Video work order allocation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of intelligent retail, and discloses a video work order distribution method and device, electronic equipment and a storage medium. A shopping video record is obtained; generating a video work order according to the shopping video record; according to a weight ratio set by a preset number of service providers, distributing the video work orders to work order pools of the service providers; and identifying and processing the video work order of the work order pool of the service provider. According to the method, the video work orders are dynamically and intelligently allocated based on the weight proportion of the service provider, so that a large batch of work orders are processed, and the uniformity and rationality of allocation are ensured. In this way, the efficiency, accuracy and stability of video work order processing are remarkably improved, and maximum utilization of resources is achieved.

Description

Technical Field

[0001] The present application relates to the field of smart retail technology, and in particular to a video work order allocation method, device, electronic device and storage medium. Background Art

[0002] The video work order system is a shopping video task generated by smart vending equipment, which is used to record and identify consumers' purchasing behavior. By analyzing the shopping actions in the video, the system can confirm whether the consumer has taken the goods and accurately perform the deduction operation. This type of video work order is very important in scenarios such as unmanned vending machines and unmanned retail stores, because it can automatically process a large number of shopping records and settlement operations, improving the efficiency of retail management. However, with the rapid development of the smart retail market, the distribution system of video work orders has exposed the following problems: (1) There is an imbalance in the distribution of video work orders, resulting in some service providers being overloaded while other resources are idle, affecting the overall processing efficiency; (2) The total transaction volume in each time period varies, and the efficiency of manual recognition is limited. Summary of the invention

[0003] The implementation method of this application mainly solves the technical problem of how to improve allocation efficiency and processing capacity to maximize resource utilization.

[0004] In order to solve the above technical problems, a technical solution adopted in the implementation mode of the present application is: to provide a video work order allocation method, the method comprising: obtaining a shopping video recording; generating a video work order based on the shopping video recording; allocating the video work order to the work order pool of the service provider according to the weight ratio set by a preset number of service providers; identifying and processing the video work order in the work order pool of the service provider.

[0005] In some embodiments, the video work order is allocated to a work order pool of a service provider according to a weight ratio set by a preset number of service providers, including: obtaining a work order number corresponding to the video work order; inputting the work order number into a work order pool to be allocated, and arranging the work order numbers in the work order pool to be allocated in ascending order; performing an allocation mode detection on the work order pool to be allocated to obtain an allocation mode detection result; according to the allocation mode detection result, the video work order is allocated to the service provider to generate an allocation record; according to the allocation record, the video work order is allocated to the work order pool of the service provider.

[0006] In some embodiments, the allocation mode detection result includes an intelligent allocation mode and a directional allocation mode; the video work order is allocated to the service provider according to the allocation mode detection result to generate an allocation record, including: when the allocation mode detection result is an intelligent allocation mode, the allocation result is obtained according to the weight ratio set by the service provider; the video work order is allocated to the service provider according to the allocation result to obtain the identity number of the service provider; the allocation record is generated according to the identity number of the service provider and the work order number; when the allocation mode detection result is a directional allocation mode, it is determined whether the designated service provider meets the preset order acceptance conditions; if the preset order acceptance conditions are met, the identity number of the designated service provider is obtained; the allocation record is generated according to the identity number of the designated service provider and the work order number; if the preset order acceptance conditions are not met, the video work order is allocated to the service provider using the intelligent allocation mode to generate the allocation record.

[0007] In some embodiments, the weight ratio calculation set by the service provider is used to obtain the allocation result, including: obtaining the allocation record within a preset time; obtaining the service provider ratio and the work order ratio corresponding to the service provider identity number according to the allocation record within the preset time; performing calculation according to the work order ratio and the service provider ratio to obtain the calculation result, and arranging the calculation result in descending order; selecting the predetermined identity number of the service provider according to the calculation result, and judging whether the service provider meets the preset order acceptance condition; if the preset order acceptance condition is met, using the identity number of the service provider as the allocation result; if the preset order acceptance condition is not met, judging whether the service provider is the last service provider; if so, setting the identity number of the service provider to empty and using it as the allocation result; if not, selecting the identity number of the next service provider of the service provider in turn, and performing subsequent judgment operations to obtain the allocation result.

[0008] In some embodiments, the identifying and processing of the video work order in the work order pool of the service provider includes: performing an algorithm interface detection on the service provider to determine whether the service provider has an algorithm interface; if the service provider has an algorithm interface, requesting the service provider to perform algorithm identification on the video work order to obtain an algorithm identification result, and deleting the video work order from the work order pool after the identification is completed; if the service provider does not have an algorithm interface, requesting the service provider to start manual service to manually identify the video work order.

[0009] In some embodiments, the request to the service provider to start manual service and manually identify the video work order includes: sending a manual service request instruction to the service provider to enable the service provider to log in to a manual account, and input the manual account into the service provider's order collection queue; performing a work order detection on the work order pool to determine whether the work order pool has the video work order; if the work order pool has the video work order, deleting the video work order from the work order pool, and removing the manual account from the order collection queue; manually identifying the video work order to obtain a manual identification result; if the work order pool does not have the video work order, generating an order collection failure record, and waiting for a preset time.

[0010] In some embodiments, the method further includes: when a record of failed order collection is obtained, the proportion of the service providers that do not have an algorithm interface is dynamically adjusted to perform the manual identification on the video work order to obtain the manual identification result.

[0011] To solve the above technical problems, another technical solution adopted in the implementation mode of the present application is: to provide a video work order allocation device, the device comprising: an acquisition module, the acquisition module is used to acquire shopping video recordings; a generation module, the generation module is used to generate a video work order based on the shopping video recordings; an allocation module, the allocation module is used to allocate the video work order to the work order pool of the service provider according to the weight ratio set by a preset number of service providers; an identification module, the identification module is used to identify and process the video work order in the work order pool of the service provider.

[0012] To solve the above technical problems, another technical solution adopted in the implementation mode of the present application is: to provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described above.

[0013] In order to solve the above technical problems, another technical solution adopted in the implementation mode of the present application is: providing a non-volatile computer-readable storage medium, characterized in that the non-volatile computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by an electronic device, the electronic device executes the method described above.

[0014] Different from the related art, the present application provides a video work order allocation method, device, electronic device and storage medium, which obtains shopping video recordings; generates a video work order based on the shopping video recordings; allocates the video work order to the service provider's work order pool according to the weight ratio set by a preset number of service providers; and identifies and processes the video work order in the service provider's work order pool. Based on this, the present application dynamically and intelligently allocates video work orders based on the weight ratio of the service provider to handle large quantities of work orders and ensure the uniformity and rationality of the allocation. In this way, the efficiency, accuracy and stability of video work order processing are significantly improved, the maximum utilization of resources is achieved, and the shopping experience of electronic devices such as vending machines is effectively optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] One or more embodiments are exemplarily described by corresponding drawings, which do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and the figures in the drawings do not constitute proportional limitations unless otherwise stated.

[0016] Figure 1 It is a schematic diagram of a specific application scenario of a video work order allocation method provided in an embodiment of the present application;

[0017] Figure 2 It is a flow chart of a video work order allocation method provided in an embodiment of the present application;

[0018] Figure 3 This is a flow chart of allocating a work order pool provided by an embodiment of the present application;

[0019] Figure 4 is a flow chart of a distribution mode detection provided by an embodiment of the present application;

[0020] Figure 5 This is a flow chart of weight ratio calculation provided in an embodiment of the present application;

[0021] Figure 6 It is a structural schematic block diagram of a video work order distribution device provided in an embodiment of the present application;

[0022] Figure 7 It is a schematic diagram of the hardware structure of an electronic device for executing the video work order allocation method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0024] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other, all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the device schematic diagram or the order in the flow chart.

[0025] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0026] See also Figure 1 , Figure 1 1 is a schematic diagram of a specific application scenario of a video work order allocation method provided in an embodiment of the present application. Specifically, the application scenario includes an electronic device 10 and a service provider 20.

[0027] The electronic device 10 generally refers to a terminal device for recording and uploading shopping videos, such as a smart vending machine, an unmanned retail device, or an automatic vending machine. These devices have built-in cameras, sensors, computing units, and network modules, and can record consumers' shopping behaviors in real time, generate video work orders, and upload video data to a service provider 20 via the network.

[0028] The service provider 20 is mainly used to communicate and interact with the electronic device 10 to complete the identification and processing of the video work order. Common service providers 20 include but are not limited to: Video processing and identification service providers: service providers specializing in image and video recognition, providing image processing algorithms, behavior detection models, etc. These service providers may develop deep learning models to identify uploaded video content and determine whether the goods have been taken away to support subsequent deduction operations. Manual review and customer service team: When there is uncertainty in the recognition results in the video work order, some service providers provide manual review services to help further confirm the consumer's shopping behavior. The review team confirms or corrects the deduction results by remotely accessing the video uploaded by the system.

[0029] This embodiment realizes real-time video uploading, work order processing and intelligent scheduling through communication and interaction between the service provider 20 and the electronic device 10, so as to ensure that the video work order system runs efficiently and accurately.

[0030] See also Figure 2 , Figure 2 : is a flow chart of a video work order allocation method provided by an embodiment of the present application. Figure 2 As shown, the method is applied to a video work order distribution system provided by an electronic device, and includes steps S11-S14:

[0031] S11: Acquire shopping video recording.

[0032] Electronic devices (e.g., smart vending machines or unmanned retail devices) are usually equipped with cameras and sensors to detect consumers' shopping behavior. When a consumer approaches the device or selects a product, the sensor triggers the video recording mechanism. The camera starts recording video, recording every shopping action of the consumer (such as picking up the product, viewing the product, putting the product back, etc.). The device caches the recorded video stream at an appropriate resolution and frame rate to ensure that the video quality is clear enough for subsequent recognition. The video stream can be transmitted to the backend server in real time or uploaded after the transaction is completed. The device usually transmits the video data to the backend via a wireless network (such as 4G / 5G or Wi-Fi). To facilitate subsequent processing, the device can divide the complete shopping process into multiple video clips by time period. Each clip is marked with a timestamp, transaction information (such as start and end time), and device ID to accurately locate key events when generating a work order.

[0033] Through the trigger mechanism, the device only records videos with shopping behavior, reducing the transmission and storage of invalid videos. The clarity and continuity of the video help with subsequent behavior recognition and improve recognition accuracy. In addition, segmented uploading and marking make video data management more efficient, saving transmission time and storage space.

[0034] S12: Generate a video work order based on the shopping video recording.

[0035] The device uses computer vision algorithms to analyze video content and identify key shopping behaviors, such as picking up, putting back, and purchasing goods. Common methods include object detection and behavior classification models. Alternatively, deep learning models (such as convolutional neural networks (CNNs)) are used to identify the interaction between consumers and goods, thereby determining whether a purchase has occurred.

[0036] After confirming the shopping behavior, the device automatically generates a video work order and records the basic information of the shopping video clip, including video ID, timestamp, device ID, recognition results, etc. The video work order contains the consumer's behavior analysis results and the recognized product information to ensure that the consumer behavior recorded in the video accurately corresponds to the product. In addition, to facilitate subsequent processing, consumption information (such as product ID, purchase price) and consumer information (such as payment method, account ID) are attached to the work order. If the system identifies abnormal behavior (such as returning the product), it will mark the abnormality in the work order for manual review or priority processing.

[0037] Through steps S11 and S12, the whole process from acquiring shopping videos to generating structured invoices can be automated. This method improves the accuracy of deductions and processing efficiency, reduces the need for manual intervention, and optimizes data storage and management.

[0038] S13: Allocate the video work order to a work order pool of a service provider according to the weight ratios set by a preset number of service providers.

[0039] See also Figure 3 , Figure 3 This is a flow chart of allocating a work order pool provided by an embodiment of the present application. Figure 3 As shown, according to the weight ratios set by a preset number of service providers, the video work order is allocated to the work order pool of the service provider, including steps S131-S135:

[0040] In the video work order allocation system, by setting the allocation weights of service providers, video work orders are allocated to the work order pools of different service providers according to preset strategies.

[0041] S131: Obtain the work order number corresponding to the video work order.

[0042] When the system generates a video work order, it assigns a unique work order number to each work order to ensure its uniqueness and traceability throughout the entire process. The work order number can be generated based on the timestamp, device ID, or video ID. Among them, the work order number usually adopts a standardized coding format, such as "device ID + timestamp + serial number", to ensure that each video work order can be uniquely identified and associated with a specific shopping event. After generating the work order number, the system will bind the generated work order number with other information of the video work order (such as shopping behavior records, product identification results) to provide complete data for subsequent allocation.

[0043] S132: Input the work order number into a pool of work orders to be allocated, and arrange the work order numbers in the pool of work orders to be allocated in ascending order.

[0044] The system puts the generated work order number into the work order pool to be assigned (i.e., a list of work orders to be assigned temporarily), to be further assigned to different service providers. The work order pool can be grouped according to different categories (such as transaction type, equipment location, time period, etc.) to ensure that the attributes of the work order are considered during the assignment process. At the same time, the work order numbers in the work order pool are sorted in ascending order, and the sorting basis can be the timestamp when the work order was generated. This ensures that the work orders are assigned in order, ensures fairness in processing, and facilitates the priority assignment of work orders generated earlier to avoid a backlog of long-term unprocessed work orders.

[0045] S133: Performing allocation mode detection on the work order pool to be allocated to obtain an allocation mode detection result.

[0046] Before allocating, the system automatically detects the current allocation mode and determines whether the allocation strategy needs to be adjusted based on the transaction volume, service provider's workload and resource usage. The detection dimensions may include: fluctuations in transaction volume, real-time processing speed of service providers, available resources of service providers, etc. If the service provider has resource overload, the system can automatically switch to a high-priority service provider or a backup service provider. The system determines the appropriate allocation mode based on the detection results, such as Round Robin, Weighted Allocation, etc. If the transaction volume increases significantly, the system will switch to load distribution mode, giving priority to service providers with high processing capabilities.

[0047] Optionally, see Figure 4 , Figure 4 This is a flow chart of a distribution mode detection provided by an embodiment of the present application. Figure 4 As shown, the allocation mode detection result includes an intelligent allocation mode and a directional allocation mode; according to the allocation mode detection result, the service provider is allocated to the video work order to generate an allocation record, including steps S1331-S1332:

[0048] S1331: When the allocation mode detection result is the intelligent allocation mode, the allocation result is obtained according to the weight ratio set by the service provider; the video work order is allocated to the service provider according to the allocation result to obtain the service provider's identity number; the allocation record is generated according to the service provider's identity number and the work order number.

[0049] It is understandable that in the intelligent allocation mode, the system will allocate work orders based on the weight ratio of each service provider. The weight ratio of each service provider is usually pre-set to reflect its processing capacity and response efficiency. The system uses the weight value of the service provider to calculate the amount of work orders that should be allocated to each service provider to ensure that the allocation is in line with the carrying capacity of the service provider. Based on the allocation results, the system allocates the video work order to the corresponding service provider and obtains the identity number of the service provider. The identity number is used to uniquely identify each service provider for subsequent tracking and management. The system generates an allocation record based on the work order number and the service provider identity number, records the allocation information and saves it to the database. The allocation record usually includes information such as the work order number, service provider ID, allocation time, weight ratio, etc., to facilitate subsequent query, statistics and management.

[0050] Optionally, see Figure 5 , Figure 5 This is a flow chart of a weight ratio calculation provided by an embodiment of the present application. Figure 5 As shown, the allocation result is obtained according to the weight ratio set by the service provider, including steps S13311-S13316:

[0051] S13311: Obtain allocation records within a preset time.

[0052] The system obtains the allocation records within a specified preset time period (such as the past hour, day, etc.) from the database or allocation record system. These records contain the historical allocation of work orders, including the number of work orders each service provider has allocated during the time period and the service provider identification number.

[0053] S13312: According to the allocation records within the preset time, obtain the proportion of the service providers and the proportion of the number of work orders corresponding to the service provider identity numbers.

[0054] S13313: Calculate according to the proportion of the number of work orders and the proportion of the service providers to obtain calculation results, and arrange the calculation results in descending order.

[0055] For example, the percentage of work orders corresponding to the service provider identity number is X1, X2, X3, etc., and the percentage of service providers is Y1, Y2, Y3, etc. Through calculation, we know that: Z1 = (Y1-X1) / Y1, Z2 = (Y2-X2) / Y2, Z3 = (Y3-X3) / Y3, that is, according to the percentage of work orders and the percentage of service providers, we can get the weight percentage of service providers. In addition, after getting the weight percentage of service providers, we sort them in descending order according to the size of the values ​​to get the calculation result after sorting.

[0056] S13314: Select the identity number of the predetermined service provider according to the calculation result, and determine whether the service provider meets the preset order acceptance conditions.

[0057] Based on the sorting results, the system selects the service provider that best matches the assigned priority and checks whether the service provider meets the order acceptance conditions (such as current load, online status, available resources, etc.). The preset conditions may include the service provider's current working status, response time, historical performance, etc. For example, the identity number of the first server in the queue (the calculated result after sorting) is selected to determine whether the service provider corresponding to the identity number meets the preset order acceptance conditions.

[0058] S13315: If the preset order acceptance conditions are met, the identity number of the service provider is used as the allocation result.

[0059] If the selected service provider meets the order acceptance conditions, the system will use the service provider's identity number as the final allocation result. The work order will then be allocated to the service provider and the allocation information of the work order will be updated in the allocation record.

[0060] S13316: If the preset order acceptance conditions are not met, determine whether the service provider is the last service provider; if so, set the identity number of the service provider to empty and use it as the allocation result; if not, select the identity number of the next service provider of the service provider in turn, and perform subsequent judgment operations to obtain the allocation result.

[0061] If the current service provider does not meet the order acceptance conditions and is the last service provider in the list, the allocation result is set to null and the allocation process ends. If it is not the last service provider, the system selects the identity number of the next service provider and repeats the condition judgment operation until a service provider that meets the conditions is found.

[0062] S1332: When the allocation mode detection result is a directional allocation mode, determine whether the designated service provider meets the preset order acceptance conditions; if the preset order acceptance conditions are met, obtain the identity number of the designated service provider; generate the allocation record according to the identity number of the designated service provider and the work order number; if the preset order acceptance conditions are not met, use the intelligent allocation mode to allocate the service provider to the video work order to generate the allocation record.

[0063] It is understandable that, first of all, the directional allocation mode is usually used for specific service providers, such as work orders for specific areas or special needs. The system first determines whether the designated service provider meets the order acceptance conditions, such as the current workload, online status, processing capacity, etc. The preset order acceptance conditions ensure that the service provider has sufficient resources and capabilities to handle the assigned work orders. Common conditions include the idle status of the service provider, the historical processing speed and success rate, etc. Secondly, if the designated service provider meets the order acceptance conditions, the system obtains the identity number of the service provider and assigns the video work order to the service provider. At the same time, an allocation record containing the work order number and the service provider identity number is generated to record the allocation information. Finally, if the designated service provider does not meet the order acceptance conditions (such as excessive load or insufficient resources), the system automatically switches to the intelligent allocation mode to ensure the efficient processing of the work order. By switching, the system uses the resources of other service providers to avoid the retention and delayed processing of work orders caused by the unavailability of a single service provider.

[0064] This embodiment combines intelligent allocation with directional allocation mode, so that the video work order allocation system can efficiently allocate work orders according to real-time conditions and preset requirements, which not only ensures the balance and flexibility of allocation, but also improves the system's adaptability to transaction volume fluctuations and special needs. Through allocation records, the system can fully track the work order allocation process and provide reliable data support for subsequent operation optimization and resource allocation.

[0065] S134: According to the allocation mode detection result, the service provider is allocated to the video work order to generate an allocation record.

[0066] According to the allocation mode, the system allocates video work orders to different service providers according to the weight ratio of the service providers. For example, service providers with higher weights will receive more work orders. In the weight allocation mode, the system can ensure that each service provider is allocated the number of work orders that matches its processing capacity through the calculated weight value. The system generates allocation records, including information such as the work order number, the assigned service provider ID, and the allocation time, to ensure that each allocation operation is traceable. The records can help the system monitor the allocation status and generate performance reports after the processing is completed to evaluate the response and processing efficiency of the service provider.

[0067] S135: Allocate the video work order to the work order pool of the service provider according to the allocation record.

[0068] The system moves the video ticket to the designated service provider's ticket pool. Each service provider has an independent ticket pool, which contains all the tickets that it currently needs to process. The service provider's ticket pool can be sorted by priority to ensure that high-priority tickets can be processed first. In addition, the system can send real-time notifications to service providers to inform them of the arrival of new tickets, ensuring that service providers respond quickly and start the ticket processing process. Notifications can be implemented through API interfaces, emails, or dedicated management backends.

[0069] The core of the allocation method provided in this embodiment is to use steps such as work order number generation, work order pool management, allocation mode detection and weight allocation mechanism to achieve intelligent and efficient allocation of video work orders, and its beneficial effects include improving the balance of work order allocation, flexibly responding to transaction volume fluctuations, optimizing the resource utilization rate of service providers, and ensuring the real-time and traceability of the allocation process. This method ensures the reasonable allocation of video work orders among different service providers, and improves the overall processing efficiency of the system and consumer experience.

[0070] S14: Identify and process the video work order in the work order pool of the service provider.

[0071] Optionally, the identifying and processing of the video work order in the work order pool of the service provider includes: performing algorithm interface detection on the service provider to determine whether the service provider has an algorithm interface; if the service provider has an algorithm interface, requesting the service provider to perform algorithm identification on the video work order to obtain an algorithm identification result, and deleting the video work order from the work order pool after the identification is completed; if the service provider does not have an algorithm interface, requesting the service provider to start manual service to manually identify the video work order.

[0072] It is understandable that after the video work order is assigned to the work order pool of the appropriate service provider, it needs to be identified and processed. First, it will be detected whether the service provider supports the automated algorithm recognition interface. This detection can be achieved through the service provider's API call or service configuration file to confirm whether the service provider has configured the algorithm recognition function. Secondly, after confirming that the service provider has the algorithm interface, the system sends an identification request to the service provider, requiring it to perform algorithm recognition on the video work order. The algorithm recognition module of the service provider receives the content of the video work order, processes it (such as target recognition, product detection, etc.), and returns the recognition results, including data such as the identified product information and purchase behavior. After the recognition is completed, the system will remove the video work order from the service provider's work order pool and synchronize the recognition results to the system's order management module. By cleaning up the work order in this way, the system ensures that only unfinished work orders remain in the work order pool, which is convenient for subsequent management and allocation.

[0073] In addition, when it is detected that the service provider lacks an algorithm interface, the system will switch to manual recognition mode and request the service provider to complete the recognition of the video work order through manual operation. The service provider's manual operation team will receive the video work order, and identify the consumer's purchase behavior by watching the video and manually annotating it, and record the product information.

[0074] Optionally, the request to the service provider to start manual service and manually identify the video work order includes: sending a manual service request instruction to the service provider so that the service provider logs in to a manual account, and inputs the manual account into the service provider's order collection queue; performing a work order detection on the work order pool to determine whether the work order pool has the video work order; if the work order pool has the video work order, deleting the video work order from the work order pool, and removing the manual account from the order collection queue; manually identifying the video work order to obtain a manual identification result; if the work order pool does not have the video work order, generating an order collection failure record and waiting for a preset time.

[0075] It is understandable that, first, when the system detects that the service provider cannot use the algorithm for identification, it sends a request instruction to the service provider, requiring it to log in to the manual account. The manual account is used to identify the manual operator within the service provider, and is used to receive and process video work orders. In the service provider system, the manual account is added to the order queue so that it can participate in the processing and identification of video work orders. Secondly, check the service provider's work order pool to confirm whether there is a video work order that needs to be identified to prevent the work order from being missed or repeatedly processed. This step usually includes finding and matching the work order number to ensure that the detected work order pool corresponds to the video work order information. After the video work order is detected, it is removed from the work order pool to prevent repeated identification. At the same time, the corresponding manual account is removed from the order queue to ensure that the manual account is only used to process one video work order to avoid resource conflicts. After processing the video work order, the manual account can return to the queue and wait for the allocation of the next work order. Again, in the manual identification process, the operator views the video work order and manually records the consumer's shopping behavior. The recognition result includes the category, quantity, and deduction information of the identified goods, ensuring accurate recognition of the consumer's operation. Finally, when the service provider's work order pool does not detect the video work order, the system generates a record of failed order collection to track unsuccessful tasks. After recording the failure information, the system enters the waiting mode and waits for a period of time (for example, the preset time is 1 second) before retrying the assignment to ensure that all work orders can be processed.

[0076] Optionally, the method further includes: when a record of failed order collection is obtained, dynamically adjusting the proportion of the service providers that do not have an algorithm interface to perform manual identification on the video work order to obtain the manual identification result.

[0077] It is understandable that when a record of failed order collection (i.e., unsuccessfully assigned video work orders) is obtained during the process of manually identifying video work orders, the system will record this abnormal state. This record provides a basis for subsequent adjustments to ensure that the system can continuously optimize the work order allocation process. Based on the failure of order collection, the system identifies service providers that do not have an algorithm interface and adjusts their proportion parameters.

[0078] First, obtain the number of order collection failures in the order collection failure records within a preset time (for example, 5 minutes), and determine whether the number of order collection failures is greater than the first set threshold, the value of the first set threshold is the number of online employees of the manual service provider × 5% × 300. If the number of order collection failures is greater than the first set threshold, the total proportion of manual service providers is increased in steps of 0.1%. After dynamically adjusting the total proportion of manual service providers, wait for a preset time (for example, 1 minute) to facilitate subsequent recognition operations. It can be understood that this can assign more video work orders to manual service providers and alleviate order collection failures caused by insufficient algorithm recognition. After the adjustment is completed, the system waits for a preset time (for example, 1 minute) to ensure that the new proportion takes effect and performs subsequent recognition.

[0079] If the number of failed orders is not greater than the first set threshold, it is further determined whether the total number of work orders in the work order pool of the manual service provider is greater than the second set threshold, and the value of the second set threshold is the number of online employees of the manual service provider × 90% × 4. If the total number of work orders in the work order pool of the manual service provider is greater than the second set threshold, the total proportion of the manual service provider is reduced by 0.1% in steps, and then wait for a preset time (for example, 1 minute). It can be understood that the system reduces the total proportion of the manual service provider in steps of 0.1%, thereby reducing the amount of work orders allocated to the manual service provider and preventing overload of manual resources. If the total number of work orders in the work order pool of the manual service provider is not greater than the second set threshold, just wait for the preset time (for example, 1 minute).

[0080] Finally, after dynamically adjusting the proportion of manual service providers, the manual recognition is performed on the video work order to obtain the manual recognition result. The specific manual recognition process has been described in the above description and will not be repeated here.

[0081] The embodiment of the present application provides a method for allocating video work orders, by obtaining shopping video recordings; generating video work orders based on the shopping video recordings; allocating the video work orders to the work order pool of the service provider according to the weight ratios set by a preset number of service providers; and identifying and processing the video work orders in the work order pool of the service provider. Based on this, the present application optimizes the processing efficiency of work orders at multiple levels, ensuring that the identification and deduction processes of shopping video work orders for vending machines are more accurate, timely and balanced in burden. First, the algorithm lays the foundation for uploading, sorting and allocating video work orders by allocating the setting and management of the work order pool, so that the work order number can quickly enter the work order pool to be allocated and be arranged in ascending order according to the upload time. This method ensures the orderliness of work order allocation, and can be allocated to the appropriate service provider for processing as soon as possible after the video is uploaded. Secondly, a flexible allocation method is provided for vending machines through intelligent allocation mode and directional allocation mode. The intelligent allocation mode allocates work orders based on the weight ratio of service providers, which is suitable for processing large quantities of work orders and ensuring uniformity of allocation; while the directional allocation mode can allocate work orders to designated service providers, which is suitable for meeting personalized needs in specific situations. This dual allocation mechanism enables the system to complete work order allocation in the best way when facing different processing requirements and service provider configurations, improving the adaptability and scalability of the system. In addition, in the work order processing stage, the differentiated use of algorithm service providers and manual service providers makes more effective use of resources. Algorithm service providers can greatly improve the efficiency of video recognition through automated processing, which is particularly suitable for large-scale data processing with a high degree of standardization; manual service providers participate when higher accuracy is required, and ensure the accuracy of product information in the video through manual recognition. This collaborative approach achieves a balance between automated processing and manual processing, effectively avoiding misjudgments. Finally, the function of dynamically adjusting the proportion of manual service providers plays an important role in adjusting the allocation ratio in real time. The system dynamically adjusts the allocation ratio of manual service providers according to the data situation, which can quickly respond to load fluctuations, avoid excessive or low manual service pressure, and ensure the stability and efficiency of the overall system. In this way, the efficiency, accuracy and stability of video work order processing are significantly improved, resources are maximized, and the shopping experience of electronic devices such as vending machines is effectively optimized.

[0082] Based on the video work order allocation method provided in the above embodiment, the embodiment of the present application further provides a video work order allocation device. Figure 6 , Figure 6 This is a schematic diagram of the structure of the device. Figure 6 As shown, the device 200 includes: an acquisition module 210 , a generation module 220 , an allocation module 230 , and an identification module 240 .

[0083] Among them, the acquisition module 210 is used to obtain the shopping video recording; the generation module 220 is used to generate a video work order based on the shopping video recording; the allocation module 230 is used to allocate the video work order to the service provider's work order pool according to the weight ratio set by a preset number of service providers; the identification module 240 is used to identify and process the video work order in the service provider's work order pool.

[0084] It should be noted that the above-mentioned video work order distribution device can execute the video work order distribution method provided in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in the embodiment of the video work order distribution device, please refer to the video work order distribution method provided in the embodiment of the present application.

[0085] The present application also provides an electronic device. Figure 7 , which shows the hardware structure of an electronic device capable of executing the method described in the above embodiment. The electronic device 300 includes: at least one processor 310; and a memory 320 in communication with the at least one processor 310, Figure 7 In the embodiment, a processor 310 is taken as an example. The memory 320 stores instructions that can be executed by the at least one processor 310. The instructions are executed by the at least one processor 310 so that the at least one processor 310 can execute the video work order allocation method described in the above embodiment. The processor 310 and the memory 320 can be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0086] The memory 320 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the video work order allocation method in the embodiment of the present application. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the video work order allocation method described in the above embodiment is implemented.

[0087] The memory 320 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created according to the use of the computing device, etc. In addition, the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 320 may optionally include a memory remotely arranged relative to the processor 310, and these remote memories may be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0088] The one or more modules are stored in the memory 320 , and when executed by the one or more processors 310 , the video work order allocation method described in the above embodiment is executed.

[0089] It should be noted that the electronic devices provided in this embodiment include but are not limited to smart vending machines, smart vending cabinets, unmanned vending machines, and unmanned retail stores.

[0090] The above product can execute the method provided in the embodiment of the present application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the video work order allocation method described in any embodiment of the present application.

[0091] The embodiment of the present application also provides a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors so that the at least one processor can execute the video work order allocation method described in the above embodiment. For example, the non-volatile computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0092] It should be noted that the above described embodiments are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0093] Through the description of the above implementation methods, ordinary technicians in this field can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Ordinary technicians in this field can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Under the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes in different aspects of the present application as described above, which are not provided in detail for the sake of simplicity. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A video work order allocation method, characterized in that: The method comprises: Get shopping video recordings; Generate a video work order based on the shopping video recording; Allocate the video work order to the work order pool of the service provider according to the weight ratio set by a preset number of service providers; The video work order in the work order pool of the service provider is identified and processed.

2. The video work order allocation method according to claim 1, characterized in that: The allocating the video work order to a work order pool of a service provider according to a weight ratio set by a preset number of service providers includes: Obtaining a work order number corresponding to the video work order; Input the work order number into a pool of work orders to be allocated, and arrange the work order numbers in the pool of work orders to be allocated in ascending order; Performing an allocation mode detection on the work order pool to be allocated to obtain an allocation mode detection result; According to the allocation mode detection result, the video work order is allocated to the service provider to generate an allocation record; According to the allocation record, the video work order is allocated to the work order pool of the service provider.

3. The video work order allocation method according to claim 2, characterized in that: The distribution mode detection result includes an intelligent distribution mode and a directional distribution mode; The allocating the service provider to the video work order according to the allocation mode detection result to generate an allocation record includes: When the allocation mode detection result is the intelligent allocation mode, the allocation result is obtained according to the weight ratio set by the service provider; the video work order is allocated to the service provider according to the allocation result to obtain the identity number of the service provider; the allocation record is generated according to the identity number of the service provider and the work order number; When the allocation mode detection result is a directional allocation mode, determine whether the designated service provider meets the preset order acceptance conditions; if the preset order acceptance conditions are met, obtain the identity number of the designated service provider; generate the allocation record based on the identity number of the designated service provider and the work order number; if the preset order acceptance conditions are not met, use the intelligent allocation mode to allocate the service provider to the video work order to generate the allocation record.

4. The video work order allocation method according to claim 3, characterized in that: The calculation based on the weight ratio set by the service provider to obtain the allocation result includes: Get the allocation records within the preset time; According to the allocation records within the preset time, the proportion of the service providers and the proportion of the number of work orders corresponding to the service provider identity numbers are obtained; Calculate according to the proportion of the number of work orders and the proportion of the service providers to obtain calculation results, and arrange the calculation results in descending order; Selecting the identity number of the predetermined service provider according to the calculation result, and determining whether the service provider meets the preset order acceptance conditions; If the preset order acceptance condition is met, the identity number of the service provider is used as the allocation result; If the preset order acceptance conditions are not met, determine whether the service provider is the last service provider; if so, set the identity number of the service provider to empty and use it as the allocation result; if not, select the identity number of the next service provider of the service provider in turn, and perform subsequent judgment operations to obtain the allocation result.

5. The video work order allocation method according to claim 1, characterized in that: The identifying and processing the video work order in the work order pool of the service provider includes: Performing algorithm interface detection on the service provider to determine whether the service provider has an algorithm interface; If the service provider has an algorithm interface, request the service provider to perform algorithm recognition on the video work order, obtain an algorithm recognition result, and delete the video work order from the work order pool after the recognition is completed; If the service provider does not have an algorithm interface, the service provider is requested to start manual service to manually identify the video work order.

6. The video work order allocation method according to claim 5, characterized in that: The requesting the service provider to start manual service and manually identify the video work order includes: Sending a manual service request instruction to the service provider, so that the service provider can log in to a manual account, and input the manual account into the order collection queue of the service provider; Performing work order detection on the work order pool to determine whether the work order pool has the video work order; If the work order pool has the video work order, the video work order is deleted from the work order pool, and the manual account is removed from the work order queue; Manually identify the video work order to obtain a manual identification result; If the work order pool does not have the video work order, a record of failed order collection is generated and a preset time is waited.

7. The video work order allocation method according to any one of claims 1 to 6, characterized in that: The method further comprises: When a record of failed order collection is obtained, the proportion of the service providers without an algorithm interface is dynamically adjusted to perform manual identification on the video work order to obtain the manual identification result.

8. A video work order distribution device, characterized in that: The device comprises: An acquisition module, the acquisition module is used to acquire shopping video recordings; A generation module, the generation module is used to generate a video work order according to the shopping video recording; An allocation module, the allocation module is used to allocate the video work order to the work order pool of the service provider according to the weight ratio set by a preset number of service providers; An identification module, wherein the identification module is used to identify and process the video work order in the work order pool of the service provider.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by an electronic device, the electronic device executes the method according to any one of claims 1 to 7.

Images