1. An abnormal order processing method is characterized by comprising the following steps:

acquiring identification characteristics of an order to be identified, wherein the identification characteristics are characteristics influencing the preparation time of the order;

determining the probability that the order to be identified is an abnormal order through a classification model according to the identification characteristics;

according to the probability, determining the order to be identified and the target extension time of the order preparation time of the order within the first preset time after the order to be identified;

and according to the target extension time, carrying out delivery scheduling on the order to be identified and the order within the first preset time.

2. The method of claim 1, wherein determining the target extension time for the order to be identified and the order preparation time for the order within a first preset time after the order to be identified according to the probability comprises:

and determining the target extended time of the order preparation time of the order to be identified and the order to be identified within the first preset time after the order to be identified according to the corresponding relation between the probability and the preset probability range and the extended time gear.

3. The method of claim 2, wherein after the determining the order to be identified and the target extension time for the order preparation time for the order within a first preset time after the order to be identified, further comprising:

taking the target extension time as a default selected time gear in the extension time gears, and sending the extension time gear to a merchant terminal of the order to be identified, so that the merchant terminal displays the extension time gear and obtains the selected time gear of the merchant;

receiving a selected time gear transmitted by the merchant end;

according to the target extension time, carrying out delivery scheduling on the order to be identified and the order within the first preset time, wherein the delivery scheduling comprises the following steps:

and according to the selected time gear, carrying out delivery scheduling on the order to be identified and the order within the first preset time.

4. The method of claim 3, further comprising:

determining an abnormal scene corresponding to the order to be identified according to the order amount and the number of the dishes of the order to be identified;

sending the extended time gear to the merchant terminal of the order to be identified, including:

and generating prompt information comprising the extended time gear according to the abnormal scene, and sending the prompt information to the merchant of the order to be identified.

5. The method of claim 1, wherein obtaining the identification characteristic of the order to be identified comprises:

acquiring merchant attribute information, merchant capacity information and order attribute information corresponding to the order to be identified;

and encoding the merchant attribute information, the merchant capacity information and the order attribute information into the identification features.

6. The method of claim 5, wherein the merchant attribute information comprises: at least one of merchant scale information, merchant operation characteristics, merchant city rating, merchant rating and merchant type;

the merchant capacity information comprises: at least one of order information in a historical peak time period of a merchant, order information in a historical peak time period of the merchant, order information in a historical time slice of the order to be identified, order information in a second preset time before the order to be identified, and a ratio of off-line transaction information to on-line transaction information of the merchant;

the order attribute information includes: at least one of order dish label, price normalization information, dish normalization information, and order dish price segmentation information.

7. The method of claim 1, further comprising, before determining the probability that the order to be identified is an abnormal order by a classification model based on the identifying characteristics:

determining the historical orders meeting the preset conditions as positive samples of the abnormal orders, and determining the historical orders not meeting the preset conditions as negative samples of the abnormal orders;

and training the classification model according to the positive sample and the negative sample to obtain the trained classification model.

8. The method according to claim 7, wherein the preset condition is that an average delay time of order preparation times corresponding to the current historical order and at least one historical order within a third preset time later is greater than a fourth preset time.

9. An abnormal order processing apparatus, comprising:

the identification feature acquisition module is used for acquiring identification features of the order to be identified, wherein the identification features are features influencing the order preparation time;

the probability prediction module is used for determining the probability that the order to be identified is an abnormal order through a classification model according to the identification characteristics;

the extended time determining module is used for determining the target extended time of the order preparation time of the order to be identified and the order to be identified within a first preset time after the order to be identified according to the probability;

and the delivery scheduling module is used for performing delivery scheduling on the order to be identified and the order within the first preset time according to the target extension time.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the exception order handling method of any one of claims 1 to 8 when executing the computer program.

11. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the steps of the exception order handling method of any one of claims 1 to 8.

Background

In the takeaway field, often meet the condition that the trade company has a slow meal and the rider arrives at the store early, this kind of condition can influence the delivery efficiency of rider, through the prediction to order meal time among the prior art, can have certain guide effect to the rider arrives at the store.

However, in the actual meal serving process of the merchant, some abnormal disturbances may exist, and these disturbances include sudden large-amount order entry, more dish order entry, and the like, and these disturbances may cause inaccuracy in the estimation of the meal serving time, and the estimation of the meal serving time may only respond to the current order, and the influence on the subsequent order is not considered, which may cause long waiting time of the rider and affect the distribution efficiency.

Disclosure of Invention

The embodiment of the application provides an abnormal order processing method and device, electronic equipment and a storage medium, which are beneficial to reducing waiting time of a rider and improving distribution efficiency.

In order to solve the above problem, in a first aspect, an embodiment of the present application provides an abnormal order processing method, including:

acquiring identification characteristics of an order to be identified, wherein the identification characteristics are characteristics influencing the preparation time of the order;

determining the probability that the order to be identified is an abnormal order through a classification model according to the identification characteristics;

according to the probability, determining the order to be identified and the target extension time of the order preparation time of the order within the first preset time after the order to be identified;

and according to the target extension time, carrying out delivery scheduling on the order to be identified and the order within the first preset time.

In a second aspect, an embodiment of the present application provides an abnormal order processing apparatus, including:

the identification feature acquisition module is used for acquiring identification features of the order to be identified, wherein the identification features are features influencing the order preparation time;

the probability prediction module is used for determining the probability that the order to be identified is an abnormal order through a classification model according to the identification characteristics;

the extended time determining module is used for determining the target extended time of the order preparation time of the order to be identified and the order to be identified within a first preset time after the order to be identified according to the probability;

and the delivery scheduling module is used for performing delivery scheduling on the order to be identified and the order within the first preset time according to the target extension time.

In a third aspect, an embodiment of the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the abnormal order processing method according to the embodiment of the present application when executing the computer program.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the abnormal order processing method disclosed in the present application.

According to the abnormal order processing method and device, the electronic equipment and the storage medium, the identification characteristics of the order to be identified are obtained, the probability that the order to be identified is the abnormal order is determined through the classification model according to the identification characteristics, the target extension time of the order preparation time of the order to be identified and the order to be identified within the first preset time after the order to be identified is determined according to the probability, and the delivery scheduling is performed on the order to be identified and the order within the first preset time according to the target extension time, so that the target extension time corresponding to the abnormal order and the abnormal order is accurately estimated, the reasonable delivery scheduling is performed, the waiting time of a rider can be reduced, and the delivery efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a flowchart of an abnormal order processing method according to a first embodiment of the present application;

fig. 2 is a schematic structural diagram of an abnormal order processing apparatus according to a second embodiment of the present application;

fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.

Detailed Description

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 is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Example one

As shown in fig. 1, the method for processing an abnormal order provided in this embodiment includes: step 110 to step 140.

Step 110, obtaining the identification characteristics of the order to be identified, wherein the identification characteristics are characteristics influencing the order preparation time.

The abnormal order to be identified in the embodiment of the application is an actual order with a long preparation time, and the take-away field can comprise a large-volume order and/or a plurality of dish orders, and when the order is received, the capacity of a merchant cannot meet the instantaneous high demand of the order, and the order is blocked, so that the order is also called a card meal order in the take-away field. The abnormal order is typically characterized in that the order is larger in amount or contains more dishes, the order preparation time of the current order is prolonged, and the subsequent order preparation time is prolonged due to the influence on the subsequent order preparation time. The order preparation time refers to the preparation time of the items in the order promised by the merchant, and for instant delivery, the order preparation time is important information for guiding the rider to the store. In the takeaway field, the order preparation time, i.e., the promised meal delivery time, is the meal delivery time promised by the merchant who has signed a service agreement with the takeaway platform, and the order preparation time extension, i.e., the meal delivery delay, is the actual meal delivery time greater than the promised meal delivery time.

When the order to be identified is an abnormal order, the identification characteristics of the order to be identified need to be acquired, and the identification characteristics of the order to be identified can be acquired according to preset factors influencing the order preparation time. The order to be identified may be an abnormal order reported by the merchant, or may be all orders.

In an embodiment of the present application, the acquiring an identification characteristic of an order to be identified includes: acquiring merchant attribute information, merchant capacity information and order attribute information corresponding to the order to be identified; and encoding the merchant attribute information, the merchant capacity information and the order attribute information into the identification features.

Wherein the merchant attribute information comprises: at least one of merchant scale information, merchant operation characteristics, merchant city rating, merchant rating and merchant type;

the merchant capacity information comprises: at least one of order information in a historical peak time period of a merchant, order information in a historical peak time period of the merchant, order information in a historical time slice of the order to be identified, order information in a second preset time before the order to be identified, and a ratio of off-line transaction information to on-line transaction information of the merchant;

the order attribute information includes: at least one of order dish label, price normalization information, dish normalization information, and order dish price segmentation information.

The factors that lead to extended order preparation time mainly include: merchant attribute information, merchant capacity information, and order attribute information. The merchant attribute information comprises at least one of merchant scale information, merchant operation characteristics, merchant city rating, merchant rating and merchant type. The merchant size information may include a ranking of the identity of the merchant in the same city and a normalized value of the merchant identity. The business operation characteristics are related to the business position, for example, when the business is located in an office building or a shopping mall, the business operation characteristics are large in change of weekends and weekdays, and at the moment, the business operation characteristics can be characterized by the ratio of the average daily unit amount of the business to the average daily unit amount of the business on weekends. The grade of the city where the merchant is located is the grade of the city where the merchant is located, and if the city where the merchant is located is Beijing, the grade of the city where the merchant is located is one grade. The merchant rating is a rating of the merchant, such as a rating of the merchant being a large merchant, a medium merchant, or a small merchant. The merchant type refers to the type of merchant, and may include chain merchants or city merchants, etc.

The merchant capacity information comprises: at least one of order information in a historical peak time period of the merchant, order information in a historical time slice of the order to be identified, order information in a second preset time before the order to be identified, and a ratio of off-line transaction information to on-line transaction information of the merchant. The historical peak time period order information of the merchant is the order information of the merchant in the historical peak time period (such as lunch time period and/or dinner time period), and comprises the following steps: an order pick-up amount during a peak time period over a period of time (e.g., within a month), an order amount taken by a merchant by a rider over a period of time, a rider wait period, an actual order preparation time (e.g., a meal length), a timeout rate, etc., where a timeout rate is a probability that an order for which the actual order preparation time exceeds the committed order preparation time over a period of time is within the period of time. The historical flat peak time period order information of the merchant is order information of the merchant in the historical flat peak time period (such as time periods except lunch time periods and dinner time periods), and comprises the following steps: the amount of orders in a flat peak period over a period of time, the rider wait period, the actual order preparation time (e.g., meal length), the timeout rate, etc. The time slice is a time slice which is obtained by averagely dividing 24 hours a day into a plurality of time slices, each time slice has specific time and time length, the time slice comprises the length of a preset time slice, for example, a time slice every 10 minutes, and the order information in the historical time slice of the order to be identified comprises the order quantity, the transaction amount, the average order price, the order number, the order quantity taken by a rider, the actual order preparation time and the like of the time slice in a period of time. The second preset time is generally a preset number of minutes, such as 10 minutes, 5 minutes, etc., and the order information in the second preset time before the order to be identified includes the order quantity in N minutes before the order to be identified, the transaction amount, the average price of the order, the number of orders taken, the amount of orders taken by the rider, the actual order preparation time, etc. The merchant offline and online transaction information ratio comprises a ratio of the offline transaction amount of the merchant to the online transaction amount in a historical period of time, and/or a ratio of the online order placing quantity of the merchant to the online order quantity in a historical period of time.

The order attribute information includes: at least one of order dish label, price normalization information, dish normalization information, and order dish price segmentation information. The order dish label mainly reflects whether the food in the order can be prepared or not and whether the meal delivery efficiency is influenced by quantity or not, and can comprise a cooking method, commodity types and the like, wherein the cooking method can comprise braising, boiling, frying and the like, and the commodity types can comprise steamed stuffed buns, fragrant pots, rice balls and the like. The price normalization information is obtained by normalizing the price of the order to be identified according to the order price in a historical period of time. The dish normalization information is information obtained by normalizing dishes of the order to be identified according to the information of the dishes in the order within a period of history. The order dish price segment information refers to a dish price segment in which the dish price in the order to be identified is located, and the dish price segment is a preset dish price segment, such as 10 yuan to 20 yuan, 20 yuan to 30 yuan, 30 yuan or more, and the like.

After acquiring the merchant attribute information, the merchant capacity information and the order attribute information corresponding to the order to be identified, respectively encoding the merchant attribute information, the merchant capacity information and the order attribute information according to the encoding mode of the corresponding information to obtain the identification characteristics of the order to be identified. The obtained identification characteristics can reflect the influence on the order preparation time well, so that the orders to be identified can be classified well, and the accurate probability that the orders to be identified are abnormal orders is obtained.

And step 120, determining the probability that the order to be identified is an abnormal order through a classification model according to the identification characteristics.

After the identification features of the order to be identified are obtained, the identification features are input into the classification model, and the probability that the order to be identified is an abnormal order is obtained through processing the identification features by the classification model. The classification model may be a neural network model.

And step 130, determining the target extension time of the order preparation time of the order to be identified and the order to be identified within a first preset time after the order to be identified according to the probability.

The corresponding relation between the probability and the extended time of the order preparation time can be preset, after the probability that the order to be identified is an abnormal order is determined through the classification model, the corresponding relation is inquired, and the target extended time of the order preparation time of the order to be identified and the order to be identified within the first preset time is obtained. After determining the target extended time, the target extended time may be extended based on an order preparation time promised by the merchant as an order preparation time for the order to be identified and all orders received within a first predetermined time after the order to be identified. The first preset time is a minute-scale time, and may be, for example, 10 minutes or 15 minutes.

In an embodiment of the application, determining the to-be-identified order and the target extension time of the order preparation time of the order within a first preset time after the to-be-identified order according to the probability includes: and determining the target extended time of the order preparation time of the order to be identified and the order to be identified within the first preset time after the order to be identified according to the corresponding relation between the probability and the preset probability range and the extended time gear.

A plurality of extended time gears can be preset, and a probability range corresponding to each extended time gear is set, so that after the probability that the order to be identified is an abnormal order is identified and obtained, the probability range where the probability is located is determined, the extended time gear corresponding to the determined probability range is obtained from the corresponding relation between the probability range and the extended time gears, and the extended time gear is used as the target extended time of the order preparation time of the order to be identified and the order to be identified within the first preset time. The probabilities in the probability ranges are all greater than or equal to the probability threshold, for example, the probability threshold is 70%, and may include 3 probability ranges, that is, 70% to 80%, 80% to 90%, and 90% to 100%, where each probability range corresponds to one extended time shift, for example, the extended time shifts may be 5 minutes, 8 minutes, and 10 minutes, respectively, the extended time shift corresponding to the probability range "70% to 80% is 5 minutes, the extended time shift corresponding to the probability range" 80% to 90% is 8 minutes, and the extended time shift corresponding to the probability range 90% to 100% is 10 minutes. The extended time gear can be obtained by counting the actual extended time of the abnormal orders in the specific area on the basis of the promised order preparation time, so that the obtained extended time gear is more reasonable.

The target extension time of the order preparation time of the order to be identified and the order to be identified within the first preset time after the order to be identified is determined according to the corresponding relation between the preset probability range and the extension time gear, so that the reasonable target extension time can be determined, the target extension time can be well used for guiding delivery scheduling, and the delivery efficiency is improved.

And 140, carrying out delivery scheduling on the order to be identified and the order within the first preset time according to the target extension time.

After the order to be identified and the target extended time of the order preparation time of the order within the first preset time after the order to be identified are determined, the target extended time is extended on the basis of the order preparation time to serve as the order preparation time of the order within the first preset time promised by a merchant, and therefore the order to be identified and the order received within the first preset time after the order to be identified are dispatched according to the extended order preparation time. When the delivery scheduling is performed according to the extended order preparation time and the order received within the first preset time after the order to be identified and the order to be identified, the delivery time of the order to be identified and the order received within the first preset time after the order to be identified can be estimated according to the extended order preparation time, so that the order reassignment is performed on the order to which the rider has been assigned according to the estimated delivery time, the time from the rider to the store is influenced, and the rider is prevented from waiting for a long time in a merchant.

According to the abnormal order processing method provided by the embodiment of the application, the identification characteristics of the order to be identified are obtained, the probability that the order to be identified is the abnormal order is determined through the classification model according to the identification characteristics, the target extension time of the order preparation time of the order to be identified and the order to be identified within the first preset time after the order to be identified is determined according to the probability, and the delivery scheduling is carried out on the order to be identified and the order within the first preset time according to the target extension time, so that the target extension time corresponding to the abnormal order and the abnormal order is accurately estimated, the reasonable delivery scheduling is carried out, the waiting time of a rider can be reduced, and the delivery efficiency is improved.

On the basis of the above technical solution, after the determining the target extension time of the order preparation time of the order in the first preset time after the order to be identified and the order to be identified, the method further includes: taking the target extension time as a default selected time gear in the extension time gears, and sending the extension time gear to a merchant terminal of the order to be identified, so that the merchant terminal displays the extension time gear and obtains the selected time gear of the merchant; receiving a selected time gear transmitted by the merchant end;

according to the target extension time, carrying out delivery scheduling on the order to be identified and the order within the first preset time, wherein the delivery scheduling comprises the following steps: and according to the selected time gear, carrying out delivery scheduling on the order to be identified and the order within the first preset time.

The target extension time is one of a plurality of preset extension time gears, so that the target extension time is used as a default selected time gear in the extension time gears, the plurality of extension time gears including the default selected time gear are sent to a merchant terminal, the order preparation time for reminding an order to be identified by the merchant terminal can be extended, the merchant terminal receives the plurality of extension time gears, displays the plurality of extension time gears, defaults to select the extension time gear where the target extension time is located, acquires the time gear selected by the merchant, obtains the selected time gear, the merchant can directly select the default selected time gear or change other extension time gears, the merchant terminal acquires the selected time gear, sends the selected time gear to a background server, and the background server can receive the selected time gear sent by the merchant terminal, and therefore, according to the selected time gear, the order to be identified and the order within the first preset time after the order to be identified are subjected to delivery scheduling. Through a plurality of extension time gears of propelling movement to trade company's end, can make the trade company select suitable extension time gear according to self condition to subsequent delivery dispatch of guidance more reasonable, in order to further promote delivery efficiency.

On the basis of the technical scheme, the method further comprises the following steps: determining an abnormal scene corresponding to the order to be identified according to the order amount and the number of the dishes of the order to be identified;

sending the extended time gear to the merchant terminal of the order to be identified, including: and generating prompt information comprising the extended time gear according to the abnormal scene, and sending the prompt information to the merchant of the order to be identified.

The abnormal scene may include a large amount scene or a multiple dish scene.

Obtaining an order average price of the merchant of the order to be identified in a historical statistical period (such as historical monthly) (if the order average price of the merchant cannot be obtained, the order average price of the same city class of the merchant is used), determining a ratio of the order amount to the order average price, taking the ratio as an order amount ratio, and if the order amount ratio is greater than or equal to a preset ratio threshold, determining that an abnormal scene of the order to be identified is a large-amount scene. And removing the weight of the dishes of the order to be identified, removing packages, gifts and the like, counting to obtain the quantity of the dishes, and if the quantity of the dishes is greater than or equal to a preset quantity threshold value, determining that the abnormal scene of the order to be identified is a multi-dish scene.

The prompt information files corresponding to different abnormal scenes are different, so that after the abnormal scene of the order to be recognized is obtained, the prompt information file corresponding to the abnormal scene can be obtained, prompt information comprising the extended time gear is generated, the prompt information is sent to a merchant terminal of the order to be recognized, when the merchant terminal detects an operation instruction of the prompt information, a plurality of extended time gears are displayed, and the extended time gear corresponding to the selected target extended time is selected by default.

For example, if the probability that the order to be identified is an abnormal order is greater than or equal to a first probability threshold and the order sum ratio is greater than or equal to a preset ratio threshold, dividing the order to be identified into a large-amount scene for pushing; and if the probability that the order to be identified is an abnormal order is greater than or equal to the first probability threshold value and the number of dishes of the order is greater than or equal to the preset number threshold value, dividing the order to be identified into multiple dish scenes for pushing. According to the high and low of the predicted probability, the order preparation time which is recommended to a merchant and is to be prolonged by X minutes, for example, the recommended order preparation time is prolonged, the order preparation time can be divided into three grades, 5 minutes, 8 minutes and 10 minutes, wherein the predicted probability is greater than or equal to the first probability threshold and smaller than a second probability threshold, a 5-minute gear is selected by default, the predicted probability is greater than or equal to the second probability threshold and smaller than a third probability threshold, an 8-minute gear is selected by default, the predicted probability is greater than or equal to a third probability threshold, and a 10-minute gear is selected by default.

Prompt information corresponding to the abnormal scene is generated according to the abnormal scene of the order to be recognized, so that a merchant can clearly know the abnormal situation of the abnormal order.

On the basis of the above technical solution, before determining the probability that the order to be identified is an abnormal order through a classification model according to the identification features, the method further includes: determining the historical orders meeting the preset conditions as positive samples of the abnormal orders, and determining the historical orders not meeting the preset conditions as negative samples of the abnormal orders; and training the classification model according to the positive sample and the negative sample to obtain the trained classification model.

The preset condition is that the average delay time of the order preparation time corresponding to the current historical order and at least one historical order in the third preset time later is greater than the fourth preset time. The third preset time may be greater than the fourth preset time, and all the third preset time is data in the order of minutes, for example, the third preset time is 10 minutes, the fourth preset time is 5 minutes, and the preset condition is that the average delay time of the current historical order and the historical order within the next 10 minutes is greater than 5 minutes.

When a sample is marked, the identification of an abnormal order is different from the estimation of meal-out time, the meal-out time or the meal-taking time of a rider can be directly used as a marking value for training, the marking value for the identification of the abnormal order needs to be adjusted based on data analysis and service characteristics, and the analysis of the online time finds that the abnormal order generally influences orders within the first preset time (such as 10 minutes) later, and shows that the timeout rate of the riders and other meals is higher and the serious timeout rate is higher. Therefore, historical orders which contain promised order preparation time and are freely distributed by using the platform can be selected from historical data, historical orders which meet preset conditions and historical orders which do not meet the preset conditions are obtained from the historical orders, the historical orders which meet the preset conditions are determined as positive samples, and the historical orders which do not meet the preset conditions are determined as negative samples. When the actual order preparation time of the merchant is not available, the rider's pickup time may be used instead.

And after the marked positive sample and the marked negative sample are obtained, respectively obtaining the identification characteristics of each sample, inputting the identification characteristics of the samples into the classification model, and adjusting the network parameters of the classification model based on the marked values of the samples until the training of the classification model is finished.

The historical orders meeting the preset conditions are determined as positive samples of the abnormal orders, and other historical orders are determined as negative samples of the abnormal orders, so that automatic marking of sample data is achieved.

Example two

As shown in fig. 2, the abnormal order processing apparatus 200 according to this embodiment includes:

an identification feature obtaining module 210, configured to obtain an identification feature of an order to be identified, where the identification feature is a feature that affects order preparation time;

a probability prediction module 220, configured to determine, according to the identification feature, a probability that the order to be identified is an abnormal order through a classification model;

an extended time determining module 230, configured to determine, according to the probability, the to-be-identified order and a target extended time of an order preparation time of the order within a first preset time after the to-be-identified order;

and a delivery scheduling module 240, configured to perform delivery scheduling on the order to be identified and the order within the first preset time according to the target extended time.

Optionally, the extended time determining module is specifically configured to:

and determining the target extended time of the order preparation time of the order to be identified and the order to be identified within the first preset time after the order to be identified according to the corresponding relation between the probability and the preset probability range and the extended time gear.

Optionally, the apparatus further comprises:

the time gear transmitting module is used for taking the target extension time as a default selected time gear in the extension time gears and transmitting the extension time gear to a merchant terminal of the order to be identified so that the merchant terminal can display the extension time gear and obtain the selected time gear of the merchant;

the selected gear receiving module is used for receiving the selected time gear sent by the merchant end;

the delivery scheduling module is specifically configured to:

and according to the selected time gear, carrying out delivery scheduling on the order to be identified and the order within the first preset time.

Optionally, the apparatus further comprises:

the abnormal scene determining module is used for determining an abnormal scene corresponding to the order to be identified according to the order amount and the number of the dishes of the order to be identified;

the time gear transmission module includes:

and the prompt information sending unit is used for generating prompt information comprising the extended time gear according to the abnormal scene and sending the prompt information to the merchant terminal of the order to be identified.

Optionally, the identifying characteristic obtaining module includes:

the information acquisition module is used for acquiring the attribute information of the merchant, the capacity information of the merchant and the attribute information of the order corresponding to the order to be identified;

and the coding module is used for coding the merchant attribute information, the merchant capacity information and the order attribute information into the identification characteristics.

Optionally, the merchant attribute information includes: at least one of merchant scale information, merchant operation characteristics, merchant city rating, merchant rating and merchant type;

the merchant capacity information comprises: at least one of order information in a historical peak time period of a merchant, order information in a historical peak time period of the merchant, order information in a historical time slice of the order to be identified, order information in a second preset time before the order to be identified, and a ratio of off-line transaction information to on-line transaction information of the merchant;

the order attribute information includes: at least one of order dish label, price normalization information, dish normalization information, and order dish price segmentation information.

Optionally, the apparatus further comprises:

the sample marking module is used for determining the historical orders meeting the preset conditions as positive samples of the abnormal orders and determining the historical orders not meeting the preset conditions as negative samples of the abnormal orders;

and the classification model training module is used for training the classification model according to the positive sample and the negative sample to obtain a trained classification model.

Optionally, the preset condition is that an average delay time of order preparation times corresponding to the current historical order and at least one historical order within a third preset time later is greater than a fourth preset time.

The abnormal order processing device provided in the embodiment of the present application is used to implement each step of the abnormal order processing method described in the first embodiment of the present application, and specific implementation of each module of the device refers to the corresponding step, which is not described herein again.

According to the abnormal order processing device provided by the embodiment of the application, the identification characteristics of the order to be identified are obtained through the identification characteristic obtaining module, the probability forecasting module determines the probability that the order to be identified is the abnormal order through the classification model according to the identification characteristics, the extension time determining module determines the target extension time of the order preparation time of the order to be identified and the order to be identified in the first preset time after the order to be identified according to the probability, and the delivery scheduling module performs delivery scheduling on the order to be identified and the order in the first preset time according to the target extension time, so that the target extension time corresponding to the abnormal order and the abnormal order is accurately estimated, reasonable delivery scheduling is performed, the waiting time of a rider can be reduced, and the delivery efficiency is improved.

EXAMPLE III

Embodiments of the present application also provide an electronic device, as shown in fig. 3, the electronic device 300 may include one or more processors 310 and one or more memories 320 connected to the processors 310. Electronic device 300 may also include input interface 330 and output interface 340 for communicating with another apparatus or system. Program code executed by processor 310 may be stored in memory 320.

The processor 310 in the electronic device 300 calls the program code stored in the memory 320 to perform the exception order handling method in the above embodiment.

The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the abnormal order processing method according to the first embodiment of the present application.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

The foregoing introduces a detailed description of an abnormal order processing method, an abnormal order processing apparatus, an electronic device, and a storage medium provided in the embodiments of the present application, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the foregoing embodiments is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.