicted, determining the service demand information of the region to be predicted in the target time period according to the feature information of the region to be predicted in the target time period, the feature information of each other region to be predicted in the clustering region to which the region to be predicted belongs in the target time period, and the correlation between each other region to be predicted and the region to be predicted, comprises:
inputting the characteristic information of the area to be predicted in a future preset time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period and the correlation degree between each other area to be predicted and the area to be predicted into a pre-trained service demand prediction model to obtain the service demand information of the area to be predicted in the future preset time period.
7. The method of claim 6, wherein the service demand prediction model is trained according to the following steps:
constructing a training sample library, wherein the training sample library comprises characteristic information of a plurality of regions to be trained in a historical time period, the correlation degree between each region to be trained and other regions to be trained belonging to the same clustering region, and service requirement information of each region to be trained in the historical time period;
obtaining model input characteristics based on the characteristic information of each to-be-trained area in the historical time period and the correlation degree between each to-be-trained area and other to-be-trained areas belonging to the same clustering area, and training to obtain the service demand prediction model by taking the service demand information of each to-be-trained area in the historical time period as model output characteristics.
8. The method of claim 1, wherein the service demand information comprises supply-demand ratio information.
9. The method of claim 1, wherein the feature information comprises a plurality of:
information of the target event occurred; weather information; historical order information; service provider information capable of providing a service.
10. The method of claim 9, wherein the weather information comprises weather forecast information if the target time period is a future predetermined time period; and if the target time period is the current preset time period, the weather information comprises the current weather information.
11. The method according to claim 1, characterized in that the plurality of regions to be predicted are clustered according to the following steps:
determining the similarity of any two areas to be predicted on the historical order information based on the historical order information of each area to be predicted;
based on the similarity of any two areas to be predicted on the historical order information, the areas to be predicted corresponding to the similarity larger than the set threshold are divided into the same type.
12. An information processing apparatus characterized by comprising:
the dividing module is used for dividing the target geographic position range into a plurality of areas to be predicted;
the clustering module is used for clustering the multiple regions to be predicted according to the historical order information of the multiple regions to be predicted to obtain at least one clustering region;
and the determining module is used for determining the service demand information of the area to be predicted in the target time period according to the characteristic information of the area to be predicted in the target time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the target time period and the correlation degree between each other area to be predicted and the area to be predicted.
13. The apparatus of claim 12, wherein the determining module is further configured to:
after determining the service demand information of the area to be predicted in a future preset time period, determining a resource configuration strategy for the area to be predicted according to the service demand information.
14. The apparatus of claim 13, wherein the determining module is further configured to:
after determining a resource configuration strategy for the area to be predicted, after receiving an access request initiated by a user terminal in the area to be predicted, configuring resources for the user terminal according to the resource configuration strategy corresponding to the area to be predicted; alternatively, the first and second electrodes may be,
when the area to be predicted comprises the historical trip location of the user side according to the historical order information of the user side, resources are allocated for the user side according to a resource allocation strategy corresponding to the area to be predicted.
15. The apparatus according to any one of claims 12 to 14, wherein the determining module is specifically configured to:
and determining the correlation degree between each other area to be predicted and the area to be predicted according to the similarity between each other area to be predicted and the area to be predicted on the historical order information and the proximity on the geographical position.
16. The apparatus of claim 15, wherein the determining module is specifically configured to:
and determining the correlation between each other area to be predicted and the area to be predicted according to the similarity on the historical order information, the proximity on the geographic position between each other area to be predicted and the correlation weight respectively corresponding to the historical order information and the geographic position.
17. The apparatus of claim 12, wherein the determining module is specifically configured to:
inputting the characteristic information of the area to be predicted in a future preset time period, the characteristic information of each other area to be predicted in the clustering area to which the area to be predicted belongs in the future preset time period and the correlation degree between each other area to be predicted and the area to be predicted into a pre-trained service demand prediction model to obtain the service demand information of the area to be predicted in the future preset time period.
18. The apparatus of claim 17, further comprising a training module to:
constructing a training sample library, wherein the training sample library comprises characteristic information of a plurality of regions to be trained in a historical time period, the correlation degree between each region to be trained and other regions to be trained belonging to the same clustering region, and service requirement information of each region to be trained in the historical time period;
obtaining model input characteristics based on the characteristic information of each to-be-trained area in the historical time period and the correlation degree between each to-be-trained area and other to-be-trained areas belonging to the same clustering area, and training to obtain the service demand prediction model by taking the service demand information of each to-be-trained area in the historical time period as model output characteristics.
19. The apparatus of claim 12, wherein the service demand information comprises supply-demand ratio information.
20. The apparatus of claim 12, wherein the feature information comprises a plurality of:
information of the target event occurred; weather information; historical order information; service provider information capable of providing a service.
21. The apparatus of claim 20, wherein the weather information comprises weather forecast information if the target time period is a future predetermined time period; and if the target time period is the current preset time period, the weather information comprises the current weather information.
22. The apparatus according to claim 12, wherein the clustering module is specifically configured to:
determining the similarity of any two areas to be predicted on the historical order information based on the historical order information of each area to be predicted;
based on the similarity of any two areas to be predicted on the historical order information, the areas to be predicted corresponding to the similarity larger than the set threshold are divided into the same type.
23. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the information processing method according to any one of claims 1 to 11.
24. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the information processing method according to any one of claims 1 to 11.
CN201910138848.3A 2019-02-25 2019-02-25 Information processing method, information processing device, electronic equipment and computer readable storage medium Pending CN111612183A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910138848.3A CN111612183A (en) 2019-02-25 2019-02-25 Information processing method, information processing device, electronic equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910138848.3A CN111612183A (en) 2019-02-25 2019-02-25 Information processing method, information processing device, electronic equipment and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN111612183A true CN111612183A (en) 2020-09-01

Family

ID=72199921

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910138848.3A Pending CN111612183A (en) 2019-02-25 2019-02-25 Information processing method, information processing device, electronic equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN111612183A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113095636A (en) * 2021-03-25 2021-07-09 深圳前海联动云软件科技有限公司 Intelligent scheduling system and method for fuel sharing automobile

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012050241A (en) * 2010-08-26 2012-03-08 Ntt Docomo Inc Demand predicting system and demand predicting method
CN105373840A (en) * 2015-10-14 2016-03-02 深圳市天行家科技有限公司 Designated-driving order predicting method and designated-driving transport capacity scheduling method
CN107045673A (en) * 2017-03-31 2017-08-15 杭州电子科技大学 Public bicycles changes in flow rate amount Forecasting Methodology based on heap Model Fusion
CN107633680A (en) * 2016-07-12 2018-01-26 阿里巴巴集团控股有限公司 Acquisition methods, device, equipment and the system of trip data
CN108108844A (en) * 2017-12-25 2018-06-01 儒安科技有限公司 A kind of urban human method for predicting and system
US20180197071A1 (en) * 2017-01-12 2018-07-12 International Business Machines Corporation Neural network computing systems for predicting vehicle requests
WO2018207878A1 (en) * 2017-05-11 2018-11-15 株式会社Ｎｔｔドコモ Demand forecast device
CN108830504A (en) * 2018-06-28 2018-11-16 清华大学 With vehicle needing forecasting method, system, server and computer storage medium
CN108960476A (en) * 2018-03-30 2018-12-07 山东师范大学 Shared bicycle method for predicting and device based on AP-TI cluster
CN108985475A (en) * 2018-06-13 2018-12-11 厦门大学 Net based on deep neural network about vehicle car service needing forecasting method

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012050241A (en) * 2010-08-26 2012-03-08 Ntt Docomo Inc Demand predicting system and demand predicting method
CN105373840A (en) * 2015-10-14 2016-03-02 深圳市天行家科技有限公司 Designated-driving order predicting method and designated-driving transport capacity scheduling method
CN107633680A (en) * 2016-07-12 2018-01-26 阿里巴巴集团控股有限公司 Acquisition methods, device, equipment and the system of trip data
US20180197071A1 (en) * 2017-01-12 2018-07-12 International Business Machines Corporation Neural network computing systems for predicting vehicle requests
CN107045673A (en) * 2017-03-31 2017-08-15 杭州电子科技大学 Public bicycles changes in flow rate amount Forecasting Methodology based on heap Model Fusion
WO2018207878A1 (en) * 2017-05-11 2018-11-15 株式会社Ｎｔｔドコモ Demand forecast device
CN108108844A (en) * 2017-12-25 2018-06-01 儒安科技有限公司 A kind of urban human method for predicting and system
CN108960476A (en) * 2018-03-30 2018-12-07 山东师范大学 Shared bicycle method for predicting and device based on AP-TI cluster
CN108985475A (en) * 2018-06-13 2018-12-11 厦门大学 Net based on deep neural network about vehicle car service needing forecasting method
CN108830504A (en) * 2018-06-28 2018-11-16 清华大学 With vehicle needing forecasting method, system, server and computer storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113095636A (en) * 2021-03-25 2021-07-09 深圳前海联动云软件科技有限公司 Intelligent scheduling system and method for fuel sharing automobile
CN113095636B (en) * 2021-03-25 2024-01-23 深圳前海联动云软件科技有限公司 Intelligent scheduling system and method for fuel sharing automobile

Similar Documents

Publication Publication Date Title
CN105894360B (en) Cheating order identification method, device and system
WO2018191856A1 (en) System and method for determining safety score of driver
CN112703517A (en) Electronic taxi service
TW201903704A (en) System and method for recommending estimated arrival time
CN111832788B (en) Service information generation method, device, computer equipment and storage medium
CN110782301A (en) Order combining method and device, electronic equipment and computer readable storage medium
US10417723B2 (en) Method and system for identifying locations for placement of replenishment stations for vehicles
CN111192090A (en) Seat allocation method and device for flight, storage medium and electronic equipment
CN111859172B (en) Information pushing method, device, electronic equipment and computer readable storage medium
WO2019206134A1 (en) Methods and systems for order allocation
US20190385262A1 (en) Information processing method and information processing device
CN111489214A (en) Order allocation method, condition setting method and device and electronic equipment
CN111275233B (en) Resource allocation method and device, electronic equipment and computer readable storage medium
CN111612183A (en) Information processing method, information processing device, electronic equipment and computer readable storage medium
CN111275229B (en) Resource model training method, resource gap prediction method, device and electronic equipment
CN111260384B (en) Service order processing method, device, electronic equipment and storage medium
JP2022521665A (en) Transportation method and equipment
CN111798283A (en) Order distribution method and device, electronic equipment and computer readable storage medium
CN111260423A (en) Order distribution method and device, electronic equipment and computer readable storage medium
CN111222900A (en) Information pushing method and device, electronic equipment and computer storage medium
CN111260101B (en) Information processing method and device
US20200293424A1 (en) Systems and methods for evaluating performance of models
CN111612198B (en) Method and device for predicting success rate of spelling and electronic equipment
CN112036774A (en) Service policy evaluation method, device, equipment and storage medium
CN112035548A (en) Identification model acquisition method, identification method, device, equipment and medium

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