CN111815101A

CN111815101A - Information processing method and device, storage medium and electronic equipment

Info

Publication number: CN111815101A
Application number: CN202010043019.XA
Authority: CN
Inventors: 程浩; 周子慕; 童咏昕; 张凌宇; 朱宏图; 叶杰平
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-01-15
Filing date: 2020-01-15
Publication date: 2020-10-23

Abstract

The embodiment of the disclosure provides an information processing method, an information processing device, a storage medium and an electronic device, wherein the method comprises the following steps: acquiring historical online data, first characteristic information and second characteristic information of each target user, wherein the first characteristic information at least comprises time characteristic information and weather characteristic information, and the second characteristic information at least comprises user characteristic information; inputting historical online data, first characteristic information and second characteristic information into a trained prediction model, and acquiring the online time of each target user in a preset time period; grouping the target users based on the online time length, and sequencing the target users in each group; and pairing the target users based on the sequencing result. The method and the system can avoid waste of server resources and social resources, and further improve the resource utilization rate of road network traffic and the operation efficiency of network taxi reservation.

Description

Information processing method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of information processing technologies, and in particular, to an information processing method and apparatus, a storage medium, and an electronic device.

Background

Usually, in order to promote net car booking driver's work enthusiasm, increase net car booking driver's income, can release some match events on net car booking platform, net car booking driver can report to the official notice voluntarily and participate in the match to make net car booking driver work with the form of match, can effectively promote the resource utilization who road network traffic like this and the operation efficiency of net car booking.

Generally, before the official match, it is necessary to issue match events, such as match time, on the networked car appointment platform in advance for the networked car appointment drivers to register, and group, match and peer the registered networked car appointment drivers at this time. However, since there may be an emergency situation during the period of the competition time, some network car booking drivers cannot participate in the competition on time or cannot complete the whole competition course, and each network car booking driver has a paired network car booking driver, during the official competition, the network car booking drivers paired with the emergency network car booking drivers cannot participate in the competition or the competition for participation is invalid, so that the grouping and pairing results are invalid, the resource utilization rate of the network traffic and the operation efficiency of the network car booking cannot be further improved, and the server resource waste and the social resource waste are caused.

Disclosure of Invention

In view of the above, an object of the embodiments of the present disclosure is to provide an information processing method, an information processing apparatus, a storage medium, and an electronic device, which can avoid the problem that the resource utilization rate of road network traffic and the operation efficiency of network reservation cannot be further improved in the prior art.

In a first aspect, an embodiment of the present disclosure provides an information processing method, including:

acquiring historical online data, first characteristic information and second characteristic information of each target user, wherein the first characteristic information at least comprises time characteristic information and weather characteristic information, and the second characteristic information at least comprises user characteristic information;

inputting the historical online data, the first characteristic information and the second characteristic information into a trained prediction model, and acquiring the online duration of each target user in a preset time period;

grouping the target users based on the online time length, and sequencing the target users in each group;

and pairing the target users based on the sequencing result.

In one possible embodiment, the predictive model is trained by:

acquiring a first historical online time of each historical user at a first time point;

acquiring a temporary historical online time of a second time point which is a first preset time interval after the first time point based on the first historical online time and the first characteristic information;

and correcting the temporary historical online time length through the second characteristic information, and determining a second historical online time length of the historical user at the second time point.

In a possible implementation manner, the inputting the historical online data, the first feature information, and the second feature information into a trained predictive model, and the obtaining the online duration of each target user within a preset time period includes:

acquiring adjacent online time lengths of adjacent time points which are separated by a second preset time interval before a starting time point of a preset time period;

determining at least one continuous time point according to the second preset time interval in the preset time period after the starting time point;

based on the adjacent online time length, acquiring the unit online time length of a first time point through the prediction model;

sequentially acquiring the unit online time length of each time point after the first time point according to the time sequence;

and summing the unit online durations of all the time points in the preset time period to obtain the online duration of each target user in the preset time period.

In one possible embodiment, the grouping the target users based on the online time length and sorting the target users in each group includes:

determining at least one online time duration packet reference value;

dividing the online time of all the target users into a plurality of groups based on the online time grouping reference value;

in each of the subgroups, the target users are ranked based on third characteristic information.

In a possible embodiment, the pairing in the target user based on the ranking result includes:

in each of the subgroups, pairing the target users based on the value of the third characteristic information;

when an unpaired target user exists in each group, constructing a new group based on the unpaired target users in all the groups, and reordering and pairing based on the online time length.

In a second aspect, an embodiment of the present disclosure further provides an information processing apparatus, including:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical online data, first characteristic information and second characteristic information of each target user, the first characteristic information at least comprises time characteristic information and weather characteristic information, and the second characteristic information at least comprises user characteristic information;

the second obtaining module is used for inputting the historical online data, the first characteristic information and the second characteristic information into a trained prediction model and obtaining the online duration of each target user in a preset time period;

the sequencing module is used for grouping the target users based on the online time length and sequencing the target users in each group;

and the pairing module is used for pairing the target users based on the sequencing result.

In one possible embodiment, the method further comprises:

the training module is used for acquiring first historical online time of each historical user at a first time point;

In a possible embodiment, the second acquisition module comprises:

the device comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring the adjacent online time length of the adjacent time point which is separated by a second preset time interval before the starting time point of the preset time period;

a first determining unit, configured to determine at least one continuous time point at the second preset time interval within the preset time period from the starting time point;

a second obtaining unit, configured to obtain, through the prediction model, a unit online time length of a first time point based on the adjacent online time lengths;

a third obtaining unit, configured to sequentially obtain the unit online duration of each time point after the first time point according to a time sequence;

and the fourth acquisition unit is used for summing the unit online durations of all the time points in the preset time period to acquire the online duration of each target user in the preset time period.

In one possible implementation, the sorting module includes:

a second determining unit for determining at least one online duration packet reference value;

a grouping unit for grouping the online durations of all the target users into a plurality of groups based on the online duration grouping reference value;

a sorting unit configured to sort the target users based on third feature information in each of the subgroups.

In a possible embodiment, the pairing module comprises:

a pairing unit configured to pair the target users based on a value of the third feature information in each of the subgroups;

a constructing unit for constructing a new group based on the unpaired target users in all the groups and reordering and pairing based on the online time length when an unpaired target user exists in each of the groups.

In a third aspect, the disclosed embodiments also provide a computer-readable storage medium, where the computer-readable storage medium stores thereon a computer program, and the computer program is executed by a processor to perform the steps of the information processing method.

In a fourth aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes: a processor, a memory and a 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 operating, the machine-readable instructions when executed by the processor performing the steps of the information processing method as described.

In the embodiment of the disclosure, the on-line time of each target user in a preset time period is predicted by using the historical on-line data, the first characteristic information and the second characteristic information of each target user, and the pairing is performed according to the on-line time of each target user, so that the problem that the target users paired with the target users in an emergency situation cannot participate in the competition or cannot complete the whole competition course on time is avoided to a certain extent, the waste of server resources and social resources can be avoided, and the resource utilization rate of road network traffic and the operation efficiency of network appointment cars are further improved.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

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

Fig. 1 shows a flowchart of an information processing method provided by an embodiment of the present disclosure;

FIG. 2 is a flow chart illustrating training a predictive model in an information processing method according to an embodiment of the disclosure;

FIG. 3 is a flowchart illustrating inputting historical online data, first feature information, and second feature information into a trained predictive model to obtain an online duration of each target user within a preset time period in an information processing method provided by an embodiment of the present disclosure;

fig. 4 is a flowchart illustrating grouping of target users based on online time and sorting of the target users in each group in an information processing method according to an embodiment of the present disclosure;

fig. 5 is a flowchart illustrating pairing of the target users based on the sorting result in an information processing method according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an information processing apparatus provided in an embodiment of the present disclosure;

fig. 7 shows a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described below clearly and completely with reference to the accompanying drawings of the embodiments of the present disclosure. It is to be understood that the described embodiments are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the disclosure without any inventive step, are within the scope of protection of the disclosure.

Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.

To maintain the following description of the embodiments of the present disclosure clear and concise, a detailed description of known functions and known components have been omitted from the present disclosure.

In view of the problems in the prior art, embodiments of the present disclosure provide an information processing method, an information processing apparatus, an electronic device, and a storage medium, which avoid to some extent the problem that a car pool driver paired with a car pool driver in an emergency cannot participate in a race or the race cannot be completed in a whole race course on time, and also avoid the waste of server resources and social resources.

A first aspect of the present disclosure provides an information processing method, as shown in fig. 1, which is a flowchart of the information processing method when a server or a processor is taken as an execution subject in an embodiment of the present disclosure, and the specific steps are as follows:

s101, obtaining historical online data, first characteristic information and second characteristic information of each target user, wherein the first characteristic information at least comprises time characteristic information and weather characteristic information, and the second characteristic information at least comprises user characteristic information.

When the game items are released on the online appointment platform, at least the region, the game time, the game duration, the entry rule and the like of the game are released. Considering that the result of the competition is affected by the locality, the network car booking drivers need to be grouped according to the regions before each competition, specifically, the registration addresses of the network car booking drivers are searched, and the network car booking drivers corresponding to the registration addresses belonging to the same region are determined to be the same group according to the registration addresses of the network car booking drivers, so that the influence of the competition result on the locality is avoided. For example, the server obtains the registered address of the network car booking driver in advance, determines all network car booking drivers with registered addresses belonging to beijing as beijing groups, and determines all network car booking drivers with registered addresses belonging to north river as north river groups, etc., but the embodiment of the disclosure is not limited to the province as a grouping basis, and may also be based on the city as a grouping basis, the county as a grouping basis, etc. And then, the same match is subjected to match time adjustment (or non-adjustment) according to the area, the match duration, the registration rule and the like, and then the match is issued to the online car reservation drivers in the area so as to allow the online car reservation drivers in the area to register.

Wherein, aiming at each area, a taxi appointment driver which registers the area competition is taken as a target user.

In a specific implementation, an entry time period is preset, that is, it is effective to perform entry within the entry time period. After the entry period is over, acquiring historical online data, first characteristic information and second characteristic information of each target user.

Specifically, the historical online data at least comprises historical online time, and for each target user, the historical online time of the target user in a preset time period after the historical time point corresponding to the current time point in a plurality of preset periods is obtained. The first characteristic information at least comprises time characteristic information and weather characteristic information, and for each target user, the time characteristic information and the weather characteristic information of the target user at the current time point in a plurality of preset periods are acquired. Of course, the first characteristic information may also include traffic condition information, road quality information, and the like, and the embodiment of the present disclosure is not limited thereto.

For example, when the time of the match is 8 pm to 12 pm on a weekday, and the preset period is 7 days (a week), after determining the target users entering the match, for each target user, respectively searching the historical online time of the target user from 8 pm to 12 pm before 7 days, 14 days, 21 days, and 28 days; acquiring weather characteristic information from 8 to 12 points in the evening before 7 days, weather characteristic information from 8 to 12 points in the evening before 14 days, weather data from 8 to 12 points in the evening before 21 days, and weather characteristic information from 8 to 12 points in the evening before 28 days, wherein the weather characteristic information comprises weather states, temperatures, precipitation intensity, wind power levels and the like; and determining time characteristic information from 8 to 12 points in the evening before 7 days, 14 days, 21 days and 28 days, wherein the time characteristic information comprises duration from 8 to 12 points, the time from 8 to 12 points in the evening before 7 days, 14 days, 21 days and 28 days belongs to the week, whether the time belongs to a holiday, whether the time is a closing date and the like.

Of course, there is an intersection between the duration of the game and the two consecutive days, for example, the time of the game is from 10 pm on weekdays to 2 am on the next monday, and at this time, the historical online data, the first feature information, and the second feature information of each target user may also be obtained in the above manner.

Considering that the stability of the historical online time of each period is poor under the condition that the preset period time is long, the historical online data may further include historical average online time, and specifically, the historical average online time corresponding to the current time point of the target user in a plurality of preset periods is calculated by using a plurality of historical online times. Here, the current time point is a time point at which the competition starts, and the period of time is less than or equal to a preset time period (i.e., the competition duration). Wherein, the online time is the working time. For example, if the preset time period is 1 hour, the adjacent online time period within one hour before 8 o ' clock in a weekday evening (i.e. 7 o ' clock to 8 o ' clock) is obtained.

Meanwhile, second characteristic information of each target user is obtained, wherein the second characteristic information at least comprises user characteristic information, wherein the user characteristic information comprises the sex, age and the like of the target user, and it is worth explaining that the identity attribute is already input when the target user registers on the network car-booking platform, so that the second characteristic information can be directly obtained from a database of the network car-booking platform. Of course, the second feature information may also include the historical pick-up amount, the historical mileage traveled, etc. of the target user.

S102, inputting the historical online data, the first characteristic information and the second characteristic information into the trained prediction model, and obtaining the online duration of each target user in a preset time period.

In specific implementation, a trained prediction model is input based on historical online data, first characteristic information and second characteristic information, and online duration of each target user in a preset time period after a current time point is predicted. Wherein, the preset time period is the competition duration.

Specifically, historical online data, first feature information and second feature information are input into a trained prediction model, and the prediction model outputs the online time of a target user in a preset time period. The prediction model in the embodiment of the present disclosure includes a Sequence to Sequence (Seq 2Seq) model, a markov model, and the like, and other models that can achieve the prediction purpose can be implemented in the information processing method provided in the embodiment of the present disclosure.

In order to ensure the accuracy of the prediction model, the prediction model to be trained is trained by using historical working data of historical users. Further, the prediction model is trained according to the method shown in fig. 2, and the specific steps are as follows:

s201, acquiring a first historical online time of each historical user at a first time point.

Specifically, after the historical users are determined, screening multiple groups of training samples from all historical working data of each historical user, wherein each group of training samples comprises a first historical online time corresponding to a first time point of each historical user, first characteristic information of the historical users, second characteristic information of the historical users and a real second historical online time of a second time point, and the second time point is a time point which is a distance from the first time point by a first preset time interval.

S202, acquiring the temporary historical online time of a second time point which is separated from the first time point by a first preset time interval based on the first historical online time and the first characteristic information.

In the training process, after a series of calculations are performed based on a first historical online time and first characteristic information of a historical user, a temporary historical online time of a second time point which is a first preset time interval after a first time point is obtained.

S203, correcting the temporary historical online time length through the second characteristic information, and determining a second historical online time length of the historical user at a second time point.

After the temporary historical online time of a second time point which is separated from the first time point by a first preset time interval is obtained, correcting the temporary historical online time through second characteristic information, determining the second historical online time of a historical user at the second time point, comparing the second historical online time determined by the prediction model with the real second historical online time to obtain an error value of the prediction model of the current round, if the error value is greater than a preset threshold, repeating the training of the current round until the error value is less than or equal to the preset threshold, and finishing the training, namely obtaining the prediction model.

After the trained prediction model is obtained, the online time of each target user in a preset time period is predicted by using the prediction model, the method is convenient and quick, and the accuracy and the efficiency are high. Specifically, after the prediction model is determined, predicting the online time of each target user within a preset time period based on the historical online data, the first feature information and the second feature information according to the method shown in fig. 3, where the specific steps are as follows:

s301, acquiring adjacent online time lengths of adjacent time points which are separated by a second preset time interval before the starting time point of the preset time period.

In a specific implementation, while obtaining the historical online data, the first feature information, and the second feature information of each target user, the adjacent online time lengths of adjacent time points that are separated by a second preset time interval before the starting time point of the preset time period are obtained, where the second preset time interval may be the same as or different from the first preset time interval. In consideration of the fact that the first preset time interval is used in determining the prediction model, it is preferable to set the second preset time interval to be the same as the first preset time interval in actual use to ensure the accuracy of the prediction model.

S302, after the starting time point, at least one continuous time point is determined according to a second preset time interval within a preset time period.

Determining at least one continuous time point according to a second preset time interval within a preset time period from the starting time point, for example, determining a time point according to the second preset time interval within the preset time period, which means that the duration corresponding to the second preset time interval is the same as the duration corresponding to the preset time period; two time points are determined according to a second preset time interval in the preset time period, and the two times of the time length corresponding to the second preset time interval are equal to the time length corresponding to the preset time period.

And S303, acquiring the unit online time length of the first time point through a prediction model based on the adjacent online time lengths.

After at least one continuous time point is determined, the unit online time length of the first time point is obtained through the prediction model based on the adjacent online time lengths, namely the adjacent online time lengths, the historical online data, the first characteristic information and the second characteristic information are input into the prediction model, and the unit online time length of the first time point is output by the prediction model.

S304, sequentially acquiring the unit online time length of each time point after the first time point according to the time sequence.

And circulating the above operations, inputting the adjacent online time of the previous time point, the historical online data, the first characteristic information and the second characteristic information into a prediction model, outputting the unit online time of the next time point by the prediction model, and sequentially obtaining the unit online time of each time point after the first time point according to the time sequence until the unit online time of each time point is obtained through prediction.

S305, summing the unit online time lengths of all time points in the preset time period to obtain the online time length of each target user in the preset time period.

After the unit online time length of each time point is obtained through prediction, the unit online time lengths of all time points in the preset time period are summed, and the online time length of each target user in the preset time period is obtained.

For example, the time of the match is 8 to 11 pm on a weekday, that is, the preset time period is 3 hours, and the time duration corresponding to the preset time period is set to be 3 times of the time duration corresponding to the second preset time interval, that is, each second preset time interval is 1 hour. From the start time point 8 points later, the determined successive time points are 9 points, 10 points and 11 points, respectively. For each target user, according to the time sequence, predicting the unit online time length of the target user at 9 points based on the historical online data of 8 points, the first characteristic information, the second characteristic information and the first adjacent online time length (namely the online time length from 7 points to 8 point target users); then, predicting the unit online time length of the target user at 10 points based on the 10-point historical online data, the first characteristic information, the second characteristic information and the second adjacent online time length (namely the predicted online time length of the target user from 8 points to 9 points); then, the unit online time length of the target user at 11 points is predicted based on the 11-point historical online data, the first characteristic information, the second characteristic information and the third adjacent online time length (namely the predicted online time length of the target user from 9 points to 10 points). And finally, carrying out summation calculation on the unit online time length of the target user at 9 points, the unit online time length of 10 points and the unit online time length of 11 points, wherein the obtained sum value is the online time length of the target user from 8 points to 11 points (namely a preset time period) at night.

It should be noted that, when the prediction calculation still has a certain error, and at least twice of the duration corresponding to the second preset time interval is the same as the duration corresponding to the preset time period, when multiple rounds of prediction calculation need to be performed, the calculation result of the second round needs to be calculated according to the calculation result of the first round, and through multiple iterations, the error of the calculation result of the last round is increased, that is, the accuracy is low. When the duration corresponding to the second preset time interval is the same as the duration corresponding to the preset time period, only one round of prediction calculation needs to be performed, and the accuracy of the calculation result obtained at this time is higher compared with the calculation result obtained when at least twice of the duration corresponding to the second preset time interval is the same as the duration corresponding to the preset time period. Therefore, in practical application, the time duration corresponding to the second preset time interval is preferably set to be the same as the time duration corresponding to the preset time period, so that the online time duration with higher accuracy is obtained.

S103, grouping the target users based on the online time length, and sequencing the target users in each group.

In specific implementation, after the online time of each target user within a preset time period is obtained, in order to avoid the problem that the target users cannot participate in a competition or cannot complete the whole competition course due to an emergency situation, and the target users paired with the emergency target users cannot participate in the competition or the competition is invalid, all the target users are grouped based on the predicted online time of each target user, and then the target users in each group are sequenced according to the sequence of the online time from long to short.

Specifically, referring to the method shown in fig. 4, in grouping the target users based on the online time and sorting the target users in each group, the specific steps are as follows:

s401, at least one online time length grouping reference value is determined.

Here, the online time grouping reference value is the maximum time interval that the online time of all target users in the same group can allow during the competition. The determination may be made based on the number of target users, the duration of a preset time period, and the like.

Of course, when the number of subsequent persons is small, the online time period grouping reference value may be changed.

S402, dividing the online time of all target users into a plurality of groups based on the online time grouping reference value.

Here, the number of subgroups is determined based on the determined online duration group reference value. For example, the duration of the race is 3 hours, and the online duration grouping reference value may be set to 0.2 hours, whereby all target users may be grouped into 15 groups, that is, 3/0.2 ═ 15. Of course, the online time grouping reference value can be adjusted at any time according to the preset time period and the number of target users.

After a plurality of groups are determined according to a preset time period and an online time grouping reference value, each group corresponds to one sub-time period, for each target user, the sub-time period in which the online time of the target user falls is judged, and then the target user is determined to be in the group corresponding to the sub-time period in which the online time is expected to fall.

And S403, in each group, sorting the target users based on the third characteristic information.

After all the target users are grouped, the target users are sorted based on the third characteristic information for the target users of each group. Specifically, for each group, third characteristic information of each target user in the group is obtained, wherein the third characteristic information includes order quantity, order scores and the like of each target user in a certain time period, and corresponding weight values are set for the order quantity, the order scores and the like.

In the embodiment of the present disclosure, the service data includes an order number and an order score, which is described in detail, and after the order number, the order score, a weight value corresponding to the order number, and a weight value corresponding to the order score of each target user are obtained, the order number, the order score, the weight value corresponding to the order number, and the weight value corresponding to the order score are used for calculation, so that a service score of each target user, that is, a value of the third feature information is obtained.

And S104, pairing the target users based on the sequencing result.

In a specific implementation, after finishing ranking the target users of each group, for each group, pairing the target users based on the ranking result of the group. For example, pairwise pairing in sequence, or pairwise pairing in odd-numbered sequence, pairwise pairing in even-numbered sequence, as shown in fig. 5, specifically includes the following steps:

s501, in each group, pairing target users based on the value of the third characteristic information;

s502, when the unpaired target users exist in each group, a new group is constructed based on the unpaired target users in all the groups, and the new group is reordered and paired based on the online time length.

And pairing the target users in the group in pairs according to the fact that the value of the third characteristic information of each target user is from high to low. That is, the target user with the first value ranking of the third feature information is paired with the target user with the second value ranking of the third feature information, the target user with the third value ranking of the third feature information is paired with the target user with the fourth value ranking of the third feature information, and so on, and then pairwise pairing of all the target users in each group is completed.

In practical applications, there are cases where the number of target users in a group is singular, that is, there are cases where the target user with the lowest value of the third feature information in the group fails to pair. If only one group in all the groups has the unpaired target user, prompting the target user that the competition fails; and if the unpaired target users exist in the plurality of groups, pairwise pairing is carried out on all the unpaired target users according to the online duration of the unpaired target users in the preset time period from long to short.

Considering that the time interval between the estimated online time lengths of the plurality of unpaired target users is large, the plurality of unpaired target users are paired pairwise according to the estimated online time lengths from long to short, and waste of server resources and social resources is avoided.

And if the unpaired target user which fails to be paired again still exists after the plurality of unpaired target users are paired pairwise, prompting that the unpaired target user fails to participate in the competition.

In summary, in the embodiment of the present disclosure, the historical online data, the first feature information, and the second feature information of each target user are used to predict the online duration of each target user in a preset time period, all target users are grouped based on the online duration of each target user, and the target users in each group are sorted; then, the target users of the group are paired based on the sequencing result of each group, so that the problem that the target users paired with the target users in an emergency cannot participate in the competition or participate in the ineffective competition to a certain extent when part of the target users cannot participate in the competition on time or cannot complete the whole competition course is avoided, namely, the waste of server resources (namely, the server performs the pairing operation) and social resources (the target users can participate in the competition on time and can complete the whole competition course) is avoided, and meanwhile, the experience and the enthusiasm of the target users who can participate in the competition on time and can complete the whole competition course can be ensured.

In specific implementation, the historical online data, the first feature information and the second feature information are input into a trained prediction model, the online time duration of each target user in a preset time period is obtained, and the time duration corresponding to the first preset time interval and the time duration corresponding to the preset time period can be set to be the same when the prediction model is trained, so that the historical online data, the first feature information and the second feature information of each target user are obtained, and the online time duration of each target user in the preset time period is predicted based on the historical online data, the first feature information and the second feature information, that is, only one round of prediction calculation is needed.

Of course, the duration corresponding to the first preset time interval may be set to be different from the duration corresponding to the preset time period, and considering that the duration corresponding to the first preset time interval is smaller than the duration corresponding to the preset time period, the integral multiple of the duration corresponding to the first preset time interval may be set to be the same as the duration corresponding to the preset time period.

According to the method and the device, the on-line time of each target user in the preset time period is predicted by utilizing the historical on-line data, the first characteristic information and the second characteristic information of each target user, pairing is carried out according to the on-line time of each target user, the problem that the target users paired with the target users in an emergency situation cannot participate in the competition or cannot complete the whole competition course on time is avoided to a certain extent, the problem that the target users cannot participate in the competition or cannot participate in the ineffective competition is avoided, waste of server resources and social resources can be avoided, and the resource utilization rate of road network traffic and the operation efficiency of a network appointment can be further improved.

Based on the same inventive concept, an embodiment of the present disclosure further provides an information processing apparatus corresponding to the information processing method, and referring to fig. 6, a second aspect of the present disclosure provides an information processing apparatus, including: a first acquisition module 10, a second acquisition module 20, a sorting module 30 and a pairing module 40, the above modules being coupled to each other, wherein:

the first obtaining module 10 is configured to obtain historical online data, first feature information, and second feature information of each target user, where the first feature information at least includes time feature information and weather feature information, and the second feature information at least includes user feature information.

A second obtaining module 20, configured to input the historical online data, the first feature information, and the second feature information into a trained prediction model, and obtain an online duration of each target user in a preset time period.

In order to ensure the accuracy of the prediction model, the apparatus of the present disclosure further includes a training module 50, and the training module 50 is used to determine the prediction model, and specifically, the training module is used to train the prediction model to be trained by using the historical working data of the historical user. Specifically, after the historical users are determined, screening multiple groups of training samples from all historical working data of each historical user, wherein each group of training samples comprises a first historical online time corresponding to a first time point of each historical user, first characteristic information of the historical users, second characteristic information of the historical users and a real second historical online time of a second time point. Specifically, in the training process, based on a first historical online time and first feature information of a historical user, a temporary historical online time of a second time point which is a first preset time interval away from the first time point is obtained, then the temporary historical online time is corrected through the second feature information, a second historical online time of the historical user at the second time point is determined, the second historical online time determined by the prediction model is compared with a real second historical online time to obtain an error value of the prediction model, if the error value is greater than a preset threshold value, the training of the training is repeated until the error value is less than or equal to the preset threshold value, and the training is finished, namely, the prediction model is obtained.

After the trained prediction model is obtained, the online time of each target user in a preset time period is predicted by using the prediction model, the method is convenient and quick, and the accuracy and the efficiency are high.

In one embodiment, the second obtaining module 20 includes:

the device comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring the adjacent online time length of the adjacent time point which is separated by a second preset time interval before the starting time point of the preset time period.

A first determining unit, configured to determine at least one continuous time point at the second preset time interval within the preset time period from the start time point.

And the second acquisition unit is used for acquiring the unit online time length of the first time point through the prediction model based on the adjacent online time length.

And the third acquisition unit is used for sequentially acquiring the unit online time length of each time point after the first time point according to the time sequence.

For example, the time of the match is 8 to 11 pm on a weekday, that is, the preset time period is 3 hours, and the time duration corresponding to the preset time period is set to be 3 times of the time duration corresponding to the second preset time interval, that is, each second preset time interval is 1 hour. From the start time point 8 points later, the determined successive time points are 9 points, 10 points and 11 points, respectively. For each target user, according to the time sequence, predicting the unit online time length of the target user at 9 points based on the historical online data of 8 points, the first characteristic information, the second characteristic information and the first adjacent online time length (namely the online time length of the target user from 7 points to 8 points); then, predicting the unit online time length of the target user at 10 points based on the 10-point historical online data, the first characteristic information, the second characteristic information and the second adjacent online time length (namely the predicted online time length of the target user from 8 points to 9 points); then, the unit online time length of the target user at 11 points is predicted based on the 11-point historical online data, the first characteristic information, the second characteristic information and the third adjacent online time length (namely the predicted online time length of the target user from 9 points to 10 points). And finally, carrying out summation calculation on the unit online time length of the target user at 9 points, the unit online time length of 10 points and the unit online time length of 11 points, wherein the obtained sum value is the online time length of the target user from 8 points to 11 points (namely a preset time period) at night.

A sorting module 30, configured to group the target users based on the online duration, and sort the target users in each group.

Specifically, the sorting module 30 includes:

a second determining unit for determining at least one online duration packet reference value.

A grouping unit for grouping the online durations of all the target users into a plurality of groups based on the online duration grouping reference value.

After all the target users are grouped, the sorting unit 303 sorts the target users for each group of target users based on the third feature information. Specifically, for each group, third characteristic information of each target user in the group is obtained, wherein the third characteristic information includes order quantity, order scores and the like of each target user in a certain time period, and corresponding weight values are set for the order quantity, the order scores and the like.

In the embodiment of the present disclosure, the sequencing unit elaborates in detail by taking the service data including the order number and the order score as an example, and after obtaining the order number, the order score, the weight value corresponding to the order number, and the weight value corresponding to the order score of each target user, calculates by using the order number, the order score, the weight value corresponding to the order number, and the weight value corresponding to the order score, to obtain the service score of each target user, that is, the value of the third feature information.

And the pairing module 40 is used for pairing the target users based on the sequencing result.

In a specific implementation, after finishing ranking the target users of each group, for each group, pairing the target users based on the ranking result of the group. For example, pairwise in order, or pairwise in odd order, pairwise in even order, and so on.

Specifically, the pairing module 40 includes:

a pairing unit configured to pair the target users based on a value of the third feature information in each of the subgroups.

The third aspect of the present disclosure also provides a storage medium, which is a computer-readable medium storing a computer program, and when the computer program is executed by a processor, the computer program implements the method provided in any embodiment of the present disclosure, including the following steps:

s11, acquiring historical online data, first characteristic information and second characteristic information of each target user, wherein the first characteristic information at least comprises time characteristic information and weather characteristic information, and the second characteristic information at least comprises user characteristic information;

s12, inputting the historical online data, the first characteristic information and the second characteristic information into a trained prediction model, and obtaining the online duration of each target user in a preset time period;

s13, grouping the target users based on the online time length, and sorting the target users in each group;

s14, based on the sorting result, the target users are paired.

The computer program is executed by the processor to input the historical online data, the first characteristic information and the second characteristic information into a trained prediction model, and before acquiring the online time of each target user in a preset time period, the processor further executes the following steps: acquiring a first historical online time of each historical user at a first time point; acquiring a temporary historical online time of a second time point which is a first preset time interval after the first time point based on the first historical online time and the first characteristic information; and correcting the temporary historical online time length through the second characteristic information, and determining a second historical online time length of the historical user at the second time point.

The computer program is executed by the processor to input the historical online data, the first feature information and the second feature information into a trained prediction model, and when the online duration of each target user in a preset time period is obtained, the processor specifically executes the following steps: acquiring adjacent online time lengths of adjacent time points which are separated by a second preset time interval before a starting time point of a preset time period; determining at least one continuous time point according to the second preset time interval in the preset time period after the starting time point; based on the adjacent online time length, acquiring the unit online time length of a first time point through the prediction model; sequentially acquiring the unit online time length of each time point after the first time point according to the time sequence; and summing the unit online durations of all the time points in the preset time period to obtain the online duration of each target user in the preset time period.

The computer program is executed by the processor to group the target users based on the online time length, and when the target users are sorted in each group, the processor specifically executes the following steps: determining at least one online time duration packet reference value; dividing the online time of all the target users into a plurality of groups based on the online time grouping reference value; in each of the subgroups, the target users are ranked based on third characteristic information.

The computer program is executed by the processor based on the sorting result, and when the target user is paired, the processor specifically executes the following steps: in each of the subgroups, pairing the target users based on the value of the third characteristic information; when an unpaired target user exists in each group, constructing a new group based on the unpaired target users in all the groups, and reordering and pairing based on the online time length.

The fourth aspect of the present disclosure also provides an electronic device, a schematic structural diagram of which may be as shown in fig. 7, and the electronic device at least includes a memory 701 and a processor 702, where the memory 701 stores a computer program, and the processor 702 implements the method provided in any embodiment of the present disclosure when executing the computer program on the memory 701. Illustratively, the electronic device computer program steps are as follows:

s21, acquiring historical online data, first characteristic information and second characteristic information of each target user, wherein the first characteristic information at least comprises time characteristic information and weather characteristic information, and the second characteristic information at least comprises user characteristic information;

s22, inputting the historical online data, the first characteristic information and the second characteristic information into a trained prediction model, and obtaining the online duration of each target user in a preset time period;

s23, grouping the target users based on the online time length, and sorting the target users in each group;

s24, based on the sorting result, the target users are paired.

Before the processor executes the trained prediction model to input the historical online data, the first feature information and the second feature information, which are stored in the memory, and acquires the online duration of each target user in a preset time period, the processor further executes the following computer program: acquiring a first historical online time of each historical user at a first time point; acquiring a temporary historical online time of a second time point which is a first preset time interval after the first time point based on the first historical online time and the first characteristic information; and correcting the temporary historical online time length through the second characteristic information, and determining a second historical online time length of the historical user at the second time point.

The processor executes the following computer program when executing the trained prediction model stored in the memory and inputting the historical online data, the first feature information and the second feature information into the trained prediction model to obtain the online time of each target user within a preset time period: acquiring adjacent online time lengths of adjacent time points which are separated by a second preset time interval before a starting time point of a preset time period; determining at least one continuous time point according to the second preset time interval in the preset time period after the starting time point; based on the adjacent online time length, acquiring the unit online time length of a first time point through the prediction model; sequentially acquiring the unit online time length of each time point after the first time point according to the time sequence; and summing the unit online durations of all the time points in the preset time period to obtain the online duration of each target user in the preset time period.

The processor, in executing the computer program stored on the memory to group the target users based on the online time duration and rank the target users in each group, further executes: determining at least one online time duration packet reference value; dividing the online time of all the target users into a plurality of groups based on the online time grouping reference value; in each of the subgroups, the target users are ranked based on third characteristic information.

The processor, when executing the sort-based result stored on the memory, further executes the following computer program when performing the pairing among the target users: in each of the subgroups, pairing the target users based on the value of the third characteristic information; when an unpaired target user exists in each group, constructing a new group based on the unpaired target users in all the groups, and reordering and pairing based on the online time length.

In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText transfer protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a Local Area Network (LAN), a Wide Area Network (WAN), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The storage medium may be included in the electronic device; or may exist separately without being assembled into the electronic device.

The storage medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquiring at least two internet protocol addresses; sending a node evaluation request comprising at least two internet protocol addresses to node evaluation equipment, wherein the node evaluation equipment selects the internet protocol addresses from the at least two internet protocol addresses and returns the internet protocol addresses; receiving an internet protocol address returned by the node evaluation equipment; wherein the obtained internet protocol address indicates an edge node in the content distribution network.

Alternatively, the storage medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: receiving a node evaluation request comprising at least two internet protocol addresses; selecting an internet protocol address from at least two internet protocol addresses; returning the selected internet protocol address; wherein the received internet protocol address indicates an edge node in the content distribution network.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It should be noted that the storage media described above in this disclosure can be computer readable signal media or computer readable storage media or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any storage medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

While the present disclosure has been described in detail with reference to the embodiments, the present disclosure is not limited to the specific embodiments, and those skilled in the art can make various modifications and alterations based on the concept of the present disclosure, and the modifications and alterations should fall within the scope of the present disclosure as claimed.

Claims

1. An information processing method characterized by comprising:

and pairing the target users based on the sequencing result.

2. The information processing method according to claim 1, wherein the predictive model is trained by:

3. The information processing method of claim 1, wherein the inputting the historical online data, the first feature information and the second feature information into a trained predictive model, and the obtaining the online duration of each target user within a preset time period comprises:

4. The information processing method of claim 1, wherein the grouping the target users based on the online time duration and ranking the target users in each group comprises:

determining at least one online time duration packet reference value;

5. The information processing method according to claim 4, wherein the pairing among the target users based on the ranking result includes:

6. An information processing apparatus characterized by comprising:

7. The information processing apparatus according to claim 6, characterized by further comprising:

8. The information processing apparatus according to claim 6, wherein the second acquisition module includes:

9. The information processing apparatus according to claim 6, wherein the sorting module includes:

10. The information processing apparatus according to claim 9, wherein the pairing module includes:

11. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, performs the steps of the information processing method according to any one of claims 1 to 5.

12. An electronic device, comprising: a processor, a memory and a 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 operating, 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 5.