CN114943846A

CN114943846A - Order complaint processing method and device

Info

Publication number: CN114943846A
Application number: CN202210356096.XA
Authority: CN
Inventors: 吴倩倩
Original assignee: Hangzhou Hikvision System Technology Co Ltd
Current assignee: Hangzhou Hikvision System Technology Co Ltd
Priority date: 2022-04-06
Filing date: 2022-04-06
Publication date: 2022-08-26

Abstract

The application provides a method and a device for processing order complaints, relates to the technical field of unmanned stores, and is used for automatically intercepting and taking out monitoring videos related to complaint orders so as to improve the processing efficiency of order complaints. The method comprises the following steps: firstly, obtaining complaint information of an order, wherein the complaint information comprises an identifier of a first commodity and an occurrence period of the order; determining behavior event information of taking/placing the first commodity in a first preset time period including the occurrence time period, wherein the behavior event information comprises a first moment of taking/placing the first commodity and a first position of the first commodity; determining a first set of activity traces from the behavioral event information; the first group of activity tracks comprise activity tracks acquired by monitoring equipment used for monitoring the first position in a second preset time period; the second preset time period comprises a first moment; determining a first target activity track in the first set of activity tracks; and acquiring a monitoring video of the first target activity track, wherein the acquired monitoring video is used for verifying the order complaint.

Description

Order complaint processing method and device

Technical Field

The application relates to the technical field of unmanned stores, in particular to a method and a device for processing order complaints.

Background

With the development of internet technology, people's lives are becoming more and more intelligent. The new-form unmanned stores of the retail industry are produced, the operation flow in the unmanned stores can be processed intelligently and automatically through technical means, no or little manual intervention exists, and convenience is provided for people to shop to a certain extent.

In the existing order complaint processing flow of the unmanned store, after a complaint request of a customer for an error order is received, customer service often needs to manually check a monitoring video in the unmanned store. Since there may be many monitoring devices in an unmanned store, processing one complaint may require viewing monitoring videos recorded by many monitoring devices. This wastes a lot of manpower and the auditing efficiency is low.

Disclosure of Invention

The application provides a method and a device for processing order complaints, which are used for automatically intercepting and taking out monitoring videos related to complaint orders so as to improve the processing efficiency of order complaints.

In a first aspect, the present application provides a method for processing an order complaint, the method including: obtaining complaint information of the order, wherein the complaint information comprises an identifier of the first commodity and an occurrence time period of the order; determining behavior event information of taking/placing a first commodity in a first preset time period including an occurrence time period according to the identification of the first commodity, wherein the behavior event information comprises a first moment of taking/placing the first commodity and a first position of the first commodity; determining a first set of activity traces from the behavioral event information; the first group of activity tracks comprise activity tracks acquired by monitoring equipment used for monitoring the first position in a second preset time period; the second preset time period comprises the first moment; determining a first target activity track in the first set of activity tracks; and acquiring a monitoring video of the first target activity track, wherein the acquired monitoring video is used for verifying the order complaint.

Based on the order complaint processing method, when a complaint request of an order is received, complaint information of the order can be obtained, behavior event information related to complaint commodities of the order is determined according to the complaint information of the order, a first target activity track related to the complaint of the order is determined according to the behavior event information, and a monitoring video for verifying the complaint of the order is intercepted according to the first target activity track. Since the first target activity track is associated with the order complaint, the surveillance video of the first target activity track is also associated with the order complaint, and thus the surveillance video of the first target activity track can be used to verify the order complaint.

It will be appreciated that the above-described method can automatically capture surveillance video associated with an order complaint for use in verifying the order complaint during processing of the order complaint. Therefore, the method is different from the mode of manually searching the relevant monitoring of the order complaint in a large amount of videos by the existing customer service personnel, a large amount of manpower can be saved, the time of searching the videos can be saved, the method is more convenient and quicker, and the order auditing efficiency is improved.

In a possible implementation manner, the determining a first target activity track in the first set of activity tracks includes: determining a first distance between each of the first set of motion trajectories and the first location; and determining a first target activity track in the first set of activity tracks according to the first distance.

It is understood that the smaller the first distance, the closer the person to which the activity track belongs is to the first position of the first commodity within the first preset time period, the more relevant the activity track is to the behavior event. Thus, the processing device for order complaints can determine at least one activity track with higher correlation degree with the order complaint in the first group of activity tracks according to the first distance.

In another possible implementation manner, the determining a first target activity track in the first set of activity tracks according to the first distance includes: sorting the first group of active tracks from small to large according to the first distance to obtain a sorting result of the first group of active tracks; and determining the first N active tracks in the sequencing result as first target active tracks, wherein N is a positive integer.

In yet another possible implementation manner, the method further includes: determining associated event information according to the first time, wherein the associated event information comprises a second time for taking/placing other commodities except the first commodity in the store and second positions of the other commodities in a third preset time period, and the third preset time period comprises the first time; determining a second group of activity tracks according to the associated event information; the second group of activity tracks comprise a plurality of activity tracks acquired by monitoring equipment for monitoring the second position within a fourth preset time period; the second preset time period comprises a second moment; determining a second target activity track in the second set of activity tracks; and acquiring a monitoring video of the second target activity track, wherein the monitoring video is used for verifying the order complaint.

It can be understood that the related event is a behavior event related to a behavior event of taking/placing a first commodity within a first preset time period, and since an operation system of the unmanned store may confuse two taking/placing events with similar time, a situation that an order is mistakenly deducted occurs, the related event is also a behavior event related to the order complaint.

In another possible implementation manner, the determining a second target activity track in the second group of activity tracks specifically includes: determining a second distance between each of the second set of motion trajectories and the second location; and determining a second target activity track in the second set of activity tracks according to the second distance.

For example, the processing device for order complaints may sequence each of the second group of activity tracks from small to large according to the second distance, and determine the top M activity tracks in the second group of activity tracks as the at least one activity track. Wherein M is a positive integer.

It is understood that the smaller the second distance, the more closely the person to which the activity track belongs is to the second location of the second item within the second predetermined time period, the more relevant the activity track is to the associated event. Therefore, the processing device for order complaint can determine at least one activity track with higher correlation degree with the order complaint in the second group of activity tracks as a second target activity track according to the second distance.

In yet another possible implementation manner, the method further includes: respectively carrying out face recognition on the monitoring video of the first target activity track and the monitoring video of the second target activity track, and determining a user to which each activity track belongs; and under the condition that the user to which each activity track belongs comprises a first user and a second user, dividing the monitoring videos into a first type of monitoring videos and a second type of monitoring videos, wherein the first type of monitoring videos are the monitoring videos of the activity track of the first user, and the second type of monitoring videos are the monitoring videos of the activity track of the second user.

In a second aspect, the present application provides an order complaint processing apparatus including modules for executing the method provided in any one of the possible implementations of the first aspect.

In a third aspect, the present application provides an electronic device comprising a memory and a processor. The memory is coupled to the processor. The memory is for storing computer program code comprising computer instructions. The computer instructions, when executed by the processor, cause the electronic device to perform any one of the processing methods for order complaints as provided in the first aspect above.

In a fourth aspect, the present application provides a chip system, which is applied to a processing apparatus for order complaints; the chip system includes one or more interface circuits, and one or more processors. The interface circuit and the processor are interconnected through a line; the interface circuit is configured to receive signals from the memory of the processing device of the order complaint and to send signals to the processor, the signals including computer instructions stored in the memory. The computer instructions, when executed by the processor, cause the electronic device to perform any one of the processing methods for order complaints as provided above in the first aspect.

In a fifth aspect, the present application provides a computer readable storage medium storing computer instructions which, when executed on a computer, cause the computer to perform any one of the methods of processing an order complaint as provided above for the first aspect.

In a sixth aspect, the present application provides a computer program product comprising computer instructions which, when run on a computer, cause the computer to perform any one of the methods of processing an order complaint as provided in the above first aspect.

Reference may be made in detail to the second to sixth aspects and various implementations of the first aspect in this application; moreover, for the beneficial effects of the second aspect to the sixth aspect and various implementation manners thereof, reference may be made to beneficial effect analysis in the first aspect and various implementation manners thereof, and details are not described here.

Drawings

Fig. 1 is a schematic layout diagram of an unmanned shop according to an embodiment of the present application;

fig. 2 is a block diagram of an operation system of an unmanned shop according to an embodiment of the present application;

FIG. 3 is a schematic layout diagram of another unmanned shop according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an activity track provided by an embodiment of the present application;

fig. 5 is a schematic hardware structure diagram of a complaint processing apparatus according to an embodiment of the present application;

fig. 6 is a flowchart of a method for processing an order complaint according to an embodiment of the present application;

fig. 7 is a schematic view of a display interface of a user equipment according to an embodiment of the present application;

fig. 8 is a schematic display interface diagram of another user equipment provided in the embodiment of the present application;

FIG. 9 is a schematic diagram of another activity track provided by embodiments of the present application;

FIG. 10 is a schematic diagram of another activity track provided by embodiments of the present application;

FIG. 11 is a flowchart of another method for processing an order complaint according to an embodiment of the present application;

FIG. 12 is a flowchart of another method for processing an order complaint according to an embodiment of the present application;

FIG. 13 is a schematic illustration of a complaint verification interface provided in accordance with an embodiment of the present application;

FIG. 14 is a schematic illustration of a complaint verification interface provided in accordance with an embodiment of the present application;

fig. 15 is a schematic structural diagram of an order complaint processing device according to an embodiment of the present application.

Detailed Description

In the description of this application, "/" means "or" unless otherwise stated, for example, A/B may mean A or B. "and/or" herein is merely an association describing an associated object, and means that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone.

Further, "at least one" means one or more, "a plurality" means two or more. The terms "first", "second", and the like do not necessarily limit the number and execution order, and the terms "first", "second", and the like do not necessarily limit the difference.

It should be noted that, in the description of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or illustrations. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

In order to improve the processing efficiency of a complaint order of an unmanned store, an embodiment of the application provides an order complaint processing method, which includes the steps of searching relevant behavior event information according to complaint information of an acquired order, determining at least one activity track according to the acquired behavior event information, and finally intercepting a monitoring video for verifying the complaint of the order based on the at least one activity track. Therefore, when the complaint requirement of the order is received, the monitoring video for verifying the complaint of the order can be automatically determined, and the customer service personnel are not required to search a large number of videos, so that the auditing efficiency is improved.

The unmanned stores refer to all or part of operation processes in the stores, intelligent automatic processing is carried out through technical means, and manual intervention is reduced or not existed. The current unmanned stores cover the management of a plurality of types of commodities such as fresh, clothes, daily necessities and the like.

Illustratively, FIG. 1 shows a layout diagram of an unmanned store. As shown in fig. 1, the unmanned store is provided with a store exit, a store entrance, and a commodity area, and the commodity area includes a shelf placement area and a shopping area corresponding to a shelf. The shopping areas corresponding to, for example, the shelves 111 in fig. 1 include area 121 and area 122.

Alternatively, fig. 2 shows a block diagram of an operation system 100 of an unmanned shop, which may further include a monitoring device 130, a weight sensor 140, and a processing device 150. Wherein the monitoring device 130 and the weight sensor 140 are connected to the processing device 150, respectively.

The number of monitoring devices 130 may be plural. For example, the monitoring devices 130 may be disposed in the store-in aisle, the store-out aisle, and the merchandise area shown in fig. 1. After acquiring the in-store surveillance video, the monitoring device 130 may send the surveillance video to the processing apparatus 150. The monitoring device 130 in the commodity area may be set at a reasonable position and angle, so that the monitoring device 130 may capture video information of users in the shopping area. For example, referring to fig. 3, a monitoring device 131, a monitoring device 132, and a monitoring device 133 may be disposed on the shelf 111, and it should be understood that the monitoring device 131, the monitoring device 132, and the monitoring device 133 may capture the shopping behavior of the user in the area 122 shown in fig. 1.

In some embodiments, surveillance videos captured by the surveillance device 130 may be used to track the movement of the same person. The monitoring video captured by the monitoring device 130 may be processed by the monitoring device, and certainly, may also be processed by the processing device 150, which is not limited in this embodiment of the present application.

In an example, taking a monitoring device 130 to process a shot monitoring video as an example, after the monitoring device 131 shown in fig. 3 shoots a person a, the monitoring device 131 identifies the location of the person a at a preset frequency, and records a track point (e.g., the track point in fig. 4) corresponding to the location until the person a leaves the field of view area of the monitoring device 131. As shown in fig. 4, the plurality of track points of the person a acquired by the monitoring device 131 in a certain period of time constitute an activity track of the person a in the field of view of the monitoring device 31 in the certain period of time.

In another example, the processing device 150 processes the captured monitoring video by the monitoring apparatus 130. The processing device 150 may obtain a surveillance video captured by the surveillance equipment 130 at a preset frequency, where the surveillance video includes the person a. The processing device 150 may identify the location of the person a in the surveillance video, and record a track point (for example, the track point in fig. 4) corresponding to the location until the person a is not included in the surveillance video acquired by the processing device 150. As also shown in fig. 4, the plurality of track points recorded by the processing device 150 during a period of time of the person a constitute the moving track of the person a during the period of time in the field of view of the monitoring device 31.

The number of the weight sensors 140 may be plural, and the weight sensors 140 may be provided at plural positions of the shelf shown in fig. 1 or 3. In the process of purchasing, if the user takes or puts back the goods on the shelf, the weight detected by the weight sensor 140 changes, and at this time, the weight sensor 140 may send the detected weight data to the processing device 150, so that the processing device 150 may determine that the user takes or puts back the goods on the shelf according to the received weight data.

The processing device 150 includes a memory 151 and a processor 152.

The memory 151 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

In some embodiments, the memory 151 may be used to store commodity information in the unmanned store, such as commodity type, commodity unit price, and commodity placement position information. In addition, the memory 151 may also be used to store software programs and data. The processor 152 executes various operation processes and data processing of the unmanned shop by executing software programs or data stored in the memory.

Processor 152 may include one or more processing units, such as: the processor 152 may include an Application Processor (AP), a modem processor, a Graphics Processing Unit (GPU), an Image Signal Processor (ISP), a controller, a video codec, a Digital Signal Processor (DSP), a baseband processor, and/or a neural-Network Processing Unit (NPU), among others. The different processing units may be separate devices or may be integrated into one or more processors.

In some embodiments, the processor 151 is configured to receive the relevant data sent by the monitoring device 130 and the weight sensor 140, and process the data to complete the operation process of the unmanned shop. For example, it may generate shopping cart information of the user when the user chooses to purchase, and generate order information of the user for this purchase when the user leaves the store, according to the related data sent by the monitoring device and the weight sensor, in combination with the commodity information stored in the memory.

In addition, although not shown in fig. 1 and 2, a money receiving device, a communication device, and the like may be further provided in the unmanned shop, and a detailed description thereof will be omitted.

The embodiment of the present application also provides an order complaint processing apparatus (hereinafter, referred to simply as a complaint processing apparatus in the embodiment of the present application) which is an electronic device having a data processing capability. For example, the complaint processing device may be a backend server of an unmanned store, or the complaint processing device may be a functional module in the backend server, or the complaint processing device may be any computing device connected to the backend server, and the like. The embodiments of the present application do not limit this. The execution subject of the processing method for order complaint provided by the embodiment of the application is the complaint processing device.

A hardware configuration of the complaint processing apparatus 200 will be described below with reference to fig. 5.

As shown in fig. 5, the complaint processing apparatus 200 includes a processor 210, a communication line 220, and a communication interface 230.

Optionally, the complaint processing apparatus 200 can further include a memory 240. The processor 210, the memory 240 and the communication interface 230 may be connected via a communication line 220.

The processor 210 may be a Central Processing Unit (CPU), a general purpose processor Network (NP), a Digital Signal Processor (DSP), a microprocessor, a microcontroller, a Programmable Logic Device (PLD), or any combination thereof. The processor 201 may also be any other device with processing function, such as a circuit, a device or a software module, without limitation.

In one example, processor 210 may include one or more CPUs, such as CPU0 and CPU1 in fig. 5.

As an alternative implementation, complaint processing apparatus 200 includes a plurality of processors, for example, processor 270 may be included in addition to processor 210. A communication line 220 for transmitting information between the respective components included in the complaint processing apparatus 200.

A communication interface 230 for communicating with other devices or other communication networks. The other communication network may be an ethernet, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), or the like. Communication interface 230 may be a module, circuitry, transceiver, or any device capable of enabling communication.

A memory 240 for storing instructions. Wherein the instructions may be a computer program.

The memory 240 may be a read-only memory (ROM) or another type of static storage device that can store static information and/or instructions, an access memory (RAM) or another type of dynamic storage device that can store information and/or instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or another optical disc storage, an optical disc storage (including a compact disc, a laser disc, an optical disc, a digital versatile disc, a blu-ray disc, etc.), a magnetic disc storage medium or another magnetic storage device, and the like, without limitation.

It should be noted that the memory 240 may exist independently from the processor 210 or may be integrated with the processor 210. The memory 240 may be used for storing instructions or program code or some data or the like. The memory 240 may be located inside the complaint processing apparatus 200, or may be located outside the complaint processing apparatus 200, without limitation.

The processor 210 is configured to execute the instructions stored in the memory 240 to implement the communication method provided by the following embodiments of the present application. For example, when the complaint processing apparatus 200 is a terminal or a chip in a terminal or a system on a chip, the processor 210 can execute instructions stored in the memory 240 to implement the steps performed by the transmitting end in the embodiments described below in the present application.

As an alternative implementation, the complaint processing apparatus 200 further includes an output device 250 and an input device 260. The output device 250 may be a display screen, a speaker, or the like capable of outputting data of the complaint processing apparatus 200 to the user. The input device 260 may be a keyboard, a mouse, a microphone, a joystick, or the like, which can input data to the complaint processing apparatus 200.

As an example, the output device 250 may be configured to output a monitoring video for verifying the order complaint determined according to the above processing method of the order complaint, for being viewed by a worker in charge of verifying the order complaint.

In some of the embodiments of the present application, after a user completes a purchase at an unmanned store, the user may initiate a complaint request for the completed order via the user device. Accordingly, the complaint processing device receives the order complaint request transmitted from the user equipment, and starts to execute the order complaint processing method provided by the present application. The specific process of the user equipment initiating the complaint request may refer to the following description, which is not repeated herein.

Illustratively, the user device may be a cell phone, a tablet, a desktop, a laptop, a handheld computer, a notebook, an ultra-mobile personal computer (UMPC), a netbook, and a terminal device such as a cellular phone, a Personal Digital Assistant (PDA), an Augmented Reality (AR), a Virtual Reality (VR) device. The present disclosure does not particularly limit the specific form of the user equipment. The system can be used for man-machine interaction with a user through one or more modes of a keyboard, a touch pad, a touch screen, a remote controller, voice interaction or handwriting equipment and the like.

The following describes the order complaint processing method provided by the present application in detail with reference to the drawings.

As shown in fig. 6, the present embodiment provides a method for processing an order complaint, which can be optionally executed by the complaint processing apparatus 200 shown in fig. 5, and includes the following steps:

s101, obtaining complaint information of the order. The complaint information includes an identification of the first item and an occurrence period of the order.

The first commodity refers to a commodity which has a fee deduction error condition and is complained by the first user.

It should be understood that the commodity described in the embodiments of the present application refers to an individual item in an unmanned store. It should be understood that when any one of the attributes of the brand, model, configuration, grade, suit, packaging capacity, unit, production date, shelf life, etc. of the commodity is different from the other commodities, it may be referred to as a single commodity. For example, the original canned 330ML beverage a may be referred to as a single serving; and the number of the same single product is one or more.

The identifier of the first commodity is used for uniquely identifying the first commodity. It should be understood that each item in the unmanned store has an identification that uniquely identifies the item. Illustratively, the identification of the first item may be a Stock Keeping Unit (SKU) of the first item, such as "Primary canned 330ML beverage A". Alternatively, a combination of characters or other possible indicia referring to the first item may also be used. For example, the original canned 330ML beverage a may be identified as "BS 10621011300327".

The occurrence time of the order refers to the store-in and store-out time when the first user purchases the order in the unmanned store. Specifically, the complaint processing device may determine the arrival time of the current consumption of the first user as the start time of the occurrence period of the order, and determine the departure time of the current consumption of the first user as the end time of the occurrence period of the order.

Optionally, the complaint processing device may receive an order complaint request sent by the user equipment before the complaint processing device obtains the complaint information of the order.

Illustratively, as shown in FIG. 7, a user of an unmanned store may view an order for a completed transaction on a user device. For example, the user may operate (e.g., click) the display button 71 of the order information interface shown in (a) in fig. 7 to view detailed information such as the item list of the order, unit prices of the respective items, amount of money of each item, and total consumption amount, such as the order detail interface shown in (b) in fig. 7.

Further, if the user wants to initiate a complaint about the order, the complaint button 72 may be operated (e.g., clicked) in the order information interface shown in fig. 8 (a). Further, in response to the user's operation, the user device may display a complaint filling-out interface as shown in (b) of fig. 8, which may include a product selection field 81 and a complaint question field 82 as shown in fig. 8. The goods selection column 81 includes the goods list of the order, so that the user can select the goods with wrong fee deduction in the goods selection column 82 and select the complaint question in the complaint column 82, wherein the complaint question includes wrong deduction, more deductions, less deductions and the like.

For example, if the user 1 actually purchases item 1 and the item recorded in the order is item 2, the user may select "make a mistake". For another example, if the user 1 actually purchases 1

item

1, and 2 items 1 are recorded in the order, or 1

item

1 and 1 item 2 are recorded in the order, the user may select "multi-discount". For another example, if the user 1 actually purchases 2

items

1 and 1 item 1 is recorded in the order, the user may select "discount.

Further, after completion of the complaint fill-out, the user may click on the "confirm" button 83. At this time, in response to the user's operation of clicking the completion button 83, the user equipment can transmit the order complaint request to the complaint processing apparatus. Accordingly, the complaint processing means can receive the order complaint request sent by the user equipment.

It should be understood that the order complaint request received by the complaint processing means may include the item name of the first item and the complaint question.

Optionally, the order complaint request may also carry an order identifier of the order and a user identifier corresponding to the user.

The order identification is used for identifying the order and has uniqueness. When a user enters the unmanned store, the operation system of the unmanned store generates a new order identification according to the received monitoring video of the store entrance channel, and the new order identification is used for identifying the order of the user for purchasing this time. It should be understood that, if the user enters the unmanned store and does not consume, the operation system of the unmanned store will still generate a new order identifier for identifying the blank order that is not consumed by the user this time.

The user identifier is used for identifying the user, and has uniqueness. When a user enters the unmanned store, the operation system of the unmanned store generates a new user identifier for the user according to the received monitoring video of the store-entering passage, and it should be understood that the user identifier and the order identifier have a one-to-one correspondence relationship. And for the same user, the operation system of the unmanned store generates a new user identification and a new order identification every time the user enters the unmanned store.

Optionally, after receiving the order complaint request sent by the user equipment, the complaint processing device may obtain complaint information of the order according to the order complaint request.

Specifically, the complaint processing device may obtain the order information of the order according to the order identifier or the user identifier, and further obtain the occurrence time period of the order. The complaint processing device may search for the product information of the first product based on the product name of the first product in the order complaint request, and may obtain the identifier of the first product.

It should be understood that the complaint processing device may store therein the order information of all orders in the near future of the unmanned store, or the complaint processing device may acquire the order information of all orders in the near future of the unmanned store from a back-office server of the unmanned store. The order information of an order may include an identifier of the order, an identifier of the user, an occurrence period of the order, a commodity list, a consumption amount, and the like.

The complaint processing device may store commodity information of commodities owned by the unmanned store, or the complaint processing device may acquire commodity information of commodities owned by the unmanned store from a backend server of the unmanned store. Therefore, the complaint processing apparatus can find the identification of the first commodity in the operation system of the unmanned shop. The commodity information of a commodity may include commodity identification, unit price, stock quantity, brand, model, configuration, grade, flower color, packaging capacity, unit, production date, shelf life and the like of the commodity.

Therefore, the complaint processing device can acquire the order information of the order and further determine the occurrence period of the order. The complaint processing device may acquire product information of the first product and may specify the identification of the first product.

S102, according to the identification of the first commodity, determining the behavior event information of taking/putting the first commodity in a first preset time period including the occurrence time period.

The first commodity is taken up from the shelf, and the first commodity is put back to the shelf. In the embodiment of the present application, one pick/place of an article is referred to as one action event of the article.

The processing means of the operating system may record event information for the behavioural event each time the weight detected by the weight sensor changes. The event information of a behavior event may include a placement location of a commodity, an event type (pick or place), a commodity identifier, and an event occurrence time.

For example, the event information that a1 can of original flavored canned 330ML beverage a is picked up from the shelf may be: 050301 BS10621011300327 takes 2022/2/1210: 01: 00. 050301 indicates a 01-row goods space on shelf 03 of unmanned store. Optionally, the operation system of the unmanned store may record position information corresponding to each cargo space, for example, the position coordinates of the deck 03 layer 01 cargo space on the 05 shelf may be (5.3,6.2, 1.5).

Therefore, the above-mentioned taking/placing behavior event information of the first article may include a first time when the first article is taken/placed and a first location of the first article, where the first location is a placement location of the first article in the unmanned store.

In addition, the first preset time period includes an occurrence time period of the order. For example, the first preset time period may be an occurrence time period of the order, or a start time of the first preset time period may be before a start time of the order and an end time of the first preset time period may be after an end time of the order.

For example, if the order occurs in a period of time from 2022/2/1210: 00 to 2022/2/1210: 05, the first predetermined period of time may be 2022/2/1210: 00 to 2022/2/1210: 05, or the starting time of the first predetermined period of time may be (2022/2/1210: 00 minus the predetermined duration) to (2022/2/1210: 05 plus the predetermined duration).

The preset time period may be 40 seconds, 50 seconds, 60 seconds, or other reasonable time period.

It should be understood that the operation system of the unmanned shop may have detection errors, which may cause detection errors of a plurality of pick-and-place events that are close in time, and the detection errors of the operation system of the unmanned shop may occur in a plurality of pick-and-place events whose occurrence time interval is less than or equal to a preset time length. For example, the preset time period may be determined by the processing device integrating all detection errors of the unmanned shop according to the time interval between the occurrence times of the picking/placing events of the detection errors.

Alternatively, the complaint processing means may acquire event information of all the behavioral events within a first preset time period. And then according to the identification of the first commodity, searching the behavior event information of the first commodity in the behavior event information of all the fetching/placing events in the first preset time period.

It should be noted that, since the first product is a product that is determined by the user and has a fee deduction error, the action event of taking/placing the first product is the action event most related to the order complaint. And, the action event of taking/placing the first commodity may occur within a preset time before or after the occurrence time of the order, and since the operation system of the unmanned shop may have a case that a plurality of taking/placing events near the time are detected incorrectly, the action event of taking/placing the first commodity is also the action event most related to the order complaint. Therefore, the complaint processing means may first determine the action event information of taking/putting the first commodity within the first preset period.

Optionally, the complaint processing device may determine at least one behavior event for picking up/placing the first commodity from all behavior events for picking up/placing the first commodity within a first preset time period, and further determine behavior event information of the at least one behavior event. It should be understood that, when the determined event is a behavior event for picking up/placing a first commodity, the behavior event information includes a first time and a first location, when the determined event is a plurality of behavior events for picking up/placing the first commodity, the first times are a plurality of first locations, and the first time corresponds to one first location, it can be understood that the number of the first commodities in the unmanned store is a plurality, so that the behavior event for picking up/placing the first commodity can occur a plurality of times within a period of time; when the number of the first commodity is 1, a behavior event of taking/putting the first commodity for a plurality of times can also occur within a period of time.

The following describes, in each case, determining at least one behavior event for picking/placing the first commodity from all behavior events for picking/placing the first commodity in a first preset time period by the complaint processing device, and further determining behavior event information of the at least one behavior event:

the first situation is as follows: in the case that only the commodity identifier of one action event is the identifier of the first commodity among all the action events in the first preset time period of the order, the complaint processing device may determine the action event as the action event for taking/placing the first commodity in the first preset time period of the order, and further determine corresponding event information.

For example, assuming that the first preset time period of the order is 2022/2/1210: 00 to 2022/2/1210: 05, referring to table 1, table 1 shows all behavioral event information within the time period, including behavioral event information of behavioral event 1 and behavioral event information of behavioral event 2. If the first commodity is the original canned 330ML beverage a and the identifier of the first commodity is BS10621011300327, the complaint processing device may determine that the behavior event 1 is a behavior event for taking/placing the first commodity within a first preset time period based on table 1. Thus, the first moment is 2022/2/1210: 01:00 and the first position is the position corresponding to the cargo space designated 050301.

TABLE 1

Behavioral events	Placing position	Commodity identification	Event type	Time of occurrence of event
					Behavioral event
1	050301	BS10621011300327	Get the	2022/2/12 10:01:00
					Behavioral event 2	050250	NFSQ633018211583	Get the	2022/2/12 10:01:25

Case two: in the case that the product identifiers of the multiple behavior events are the identifiers of the first product in all the behavior events in the first preset time period of the order, the complaint processing device may determine all the multiple behavior events as the behavior events for taking/placing the first product in the first preset time period of the order, and further determine corresponding event information.

Illustratively, the first preset time period of the order is 2022/2/1210: 00 to 2022/2/1210: 05, referring to table 2, table 2 shows all behavioral event information within the time period, including behavioral event information of behavioral event 1, behavioral event information of behavioral event 2, and behavioral event information of behavioral event 3. If the first commodity is the original canned 330ML beverage a and the identifier of the first commodity is BS10621011300327, the complaint processing apparatus may determine the behavior event 1 and the behavior event 3 as behavior events for taking/placing the first commodity within the first preset time period based on table 2. Thus, the first time is 2022/2/1210: 01:00 and 2022/2/1210: 01:25, and the first position is a position corresponding to the 050301 cargo space and a position corresponding to the 050302 cargo space.

TABLE 2

Behavioral events	Placing position	Commodity identification	Event type	Time of occurrence of event
					Behavioral event
1	050301	BS10621011300327	Get	2022/2/12 10:01:00
					Behavioral event 2	050250	NFSQ633018211583	Get	2022/2/12 10:01:25
Action event 3	050302	BS10621011300327	Get the	2022/2/12 10:01:25

And S103, determining a first group of activity tracks according to the behavior event information.

And the first group of activity tracks comprise activity tracks acquired by monitoring equipment used for monitoring the first position in a second preset time period.

The second preset time period is a time period with the duration being a preset duration and including the first moment. Wherein the preset time period may be 40 seconds, 50 seconds, 60 seconds or other reasonable time period. The description of the preset duration may refer to the description of the preset duration in step S102, and is not repeated here.

Optionally, the second preset time period may be a time period with the first time as a middle time and the duration as a preset time. For example, assuming that the first time is 2022/2/1210: 01:00 and the preset time period is 60 seconds, the first preset time period is 2022/2/1210: 00:30 to 2022/2/1210: 01: 30.

It should be understood that the first time may be one or more times, and the second preset time period may be one or more time periods determined according to the first time. Optionally, the second preset time period may be the same as the first preset time period, or may be different from the first preset time period.

The first set of activity tracks is activity tracks associated with the order complaint. As can be seen from the above description of the monitoring device of the unmanned shop, the monitoring device may generate an activity track as shown in fig. 4 for persons present in the field of view. It should be appreciated that, when a user completes a purchase process in an unmanned store, the user may be present in the field of view of a plurality of monitoring devices, and the plurality of monitoring devices respectively generate an activity track of the user. Optionally, the monitoring device may also generate a unique track identifier for each activity track.

The complaint processing means may determine the first set of activity traces from the behavioural event information.

The first group of activity tracks comprise a plurality of activity tracks acquired by monitoring equipment used for monitoring the first position in the unmanned store in a second preset time period. Optionally, the monitoring device installed in the unmanned store has a corresponding relationship with the cargo space in the unmanned store, and one monitoring device may be used to monitor the positions of a plurality of cargo spaces located within the field of view of the monitoring device.

The complaint processing means may obtain, according to the first location, all activity tracks generated by the monitoring device for monitoring the first location within a second preset time period, and determine them as the first group of activity tracks.

Optionally, if one of the activity tracks includes a plurality of track points acquired by the monitoring device in the second preset time period and a plurality of track points acquired by the monitoring device in other time periods except the first preset time period, the complaint processing device may intercept a sub-activity track composed of the plurality of track points acquired in the second preset time period, and divide the sub-activity track into the first group of activity tracks.

Illustratively, if the second predetermined period of time is from 2022/2/1210: 00:30 to 2022/2/1210: 01: 30. As shown in fig. 9, the monitoring device finds two active tracks, track 1 and track 2, according to a second preset time period. If the acquisition period of the track 1 is 2022/2/1210: 00:56 to 2022/2/1210: 01:05, the acquisition period of the track 2 is 2022/2/1210: 00:20 to 2022/2/1210: 01: 35. It can be seen that the second preset period completely comprises the acquisition period of trajectory 1. In addition, the point a in the track 2 is the track point acquired by the monitoring device at 2022/2/1210: 01:20, and the point B is the track point acquired by the monitoring device at 2022/2/1210: 01:30, that is, the first time period is the time period for acquiring the track of the segment AB. Thus, the complaint handling means may determine the AB segment in trace 1 and trace 2 as the first set of active traces.

It is noted that the first set of activity tracks may include one or more activity tracks of the first user. The first user is the user who initiated the order complaint. In addition, within the first preset time period, if the second user is moving near the first position, the first set of activity tracks may further include one or more activity tracks of the second user. Wherein the second user is a different user than the first user, and the first set of activity tracks may include activity tracks of one or more second users.

And S104, determining a first target activity track in the first group of activity tracks.

Further, the complaint processing means may determine at least one activity trace among the first set of activity traces as a first target activity trace.

In one implementation, the complaint processing means may determine all of the activity traces in the first set of activity traces as the first target activity trace.

In another implementation, the complaint processing means may determine a partial activity track of the first set of activity tracks as the first target activity track.

Alternatively, the complaint processing means may determine a first distance between the first set of activity traces and the first location. Further, the complaint processing device may derive the first target motion trajectory from the first set of motion trajectories according to the first distance.

Optionally, the complaint processing device may sort each of the first group of motion trajectories according to a first distance from small to large, and determine the first N motion trajectories in the first group of motion trajectories as the at least one motion trajectory. Wherein N is a positive integer.

For example, for an active track 1 in the first set of active tracks, the complaint processing means may first determine the distance between a track point m in the active track 1 and the first position based on equation (1):

wherein, a _n The distance between a track point m and a first position is represented, and the position coordinate of the track point m is (x) _m ，y _m ，z _m ) The position coordinate of the first position is (x) ₁ ，y ₁ ，z ₁ )。

Then, the complaint processing means can calculate the distance between the activity track 1 and the first position by equation (2):

wherein S is ₁ Represents the distance, a, between the moving track 1 and the first position ₁ 、a ₂ 、…、a _n The distance between all track points in the movable track 1 and the first position is shown, and n represents the number of the track points in the movable track 1.

Thus, the complaint processing means can determine a first distance between each of the trajectories in the first group to the first position based on equation 1 and equation 2. Optionally, for any one of the first set of motion trajectories, the complaint processing device may respectively calculate a distance between each trajectory point in the any one of the motion trajectories and the first position according to formula (1), and determine an average distance between each trajectory point and the first position as the first distance between the any one of the motion trajectories and the first position according to formula (2).

Further, after obtaining the first distance between each of the first group of activity tracks and the first position, the complaint processing device may sort the first group of activity tracks according to the first distance from small to large, and determine the activity track N before the sorting as the activity track related to the order according to the sorting result.

Illustratively, if the first set of activity traces is shown in fig. 10, the first set of activity traces includes trace a1, trace a2, trace a3, trace a4, trace a5 and trace a6, and the distances from trace a1, trace a2, trace a3, trace a4, trace a5 and trace a6 to the first location are 1.23 meters, 1.12 meters, 0.30 meters, 0.21 meters, 0.92 meters and 0.80 meters, respectively. Therefore, the first group of active tracks are sorted according to the first distance from small to large, and the sorting result is track a4, track a3, track a6, track a5, track a2 and track a 1. If the value of N is 2, the complaint processing means may determine the trajectory a4 and the trajectory a3 as the activity trajectories related to the order complaint.

It should be noted that the first distance may be used to indicate a degree of correlation between each activity track in the first group of activity tracks and an action event of taking/placing the first product within the order occurrence period. The smaller the first distance is, the closer the person to which the activity track belongs is to the first position of the first commodity in the first preset time period is, and the more relevant the activity track is to the behavior event.

And S105, acquiring a monitoring video of the first target activity track, wherein the monitoring video is used for verifying the order complaint.

For any one of the first target activity tracks, the complaint processing device may intercept a section of monitoring video including a corresponding activity track from the complete monitoring video of the monitoring device according to the monitoring device to which the activity track belongs, and the section of monitoring video may be used to verify a complaint of the order.

It should be understood that the memory of the unmanned store or the backend management server of the unmanned store may have stored therein the complete surveillance video in the unmanned store for a recent period of time.

Based on the order complaint processing method, when a complaint request of an order is received, complaint information of the order is obtained, behavior event information related to complaint commodities of the order is determined according to the complaint information of the order, a first target activity track related to the complaint of the order is determined according to the behavior event information, further the behavior event information of the order and at least one related activity track are determined, and finally a monitoring video for verifying the complaint of the order is intercepted according to the at least one related activity track and the first target activity track. Since the first target activity track is associated with the order complaint, the surveillance video of the first target activity track is also associated with the order complaint, and thus the surveillance video of the first target activity track can be used to verify the order complaint.

It will be appreciated that the above-described method can automatically capture surveillance video associated with an order complaint for use in verifying the order complaint during processing of the order complaint. Therefore, the method is different from the mode of manually searching the relevant monitoring of the order complaint in a large amount of videos by the existing customer service personnel, a large amount of manpower can be saved, the time of searching the videos can be saved, the method is more convenient and quicker, and the order auditing efficiency is improved. .

In some embodiments, based on the order complaint processing method shown in fig. 6, as shown in fig. 11, the method may further include:

and S106, determining the associated event information according to the first moment.

The related event information comprises a second time for taking/placing other commodities except the first commodity in the store and second positions of the other commodities in a third preset time period, wherein the third preset time period comprises the first time.

The third preset time period is a time period with the duration being a preset duration and including the first moment. Wherein the preset time period may be 40 seconds, 50 seconds, 60 seconds or other reasonable time period. The description of the preset duration may refer to the description of the preset duration in step S102, and is not described herein again. It should be understood that the third preset time period may be the same as the second preset time period or different from the second preset time period.

It should be understood that the related events refer to one or more action events in the store within the third preset time period, except for the action event of taking/placing the first commodity. The associated event information thus includes a second time and a second location. The second time is the event occurrence time of the associated event information, and the second position is the placement position of the commodity included in the associated event information. Also, the complaint processing means may determine at least one associated event. Therefore, there may be only one or a plurality of second time points in the related event information of the at least one related event. Of course, there may be only one or a plurality of second positions in the associated event information of the at least one associated event. It is to be understood that a second time corresponds to only one second location, and that a second time and a second location having a correspondence correspond to one associated event.

It should be noted that, in the operation system of the unmanned store, two pick/place events with similar time may be mixed up, and thus, the order may be mistakenly deducted. The related event is a behavior event related to the behavior event of taking/placing the first commodity, and therefore, the related event is also a behavior event related to the order complaint. Therefore, after determining the action event of taking/placing the first commodity in the third preset time period, the complaint processing device can further determine the related associated event.

In this way, the complaint processing means may determine the action event other than the action event of the first commodity in the third preset time period as the related event.

Illustratively, if the third preset time period determined by the complaint processing means is 2022/2/1210: 00:30 to 2022/2/1210: 01:30, referring to table 1, table 1 shows all behavioral event information within the time period, including behavioral event information of behavioral event 1 and behavioral event information of behavioral event 2. If the action event 1 is an action event of taking/placing the first commodity determined by the complaint processing means, the action event 2 is of the second commodity. The complaint handling means can determine event 2 as a correlated event. Therefore, the second time is 2022/2/1210: 01:25, and the second position is 050250 cargo space.

In some embodiments, the complaint processing apparatus can also determine the associated event information based on the first time and the first location.

It should be understood that the operation system of the unmanned store has a higher possibility of detecting the picking/placing events of the commodities close to each other, and therefore, the picking/placing events of the commodities close to the first position are action events with higher relevance to the order complaint.

Optionally, when determining one or more behavior events other than the behavior event of the first commodity in the third preset time period, the complaint processing device may further take a behavior event with a position close to the first position as an associated event according to a position included in each event information in the one or more behavior events.

For example, after the complaint processing device determines the commodity position related to each event according to one or more behavioral events except the behavioral event of the first commodity in the third preset time period, the complaint processing device may determine the correlated event according to the behavioral event indicating that the commodity position is on the same shelf as the shelf where the first commodity is located. If the first position is a position corresponding to the 050301 location, and 050301 indicates a 01-tier shelf on shelf 03 of an unmanned store, the location of the first goods is the same as the shelf where the location of the first goods is located, for example, 050122, 050209, and so on.

Alternatively, after the complaint processing means performs one or more behavioral events other than the behavioral event of the first commodity within the third preset time period, the complaint processing means may calculate a distance between the position included in each of the one or more behavioral events and the first position, and determine a behavioral event less than or equal to the preset distance as the related event. The preset distance may be 5 meters, 6 meters, or other reasonable distance.

As can be seen from the description about the cargo space in step S102, the operation system of the unmanned shop may record the position information corresponding to each cargo space, such as the position coordinates (5.3,6.2, 1.5). Therefore, the complaint processing device can determine the position coordinates of the commodity related to each action event according to the event information of the one or more action events. Therefore, the complaint processing device can calculate the distance between the position of the commodity related to each behavior event and the first position based on the position coordinates.

Further, the complaint processing means may determine 0 related events if all the behavior events occurring in the unmanned shop within the third preset time period are behavior events for picking/placing the first commodity.

In some embodiments, if the complaint processing means determines 0 associated events, the complaint processing means does not need to execute step S107 described below, in which case 0 activity trace is included in the second set of activity traces.

And S107, determining a second group of activity tracks according to the associated event information.

The second group of activity tracks comprise a plurality of activity tracks acquired by monitoring equipment for monitoring the second position within a fourth preset time period; the second preset time period includes a second time instant.

The third preset time period is a time period with the duration being a preset duration and including the second moment. Wherein the preset time period may be 40 seconds, 50 seconds, 60 seconds or other reasonable time period. The description of the preset duration may refer to the description of the preset duration in step S102, and is not repeated here.

The complaint processing device may obtain, according to the second location, all activity tracks generated by the monitoring apparatus for monitoring the second location within a fourth preset time period, and determine them as the second group of activity tracks. For a detailed process, in step 103, the complaint processing device obtains all activity tracks generated by the monitoring device for monitoring the first location within the second preset time period according to the first location, and determines a description of the first group of activity tracks, which is not described again.

It should be understood that the second set of activity tracks may likewise include one or more activity tracks of the first user, and may also include one or more activity tracks of the second user.

And S108, determining a second target activity track in the second group of activity tracks.

Further, the complaint processing means may determine at least one of the activity traces in the second set of activity traces as a second target activity trace.

In one implementation, the complaint processing means may determine all of the activity traces in the second set of activity traces as the second target activity trace.

In another implementation, the complaint processing means may determine a portion of the activity traces in the first set of activity traces as the at least one activity trace.

Alternatively, the complaint processing means may determine a first distance between the second set of motion trajectories and the second location. Further, the complaint processing device may derive the second target motion trajectory from the first set of motion trajectories according to the second distance.

Optionally, the complaint processing device may sort each of the second group of motion trajectories from small to large according to the second distance, and determine the motion trajectory M before the sorting in the second group of motion trajectories as the second target motion trajectory. Wherein M is a positive integer. It should be understood that M may or may not be equal to N in step S104.

For example, for any of the second set of motion tracks, the complaint processing device may respectively calculate the distances between all the track points in the motion track and the second position according to formula (1), and then determine the average distance between all the track points and the second position as the second distance between the motion track and the second position according to formula (2).

Further, after obtaining a second distance between each of the second group of activity tracks and the second position, the complaint processing device may sort the second group of activity tracks from small to large according to the second distance, and determine the top M activity tracks as the activity tracks related to the order according to the sorting result.

It should be noted that the second distance may be used to indicate the degree of correlation between each activity track in the second set of activity tracks and the associated event. The smaller the second distance is, the closer the person to which the activity track belongs is to the second position of the second commodity within the second preset time period is, and the more relevant the activity track is to the associated event.

And S109, acquiring a monitoring video of the second target activity track, wherein the monitoring video is used for verifying order complaints. For any one of the second target activity tracks, the complaint processing device may intercept a section of monitoring video including a corresponding activity track from the complete monitoring video of the monitoring device according to the monitoring device to which the activity track belongs, and the section of monitoring video may be used to verify a complaint of the order.

It should be understood that the memory of the unmanned store or the background management server of the unmanned store may have stored therein the complete surveillance video for a recent period of time within the unmanned store.

It can be understood that the related event is a behavior event related to a behavior event of taking/placing a first commodity within a first preset time period, and since an operation system of the unmanned store may confuse two taking/placing events with similar time, a situation that an order is mistakenly deducted occurs, the related event is also a behavior event related to the order complaint. Therefore, the second group of activity tracks determined according to the correlated events are also the activity tracks related to the order complaints, so that the monitoring videos of the second group of activity tracks can also be used for verifying the order complaints, and thus, the related monitoring for verifying the order complaints can be more comprehensive, and the accuracy of the verification of the order complaints can be improved.

Optionally, based on the processing method of the order complaint, as shown in fig. 12, the method further includes the following steps:

s201, acquiring a monitoring video for verifying order complaints.

Optionally, the monitoring video for verifying the order complaint includes a monitoring video of the first target activity track. Or the monitoring videos for verifying the order complaints comprise the monitoring video of the first target activity track and the monitoring video of the second target activity track.

Optionally, for specific steps of the order complaint apparatus acquiring the monitoring video of the first target activity track and acquiring the monitoring video of the second target activity track, reference may be made to the related description of steps S101 to S109, which is not described herein again.

And S202, outputting a monitoring video for verifying the order complaint.

It should be appreciated that the order complaint means may output a surveillance video of the first target activity track. Alternatively, the order complaint device may output the monitoring video of the first target activity track and the monitoring video of the second target activity track. The following describes step S202 in detail by using the order complaint device to output the monitoring video of the first target activity track and the monitoring video of the second target activity track.

Optionally, after obtaining the instruction for order complaint verification, the complaint processing device may output the obtained monitoring video through an output device 250 (e.g., a display) shown in fig. 5 for viewing by a worker in charge of order complaint verification.

Optionally, the complaint processing device may output the output monitoring video according to the sizes of the first distance and the second distance and the priorities of the first distance and the second distance. Wherein the first distance has a higher priority than the second distance.

That is, the monitoring video determined according to the first target activity track is output first, and then the monitoring video determined according to the second target activity track is output. For the monitoring video determined according to the first target activity track, the monitoring video of the activity track with the first short distance is output firstly, and then the monitoring video of the activity track with the long distance is output. And the monitoring video determined by the second target activity track is the same as the monitoring video.

It should be noted that the monitor video a4 and the monitor video a3 are videos determined based on the action event information of the first commodity taken/placed during the order occurrence time period, and because the action event is the most relevant taking/placing event to the complaint of the current order, the degree of relevance between the monitor video a4 and the monitor video a3 to the complaint of the current order is higher. In addition, the smaller the first distance, the closer the explaining person is to the first commodity, the more relevant the activity track is to the behavior event, and thus the more relevant the monitoring video of the activity track is to the order complaint. Correspondingly, the smaller the second distance is, the more relevant the monitoring video of the activity track is to the order complaint.

Therefore, the monitoring video more relevant to the order complaint at this time can be firstly checked by the staff in charge of verifying the order complaint, and the activity process of the user corresponding to the deduction error of the complaint at this time is more likely to be recorded in the monitoring video. Therefore, the auditing efficiency can be improved.

Illustratively, if the first target activity track includes a track a4, a track a3, and the second target activity track includes a track b1 and a track b2, the obtained surveillance videos include a surveillance video a4, a surveillance video a3, a surveillance video b1, and a surveillance video b 2.

If the first distance between the track a4 and the first position is smaller than the first distance between the track a3 and the first position, and the second distance between the track b2 and the second position is smaller than the second distance between the track b1 and the second position, the sequencing result of the surveillance videos is: surveillance video a4, surveillance video a3, surveillance video b2, and surveillance video b 1.

Therefore, referring to fig. 13, the sequencing result of the monitoring video may be: surveillance video a4, surveillance video a3, surveillance video b2, and surveillance video b 1.

As shown in fig. 13, the complaint processing device may output information on order complaints such as details of orders and causes of complaints.

In some embodiments, face and body feature analysis may be performed on the obtained monitoring videos to determine whether all the people in the monitoring videos are the same user. When the obtained monitoring videos are different users, the monitoring videos can be classified, and the monitoring videos of the same user are classified into the same type of monitoring videos.

Optionally, the complaint processing device may perform face recognition on the surveillance video of the first target activity track and the surveillance video of the second target activity track, respectively, and determine a user to which each activity track belongs. And under the condition that the users to which the activity track belongs comprise a first user and a second user, the monitoring videos are divided into a first type of monitoring videos and a second type of monitoring videos.

The first type of monitoring video is a monitoring video of an activity track of a first user, and the second type of monitoring video is a monitoring video of an activity track of a second user. And, the second user is another user different from the first user.

For example, if it is recognized that the person in surveillance video a4, surveillance video a3, and surveillance video b1 are the same user and the person in surveillance video b2 is another user, as shown in fig. 14, the characters "user 1" may be labeled for surveillance video a4, surveillance video a3, and surveillance video b1, and the characters "user 2" may be labeled for surveillance video b 2.

In some embodiments, the complaint processing means may output order information associated with the order.

The associated order may be another order corresponding to the at least one activity track.

For example, if the first user actually purchases the second product, the product recorded in the order is the first product. The order complaint at this point may relate to another order, which the second user who purchased may intend to pick up the first item, but recorded in the second user's order (i.e., the other order). In this case, the order of the second user is the related order. And the monitoring video of each activity track in the at least one activity track can also be used for correcting the fee deduction error of the first commodity in the associated order.

The scheme provided by the embodiment of the application is mainly introduced from the perspective of a method. To implement the above functions, it includes hardware structures and/or software modules for performing the respective functions. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

As shown in fig. 15, a schematic structural diagram of an order complaint processing device 300 according to an embodiment of the present invention is further provided. The apparatus 300 may include: an information acquisition module 301, an information processing module 302, and a video acquisition module 303. Optionally, the apparatus 300 may include an identification module 304.

The information obtaining module 301 is configured to obtain complaint information of the order, where the complaint information includes an identifier of the first product and an occurrence time period of the order.

The information processing module 302 is configured to determine, according to the identifier of the first commodity, behavior event information of taking/placing the first commodity within a first preset time period including an occurrence time period, where the behavior event information includes a first time of taking/placing the first commodity and a first position of the first commodity.

The information processing module 302 is further configured to determine a first set of activity tracks according to the behavior event information; the first group of activity tracks comprise activity tracks acquired by monitoring equipment used for monitoring the first position in a second preset time period; the second preset period includes the first time.

The information processing module 302 is further configured to determine a first target activity track in the first set of activity tracks.

The video obtaining module 303 is configured to obtain a monitoring video of the first target activity track, where the monitoring video is used to verify an order complaint.

In a possible implementation manner, the information processing module 302 is specifically configured to: determining a first distance between each of the first set of motion trajectories and the first location; a first target activity track is determined in the first set of activity tracks based on the first distance.

In another possible implementation manner, the information processing module 302 is specifically configured to: sorting the first group of active tracks from small to large according to the first distance to obtain a sorting result of the first group of active tracks; and determining the first N active tracks in the sequencing result as first target active tracks, wherein N is a positive integer.

In another possible implementation manner, the information processing module 302 is further configured to: and determining associated event information according to the first time, wherein the associated event information comprises a second time for taking/placing other commodities except the first commodity in the store and second positions of the other commodities in a third preset time period, and the third preset time period comprises the first time. Determining a second group of activity tracks according to the associated event information; the second group of activity tracks comprise a plurality of activity tracks acquired by monitoring equipment for monitoring the second position within a fourth preset time period; the second preset time period includes a second time instant. And determining a second target activity track in the second set of activity tracks. The video obtaining module 303 is further configured to obtain a monitoring video of the second target activity track, where the monitoring video is used to verify the order complaint.

In another possible implementation manner, the information processing module 303 is specifically configured to: determining a second distance between each of the second set of motion trajectories and the second location; and determining a second target activity track in the second set of activity tracks according to the second distance.

In yet another possible implementation manner, the processing apparatus 300 for order complaints further includes a recognition module 304, where the recognition module 304 is configured to perform face recognition on the surveillance video of the first target activity track and the surveillance video of the second target activity track, respectively, and determine a user to which each activity track belongs. The information processing module 303 is further configured to, when the user to which each activity track belongs includes a first user and a second user, divide the surveillance videos into a first type of surveillance video and a second type of surveillance video, where the first type of surveillance video is a surveillance video of the activity track of the first user, and the second type of surveillance video is a surveillance video of the activity track of the second user.

For the detailed description of the above alternative modes, reference may be made to the foregoing method embodiments, which are not described herein again. In addition, for the explanation and the description of the beneficial effects of any of the order complaints provided above, reference may be made to the corresponding method embodiment, which is not repeated herein.

As an example, in connection with fig. 5, the functions implemented by the information processing module 302 in the processing apparatus of the order complaint can be implemented by the processor 210 or the processor 270 in fig. 5 executing the program code in the memory 240 in fig. 5. The functions implemented by the information acquisition module 301 and the video acquisition module 303 can be implemented by the communication line 220 in fig. 5. Video output module 304 may be implemented by output device 260 of fig. 5, although is not limited thereto.

Those of skill in the art would readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It should be noted that the division of the modules in fig. 15 is schematic, and is only one logic function division, and there may be another division manner in actual implementation. For example, two or more functions may also be integrated in one processing module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

The embodiment of the present application further provides a computer-readable storage medium, which includes computer-executable instructions, and when the computer-readable storage medium is run on a computer, the computer is caused to execute any one of the methods provided by the above embodiments. For example, one or more features of S101-S105 in FIG. 6 may be undertaken by one or more computer-executable instructions stored in the computer-readable storage medium.

Embodiments of the present application further provide a computer program product containing instructions for executing a computer, which when executed on a computer, causes the computer to perform any one of the methods provided in the foregoing embodiments.

An embodiment of the present application further provides a chip, including: a processor coupled to the memory through the interface, and an interface, when the processor executes the computer program or the computer execution instructions in the memory, the processor causes any one of the methods provided by the above embodiments to be performed.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The processes or functions according to the embodiments of the present application are generated in whole or in part when the computer-executable instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). Computer-readable storage media can be any available media that can be accessed by a computer or can comprise one or more data storage devices, such as servers, data centers, and the like, that can be integrated with the media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.

The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for processing an order complaint, comprising:

obtaining complaint information of an order, wherein the complaint information comprises an identifier of a first commodity and an occurrence time period of the order;

determining behavior event information of taking/placing the first commodity in a first preset time period including the occurrence time period according to the identifier of the first commodity, wherein the behavior event information comprises a first moment of taking/placing the first commodity and a first position of the first commodity;

determining a first set of activity trajectories according to the behavioral event information; the first group of activity tracks comprise activity tracks acquired by monitoring equipment used for monitoring the first position within a second preset time period; the second preset time period comprises the first moment;

determining a first target activity track in the first set of activity tracks;

and acquiring a monitoring video of the first target activity track, wherein the monitoring video is used for verifying the order complaint.

2. The method of claim 1, wherein determining a first target activity track in the first set of activity tracks comprises:

determining a first distance between each of the first set of motion trajectories and the first location;

determining the first target activity track in the first set of activity tracks according to the first distance.

3. The method of claim 2, wherein determining the first target activity track in the first set of activity tracks based on the first distance comprises:

sorting the first group of active tracks from small to large according to the first distance to obtain a sorting result of the first group of active tracks;

and determining the first N active tracks in the sequencing result as the first target active tracks, wherein N is a positive integer.

4. The method according to any one of claims 1 to 3, further comprising:

determining associated event information according to the first time, wherein the associated event information comprises a second time for taking/placing other commodities except the first commodity in the store and a second position of the other commodities in a third preset time period, and the third preset time period comprises the first time;

determining a second group of activity tracks according to the associated event information; the second group of activity tracks comprise a plurality of activity tracks acquired by monitoring equipment for monitoring the second position within a fourth preset time period; the second preset time period comprises the second moment;

determining a second target activity track in the second set of activity tracks;

and acquiring a monitoring video of the second target activity track, wherein the monitoring video is used for verifying the order complaint.

5. The method of claim 4, wherein determining a second target activity track in the second set of activity tracks comprises:

determining a second distance between each of the second set of motion trajectories and the second location;

and determining the second target activity track in the second group of activity tracks according to the second distance.

6. The method of claim 4,

respectively carrying out face recognition on the monitoring video of the first target activity track and the monitoring video of the second target activity track, and determining a user to which each activity track belongs;

and under the condition that the user to which each activity track belongs comprises a first user and a second user, dividing the monitoring videos into a first type of monitoring videos and a second type of monitoring videos, wherein the first type of monitoring videos are monitoring videos of the activity track of the first user, and the second type of monitoring videos are monitoring videos of the activity track of the second user.

7. An order complaint processing apparatus, characterized in that the apparatus comprises:

the information acquisition module is used for acquiring complaint information of the order, wherein the complaint information comprises an identifier of the first commodity and an occurrence time period of the order;

the information processing module is used for determining behavior event information of taking/placing the first commodity in a first preset time period including the occurrence time period according to the identification of the first commodity, wherein the behavior event information comprises a first moment of taking/placing the first commodity and a first position of the first commodity;

the information processing module is further used for determining a first group of activity tracks according to the behavior event information; the first group of activity tracks comprise activity tracks acquired by monitoring equipment used for monitoring the first position within a second preset time period; the second preset time period comprises the first moment;

the information processing module is further configured to determine a first target activity track in the first set of activity tracks;

a video obtaining module, configured to obtain a monitoring video of the first target activity track, where the monitoring video is used to verify the order complaint.

8. The apparatus of claim 7,

the information processing module is specifically configured to:

determining the first target activity track in the first group of activity tracks according to the first distance;

the information processing module is specifically configured to:

determining the first N active tracks in the sequencing result as the first target active tracks, wherein N is a positive integer;

the information processing module is further configured to: determining associated event information according to the first time, wherein the associated event information comprises a second time for taking/placing other commodities except the first commodity in a store and a second position of the other commodities in a third preset time period, and the third preset time period comprises the first time;

determining a second group of activity tracks according to the associated event information; the second group of activity tracks comprise a plurality of activity tracks acquired by monitoring equipment used for monitoring the second position within a fourth preset time period; the second preset time period comprises the second moment;

the video obtaining module is further configured to obtain a monitoring video of the second target activity track, where the monitoring video is used to verify the order complaint;

the information processing module is specifically configured to:

determining the second target activity track in the second set of activity tracks according to the second distance;

the device further comprises:

the recognition module is used for respectively carrying out face recognition on the monitoring video of the first target activity track and the monitoring video of the second target activity track and determining a user to which each activity track belongs;

the information processing module is further configured to, under the condition that the user to which each of the activity tracks belongs includes a first user and a second user, divide the surveillance videos into a first type of surveillance video and a second type of surveillance video, where the first type of surveillance video is a surveillance video of an activity track of the first user, and the second type of surveillance video is a surveillance video of an activity track of the second user.

9. An electronic device, comprising a memory and a processor; the memory and the processor are coupled; the memory for storing computer program code, the computer program code comprising computer instructions;

wherein the computer instructions, when executed by the processor, cause the electronic device to perform the method of processing an order complaint of any of claims 1-6.

10. A computer-readable storage medium storing computer instructions which, when executed on an electronic device, cause the electronic device to perform the method of processing order complaints of any of claims 1-6.