Information processing method, related device, related storage medium and computer program
The digital human-in-one machine enhances unmanned vending systems by integrating facial recognition and Wi-Fi analysis to recommend products and schedule try-ons, addressing the lack of intelligence and adaptability in existing systems, thereby improving user experience and sales efficiency.
Patent Information
- Application Number
- CN202411127702.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-12-06
AI Technical Summary
Unmanned vending systems lack intelligence and cannot adapt to diverse shopping needs, resulting in a poor user experience and limited functionality.
A digital human-in-one machine that integrates facial recognition, Wi-Fi signal analysis, and congestion monitoring to recommend products, schedule try-on appointments, and manage purchase orders, enhancing user interaction and optimizing store operations.
Improves user experience by adapting to diverse shopping needs, expanding sales scope, and reducing costs through intelligent product recommendation and order management.
Smart Images

Figure CN119090035A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of data processing, and specifically relates to an information processing method and related devices and related storage media and computer programs. Background Art
[0002] The current unmanned vending method is that there are no salespersons and cashiers in the store, and the cashier function is realized by the unmanned vending system. In other words, the current unmanned vending system can only realize the purchase function for goods. And users need to go to the store to buy goods. Therefore, the current unmanned vending system can only process simple cashier data, which makes the unmanned vending system not very intelligent and cannot adapt to a variety of shopping scenarios, so that it cannot meet the diverse purchasing needs of users. Summary of the invention
[0003] The embodiments of the present application provide an information processing method and related devices and related storage media and computer programs to improve the intelligence of processing sales data, to adapt to users' various purchasing needs, and to improve users' shopping experience.
[0004] In a first aspect, an embodiment of the present application provides a method for processing information of a digital human machine, which is applied to a digital human machine, wherein the digital human machine is communicatively connected to a terminal device of a target store, and the digital human machine includes a display screen, and the method includes:
[0005] Determining at least one candidate commodity from a plurality of reference commodities according to the commodity recommendation request, wherein the plurality of reference commodities are commodities sold by the target store;
[0006] Playing the digital human introduction video corresponding to the at least one candidate product in sequence on the display screen;
[0007] Acquire first feedback information, where the first feedback information is used to indicate a target commodity, where the target commodity is a commodity among the at least one candidate commodity;
[0008] If the first feedback information includes a request for trying on the target product, facial recognition is performed on the surveillance image of the target store during the current time period to obtain current human traffic information; and the Wi-Fi signal strength of the target store during the current time period is obtained; the current human traffic information is updated according to the Wi-Fi signal strength to obtain target human traffic information; the congestion level of the target store is determined according to the target human traffic information; and the best time period for trying on the products is determined according to the congestion level;
[0009] A try-on reservation request is sent to the terminal device, wherein the try-on reservation request includes the optimal try-on time period.
[0010] In some possible implementations, updating the pedestrian flow information according to the Wi-Fi signal strength to obtain target pedestrian flow information includes:
[0011] Acquire reference traffic information of the target store in a first time period, where the first time period is an adjacent time period of the current time period;
[0012] Obtaining a reference Wi-Fi signal strength of the target store during the first time period;
[0013] Determine a Wi-Fi signal strength change trend according to the Wi-Fi signal strength in the current period and the reference Wi-Fi signal strength;
[0014] Determine a crowd flow change trend according to the current crowd flow information and the reference crowd flow information;
[0015] When the change trend of the Wi-Fi signal strength is consistent with the change trend of the human flow, determining the current human flow information as the target human flow information;
[0016] When the Wi-Fi signal strength variation trend is inconsistent with the human flow variation trend, target human flow information is obtained according to the Wi-Fi signal strength variation trend and the reference human flow information.
[0017] In some possible implementations, determining the best fitting time period according to the degree of crowding includes:
[0018] When the congestion level is greater than a preset value, obtaining the number of target products that the target account has reserved for trying on;
[0019] Determine whether the quantity of the target product is greater than a preset quantity;
[0020] If yes, then respectively calculate the predicted congestion levels of a plurality of remaining time periods, where the plurality of remaining time periods are time periods after the current time period during the business hours of the target store on the day;
[0021] It is determined that the predicted congestion level is less than the preset value, and the remaining time period closest to the current time period is the optimal fitting time period.
[0022] In some possible implementations, when determining that the predicted congestion level is less than the preset value and the remaining time period closest to the current time period is before the optimal fitting time period, the method further includes:
[0023] Determine the number of accounts that have made reservations for trying on clothes corresponding to the remaining time period closest to the current time period;
[0024] If the number of accounts is greater than the first preset number, obtaining the first product type of the target product, and obtaining the second product type of the try-on product corresponding to the account that has made an appointment for the try-on;
[0025] When the number of try-on products of the same type as the first product in the second product type is greater than a second preset number, the remaining time period whose predicted congestion level is less than the preset value and whose distance from the current time period is less than a preset time is determined to be the optimal try-on time period.
[0026] In some possible implementations, after obtaining the first feedback information, the method further includes:
[0027] If the first feedback information includes a purchase request for the target product, a purchase order for the target product is generated, and when an offline payment request is obtained, a pickup reservation code is displayed on the display screen, and after a pickup reservation request for the pickup reservation code is obtained, a pickup voucher and a latest pickup time are displayed on the display screen; the order information of the purchase order is sent to the terminal device, and the pickup voucher and the latest pickup time are displayed on the display screen;
[0028] Sending stocking information to the terminal device according to the purchase order, wherein the stocking information includes the target commodity;
[0029] After the latest delivery time has passed, query the order status of the purchase order, where the order status includes completed or uncompleted;
[0030] When the order status is incomplete, an order cancellation instruction is sent to the terminal device, where the order cancellation instruction is used to instruct the terminal device to cancel the purchase order.
[0031] In some possible implementations, before displaying the pickup voucher and the latest pickup time on the display screen, the method further includes:
[0032] Obtaining the inventory quantity of the target product in the target store;
[0033] Obtaining sales records of the target product;
[0034] Predicting today's sales volume of the target product based on the sales record;
[0035] When the inventory quantity is greater than the today's sales volume, the latest pickup time is determined to be the closing time of the target store;
[0036] When the inventory quantity is not greater than the today's sales volume, determining the hot-selling period of the target product according to the sales record;
[0037] Determine whether the current moment belongs to the hot selling period;
[0038] If yes, then determine the latest delivery time as a time after a preset period of time from the current time;
[0039] If not, the latest pickup time is determined to be the starting time of the hot-selling period.
[0040] In some possible implementations, after obtaining the pickup reservation request for the pickup reservation code, the method further includes:
[0041] Determine a target reservation account number according to the pickup reservation request;
[0042] Determine the historical reservation records of the target reservation account;
[0043] Determining the probability that the purchase order of the target reservation account in the historical reservation record is cancelled;
[0044] When the probability that the purchase order is cancelled is greater than a preset probability, outputting a prompt message, wherein the prompt message is used to indicate that the reservation has failed;
[0045] When the probability that the purchase order is cancelled is not greater than the preset probability, the pick-up voucher and the latest pick-up time are displayed on the display screen.
[0046] In a second aspect, an embodiment of the present application provides a digital human integrated machine, wherein the digital human integrated machine is communicatively connected to a terminal device of a target store, the digital human integrated machine includes a display screen, and the device includes:
[0047] a determination unit, configured to determine at least one candidate commodity from a plurality of reference commodities according to the commodity recommendation request, wherein the plurality of reference commodities are commodities sold by the target store;
[0048] A playback unit, configured to play the digital human introduction video corresponding to the at least one candidate product in sequence on the display screen;
[0049] an acquiring unit, configured to acquire first feedback information, wherein the first feedback information is used to indicate a target commodity, and the target commodity is a commodity among the at least one candidate commodity;
[0050] a generating unit, configured to perform facial recognition on the surveillance image of the target store in the current time period to obtain current human flow information if the first feedback information includes a try-on request for the target product; and to obtain the Wi-Fi signal strength of the target store in the current time period; and to update the current human flow information according to the Wi-Fi signal strength to obtain target human flow information; and to determine the congestion level of the target store according to the target human flow information; and to determine the best try-on time period according to the congestion level;
[0051] The sending unit is used to send a try-on reservation request to the terminal device, wherein the try-on reservation request includes the optimal try-on time period.
[0052] In a possible example, in terms of updating the pedestrian flow information according to the Wi-Fi signal strength to obtain target pedestrian flow information, the generating unit is specifically used to: obtain reference pedestrian flow information of the target shop in a first time period, where the first time period is an adjacent time period of the current time period; obtain a reference Wi-Fi signal strength of the target shop in the first time period; determine a Wi-Fi signal strength change trend according to the Wi-Fi signal strength of the current time period and the reference Wi-Fi signal strength; determine a pedestrian flow change trend according to the current pedestrian flow information and the reference pedestrian flow information; when the Wi-Fi signal strength change trend is consistent with the pedestrian flow change trend, determine the current pedestrian flow information as the target pedestrian flow information; when the Wi-Fi signal strength change trend is inconsistent with the pedestrian flow change trend, obtain the target pedestrian flow information according to the Wi-Fi signal strength change trend and the reference pedestrian flow information.
[0053] In a possible example, in terms of determining the optimal try-on time period according to the congestion level, the generating unit is specifically used to: when the congestion level is greater than a preset value, obtain the number of target products that the target account has reserved for try-on; determine whether the number of target products is greater than a preset number; if so, calculate the predicted congestion levels of multiple remaining time periods respectively, the multiple remaining time periods being the time periods after the current time period during the business hours of the target store on that day; determine that the remaining time period whose predicted congestion level is less than the preset value and is closest to the current time period is the optimal try-on time period.
[0054] In a possible example, before determining that the predicted degree of congestion is less than the preset value and the remaining time period closest to the current time period is the optimal try-on time period, the generation unit is further used to: determine the number of accounts that have made reservations for try-ons corresponding to the remaining time period closest to the current time period; if the number of accounts is greater than a first preset number, obtain the first product type of the target product, and obtain the second product type of the try-on product corresponding to the account that has made a reservation for try-on; when the number of try-on products of the same type as the first product in the second product type is greater than a second preset number, determine that the predicted degree of congestion is less than the preset value and the remaining time period that is less than the preset time from the current time period is the optimal try-on time period.
[0055] In a possible instance, after obtaining the first feedback information, the generating unit is further used to: if the first feedback information includes a purchase request for the target commodity, generate a purchase order for the target commodity, and display a pick-up appointment code on the display screen when an offline payment request is obtained, and after obtaining a pick-up appointment request for the pick-up appointment code, display a pick-up voucher and a latest pick-up time on the display screen; send order information of the purchase order to the terminal device, and display a pick-up voucher and a latest pick-up time on the display screen; send stocking information to the terminal device according to the purchase order, the stocking information including the target commodity; after the latest pick-up time has passed, query the order status of the purchase order, the order status including completed or incomplete; when the order status is incomplete, send an order cancellation instruction to the terminal device, the order cancellation instruction is used to instruct the terminal device to cancel the purchase order.
[0056] In a possible example, before displaying the pick-up voucher and the latest pick-up time on the display screen, the generating unit is further used to: obtain the inventory quantity of the target product in the target store; obtain the sales record of the target product; predict today's sales volume of the target product based on the sales record; when the inventory quantity is greater than today's sales volume, determine the latest pick-up time as the closing time of the target store; when the inventory quantity is not greater than today's sales volume, determine the hot-selling period of the target product based on the sales record; determine whether the current moment belongs to the hot-selling period; if so, determine the latest pick-up time as the moment after a preset period from the current moment; if not, determine the latest pick-up time as the starting moment of the hot-selling period.
[0057] In a possible instance, after obtaining the pickup appointment request for the pickup appointment code, the generation unit is further used to: determine the target appointment account according to the pickup appointment request; determine the historical appointment record of the target appointment account; determine the probability that the purchase order of the target appointment account is canceled in the historical appointment record; when the probability that the purchase order is canceled is greater than a preset probability, output a prompt message, wherein the prompt message is used to indicate that the appointment has failed; when the probability that the purchase order is canceled is not greater than the preset probability, display the pickup voucher and the latest pickup time on the display screen.
[0058] In the third aspect, an embodiment of the present application provides a digital human-in-one machine, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes relevant instructions for executing the method of the first aspect of the embodiment of the present application.
[0059] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, can implement the method of the first aspect of the embodiment of the present application.
[0060] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when the computer program or instructions included in the computer program product are executed by a processor, can implement the method of the first aspect of the embodiment of the present application.
[0061] It can be seen that in this example, the digital human integrated machine first determines at least one candidate product from multiple reference products according to the product recommendation request, and then plays the digital human introduction video corresponding to the at least one candidate product on the display screen in sequence, and then obtains the first feedback information. If the first feedback information includes a try-on request for the target product, facial recognition is performed on the surveillance image of the target store in the current period to obtain the current traffic information; and the Wi-Fi signal strength of the target store in the current period is obtained; the current traffic information is updated according to the Wi-Fi signal strength to obtain the target traffic information; the congestion level of the target store is determined according to the target traffic information; the best try-on time period is determined according to the congestion level, and finally a try-on appointment request is sent to the terminal device, and the try-on appointment request includes the best try-on time period. In this application, the digital human integrated machine realizes the functions of recommending products to users, introducing product information, and making product try-on appointments for users based on the best try-on time, which improves the intelligence of the processing of sales information, can adapt to the diverse shopping needs of users, and improves the shopping experience of users. At the same time, this solution also expands the actual sales scope of the target store and reduces sales costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0063] Figure 1 It is a schematic diagram of the composition of a sales system provided in an embodiment of the present application;
[0064] Figure 2 is a structural schematic diagram of an electronic device provided in an embodiment of the present application;
[0065] Figure 3 It is a flowchart of a method for processing information of a digital human-in-one machine provided in an embodiment of the present application;
[0066] Figure 4 This is a schematic diagram of a sales interface of a digital human-in-one machine provided in an embodiment of the present application;
[0067] Figure 5 This is a schematic diagram of a try-on reservation interface of a digital human all-in-one machine provided in an embodiment of the present application;
[0068] Figure 6 This is a schematic diagram of an order display interface of a digital human-in-one machine provided in an embodiment of the present application;
[0069] Figure 7 This is a block diagram of the functional units of a digital human-in-one machine provided in an embodiment of the present application;
[0070] Figure 8 This is a block diagram of the functional units of another digital human-in-one machine provided in an embodiment of the present application. DETAILED DESCRIPTION
[0071] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0072] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0073] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0074] At present, unmanned sales systems can only process simple checkout data and cannot adapt to users' various shopping needs, making the existing unmanned sales systems not smart enough and the user experience low.
[0075] In view of the above problems, an embodiment of the present application provides a digital human-in-one machine information processing solution, which is described in detail below in conjunction with the accompanying drawings.
[0076] See also Figure 1 , Figure 1 1 is a schematic diagram of the composition of a sales system provided in an embodiment of the present application. The sales system 10 includes a digital human machine 101 and a terminal device 102, and the digital human machine 101 and the terminal device 102 are communicatively connected. The digital human machine 101 and the terminal device 102 both correspond to the same target store. The digital human machine 101 may be located at the entrance of the target store corresponding to the machine or at a specific location in a shopping mall. The digital human machine 101 includes a display screen for displaying goods and providing corresponding services according to the user's shopping needs. The terminal device 102 is used to receive sales information from the digital human machine and respond to the acquired sales information.
[0077] See also Figure 2 , Figure 2 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. As shown in the figure, the electronic device 110 may be Figure 1The digital human machine 101 shown can also be a terminal device 102. The electronic device 110 includes a processor 120, a memory 130, a communication interface 140, and one or more programs 131, wherein the one or more programs 131 are stored in the above-mentioned memory 130 and are configured to be executed by the above-mentioned processor 120, and the one or more programs 131 include instructions for executing any step in the following method embodiment. In a specific implementation, the processor 120 is used to execute any step executed by the electronic device in the following method embodiment, and when performing data transmission such as sending, the communication interface 140 can be selectively called to complete the corresponding operation.
[0078] Please refer to Figure 3 , Figure 3 The present invention provides a flowchart of a method for processing information of a digital human machine provided by an embodiment of the present invention. The method is applied to a digital human machine, the digital human machine is connected to a terminal device of a target store, the digital human machine includes a display screen and a camera, and the method includes the following steps.
[0079] S210: The digital human-in-one machine determines at least one candidate commodity from a plurality of reference commodities according to the commodity recommendation request.
[0080] Among them, the multiple reference commodities are commodities sold by the target shop. The target shop includes one or more, and the commodities sold by the digital human integrated machine are commodities in the corresponding target shop. The target shop can be a chain store selling the same commodities, or it can be a plurality of different shops selling different types of commodities. When the digital human integrated machine is not used by a user, it will display pictures or advertising content of the commodities corresponding to the digital human integrated machine. When a user uses the digital human integrated machine, the user can send a commodity browsing instruction to the digital human integrated machine, and the digital human integrated machine can display all corresponding commodities to the user, and the user can browse and view all commodities sold by the target shop. The user can also send a commodity recommendation request to the digital human integrated machine, and the commodity recommendation request includes a commodity type. At this time, the digital human integrated machine obtains the commodity recommendation request, determines a plurality of reference commodities according to the commodity type, and then obtains the user's target body information according to the commodity type, and the target body information is a part of the user's body information related to the commodity type. Then, at least one alternative commodity is selected from the plurality of reference commodities according to the target body information. That is to say, the digital human-in-one machine may also include a camera for acquiring the user's body shape information.
[0081] S220: the digital human integrated machine plays the digital human introduction video corresponding to the at least one candidate product in sequence on the display screen.
[0082] Each product has a corresponding digital human introduction video. Users can watch only the digital human introduction video to learn about the product information. Users can also communicate with the digital human through voice for the product corresponding to the currently playing digital human introduction video during playback, so that users can obtain specific information in a targeted manner. Figure 4 As shown, Figure 4 It is a schematic diagram of a sales interface of a digital human-in-one machine provided in an embodiment of the present application. Figure 4 In the example, the digital human machine first selects multiple candidate products for the user according to the user's product recommendation instruction and displays them on the display screen, including product A, product B, product C, product D, product E and product F. If the user selects product B at this time, the digital human machine will play the digital human introduction video corresponding to product B. Figure 4 In the example, digital human G is introducing product B. At this time, the user can also communicate with digital human G by voice. The digital human introduction video can be a video generated according to the sales point of the product. The video can also include a main introduction video and a communication video. The main introduction video is a video generated by the implementation. The communication video is a video generated in real time according to the target speech, which is generated by obtaining the user's feedback voice information and searching for the sales speech and the target speech in the basic information of the product according to the user's feedback voice information.
[0083] S230: the digital human all-in-one machine obtains first feedback information.
[0084] The first feedback information is used to indicate a target product, which is a product among the at least one candidate product. The first feedback information can be determined based on a click operation of the user on the display screen, or based on the user's voice information. For example Figure 4 As shown, the first feedback information includes a purchase request, a try-on request, or a return request for the target product, and the return request includes returning to the product recommendation interface, playing the previous digital human video, or playing the next digital human video.
[0085] S240, if the first feedback information includes a try-on request for the target product, the digital human integrated machine performs facial recognition on the surveillance image of the target store during the current time period to obtain current pedestrian flow information; and obtains the Wi-Fi signal strength of the target store during the current time period; updates the current pedestrian flow information according to the Wi-Fi signal strength to obtain target pedestrian flow information; determines the congestion level of the target store according to the target pedestrian flow information; and determines the best try-on time period according to the congestion level.
[0086] S250, the digital human machine sends a try-on reservation request to the terminal device, wherein the try-on reservation request includes the best try-on time period.
[0087] The try-on reservation request is used to indicate that the user needs to experience the actual product on site, including a try-on and trial-wear request for wearable products. Figure 4 In the video, when the user is watching the digital human video of product B, he can choose to try it on. At this time, the digital human integrated machine generates a try-on request based on product B and informs the user of the best time to try it on. Figure 5 As shown, Figure 5 : is a schematic diagram of a try-on appointment interface of a digital human all-in-one machine provided in an embodiment of the present application. After the user clicks the try-on control for product B, a successful appointment prompt and an appointment code will be generated, and the user will be prompted for the try-on time. Figure 5 The reservation success prompt "A reservation has been made for you to try on the product" and the trying on time prompt "It is recommended to go to the store to try on the product at 3 pm" are shown in the figure.
[0088] In a specific implementation, facial recognition of surveillance images includes obtaining multiple surveillance images of the current period, then extracting facial features from the image screen in each frame, determining the number of faces in the current image screen based on the extracted features, and obtaining the number of customers in the current frame screen. Then, the acquired feature data in the multiple frames are matched to determine the number of people with the same face in the multiple frames; and the flow of people information is determined based on the number of faces in each frame and the number of people with the same face in the frame and other frames. For example, although the number of faces in the first frame and the Nth frame is greater than the preset value, the number of people with the same face in the first frame and the Nth frame is too high, and it is still considered that the flow of people is not large. That is, the number of people leaving the target store can be determined based on the changing trend of the number of the same faces in each frame, and the current number of people in the target store can be determined based on the number of faces determined in each frame, and the flow of people information can be comprehensively determined based on the number of people leaving the target store and the current number of people in the target store. The flow of people information is used to comprehensively evaluate the number of people currently accommodated in the target store and the flow of people.
[0089] In the specific implementation, when determining the congestion level of the target store based on the target traffic information, the initial congestion level is determined based on the current number of people in the target store, and then the weighted parameters are determined based on the flow of people, and finally the congestion level of the target store is determined based on the weighted parameters and the initial congestion level.
[0090] It can be seen that in this example, the digital human machine can recommend products to users, introduce product information, and make product trial appointments for users based on the best trial time, which improves the intelligence of sales information processing, adapts to users' diverse shopping needs, and improves users' shopping experience. At the same time, this solution also expands the actual sales scope of the target store and reduces sales costs.
[0091] In a possible example, updating the pedestrian flow information according to the Wi-Fi signal strength to obtain target pedestrian flow information includes: obtaining reference pedestrian flow information of the target shop in a first time period, where the first time period is an adjacent time period of the current time period; obtaining a reference Wi-Fi signal strength of the target shop in the first time period; determining a Wi-Fi signal strength change trend according to the Wi-Fi signal strength of the current time period and the reference Wi-Fi signal strength; determining a pedestrian flow change trend according to the current pedestrian flow information and the reference pedestrian flow information; when the Wi-Fi signal strength change trend is consistent with the pedestrian flow change trend, determining the current pedestrian flow information as the target pedestrian flow information; when the Wi-Fi signal strength change trend is inconsistent with the pedestrian flow change trend, obtaining the target pedestrian flow information according to the Wi-Fi signal strength change trend and the reference pedestrian flow information.
[0092] Among them, the target store includes free wireless Wi-Fi, and the user will automatically connect to the wireless Wi-Fi after entering the target store. Because when multiple devices are connected to the same Wi-Fi network at the same time, they will share the available bandwidth and channel resources. Each device will occupy a certain bandwidth when sending and receiving data, and when the number of devices increases, the available bandwidth will be dispersed, and the bandwidth obtained by each device will be reduced, resulting in a decrease in signal strength. Therefore, the increase in the number of people in the current store can be roughly determined based on the change trend of the Wi-Fi signal strength. Determining whether the change trend of the Wi-Fi signal strength is consistent with the change trend of the flow of people includes: determining the percentage change of the connected device according to the change trend of the Wi-Fi signal strength, and then determining whether the difference between the percentage change of the number of people corresponding to the change trend of the flow of people and the percentage change of the device is less than the preset difference. If so, it is considered consistent. For example, if the signal drops by K, it is known that 20% of the device connections have increased in the current target store. Then, based on the flow of people information obtained by facial recognition, the change value of the flow of people in the first period and the flow of people in the current period is determined. If it is confirmed that the number of customers in the target store in the current period has increased by 17% compared with the first period, it is consistent with the signal drop strength, and the flow of people information obtained by facial recognition is considered to be accurate. If it is confirmed that the number of customers in the target store in the current period has increased by 10% compared with the first period, the change value of the number of people corresponding to the signal strength change trend determined by the signal strength is the accurate value, and the current flow of people information is updated, that is, the number of people in the first period is increased by 20% as the current number, and the flow of people is updated synchronously.
[0093] It can be seen that in this example, the target store's traffic information is comprehensively determined based on facial recognition technology and changes in Wi-Fi signal strength, which can improve the accuracy of traffic flow determination, so that the calculated optimal try-on time period can meet user needs and improve user experience.
[0094] In a possible example, determining the best try-on time period based on the congestion level includes: when the congestion level is greater than a preset value, obtaining the number of target products that the target account has reserved for try-on; determining whether the number of target products is greater than a preset number; if so, calculating the predicted congestion levels of multiple remaining time periods respectively, the multiple remaining time periods being the time periods after the current time period during the business hours of the target store on that day; and determining that the remaining time period whose predicted congestion level is less than the preset value and is closest to the current time period is the best try-on time period.
[0095] Among them, since the more products the user needs to try on, the longer it takes, and the salesperson may need to accompany him for a longer time. If the current store is crowded, the user cannot try on multiple products freely, and it will also take up the salesperson's time, resulting in a bad shopping experience for other customers in the store. Therefore, the best try-on time can be determined comprehensively based on the number of products the user tries on and the congestion level of the store. The calculation of the predicted congestion level of multiple remaining time periods includes obtaining a monitoring screenshot at any time in each remaining time period within a week, and then determining the number of people in the store corresponding to each remaining time period every day based on the monitoring screenshot, and then obtaining the average number of people in the store at each time within a week, determining the average value as the current number of people in the remaining time period, and determining the congestion level based on the current number of people in the remaining time period.
[0096] It can be seen that in this example, the best trying-on time period is determined for the user based on the number of products the user wants to try on and the congestion level of the store, so that the calculated best trying-on time period can meet the user's needs and improve the user experience.
[0097] In a possible example, before determining that the predicted degree of congestion is less than the preset value and the remaining time period closest to the current time period is the optimal try-on time period, the method further includes: determining the number of accounts that have made reservations for try-ons corresponding to the remaining time period closest to the current time period; if the number of accounts is greater than a first preset number, obtaining a first product type of the target product, and obtaining a second product type of the try-on product corresponding to the account that has made a reservation for try-on; when the number of try-on products of the same type as the first product in the second product type is greater than a second preset number, determining that the predicted degree of congestion is less than the preset value and the remaining time period that is less than a preset time from the current time period is the optimal try-on time period.
[0098] If many people have already made reservations for trying on items during the best appointment time slot, in order to avoid everyone trying on the same item and having to queue up for a try-on, which would result in a poor user experience, other nearby try-on time slots can be booked for the user, and there are fewer other customers trying on the same type of item as the user (for example, the number is less than a certain threshold), so that the user will have a wider range of choices and try-ons for the item.
[0099] It can be seen that in this example, the best trying-on period is calculated for the user based on the product type of the target product the user is trying on, which can improve the intelligence of determining the best trying-on period, so that the calculated best trying-on period can meet the user's needs and improve the user experience.
[0100] In a possible example, after obtaining the first feedback information, the method further includes: if the first feedback information includes a purchase request for the target commodity, generating a purchase order for the target commodity, and displaying a pick-up appointment code on the display screen when an offline payment request is obtained, and displaying a pick-up voucher and a latest pick-up time on the display screen after obtaining a pick-up appointment request for the pick-up appointment code; sending order information of the purchase order to the terminal device, and displaying a pick-up voucher and a latest pick-up time on the display screen; sending stocking information to the terminal device according to the purchase order, the stocking information including the target commodity; after the latest pick-up time has passed, querying the order status of the purchase order, the order status including completed or incomplete; when the order status is incomplete, sending an order cancellation instruction to the terminal device, the order cancellation instruction being used to instruct the terminal device to cancel the purchase order.
[0101] Among them, the order information includes the product name, product model, user payment method and pick-up shop. In particular, when the digital human all-in-one machine corresponds to multiple shops, and multiple shops sell the target product, you can first select a shop with spot goods as a reference shop, and then show the location information of multiple reference shops to the user. After obtaining the final shop selected by the user, a purchase order is generated. Then the order information is sent to the terminal device corresponding to the final shop, so that the terminal device informs the final shop that there is a purchase demand and prepares goods for the user in advance. The order information includes whether the user has paid. If not, the server will save the order until the latest pickup time, at which time the target product will be reserved for the user.
[0102] Among them, for example Figure 6 As shown, Figure 6This is a schematic diagram of an order display interface of a digital human machine provided in an embodiment of the present application. After the user determines to purchase the target product, the digital human machine will display online payment controls and offline payment controls on the display screen. If the user clicks on online payment, the digital human machine will obtain an online payment request, and the payment code will be displayed on the screen. The user then scans the code to pay the order. When the order is paid successfully, a pickup voucher will be displayed on the digital human machine. At this time, the user can go to the store to pick up the goods during any sales period of the target store. If the user chooses to pay offline, the pickup voucher and the latest pickup time will be displayed. In particular, the digital human machine can also provide paper vouchers simultaneously, and the user can pick up the goods according to the paper voucher. In this way, the sales information is adapted based on the user's payment method, which can improve the intelligence of the processing of sales information and meet the diverse shopping needs of users.
[0103] Among them, the pickup voucher can be a QR code or a paper pickup information. Or the user's phone number can be obtained, and a pickup SMS can be sent to the user according to the user's phone number. When the user confirms the purchase, the user can pick up the goods in the target store before the latest pickup time displayed. At this time, the target store will reserve the target product for the user after obtaining the order information until the latest pickup time. If it is detected that the user has not performed the pickup operation before the preset time of the latest pickup time, a notification message can be sent to the user to inform the user that the target product will no longer be reserved after the preset time. When the latest pickup time is reached, the user's purchase order is automatically canceled and no goods are reserved for the user. In particular, after canceling the order, the order cancellation information can also be sent to the user, and the current inventory of the target product can be obtained at the same time. When the inventory is sufficient, the user is prompted that he can still pick up the goods at the target store with the purchase order. If the inventory is insufficient, the inventory quantity will be notified simultaneously when the order cancellation information is sent.
[0104] It can be seen that in this example, the purchase order is canceled after the user exceeds the latest pickup time, which realizes real-time monitoring of the status of the purchase order and improves the intelligence and timeliness of the processing of sales information.
[0105] In a possible example, before displaying the pick-up voucher and the latest pick-up time on the display screen, the method further includes: obtaining the inventory quantity of the target product in the target store; obtaining the sales record of the target product; predicting today's sales volume of the target product based on the sales record; when the inventory quantity is greater than today's sales volume, determining the latest pick-up time as the closing time of the target store; when the inventory quantity is not greater than today's sales volume, determining the hot-selling period of the target product based on the sales record; determining whether the current moment belongs to the hot-selling period; if so, determining the latest pick-up time as a moment after a preset period from the current moment; if not, determining the latest pick-up time as the starting time of the hot-selling period.
[0106] If the inventory is sufficient, the latest delivery time may be the closing time of the target store. If the inventory is insufficient, in order to ensure the actual sales in the store, the latest delivery time is set before the hot-selling period. The hot-selling period may be a period when the sales frequency of the target product is greater than the preset frequency. Before determining the hot-selling period, the current time may be determined to determine whether the current time is a specific time, such as a weekend or holiday. If so, the sales record corresponding to the specific period is obtained to determine the hot-selling period.
[0107] Among them, if the current period is a hot-selling period, some time can be reserved for the user to pick up the goods, and if the current period is not a hot-selling period, it can be reserved for the user before the hot-selling period. In particular, if the current period is not a hot-selling period, before determining the latest pick-up time, an optional time can also be sent to the user, and the optional time includes a preset time period after the start time of the hot-selling period, or the start time of the hot-selling period. If the user chooses the first option, the user's level in the target store is obtained. If the level is sufficient, the latest pick-up time at this time is determined to be the time corresponding to the first option. If the level is not enough, the user's deposit can be obtained, and the latest pick-up time is determined to be this time. The user's level in the target store can be determined based on whether the user is a member, the number of historical purchase orders of the user, the total purchase amount, etc.
[0108] It can be seen that in this example, determining the latest pickup time according to the hot-selling period can improve the intelligence of message processing for users' purchase orders and ensure the shopping experience of customers in the target store.
[0109] In a possible instance, after obtaining the pickup appointment request for the pickup appointment code, the method further includes: determining the target appointment account according to the pickup appointment request; determining the historical appointment record of the target appointment account; determining the probability that the purchase order of the target appointment account in the historical appointment record is canceled; when the probability that the purchase order is canceled is greater than a preset probability, outputting a prompt message, the prompt message being used to indicate that the appointment has failed; when the probability that the purchase order is canceled is not greater than the preset probability, displaying the pickup voucher and the latest pickup time on the display screen.
[0110] When users choose offline payment, the store will reserve the target product for the user before the latest pickup time, and the user has not paid at this time. Therefore, it is necessary to determine the user's purchase history when purchasing the product. If the user's purchase orders are cancelled multiple times, it means that the user has repeatedly timed out and failed to pick up the goods. At this time, it is determined that the user cannot use the offline payment function.
[0111] It can be seen that in this example, the user's payment methods are determined based on the probability of the user's purchase order being cancelled, which improves the intelligence and flexibility of sales information processing and ensures the sales needs of the target store.
[0112] It can be seen that in this example, a try-on time period is recommended for users who need to try on clothes, which improves the intelligence of processing sales information and improves the user experience.
[0113] For the above embodiments, please refer to Figure 7 , Figure 7 1 is a functional unit block diagram of a digital human-in-one machine provided in an embodiment of the present application. Figure 7As shown, the digital human integrated machine is connected to the terminal device of the target shop in communication, and the digital human integrated machine includes a display screen, including: a determination unit 301, used to determine at least one candidate product from multiple reference products according to a product recommendation request, and the multiple reference products are products sold by the target shop; a playback unit 302, used to play the digital human introduction video corresponding to the at least one candidate product on the display screen in sequence; an acquisition unit 303, used to acquire first feedback information, the first feedback information is used to indicate the target product, and the target product is a product among the at least one candidate product; a generation unit 304, used to If the feedback information includes a try-on request for the target product, facial recognition is performed on the surveillance image of the target store in the current time period to obtain current pedestrian flow information; and is used to obtain the Wi-Fi signal strength of the target store in the current time period; and is used to update the current pedestrian flow information according to the Wi-Fi signal strength to obtain target pedestrian flow information; and is used to determine the congestion level of the target store according to the target pedestrian flow information; and is used to determine the best try-on time period according to the congestion level; a sending unit 305 is used to send a try-on appointment request to the terminal device, and the try-on appointment request includes the best try-on time period.
[0114] In a possible example, in terms of updating the pedestrian flow information according to the Wi-Fi signal strength to obtain target pedestrian flow information, the generating unit 304 is specifically used to: obtain reference pedestrian flow information of the target store in a first time period, where the first time period is an adjacent time period of the current time period; obtain a reference Wi-Fi signal strength of the target store in the first time period; determine a Wi-Fi signal strength change trend according to the Wi-Fi signal strength of the current time period and the reference Wi-Fi signal strength; determine a pedestrian flow change trend according to the current pedestrian flow information and the reference pedestrian flow information; when the Wi-Fi signal strength change trend is consistent with the pedestrian flow change trend, determine the current pedestrian flow information as the target pedestrian flow information; when the Wi-Fi signal strength change trend is inconsistent with the pedestrian flow change trend, obtain the target pedestrian flow information according to the Wi-Fi signal strength change trend and the reference pedestrian flow information.
[0115] In a possible example, in terms of determining the optimal try-on time period according to the congestion level, the generation unit 304 is specifically used to: when the congestion level is greater than a preset value, obtain the number of target products that the target account has reserved for try-on; determine whether the number of target products is greater than a preset number; if so, calculate the predicted congestion levels of multiple remaining time periods respectively, and the multiple remaining time periods are the time periods that are located after the current time period during the business hours of the target store on that day; determine that the remaining time period whose predicted congestion level is less than the preset value and is closest to the current time period is the optimal try-on time period.
[0116] In a possible example, before determining that the predicted degree of congestion is less than the preset value and the remaining time period closest to the current time period is the optimal try-on time period, the generation unit 304 is further used to: determine the number of accounts that have made reservations for try-ons corresponding to the remaining time period closest to the current time period; if the number of accounts is greater than a first preset number, obtain the first product type of the target product, and obtain the second product type of the try-on product corresponding to the account that has made a reservation for try-on; when the number of try-on products of the same type as the first product in the second product type is greater than a second preset number, determine that the predicted degree of congestion is less than the preset value and the remaining time period that is less than the preset time from the current time period is the optimal try-on time period.
[0117] In a possible example, after obtaining the first feedback information, the generation unit 304 is further used to: if the first feedback information includes a purchase request for the target commodity, generate a purchase order for the target commodity, and display a pick-up appointment code on the display screen when an offline payment request is obtained, and after obtaining a pick-up appointment request for the pick-up appointment code, display a pick-up voucher and a latest pick-up time on the display screen; send order information of the purchase order to the terminal device, and display a pick-up voucher and a latest pick-up time on the display screen; send stocking information to the terminal device according to the purchase order, the stocking information includes the target commodity; after the latest pick-up time has passed, query the order status of the purchase order, the order status includes completed or incomplete; when the order status is incomplete, send an order cancellation instruction to the terminal device, the order cancellation instruction is used to instruct the terminal device to cancel the purchase order.
[0118] In a possible example, before displaying the pick-up voucher and the latest pick-up time on the display screen, the generation unit 304 is further used to: obtain the inventory quantity of the target product in the target store; obtain the sales record of the target product; predict today's sales volume of the target product based on the sales record; when the inventory quantity is greater than today's sales volume, determine the latest pick-up time as the closing time of the target store; when the inventory quantity is not greater than today's sales volume, determine the hot-selling period of the target product based on the sales record; determine whether the current moment belongs to the hot-selling period; if so, determine the latest pick-up time as a moment after a preset period from the current moment; if not, determine the latest pick-up time as the starting moment of the hot-selling period.
[0119] In a possible example, after obtaining the pickup reservation request for the pickup reservation code, the generation unit 304 is further used to: determine the target reservation account according to the pickup reservation request; determine the historical reservation record of the target reservation account; determine the probability that the purchase order of the target reservation account in the historical reservation record is canceled; when the probability that the purchase order is canceled is greater than a preset probability, output a prompt message, wherein the prompt message is used to indicate that the reservation has failed; when the probability that the purchase order is canceled is not greater than the preset probability, display the pickup voucher and the latest pickup time on the display screen.
[0120] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.
[0121] In the case of integrated units, see Figure 8 , Figure 8 This is a functional unit block diagram of another digital human-in-one machine provided by an embodiment of the present application. Figure 8 In the embodiment, the digital human integrated machine 30 includes: a processing module 312 and a communication module 311. The processing module 312 is used to control and manage the actions of the digital human integrated machine, for example, to execute the steps of the determination unit 301, the playback unit 302, the acquisition unit 303, the generation unit 304 and the sending unit 305, and / or to execute other processes of the technology described herein. The communication module 311 is used for the interaction between the digital human integrated machine 30 and other devices. Figure 8 As shown, the digital human integrated machine 30 may further include a storage module 313 , and the storage module 313 is used to store program codes and data of the digital human integrated machine 30 .
[0122] Among them, the processing module 312 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 311 can be a transceiver, an RF circuit or a communication interface, and the like. The storage module 313 can be a memory.
[0123] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The above digital human integrated machine 30 can execute the above Figure 3 The digital human-in-one machine sales information processing method shown.
[0124] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can 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 or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0125] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.
[0126] An embodiment of the present application also provides a computer program product, wherein a computer program product includes a computer program, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes a digital human all-in-one machine.
[0127] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0128] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0129] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0130] The units described above 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 distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0131] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0132] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.
[0133] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.
[0134] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for processing information of a digital human-in-one machine, characterized in that: Applied to a digital human machine, the digital human machine is communicatively connected with a terminal device of a target store, the digital human machine includes a display screen, and the method includes: The digital human machine determines at least one candidate commodity from a plurality of reference commodities according to the commodity recommendation request, wherein the plurality of reference commodities are commodities sold by the target store; Playing the digital human introduction video corresponding to the at least one candidate product in sequence on the display screen; Acquire first feedback information, where the first feedback information is used to indicate a target commodity, where the target commodity is a commodity among the at least one candidate commodity; If the first feedback information includes a request for trying on the target product, facial recognition is performed on the surveillance image of the target store during the current time period to obtain current human traffic information; and the Wi-Fi signal strength of the target store during the current time period is obtained; the current human traffic information is updated according to the Wi-Fi signal strength to obtain target human traffic information; the congestion level of the target store is determined according to the target human traffic information; and the best time period for trying on the products is determined according to the congestion level; A try-on reservation request is sent to the terminal device, wherein the try-on reservation request includes the optimal try-on time period.
2. The method according to claim 1, characterized in that The updating of the human flow information according to the Wi-Fi signal strength to obtain target human flow information includes: Acquire reference traffic information of the target store in a first time period, where the first time period is an adjacent time period of the current time period; Obtaining a reference Wi-Fi signal strength of the target store during the first time period; Determine a Wi-Fi signal strength change trend according to the Wi-Fi signal strength in the current period and the reference Wi-Fi signal strength; Determine a crowd flow change trend according to the current crowd flow information and the reference crowd flow information; When the change trend of the Wi-Fi signal strength is consistent with the change trend of the human flow, determining the current human flow information as the target human flow information; When the Wi-Fi signal strength variation trend is inconsistent with the human flow variation trend, target human flow information is obtained according to the Wi-Fi signal strength variation trend and the reference human flow information.
3. The method according to claim 2, characterized in that Determining the best fitting time period according to the degree of crowding includes: When the congestion level is greater than a preset value, obtaining the number of target products that the target account has reserved for trying on; Determine whether the quantity of the target product is greater than a preset quantity; If yes, then respectively calculate the predicted congestion levels of a plurality of remaining time periods, where the plurality of remaining time periods are time periods after the current time period during the business hours of the target store on the day; It is determined that the predicted congestion level is less than the preset value, and the remaining time period closest to the current time period is the optimal fitting time period.
4. The method according to claim 3, characterized in that Before determining that the predicted congestion level is less than the preset value and the remaining time period closest to the current time period is the optimal fitting time period, the method further includes: Determine the number of accounts that have made reservations for trying on clothes corresponding to the remaining time period closest to the current time period; If the number of accounts is greater than the first preset number, obtaining the first product type of the target product, and obtaining the second product type of the try-on product corresponding to the account that has made an appointment for the try-on; When the number of try-on products of the same type as the first product in the second product type is greater than a second preset number, the remaining time period whose predicted congestion level is less than the preset value and whose distance from the current time period is less than a preset time is determined to be the optimal try-on time period.
5. The method according to any one of claims 1 to 4, characterized in that: After obtaining the first feedback information, the method further includes: If the first feedback information includes a purchase request for the target product, a purchase order for the target product is generated, and when an offline payment request is obtained, a pickup reservation code is displayed on the display screen, and after a pickup reservation request for the pickup reservation code is obtained, a pickup voucher and a latest pickup time are displayed on the display screen; the order information of the purchase order is sent to the terminal device, and the pickup voucher and the latest pickup time are displayed on the display screen; Sending stocking information to the terminal device according to the purchase order, wherein the stocking information includes the target commodity; After the latest delivery time has passed, query the order status of the purchase order, where the order status includes completed or uncompleted; When the order status is incomplete, an order cancellation instruction is sent to the terminal device, where the order cancellation instruction is used to instruct the terminal device to cancel the purchase order.
6. The method according to claim 5, characterized in that After obtaining the pickup reservation request for the pickup reservation code, the method further includes: Determine a target reservation account number according to the pickup reservation request; Determine the historical reservation records of the target reservation account; Determining the probability that the purchase order of the target reservation account in the historical reservation record is cancelled; When the probability that the purchase order is cancelled is greater than a preset probability, outputting a prompt message, wherein the prompt message is used to indicate that the reservation has failed; When the probability that the purchase order is cancelled is not greater than the preset probability, the pick-up voucher and the latest pick-up time are displayed on the display screen.
7. A digital human all-in-one machine, characterized in that: The digital human integrated machine is connected to the terminal device of the target store through communication, the digital human integrated machine includes a display screen, and the device includes: a determination unit, configured to determine at least one candidate commodity from a plurality of reference commodities according to the commodity recommendation request, wherein the plurality of reference commodities are commodities sold by the target store; A playback unit, configured to play the digital human introduction video corresponding to the at least one candidate product in sequence on the display screen; an acquiring unit, configured to acquire first feedback information, wherein the first feedback information is used to indicate a target commodity, and the target commodity is a commodity among the at least one candidate commodity; a generating unit, configured to perform facial recognition on the surveillance image of the target store in the current time period to obtain current human flow information if the first feedback information includes a try-on request for the target product; and to obtain the Wi-Fi signal strength of the target store in the current time period; and to update the current human flow information according to the Wi-Fi signal strength to obtain target human flow information; and to determine the congestion level of the target store according to the target human flow information; and to determine the best try-on time period according to the congestion level; The sending unit is used to send a try-on reservation request to the terminal device, wherein the try-on reservation request includes the optimal try-on time period.
8. A digital human all-in-one machine, characterized in that: The method comprises a processor, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the method according to any one of claims 1 to 7 can be implemented.
10. A computer program product having a computer program or instructions stored thereon, characterized in that: When the computer program or instructions included in the computer program product are executed by a processor, the method according to any one of claims 1 to 7 can be implemented.
