CN111260101B

CN111260101B - Information processing method and device

Info

Publication number: CN111260101B
Application number: CN201811457900.3A
Authority: CN
Inventors: 栾桂凯; 卓呈祥; 路劲
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2018-11-30
Filing date: 2018-11-30
Publication date: 2022-07-08
Anticipated expiration: 2038-11-30
Also published as: CN111260101A

Abstract

The application provides an information processing method and device, wherein the method comprises the following steps: acquiring historical service order information of a user side in a preset historical time period; determining the quantity of service orders respectively initiated by a user side under different service environments according to historical service order information and service environment information respectively corresponding to different historical times; the preference information of the user side for initiating the service orders under any service environment is determined according to the quantity of the service orders respectively initiated by the user side under different service environments and the service environment information respectively corresponding to different historical times, so that service resources can be reasonably configured for the user side in advance, and the service efficiency is improved.

Description

Information processing method and device

Technical Field

The present application relates to the field of computer information technologies, and in particular, to an information processing method and apparatus.

Background

With the development of the internet and the mobile terminal, people can finish respective trips through the mobile terminal and the internet, and convenience is brought to the trips of people.

Because of the difference in the aspects of living environment, occupation, habit and the like, everyone has respective taxi taking requirements, such as: the user may choose to drive a car for travel in heavy snow or heavy rain. At present, generally, service resource scheduling is performed temporarily when a user has a travel demand, so as to provide a travel service for the user. In this case, since the travel demand of the user in extreme weather cannot be predicted in advance, the service resources are often not allocated enough in extreme weather, and the user cannot travel or travel is inconvenient.

Disclosure of Invention

In view of this, embodiments of the present application provide an information processing method and apparatus, so as to predict preference information of a user initiating a service order in any service environment, reasonably allocate service resources to a user side in advance, and improve service efficiency.

In a first aspect, an information processing method provided in an embodiment of the present application includes:

acquiring historical service order information of a user side in a preset historical time period;

determining the quantity of service orders respectively initiated by the user side under different service environments according to the historical service order information and the service environment information respectively corresponding to different historical times;

and determining preference information of the user side for initiating the service orders under any service environment according to the quantity of the service orders respectively initiated by the user side under different service environments and the service environment information respectively corresponding to different historical times.

In a possible implementation manner, the determining, according to the number of the service orders respectively initiated by the user side in different service environments and the service environment information respectively corresponding to different historical times, preference information of the user side for initiating the service orders in any service environment includes:

determining the historical time of the user side for initiating the service order for the first time in the preset historical time period from the beginning to the end of the preset historical time period and the historical statistical time corresponding to each service environment according to the service environment information corresponding to the different historical times;

and determining preference information of the user side for initiating the service orders in any service environment according to the quantity of the service orders respectively initiated by the user side in different service environments and the historical statistical time corresponding to each service environment.

In a possible implementation manner, the determining, according to the number of service orders respectively initiated by the user side in different service environments and the historical statistical time corresponding to each service environment, preference information of the user side initiating a service order in any service environment includes:

determining a scaling coefficient of the historical statistical time of the first service environment relative to the historical statistical time of the second service environment according to the historical statistical time corresponding to each service environment;

determining the tendency of the user side to initiate the service orders in the first service environment according to the scaling coefficient and the quantity of the service orders respectively initiated by the user side in the first service environment and the second service environment;

and determining preference information of the user side for initiating the service orders in the first service environment according to the tendency of the first service environment, the number of the service orders respectively initiated by the user side in the first service environment and the second service environment, and the historical statistical time corresponding to each service environment.

In a possible embodiment, the scaling factor ratio of the historical statistical time of the first service environment relative to the second service environment is_1,2Satisfies the following formula:

wherein, alive₁Representing historical statistical time, alive, of the first service environment₂Representing a historical statistical time of the second service environment.

In a possible implementation, the user terminal initiates the tendency score of the service order in the first service environment₁Satisfies the following formula:

wherein, size₁Indicating the number of service orders, size, initiated in the first service context₂Indicating the number of service orders, ratio, initiated in the second service environment_1,2A scaling factor representing a historical statistical time of the first service environment relative to the second service environment.

In a possible implementation manner, the determining, according to the tendency of the first service environment, the number of service orders respectively initiated by the user side in the first service environment and the second service environment, and the historical statistical time corresponding to each service environment, the preference information of initiating a service order by the user side in the first service environment includes:

determining a penalty value of service order initiation under the first service environment according to the quantity of service orders initiated by the user side under the second service environment and the historical statistical time corresponding to the second service environment;

and determining preference information of the user side for initiating the service order in the first service environment according to the penalty value for initiating the service order in the first service environment and the tendency degree for initiating the service order in the first service environment.

In a possible embodiment, a penalty value F for placing a service order in said first service context₁Satisfies the following formula:

wherein, size₂Indicating the number of service orders, alive, initiated in the second service context₂Representing a historical statistical time of the second service environment.

In a possible implementation manner, the preference information includes a preference degree, and the user side initiates a preference degree Y of the service order in the first service environment₁Satisfies the following formula:

Y₁＝F₁×score₁；

wherein, score₁Representing a tendency to place a service order in a first service context, F₁Representing a penalty value for initiating a service order in the first service context.

In a possible implementation manner, determining, according to the historical service order information and the service environment information respectively corresponding to different historical times, the number of service orders respectively initiated by the user side in different service environments includes:

determining the quantity of service orders initiated by the user side under different service environments in each preset time interval of a plurality of preset time intervals according to the historical service order information and the service environment information respectively corresponding to different historical times;

the determining, according to the number of the service orders respectively initiated by the user side in different service environments and the service environment information respectively corresponding to the different historical times, preference information of the user side for initiating the service orders in any service environment includes:

constructing a service order characteristic vector according to the quantity of service orders initiated by the user side in different service environments in each preset time interval of a plurality of preset time intervals;

and inputting the service order feature vector into a pre-trained preference information detection model, and determining preference information of the user side for initiating the service order under any service environment.

In one possible implementation, the preference information detection model is trained by:

acquiring the quantity of service orders initiated by each sample user side in a plurality of preset time intervals in different service environments and actual preference information corresponding to the sample user side;

constructing a characteristic vector of the sample user side according to the quantity of service orders initiated by the sample user side in each preset time interval in a plurality of preset time intervals under different service environments; inputting the characteristic vector into a basic detection model to obtain a preference information detection result of the sample user side;

and training the basic detection model according to the preference information detection result and the actual preference information to obtain the preference information detection model.

In a possible implementation manner, the training the basic detection model according to the preference information detection result and the actual preference information to obtain the preference information detection model includes:

according to the preference information detection result of each sample user side and corresponding actual preference information, after one round of training is carried out on the basic detection model, the training parameters of the basic detection model are adjusted and the next round of training is carried out, and the basic detection model after multiple rounds of training is determined as the preference information detection model.

In one possible embodiment, each round of training of the basic detection model is performed by the following steps:

determining any one sample user side in the sample user sides which have not completed training in the current round as a target sample user side, and determining the cross entropy loss of the target sample user side in the current round according to the preference information detection result of the target sample user side and the corresponding actual preference information;

adjusting the training parameters of the basic detection model according to the cross entropy loss of the target sample user side in the current round;

taking the target sample user side as a sample user side which completes training in the current round, and determining any one sample user side in the sample user sides which do not complete training in the current round as a new target sample user;

obtaining a preference information detection result of the new target sample user side by using the basic detection model with the adjusted parameters, and returning back the preference information detection result of the target sample user and corresponding actual preference information to determine the cross entropy loss of the target sample user in the current round;

and completing the training of the current round of the basic detection model until all the sample user sides finish the training of the current round.

In a second aspect, an information processing apparatus includes:

the acquisition module is used for acquiring historical service order information of the user terminal in a preset historical time period;

the quantity determining module is used for determining the quantity of the service orders respectively initiated by the user side under different service environments according to the historical service order information and the service environment information respectively corresponding to different historical times;

and the information determining module is used for determining preference information of the user side for initiating the service orders under any service environment according to the quantity of the service orders respectively initiated by the user side under different service environments and the service environment information respectively corresponding to different historical times.

In a possible implementation manner, the information determining module is configured to determine, according to the number of the service orders respectively initiated by the user side in different service environments and the service environment information respectively corresponding to the different historical times, preference information of the user side initiating the service order in any service environment, by using the following method:

In one possible embodiment, the different service environments include a first service environment and a second service environment;

the information determining module is configured to determine, according to the number of service orders respectively initiated by the user side in different service environments and the historical statistical time corresponding to each service environment, that the preference information for the user side to initiate a service order in any service environment includes:

In a possible implementation manner, the information determining module is specifically configured to determine, according to the tendency of the first service environment, the number of service orders that the user terminal initiates in the first service environment and the second service environment, and the historical statistical time corresponding to each service environment, preference information that the user terminal initiates a service order in the first service environment by using the following method:

wherein, size₂Indicating the number of service orders, alive, initiated in the second service environment₂Representing a historical statistical time of the second service environment.

Y₁＝F₁×score₁；

In a possible implementation manner, the quantity determining module is further configured to determine, according to the historical service order information and the service environment information respectively corresponding to different historical times, the quantity of the service orders respectively initiated by the user side in different service environments by using the following method:

the information determining module is further configured to determine preference information of the user terminal initiating the service order in any service environment according to the number of the service orders respectively initiated by the user terminal in different service environments and the service environment information respectively corresponding to different historical times in the following manners:

constructing a service order feature vector according to the quantity of service orders initiated by the user side in different service environments in each preset time interval of a plurality of preset time intervals;

In a possible embodiment, the apparatus further comprises a training module;

the training module is used for training to obtain the preference information detection model in the following way:

In a possible implementation manner, the training module is specifically configured to train the basic detection model according to the preference information detection result and the actual preference information by using the following method to obtain the preference information detection model:

In a possible implementation, the training module is specifically configured to perform each round of training on the basic detection model by using the following steps:

In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory communicate with each other via the bus when the electronic device runs, and the machine-readable instructions, when executed by the processor, perform the steps of the first aspect or the information processing method according to any one of the possible implementation manners of the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to perform the steps of the first aspect, or the information processing method according to any one of the possible implementation manners of the first aspect.

According to the information processing method and device provided by the embodiment of the application, historical service order information of a user side in a preset historical time period is obtained, then the quantity of service orders respectively initiated by the user side in different service environments can be obtained by combining the obtained historical service order information and service environment information corresponding to different historical times, and preference information of the user side for initiating the service orders in any service environment is obtained according to the quantity of the service orders respectively initiated by the user side in different service environments and the service environment information respectively corresponding to different historical times. Based on the compiled information, the configuration of service resources can be optimized, and the service efficiency is improved. For example, through the predicted travel demand of the user in a specific service environment (such as extreme weather), service resources (such as vehicles) can be reasonably configured in advance for the user side, and the service efficiency is improved.

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 shows a system 100 structure diagram of an application scenario provided in an embodiment of the present application;

FIG. 2 is a flow chart illustrating an information processing method provided by an embodiment of the present application;

fig. 3 is a flowchart illustrating a specific method for determining preference information of a service order initiated by the user side in any service environment in the information processing method provided in the embodiment of the present application;

fig. 4 is a flowchart illustrating another specific method for determining preference information of a service order initiated by the user side in the first service environment in the information processing method according to the embodiment of the present application;

fig. 5 is a flowchart illustrating a specific method for determining preference information of a service order initiated by the user side in any service environment in the information processing method provided in the embodiment of the present application;

fig. 6 is a flowchart illustrating a specific method for training a preference information detection model in an information processing method provided in an embodiment of the present application;

fig. 7 is a schematic structural diagram illustrating an information processing apparatus according to an embodiment of the present application;

fig. 8 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.

Detailed Description

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.

The method or the device described below in the embodiments of the present application can be applied to any scene that needs to generate preference information, for example, can be applied to mobile phone application software, a web page design platform, and the like. The embodiment of the present application does not limit a specific application scenario, and any scheme for generating preference information by using the method provided by the embodiment of the present application is within the protection scope of the present application.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

The term "user side" in this application may refer to an individual, entity or tool that requests a service, subscribes to a service, provides a service, or facilitates the provision of a service. For example, the user side may be a passenger, a driver, an operator, etc., or any combination thereof.

The terms "service order" and "service request" are used interchangeably herein to refer to an order initiated by a passenger, a service requester, a driver, a service provider, a supplier, or the like, or any combination thereof. Accepting the "service order" or "request" may be a passenger, a service requester, a driver, a service provider, a supplier, or the like, or any combination thereof. The service order may be charged or free.

In the embodiment of the application, historical service order information of a user terminal in a preset historical time period can be acquired, then the quantity of service orders respectively initiated by the user terminal in different service environments can be determined according to the historical service order information and service environment information corresponding to different historical times in the preset historical time period, and preference information of the user terminal for initiating the service orders in any service environment can be determined according to the quantity of the service orders respectively initiated by the user terminal in different service environments and the service environment information corresponding to different historical times. Therefore, on one hand, when providing some preferential resource information of travel services for the user, the preferential resources can be provided for the user in a targeted manner according to the predicted preference information of the user in a specific service environment (such as extreme weather), and the resources are effectively and reasonably utilized; on the other hand, through the predicted travel demand of the user in a specific service environment (such as extreme weather), service resources (such as vehicles) can be reasonably configured in advance for the user side, and the service efficiency is improved.

Fig. 1 is a system 100 structure diagram of an application scenario according to an embodiment of the present application. For example, the system 100 may be an online transportation service platform for transportation services such as taxi cab, designated drive service, express, carpool, bus service, driver rental, or regular service, or any combination thereof. System 100 may include one or more of a server 110, a network 120, a client 130, and a database 140, and server 110 may include a processor that performs operations on instructions.

In some embodiments, the server 110 may be a single server or a group of servers. The set of servers can be centralized or distributed (e.g., the servers 110 can be a distributed system). In some embodiments, the server 110 may be local or remote to the terminal. For example, server 110 may access information and/or data stored in user terminal 130, or database 140, or any combination thereof, via network 120. As another example, server 110 may be directly connected to at least one of user terminal 130 and database 140 to access stored information and/or data. In some embodiments, the server 110 may be implemented on a cloud platform; by way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (community cloud), a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof. In some embodiments, the server 110 may be implemented on an electronic device having one or more components.

In some embodiments, a processor may include one or more processing cores (e.g., a single-core processor or a multi-core processor). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set computer (Reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

Network 120 may be used for the exchange of information and/or data. In some embodiments, one or more components in system 100 (e.g., server 110, client 130, and database 140) may send information and/or data to other components. For example, the server 110 may obtain a service request from the user terminal 130 via the network 120. In some embodiments, the network 120 may be any type of wired or wireless network, or combination thereof.

In some embodiments, the user terminal 130 may include a mobile device, a tablet computer, a laptop computer, or a built-in device in a motor vehicle, etc., 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. In some embodiments, the built-in devices in the motor vehicle may include an on-board computer, an on-board television, and the like. In some embodiments, the user terminal 130 may be a device having a positioning technology for locating the location of the service requester and/or the user terminal.

Database 140 may store data and/or instructions. In some embodiments, database 140 may store data obtained and/or obtained from user terminals 130. In some embodiments, database 140 may store data and/or instructions for the exemplary methods described herein. In some embodiments, the database 140 may include mass storage, removable storage, volatile Read-write Memory, or Read-Only Memory (ROM), among others, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state drives, etc.; removable memory may include flash drives, floppy disks, optical disks, memory cards, zip disks, tapes, and the like; volatile read-write Memory may include Random Access Memory (RAM); the RAM may include Dynamic RAM (DRAM), Double data Rate Synchronous Dynamic RAM (DDR SDRAM); static RAM (SRAM), Thyristor-Based Random Access Memory (T-RAM), Zero-capacitor RAM (Zero-RAM), and the like. By way of example, ROMs may include Mask Read-Only memories (MROMs), Programmable ROMs (PROMs), Erasable Programmable ROMs (PERROMs), Electrically Erasable Programmable ROMs (EEPROMs), compact disk ROMs (CD-ROMs), digital versatile disks (ROMs), and the like. In some embodiments, database 140 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, across clouds, multiple clouds, or the like, or any combination thereof.

In some embodiments, a database 140 may be connected to network 120 to communicate with one or more components in system 100 (e.g., server 110, client 130, etc.). One or more components in system 100 may access data or instructions stored in database 140 via network 120. In some embodiments, the database 140 may be directly connected to one or more components in the system 100 (e.g., the server 110, the client 130, etc.); alternatively, in some embodiments, database 140 may also be part of server 110.

In some embodiments, one or more components in system 100 (e.g., server 110, client 130, etc.) may have access to database 140.

The following embodiment will explain the information processing procedure in detail. The following information processing method may be implemented in the server 110, and specifically, the processor in the server 110 may execute the relevant method instructions.

Referring to fig. 2, a basic flow of an information processing method provided in an embodiment of the present application includes:

s201: acquiring historical service order information of a user terminal in a preset historical time period.

In a specific implementation, the preset historical time period may be a time length from a certain time point of the history to a time point of acquiring the historical service order information of the user terminal, for example, the historical service order information of the user terminal needs to be acquired in 3/9 th in 2018, and if the preset historical time period is one year, the acquired historical service order information is from 3/9 th in 2017 to 3/9 th in 2018; the preset historical time period may also be a time length with any time as a starting point or an ending point, for example, the preset historical time period is one year, historical service order information of the user terminal needs to be acquired in 3/9/2018, and the acquired historical service order information is from 1/9/2017 to 1/9/2018.

In some embodiments, the server may obtain the historical service order information of the user terminal in the preset historical time period in the database, for example, store data of each time the user terminal initiates a service order as the historical service order information in the database, and when the server needs to obtain the historical service order information of the user terminal, the server may retrieve the historical service order information from the database. The historical service order information may include service order content, user information, time for initiating a service order, service time corresponding to the order, and the like, for example, if the service order is a travel service order, the historical service order information may include travel time and a travel location, and the travel location may include a travel starting point and a travel ending point.

Here, when obtaining the historical service order information of the user terminal, the corresponding historical service order information may be obtained based on the user account registered by the user terminal.

S202: and determining the quantity of service orders respectively initiated by the user side under different service environments according to the historical service order information and the service environment information respectively corresponding to different historical times.

In specific implementation, the service environment information refers to objective factors corresponding to the historical service orders in the service process, for example, the service orders are travel service orders, and the corresponding service environment information may include weather in the travel process, such as extreme weather like rainstorm, snowstorm, hail, sleet and the like, or normal weather like sunny days, cloudy days, light rain, medium rain and the like, and may also include information such as congestion, traffic control and the like. When obtaining the historical service order information, the server may determine the service environment information corresponding to the service order according to the order service time in the historical service order, for example, if the weather of the hai lake region in 11, 25, 2018 is a fine day, the service environment information corresponding to 11, 25, 2018 is a fine day.

After acquiring historical service order information and service environment information corresponding to different historical times within a preset historical time period, determining the number of service orders respectively initiated by a user terminal under different service environments according to the historical service order information and the service environment information, for example, acquiring a trip order of the user terminal A, wherein the preset historical time period is one year, the acquired historical service order information is trip information corresponding to the service order initiated by the user terminal A from 11.1.2017 to 11.1.11.1.2017, and according to the time, the place and the weather corresponding to the trip order of the user terminal A, the number of service orders initiating the trip order of the user terminal A in extreme weather in the past year is 98 sheets and the number of service orders initiating the trip order in normal weather is 7 sheets.

S203: and determining preference information of the user side for initiating the service orders under any service environment according to the quantity of the service orders respectively initiated by the user side under different service environments and the service environment information respectively corresponding to different historical times.

In a specific implementation, the preference information refers to information that can reflect that the user end initiates a service order in different service environments, and may be a probability value or character information indicating whether preference is given. According to the quantity of the service orders respectively initiated by the user side under different service environments and the service environment information respectively corresponding to different historical times, the preference information of the service orders initiated by the user side under any service environment can be determined. According to the preference information of the user side, the corresponding service resources are matched for the user side, for example, when the service order is a trip order, preferential resources corresponding to the preference information, such as discount information, deduction information and the like of the trip order corresponding to the preference information, can be pushed to the user side. In addition, according to the preference information of the user side, the corresponding service resources can be matched for the user side in advance, for example, the service resources such as vehicles and the like are prepared for the user in advance, so that the situation that the user cannot go out or is inconvenient to go out is avoided.

In some embodiments, historical statistical time corresponding to each service environment information can be determined according to service environment information corresponding to different historical times, for different users, for example, a new user may not be account information registered before a preset historical time period, so that there is a period of time within the preset historical time period when no historical service order information of the new user exists, and counting the time period when no order is available for the new user into the statistical time causes an imbalance of historical statistical time between the new user and an old user. Therefore, when determining the historical statistical time corresponding to different service environments, starting from the historical time when the user terminal initiates a service order for the first time in the preset historical time period and ending the preset historical time period, the historical statistical time corresponding to each service environment, for example, the service order is a travel order, the preset historical time period is 1 year, the obtained historical service order information is 26 days in 11 months in 2017 to 26 days in 11 months in 2018, the account registration time of the user terminal a is 2 months in 2018 and 5 days, the time for initiating the service order is 3 months in 2018 and 9 days in 9 months, in this year, the number of days when the service environment is extreme weather is 28 days, and the number of days when the service environment is extreme weather is 19 days from the time when the user terminal a service order is started to 26 days in 11 months in 2018, the historical statistical time when the service environment is extreme weather is 19 days.

In some embodiments, the different service environments may include a first service environment and a second service environment, for example, the service order is a travel service order, the service environment refers to weather, and then the first service environment is extreme weather, such as heavy rain, heavy snow, hail, snow and rain, and the second service environment is normal weather, such as sunny day, cloudy day, light rain, and the like.

Here, the first service environment and the second service environment may also be other service environments, for example, the first service environment is during peak commute, and the second service environment is during non-peak commute. The information processing method in the application can determine the preference information of the user side in any service environment, so that any one of different service environments can be used as the first service environment in the application.

The present application will be described below with respect to a service environment including a first service environment and a second service environment.

Specifically, referring to fig. 3, an embodiment of the present application provides a specific method for determining preference information of a user initiating a service order in any service environment according to the number of service orders respectively initiated by the user in different service environments and historical statistical time corresponding to each service environment, where the method includes:

s301: and determining a scaling coefficient of the historical statistical time of the first service environment relative to the historical statistical time of the second service environment according to the historical statistical time corresponding to each service environment.

In a specific implementation, after determining the historical statistical time corresponding to each service environment, the scaling factor of the historical statistical time of the first service environment relative to the historical statistical time of the second service environment may be determined according to the historical statistical time corresponding to each service environment. Wherein the scaling factor ratio of the historical statistical time of the first service environment relative to the second service environment_1,2Satisfies the following formula:

wherein, alive₁Representing historical statistical time, alive, of the first service environment₂Representing a historical statistical time of the second service environment. For example, if the historical statistical time of the first service environment is 28 days, and the historical statistical time of the second service environment is 12 days, the scaling factor of the historical statistical time of the first service environment relative to the second service environment is:

s302: and determining the tendency of the user side to initiate the service orders in the first service environment according to the scaling coefficient and the quantity of the service orders respectively initiated by the user side in the first service environment and the second service environment.

In a specific implementation, after determining a scaling factor of the first service environment relative to the second service environment, the service order initiated by the user side in the first service environment based on the scaling factorThe quantity and the quantity of the service orders initiated by the user side in the second service environment are obtained to obtain the tendency of the user side to initiate the service orders in the first service environment, wherein the tendency score of the user side to initiate the service orders in the first service environment is obtained₁Satisfies the following formula:

S303: and determining preference information of the user side for initiating the service orders in the first service environment according to the tendency of the first service environment, the number of the service orders respectively initiated by the user side in the first service environment and the second service environment, and the historical statistical time corresponding to each service environment.

In a specific implementation, the tendency degree refers to a tendency degree of the user terminal to initiate the service order, the tendency degree of the first service environment refers to a tendency degree of the user terminal to initiate the service order in the first service environment, and the higher the tendency degree of the first service environment is, the more the user terminal tends to initiate the service order in the first service environment. And determining preference information for initiating the service orders under the first service environment of the user side based on the tendency of the first service environment, the quantity of the service orders respectively initiated by the user side under the first service environment and the second service environment, and the historical statistical time corresponding to each service environment.

Specifically, an embodiment of the present application further provides a specific method for determining, according to the tendency of the first service environment, the number of service orders respectively initiated by the user side in the first service environment and the second service environment, and historical statistical time corresponding to each service environment, preference information of service orders initiated by the user side in the first service environment, including:

s401: and determining a penalty value of the service order initiated under the first service environment according to the quantity of the service order initiated under the second service environment by the user side and the historical statistical time corresponding to the second service environment.

In this embodiment, the lower the penalty value in one service environment, the more the user terminal is initiating a service order in another service environment. According to the number of service orders initiated by the user side in the second service environment and the historical statistical time corresponding to the second service environment, the penalty value of initiating the service orders in the first service environment of the user side can be determined, wherein the penalty value F of initiating the service orders in the first service environment of the user side₁Satisfies the following formula:

S402: and determining preference information of the user side for initiating the service order in the first service environment according to the penalty value for initiating the service order in the first service environment and the tendency degree for initiating the service order in the first service environment.

In a specific implementation, the preference information includes a preference degree, a penalty value for initiating the service order in the first service environment of the user terminal is determined, and after the preference degree for initiating the service order in the first service environment is determined, the preference degree for initiating the service order in the first service environment of the user terminal is calculated according to the penalty value and the preference degree, wherein the preference degree Y for initiating the service order in the first service environment of the user terminal is calculated₁Satisfies the following formula:

Y₁＝F₁×score₁；

wherein, score₁Representing a tendency to place a service order in a first service context, F₁To representA penalty value for the service order is initiated in the first service context.

In some embodiments, the step S202 may further include determining, according to the historical service order information and the service environment information respectively corresponding to different historical times, the number of service orders initiated by the user terminal in different service environments in each of a plurality of preset time intervals.

In a specific implementation, the preset time interval refers to a time interval obtained by dividing a preset historical time period according to a certain time length, for example, the preset historical time period is a whole year from 1 month and 1 day in 2018 to 12 months and 31 days in 2018, and the preset time interval may be one month, one quarter or 15 days. According to the historical service order information and the service environment information respectively corresponding to different historical times, the number of service orders initiated by the user side under different service environments in each preset time interval in the preset time intervals in the preset historical time period can be determined.

Based on this, referring to fig. 5, an embodiment of the present application further provides another specific method for determining, according to the number of service orders respectively initiated by the user side in different service environments and the service environment information respectively corresponding to different historical times, preference information for initiating a service order by the user side in any service environment, where the specific method includes:

s501: and constructing a service order feature vector according to the quantity of service orders initiated by the user side in different service environments in each preset time interval of a plurality of preset time intervals.

In specific implementation, for each service environment, the service order quantity initiated by the user terminal in each of a plurality of preset time intervals in the service environment is used as a characteristic value, and a service order characteristic vector is obtained, for example, when the service environment is extreme weather, the preset historical time period is from 6 months in 2017 to 12 months in 2017, the preset time interval is one month, the service order quantity initiated by the user terminal in each preset time interval is respectively 3, 3, 5, 6, 4, 2, and the service order characteristic vector is [3, 3, 5, 6, 4, 2 ].

S502: and inputting the service order feature vector into a pre-trained preference information detection model, and determining preference information of the user side for initiating the service order under any service environment.

In specific implementation, the constructed feature vector of the service order is input into the pre-trained preference information detection model, so as to determine the preference information of the user initiating the service order in any service environment, for example, when the service environment of the user is extreme weather, the corresponding feature vector of the service order is [3, 3, 5, 6, 4, 2], and then the feature vector is input into the pre-trained preference information detection model, so that the preference information of the user initiating the service order in extreme weather can be obtained.

Specifically, referring to fig. 6, an embodiment of the present application further provides a specific method for training a preference information detection model, including:

s601: the method comprises the steps of obtaining the quantity of service orders initiated by each sample user side in a plurality of preset time intervals in different service environments and actual preference information corresponding to the sample user side.

In a specific implementation, the sample user side includes a positive sample user side and a negative sample user side, for example, when the service environment includes extreme weather and normal weather, the preset historical time period is one year, the positive sample user side may be the sample user side that has a number of days for initiating a service order in the extreme weather in the year that accounts for 98% of the total number of days for initiating the service order in the year, the positive sample user side that has a number of days for initiating a service order in the normal weather that accounts for 2% of the total number of days for initiating the service order in the normal weather, or the sample user side that has a number of days for initiating a service order in the year that is less than 5 days. The negative sample user side can be the sample user side which takes 2% of the total days for initiating the service order in extreme weather and 98% of the total days for initiating the service order in normal weather in the year.

After the sample user sides are determined, according to historical service order information of the sample user sides, the number of service orders initiated by each sample user side in each preset time interval in different service environments is determined, and actual preference information corresponding to each sample user side is obtained, wherein the actual preference information can be a label or a numerical value, for example, the actual preference information of a positive sample user side can be 1, and the actual preference information of a negative sample user side can be 0.

S602: constructing a characteristic vector of the sample user side according to the quantity of service orders initiated by the sample user side in each preset time interval in a plurality of preset time intervals under different service environments; and inputting the characteristic vector into a basic detection model to obtain a preference information detection result of the sample user side.

When constructing the feature vector of the sample user side, step S501 is described in detail as in step S501.

In some embodiments, the underlying detection model may be comprised of a neural network and a classifier, such as a recurrent neural network. The neural network comprises a plurality of layers of feature extraction layers, the plurality of layers of feature extraction layers can extract features of the constructed measured feature vectors, and the results after feature extraction are input into the classifier to obtain preference information detection results.

S603: and training the basic detection model according to the preference information detection result and the actual preference information to obtain the preference information detection model.

In the specific implementation, after the preference information detection result is obtained, the basic detection model is trained according to the preference information detection result and the actual preference information, and in the training process, parameters of the basic detection model are adjusted according to the preference information detection result and the actual preference information, so that the preference information detection model is obtained, and the basic detection model is trained for multiple times.

In some embodiments, during each round of training of the basic detection model, one sample user side of the round of sample user sides which have not been trained is used as a target user side, cross entropy loss between the round of preference information detection result and the actual preference information of the target sample user side can be determined according to the preference information detection result and the actual preference information of the sample user side, training parameters of the basic detection model are adjusted according to the cross entropy loss of the sample user side in the round, the target sample user side is used as the round of sample user side which has been trained, any sample user side of the round of sample user sides which have not been trained is determined as a new target sample user, the parameter-adjusted basic detection model is used to obtain the preference information detection result of the new target sample user side, and the cross entropy loss between the preference information detection result of the new target sample user and the corresponding actual preference information is calculated And repeating the steps until all the sample user terminals finish the training of the current round, and finishing the training of the current round of the basic detection model.

The information processing method provided by the embodiment of the application comprises the steps of firstly obtaining historical service order information of a user terminal in a preset historical time period, then obtaining the quantity of service orders respectively initiated by the user terminal in different service environments according to the obtained historical service order information and combining service environment information corresponding to different historical times, obtaining preference information of the user terminal initiating the service orders in any service environment according to the quantity of the service orders respectively initiated by the user terminal in different service environments and the service environment information corresponding to different historical times, and further performing configuration of service resources (including preference resources and service resources such as vehicles) on the user in a more targeted manner according to the preference information of the user, so that the service efficiency of the service resources is improved.

Based on the above information processing method, referring to fig. 7, an embodiment of the present application further provides an information processing apparatus 700, including: an acquisition module 710, a number determination module 720, and an information determination module 730; wherein,

an obtaining module 710, configured to obtain historical service order information of a user within a preset historical time period;

a quantity determining module 720, configured to determine, according to the historical service order information and the service environment information corresponding to different historical times, quantities of service orders respectively initiated by the user in different service environments;

the information determining module 730 is configured to determine, according to the number of the service orders respectively initiated by the user in different service environments and the service environment information respectively corresponding to the different historical times, preference information for initiating the service orders by the user in any service environment.

In some embodiments, the information determining module 730 is configured to determine, according to the number of the service orders respectively initiated by the user side in different service environments and the service environment information respectively corresponding to the different historical times, preference information for initiating the service orders by the user side in any service environment, by using the following method:

In some embodiments, the different service environments include a first service environment and a second service environment;

the information determining module 730 is configured to determine, according to the number of the service orders respectively initiated by the user in different service environments and the historical statistical time corresponding to each service environment, preference information of the user initiating the service order in any service environment by using the following method:

In some embodiments, the scaling factor ratio of the historical statistical time of the first service environment relative to the second service environment is_1,2Satisfies the following formula:

In some embodiments, the user terminal initiates the tendency score of the service order in the first service environment₁Satisfies the following formula:

In some embodiments, the information determining module 730 is specifically configured to determine, according to the tendency of the first service environment, the number of the service orders respectively initiated by the user side in the first service environment and the second service environment, and the historical statistical time corresponding to each service environment, preference information of the service orders initiated by the user side in the first service environment by using the following method:

In some embodiments, a penalty value F for placing a service order under the first service environment₁Satisfies the following formula:

In some embodiments, the preference information includes a preference degree, and the user terminal initiates a preference degree Y of the service order in the first service environment₁Satisfies the following formula:

Y₁＝F₁×score₁；

In some embodiments, the quantity determining module 720 is further configured to determine, according to the historical service order information and the service environment information corresponding to different historical times, the quantity of service orders respectively initiated by the user side in different service environments by:

the information determining module 730 is further configured to determine, according to the number of the service orders respectively initiated by the user in different service environments and the service environment information respectively corresponding to the different historical times, preference information of the user initiating the service orders in any service environment, in the following manner:

In some embodiments, the information processing apparatus 700 further comprises a training module 740;

a training module 740, configured to train to obtain the preference information detection model by:

In some embodiments, the training module 740 is specifically configured to train the basic detection model according to the preference information detection result and the actual preference information by using the following method to obtain the preference information detection model:

In some embodiments, the training module 740 is specifically configured to perform each round of training on the basic detection model by:

obtaining a preference information detection result of the new target sample user side by using the basic detection model with the adjusted parameters, and returning back again according to the preference information detection result of the target sample user and corresponding actual preference information to determine the cross entropy loss of the target sample user in the current round;

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.

Referring to fig. 8, embodiments of the present application further provide a schematic diagram of exemplary hardware and software components of an electronic device 800 that may implement the concepts of the present application. A processor 820 may be used on the electronic device 800 and to perform functions in the present application.

The electronic device 800 may be a general-purpose computer or a special-purpose computer, both of which may be used to implement the information pushing 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.

For example, electronic device 800 may include a network port 810 connected to a network, one or more processors 820 for executing program instructions, a communication bus 830, and different forms of storage media 840, 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 800 also includes Input/Output (I/O) interfaces 850 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 800. It should be noted, however, that the electronic device 800 in the present application may also include multiple processors, and thus steps performed by one processor described in the present application may also be performed by multiple processors in combination or separately. For example, if the processor of the electronic device 800 performs step a and step B, it should be understood that step a and step B may also be performed by two different processors together or performed 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.

In a specific implementation, the storage medium 840 stores machine-readable instructions executable by the processor 820, when the electronic device runs, the processor 820 and the storage medium 840 communicate through the communication bus 830, and the machine-readable instructions are executed by the processor 820 to perform the information processing method, so that the problem of inaccurate service resource configuration in the prior art is solved, and the effects of reasonably configuring service resources in advance for a user side and improving service efficiency are achieved.

The embodiment of the application also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the steps of the information processing method are executed.

Specifically, the storage medium can be a general storage medium, such as a mobile 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 inaccurate service resource configuration in the prior art is solved, the service resources are reasonably configured for the user side in advance, and the service efficiency is improved.

The computer program product of the information processing method and apparatus provided in the embodiments of the present application includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiments, and specific implementation may refer to the method embodiments, and will not be described herein again.

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

1. An information processing method characterized by comprising:

determining preference information of the user side for initiating the service orders in any service environment according to the quantity of the service orders respectively initiated by the user side in different service environments and the historical statistical time corresponding to each service environment;

wherein the different service environments include a first service environment and a second service environment, and the preference information is determined according to a scaling factor of a historical statistical time of the first service environment relative to the second service environment.

2. The method according to claim 1, wherein the determining, according to the quantity of the service orders respectively initiated by the user side in different service environments and the historical statistical time corresponding to each service environment, the preference information of the user side for initiating a service order in any service environment comprises:

and determining preference information of the user side for initiating the service orders in the first service environment according to the tendency of the first service environment, the quantity of the service orders respectively initiated by the user side in the first service environment and the second service environment, and the historical statistical time corresponding to each service environment.

3. The method of claim 2, wherein the scaling factor of the historical statistical time of the first service environment relative to the second service environment

Satisfies the following formula:

；

wherein,

representing the historical statistical time of the first service environment,

representing a historical statistical time of the second service environment.

4. The method of claim 2, wherein the user side has a tendency to place a service order in the first service environment

Satisfies the following formula:

；

wherein,

indicating the number of service orders initiated in the first service context,

indicating the number of service orders initiated in the second service environment,

a scaling factor representing a historical statistical time of the first service environment relative to the second service environment.

5. The method according to claim 2, wherein the determining preference information of the user terminal for placing the service order in the first service environment according to the tendency of the first service environment, the number of the service orders respectively placed by the user terminal in the first service environment and the second service environment, and the historical statistical time corresponding to each service environment comprises:

determining a penalty value of service order initiation under the first service environment according to the quantity of service orders initiated by the user side under the second service environment and historical statistical time corresponding to the second service environment;

6. The method of claim 5, wherein a penalty value for placing a service order in the first service environment

Satisfies the following formula:

；

wherein,

representing a historical statistical time of the second service environment.

7. The method of claim 5, wherein the preference information comprises a preference degree of the user side to initiate the service order under the first service environment

Satisfies the following formula:

；

wherein,

indicating a propensity to place a service order in a first service context,

representing a penalty value for initiating a service order in the first service context.

8. The method according to claim 1, wherein determining, according to the historical service order information and the service environment information corresponding to different historical times, the number of service orders respectively initiated by the user side in different service environments comprises:

9. The method of claim 8, wherein the preference information detection model is trained by:

10. The method of claim 9, wherein the training the basic detection model according to the preference information detection result and the actual preference information to obtain the preference information detection model comprises:

11. The method of claim 10, wherein each round of training of the base detection model is performed by:

12. An information processing apparatus characterized by comprising:

the information determining module is used for determining the historical time of the user side for initiating the service order for the first time in the preset historical time period from the beginning to the end of the preset historical time period according to the service environment information corresponding to the different historical times;

13. The apparatus according to claim 12, wherein the information determining module is configured to determine the preference information of the user terminal for initiating the service order in any service environment according to the number of the service orders respectively initiated by the user terminal in different service environments and the historical statistical time corresponding to each service environment in the following manner:

14. The apparatus of claim 13, wherein the scaling factor of the historical statistical time of the first service environment relative to the second service environment

Satisfies the following formula:

；

wherein,

representing the historical statistical time of the first service environment,

representing a historical statistical time of the second service environment.

15. The apparatus of claim 13, wherein the user side has a tendency to place a service order in the first service environment

Satisfies the following formula:

；

wherein,

is indicated in the first serviceThe number of service orders placed under the business environment,

16. The apparatus of claim 13, wherein the information determining module is specifically configured to determine, according to the tendency of the first service environment, the number of service orders that the user terminal initiates in the first service environment and the second service environment respectively, and the historical statistical time corresponding to each service environment, the preference information that the user terminal initiates a service order in the first service environment includes:

17. The apparatus of claim 16, wherein a penalty value for placing a service order in the first service environment

Satisfies the following formula:

；

wherein,

representing a historical statistical time of the second service environment.

18. The apparatus of claim 16, wherein the preference information comprises a preference degree of the user side to initiate the service order under the first service environment

Satisfies the following formula:

；

wherein,

indicating a propensity to place a service order in a first service context,

19. The apparatus according to claim 12, wherein the quantity determining module is further configured to determine the quantity of the service orders respectively initiated by the user side in different service environments according to the historical service order information and the service environment information respectively corresponding to different historical times in the following manners:

20. The apparatus of claim 19, further comprising a training module;

21. The apparatus according to claim 20, wherein the training module is specifically configured to train the basic detection model according to the preference information detection result and the actual preference information in the following manner to obtain the preference information detection model:

22. The apparatus of claim 21, wherein the training module is specifically configured to perform each round of training on the basic detection model by:

23. An electronic device, comprising: processor, memory and bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine readable instructions when executed by the processor performing 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 a computer program is stored thereon, which, when being executed by a processor, performs the steps of the information processing method according to any one of claims 1 to 11.