Intelligent shopping guide system and method for store

Abstract

The invention relates to the technical field of shopping guidance, in particular to an intelligent shopping guidance system and method for a store. A plurality of human body sensors; a plurality of shopping guide electronic screens; the customer ID determining module is used for determining a customer ID in a video frame image in the panoramic video stream data according to an image area; the to-be-selected commodity determination module is used for forming a to-be-selected container commodity set based on the commodity codes associated with the container codes; the historical commodity determination module is used for forming a historical commodity code set based on commodity codes in historical shopping records; the pushed commodity selection module is used for selecting at least one pushed commodity code from the to-be-selected container commodity set according to the historical commodity code set; and the pushing module is used for matching the commodity pushing information according to the at least one pushing commodity code and playing the commodity pushing information after the shopping guide electronic screen receives the commodity pushing information. According to the invention, the shopping behavior of the customer is analyzed, personalized commodity recommendation is realized, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shopping guidance, and in particular to an intelligent store shopping guidance system and method. Background Art

[0002] With the development of modern retail industry, convenience stores, as a convenient and efficient retail format, play an increasingly important role in people's lives. However, despite the continuous optimization of convenience stores in terms of product variety, store layout and customer service, there are still obvious deficiencies in intelligently analyzing customer purchasing needs and guiding purchases.

[0003] At present, most convenience stores still rely on traditional sales data and customer feedback to analyze customer needs, which has obvious lags and limitations. Convenience stores often lack precision and pertinence in product recommendations and promotion strategy formulation.

[0004] In addition, the existing convenience store intelligent systems are mostly limited to the automation of basic functions such as inventory management and cashier settlement, but lack in-depth analysis of customer purchasing behavior and personalized guidance. Although some convenience stores have installed video surveillance equipment, it is mainly used for security precautions and has yet to be developed in terms of marketing promotion. Summary of the invention

[0005] In order to analyze customer shopping behavior, implement personalized product recommendations, and improve user experience, this application provides a smart store guidance system.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A smart store guidance system, comprising: An image acquisition module is used to collect panoramic video stream data in the store, where the store area is divided into a plurality of store sub-areas, and each store sub-area is pre-calibrated and matched with each image area of ​​a video frame image in the panoramic video stream data, and the plurality of store sub-areas include a verification sub-area; An identity verification module located in the verification sub-area, for providing identity verification services, obtaining a customer ID, and issuing a verification signal; A customer identification module is used to analyze the image area associated with the verification sub-area to obtain customer features after receiving the verification signal, and associate the customer features with the customer ID; Multiple human body sensors are installed in each container; Multiple shopping guide electronic screens are installed in each container; The human body sensor has a sensor code, the container has a container code, the shopping guide electronic screen has an electronic screen code, and the product has a product code. The sensor code is associated with the container code of the container where it is located, the shopping guide electronic screen code is associated with the container code of the container where it is located, and the product code is associated with the container code of the container where the product is located. When the human body sensor senses the presence of a person, it sends a first signal, wherein the first signal carries a sensor code; The store's intelligent shopping guidance system also includes: A customer ID determination module, configured to, upon receiving the first signal, match the container code according to the sensor code, match the store sub-area according to the container code, match the image area according to the store sub-area mapping, and determine the customer ID according to the image area in the video frame image in the panoramic video stream data; A module for determining commodities to be selected, used for forming a set of commodities to be selected in a container based on the commodity codes associated with the container codes; A historical commodity determination module, used to obtain historical shopping records associated with a customer ID, and to form a historical commodity code set based on commodity codes in the historical shopping records; A push commodity selection module, used for selecting at least one push commodity code from the to-be-selected container commodity set according to the historical commodity code set; The push module is used to match the product push information according to the at least one pushed product code and send it to the shopping guide electronic screen associated with the container code. The shopping guide electronic screen plays the product push information after receiving it.

[0007] In a preferred example, the present application can be further configured as: pushing a product selection module, including: A judgment unit, used for judging whether any element in the to-be-selected container commodity set exists in the historical commodity code set; A unit for determining commodities to be pushed, used to use the same commodity code in the historical commodity code set and the commodity set to be selected as a commodity code element in the commodity set to be pushed, if any; A selection unit is used to select at least one push commodity code from the set of commodities to be pushed.

[0008] In a preferred example, the present application can be further configured as: pushing a product selection module, further comprising: a reference value determination unit, configured to determine the reference value p according to the quantity of goods in each historical purchase order associated with the customer ID if the reference value p does not exist; A sampling value determination unit, used to determine a sampling value m in a projectable range 1 to b according to a reference value p, wherein b is a positive integer and m is a positive integer; The commodity traversal combination unit is used to select 1 to a elements in the historical commodity code set at random, and select 1 to m elements in the commodity code associated with the container code at random, to form an associated commodity set, and traverse the combination to obtain multiple groups of associated commodity sets; A statistical unit, used to count the number of times n each group of associated product sets appears in historical orders; The calculation unit is used to calculate the recommendation value D of each group of associated product sets; it is calculated in the following way: Among them, i is the number of elements in the associated product set, n is the number of times the associated product set appears in historical orders; α is the recommendation index, β is the penalty coefficient, and m is the sampling value.

[0009] In a preferred example, the present application can be further configured as follows: determining the sampling value m in the projectable range 1-b according to the reference value p includes: If p>b, then m=b; If p≤b, then m=p.

[0010] In a preferred example, the present application may be further configured as follows: the reference value p is the average rounded value of the quantity of goods in each historical purchase order associated with the customer ID.

[0011] The second object of the invention is achieved by the following technical solutions: A store intelligent shopping guidance method, comprising: When the first signal is received, the container code is matched according to the sensor code, the store sub-area is matched according to the container code, the image area is matched according to the store sub-area mapping, and the customer ID is determined according to the image area in the video frame image in the panoramic video stream data; Forming a container commodity set to be selected based on the commodity codes associated with the container codes; Acquire historical shopping records associated with the customer ID, and form a historical product code set based on product codes in the historical shopping records; Select at least one pushed commodity code from the to-be-selected container commodity set according to the historical commodity code set; The product push information is matched according to the at least one pushed product code and sent to the shopping guide electronic screen associated with the container code. The shopping guide electronic screen plays the product push information after receiving it.

[0012] In a preferred example, the present application may be further configured as follows: selecting at least one push commodity code from the to-be-selected container commodity set according to the historical commodity code set, including: Determine whether any element in the to-be-selected container commodity set exists in the historical commodity code set; If it exists, the same commodity code in the historical commodity code set and the commodity set to be selected is used as the commodity code element in the commodity set to be pushed; At least one pushed commodity code is selected from the set of commodities to be pushed.

[0013] In a preferred example, the present application may be further configured as follows: selecting at least one push commodity code from the to-be-selected container commodity set according to the historical commodity code set, and further comprising: If it does not exist, determine the reference value p based on the quantity of goods in each historical purchase order associated with the customer ID; Determine the sampling value m in the projectable range 1~b according to the reference value p, where b is a positive integer and m is a positive integer; Randomly select 1 to a elements in the historical commodity code set, and randomly select 1 to m elements in the commodity code associated with the container code to form an associated commodity set, and traverse the combination to obtain multiple sets of associated commodity sets; Count the number of times each group of associated product sets appears in historical orders; Calculate the recommendation value D of each group of associated product sets; it is calculated as follows: Among them, i is the number of elements in the associated product set, n is the number of times the associated product set appears in historical orders; α is the recommendation index, β is the penalty coefficient, and m is the sampling value.

[0014] In summary, the present application includes at least one of the following beneficial technical effects: 1. Through video surveillance and artificial intelligence technology, intelligent services such as in-store customer behavior analysis and product recommendations can be realized, which can accurately identify the customer's identity and make accurate product recommendations based on the customer's shopping history and preferences; 2. Prioritize the associated product sets with more elements and more occurrences, use the above formula to calculate the recommendation value D, and then recommend more appropriate associated product sets to improve customer shopping experience and increase sales; 3. The image acquisition module collects panoramic video stream data in the store to achieve comprehensive monitoring of customer behavior. At the same time, the identity authentication module and customer identification module are used to accurately identify and extract customer identities. In addition, through multiple human sensors, multiple shopping guide electronic screens and related code matching, combined with user historical shopping record analysis technology, suitable products are recommended in real time during the user's shopping process, achieving accurate analysis of customer shopping behavior and product recommendations, improving customer shopping experience, increasing sales, and promoting the transformation and upgrading of retail stores. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the connection of various modules of the smart store guidance system in one embodiment of the present application; Figure 2 This is a schematic diagram of a list of stores where the smart store guidance system is applied in one embodiment of the present application; Figure 3 It is a schematic diagram of the positions of the cargo cabinet, the electronic shopping guide screen and the human body sensor in one embodiment of the present application; Figure 4 This is a flow chart for implementing the smart store guidance method in one embodiment of the present application.

[0016] Figure numerals: 1. cabinet; 2. shopping guide electronic screen; 3. human body sensor. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0018] It should be noted that the terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure.

[0019] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0020] Reference Figures 1 to 3 The smart store guidance system includes an image acquisition module, a customer recognition module, multiple human body sensors 3 and multiple shopping guide electronic screens 2.

[0021] Among them, the image acquisition module adopts a panoramic camera module, which is installed on the top ceiling of the store to collect panoramic video stream data in the store. Multiple human sensors 3 are installed on each container, and multiple shopping guide electronic screens 2 are installed on each container; the store area is divided into multiple store sub-areas, and the specific division basis can be based on the containers and / or functional areas in the sub-area, for example, a container and part of its front or surrounding area are used as a sub-area, and for example, the cashier counter and its surrounding area are used as a cashier sub-area, etc., which are specifically pre-divided and set according to the actual store conditions. Each store sub-area is pre-calibrated and matched with each image area of ​​the video frame image in the panoramic video stream data, that is, each store sub-area is pre-calibrated and matched with each image area of ​​the video frame image in the panoramic video stream data. Specifically, the personnel use annotation tools to manually draw the annotation area in the video frame image according to the actual layout of the convenience store, and can also add tags to define the area name, such as "verification sub-area".

[0022] The multiple storefront sub-areas include a verification sub-area; the verification sub-area is set at the store entrance, and the verification sub-area is set with an identity verification module to provide customers with identity verification services, obtain customer IDs, and send verification signals; the identity verification module can be a method of scanning a code / swiping a card to identify the login mini program / app, etc., to obtain the customer ID. Moreover, after obtaining the customer ID, the identity verification module sends a verification signal.

[0023] The customer identification module is used to analyze the image area associated with the verification sub-area to obtain customer features after receiving the verification signal, and associate the customer features with the customer ID.

[0024] Specifically, first, the image region associated with the verification sub-region is segmented and extracted. Specifically, an image segmentation algorithm, such as threshold segmentation, edge detection, region growing, etc., can be used to accurately extract the target region.

[0025] The human body contour is further segmented and extracted, such as Freeman Chain Codes, to extract the customer's boundary and shape features.

[0026] Then, feature extraction is performed. Different algorithms can be used to extract different features, such as clothing features (such as color, style, brand), etc. Some of them are used as customer features of the customer, and the customer features are associated with the customer ID. For example, shape analysis algorithms can be used, and color histograms, color moments and other methods can be used to extract color features, etc. This step is mainly used to distinguish customers from other customers.

[0027] In one embodiment, denoising and image enhancement may be performed after segmentation and extraction to remove noise and interference in the image and improve the clarity and recognition of the image.

[0028] The human body sensor 3 has a sensor code, the container has a container code, the shopping guide electronic screen 2 has an electronic screen code, and the product has a product code. The sensor code is associated with the container code of the container where it is located, the shopping guide electronic screen 2 code is associated with the container code of the container where it is located, and the product code is associated with the container code of the container where the product is located.

[0029] When the human body sensor 3 senses the presence of a person, it sends out a first signal, and the first signal carries the sensor code.

[0030] The store intelligent shopping guidance system also includes a customer ID determination module, a to-be-selected product determination module, a historical product determination module, a push product selection module and a push module.

[0031] Among them, the customer ID determination module is used to match the container code according to the sensor code when receiving the first signal, match the store sub-area according to the container code, match the image area according to the store sub-area mapping, and determine the customer ID according to the image area in the video frame image in the panoramic video stream data.

[0032] Specifically, after matching the store sub-area according to the container code, the image area is matched according to the store sub-area mapping, the matched image area is segmented and extracted, and then the customer outline is extracted from the extracted graphic area again to perform feature recognition, such as clothing features (such as color, style, brand), etc., and several of them are used as customer features of the customer; then they are matched and compared with the customer features of each customer ID recognized by the aforementioned customer recognition module. If they are the same, the customer ID is determined.

[0033] The module for determining commodities to be selected is used to form a container commodity set to be selected based on commodity codes associated with the container codes.

[0034] Specifically, the system database has built-in commodity codes associated with each container code, such as commodity codes of various beverage commodities stored in the water tank container, which can be pre-entered by personnel and regularly updated through inbound and outbound goods management.

[0035] The historical product determination module is used to obtain the historical shopping records associated with the customer ID, and to form a historical product code set based on the product codes in the historical shopping records.

[0036] It can be understood that each customer ID is a member who has registered for the app / mini program. By recording the order information of each settlement of each customer ID, the shopping record of each time can be obtained, and then the historical shopping records of each customer ID can be recorded and stored; each historical shopping record contains at least the product code, quantity, price, etc. of the product purchased by the customer, so the product codes in all historical shopping records associated with the customer ID can be summarized into a historical product code set.

[0037] The pushed commodity selection module is used to select at least one pushed commodity code from the to-be-selected container commodity set according to the historical commodity code set; specifically, the pushed commodity selection module includes a judgment unit, a to-be-pushed commodity determination unit, a selection unit, a reference value determination unit, a sampling value determination unit, a commodity traversal combination unit, a statistical unit and a calculation unit.

[0038] The judging unit is used to judge whether there is any element in the to-be-selected container commodity set in the historical commodity code set.

[0039] If there is, the commodity determination unit to be pushed uses the same commodity code in the historical commodity code set and the commodity set to be selected as the commodity code element in the commodity set to be pushed, and then obtains the commodity set to be pushed; the selection unit is used to select at least one push commodity code in the commodity set to be pushed. The number of pushed commodity codes selected is based on the actual number of pushable codes configured by the shopping guide electronic screen 2. For example, if the number of split screens of the shopping guide electronic screen 2 is 2, then 2 push commodity codes are selected; if the elements in the commodity set to be pushed are insufficient, all are selected; if the elements in the commodity set to be pushed are exceeded, 2 are selected at random.

[0040] If not, the reference value determination unit determines the reference value p according to the quantity of commodities in each historical purchase order associated with the customer ID.

[0041] The sampling value determination unit is used to determine a sampling value m in the projectable range 1-b according to a reference value p, wherein b is a positive integer and m is a positive integer.

[0042] The commodity traversal combination unit is used to arbitrarily select 1 to a elements in the historical commodity code set and arbitrarily select 1 to m elements in the commodity code associated with the container code to form an associated commodity set, and traverse the combination to obtain multiple groups of associated commodity sets.

[0043] Specifically, the reference value p is the average rounded value of the quantity of goods in each historical purchase order associated with the customer ID. In one embodiment, the reference value p may also be a mode value.

[0044] Determining the sampling value m in the projectable range 1~b according to the reference value p includes: if p>b, then m=b; if p≤b, then m=p. b is the number of pushable items that the actual shopping guide electronic screen 2 is configured with. For example, if the number of split screens of the shopping guide electronic screen 2 is 4, and the number of items that can be pushed at the same time when the shopping guide electronic screen 2 is configured is 4, then b=4.

[0045] Continuing with the previous example, if p is 3, p≤b, then m=p=3; if p is 5, p>b, then m=4. By limiting m to the range of 1~b, computing power can be saved and the number of combinations can be reduced.

[0046] The statistical unit is used to count the number of times n that each group of associated product sets appears in historical orders.

[0047] It is worth noting that a group of related product sets appearing in a historical order means that all elements in the group of related product sets appear in a historical order.

[0048] The calculation unit is used to calculate the recommendation value D of each group of associated product sets; it is calculated in the following way:

[0049] Among them, i is the number of elements in the associated product set, n is the number of times the associated product set appears in historical orders; α is the recommendation index, β is the penalty coefficient, and m is the sampling value.

[0050] Based on this basic formula, through a large amount of sample data training, the values ​​of α and β can be finally obtained. A sample data includes at least two sub-sample data, each sub-sample data includes the number of elements i, the number of times n, the sampling value m, and the comparison relationship of the recommended value D between the two sub-sample data.

[0051] For example, a sub-sample data includes i=4, n=5, m=4, and a sub-sample data includes i=3, n=8, m=4, D1>D2; wherein D1 is the recommended value of the former sub-sample data, and D2 is the recommended value of the latter sub-sample data. In one embodiment, α is 1.6 and β is 1.5.

[0052] It is understandable that the fewer elements in the associated product set, the more likely they appear in historical orders. Therefore, in order to avoid this situation, the associated product set with more elements and more occurrences is preferentially selected, and the recommendation value D is calculated using the aforementioned formula to recommend a more appropriate associated product set, thereby improving customer shopping experience and increasing sales.

[0053] The push module is used to match the product push information according to at least one pushed product code, and send it to the shopping guide electronic screen 2 associated with the container code, and the shopping guide electronic screen 2 plays it after receiving the product push information. Specifically, the product push information corresponding to each product code is pre-stored in the database, and the product push information can be the publicity and promotion information of the product.

[0054] This application also provides a store intelligent shopping guidance method, refer to Figure 4 ,include: S1. When a first signal is received, the container code is matched according to the sensor code, the store sub-area is matched according to the container code, the image area is matched according to the store sub-area mapping, and the customer ID is determined according to the image area in the video frame image in the panoramic video stream data.

[0055] S2. Composing a container commodity set to be selected based on the commodity codes associated with the container codes.

[0056] S3. Obtain historical shopping records associated with the customer ID, and form a historical product code set based on the product codes in the historical shopping records.

[0057] S4. Select at least one pushed product code from the to-be-selected container product set according to the historical product code set.

[0058] S5. Match the product push information according to at least one pushed product code and send it to the shopping guide electronic screen 2 associated with the container code. The shopping guide electronic screen 2 plays the product push information after receiving it.

[0059] Among them, S4 includes: S41. Determine whether any element in the to-be-selected container commodity set exists in the historical commodity code set.

[0060] S42: If so, the same commodity code in the historical commodity code set and the commodity set to be selected is used as the commodity code element in the commodity set to be pushed.

[0061] S43: Select at least one push product code from the set of products to be pushed.

[0062] S44. If it does not exist, determine the reference value p according to the quantity of goods in each historical purchase order associated with the customer ID.

[0063] S45. Determine a sampling value m in the projectable range 1 to b according to the reference value p, wherein b is a positive integer and m is a positive integer.

[0064] S46. Randomly select 1 to a elements in the historical commodity code set, and randomly select 1 to m elements in the commodity code associated with the container code to form an associated commodity set, and traverse the combination to obtain multiple groups of associated commodity sets.

[0065] S47. Count the number of times n that each group of associated product sets appears in the historical orders.

[0066] S48, calculating the recommendation value D of each group of associated product sets; the calculation is performed in the following way:

[0067] Among them, i is the number of elements in the associated product set, n is the number of times the associated product set appears in historical orders; α is the recommendation index, β is the penalty coefficient, and m is the sampling value.

[0068] The specific definition of the store intelligent shopping guidance method can be found in the above definition of the store intelligent shopping guidance system, which will not be repeated here. Each step of the above store intelligent shopping guidance method can be implemented in whole or in part by software, hardware or a combination thereof.

[0069] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0070] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0071] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0072] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0073] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0074] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. The store intelligent shopping guidance system is characterized by: include: An image acquisition module is used to collect panoramic video stream data in the store, where the store area is divided into a plurality of store sub-areas, and each store sub-area is pre-calibrated and matched with each image area of ​​a video frame image in the panoramic video stream data, and the plurality of store sub-areas include a verification sub-area; An identity verification module located in the verification sub-area, for providing identity verification services, obtaining a customer ID, and issuing a verification signal; A customer identification module is used to analyze the image area associated with the verification sub-area to obtain customer features after receiving the verification signal, and associate the customer features with the customer ID; Multiple human body sensors are installed in each container; Multiple shopping guide electronic screens are installed in each container; The human body sensor has a sensor code, the container has a container code, the shopping guide electronic screen has an electronic screen code, and the product has a product code. The sensor code is associated with the container code of the container where it is located, the shopping guide electronic screen code is associated with the container code of the container where it is located, and the product code is associated with the container code of the container where the product is located. When the human body sensor senses the presence of a person, it sends a first signal, wherein the first signal carries a sensor code; The store's intelligent shopping guidance system also includes: A customer ID determination module, configured to, upon receiving the first signal, match the container code according to the sensor code, match the store sub-area according to the container code, match the image area according to the store sub-area mapping, and determine the customer ID according to the image area in the video frame image in the panoramic video stream data; A module for determining commodities to be selected, used for forming a set of commodities to be selected in a container based on the commodity codes associated with the container codes; A historical commodity determination module, used to obtain historical shopping records associated with a customer ID, and to form a historical commodity code set based on commodity codes in the historical shopping records; A push commodity selection module, used for selecting at least one push commodity code from the to-be-selected container commodity set according to the historical commodity code set; The push module is used to match the product push information according to the at least one pushed product code and send it to the shopping guide electronic screen associated with the container code. The shopping guide electronic screen plays the product push information after receiving it.

2. The store intelligent shopping guidance system according to claim 1, characterized in that: Push product selection module, including: A judgment unit, used for judging whether any element in the to-be-selected container commodity set exists in the historical commodity code set; A unit for determining commodities to be pushed, used to use the same commodity code in the historical commodity code set and the commodity set to be selected as a commodity code element in the commodity set to be pushed, if any; A selection unit is used to select at least one push commodity code from the set of commodities to be pushed.

3. The store intelligent shopping guidance system according to claim 2, characterized in that: The push product selection module also includes: a reference value determination unit, configured to determine the reference value p according to the quantity of goods in each historical purchase order associated with the customer ID if the reference value p does not exist; A sampling value determination unit, used to determine a sampling value m in a projectable range 1 to b according to a reference value p, wherein b is a positive integer and m is a positive integer; The commodity traversal combination unit is used to select 1 to a elements in the historical commodity code set at random, and select 1 to m elements in the commodity code associated with the container code at random, to form an associated commodity set, and traverse the combination to obtain multiple groups of associated commodity sets; A statistical unit, used to count the number of times n that each group of associated product sets appears in historical orders; The calculation unit is used to calculate the recommendation value D of each group of associated product sets; it is calculated in the following way: ; Where i is the number of elements in the associated product set, n is the number of times the associated product set appears in historical orders; α is the recommendation index, β is the penalty coefficient, and m is the sampling value.

4. The store intelligent shopping guidance system according to claim 3, characterized in that: Determining the sampling value m in the projectable range 1~b according to the reference value p includes: If p>b, then m=b; If p≤b, then m=p.

5. The store intelligent shopping guidance system according to claim 3, characterized in that: The reference value p is the average rounded value of the quantity of goods in each historical purchase order associated with the customer ID.

6. The store intelligent shopping guidance method based on the store intelligent shopping guidance system of claim 1 is characterized in that: include: When the first signal is received, the container code is matched according to the sensor code, the store sub-area is matched according to the container code, the image area is matched according to the store sub-area mapping, and the customer ID is determined according to the image area in the video frame image in the panoramic video stream data; Forming a container commodity set to be selected based on the commodity codes associated with the container codes; Acquire historical shopping records associated with the customer ID, and form a historical product code set based on product codes in the historical shopping records; Select at least one pushed commodity code from the to-be-selected container commodity set according to the historical commodity code set; The product push information is matched according to the at least one pushed product code and sent to the shopping guide electronic screen associated with the container code. The shopping guide electronic screen plays the product push information after receiving it.

7. The store intelligent shopping guidance method according to claim 6, characterized in that: Selecting at least one pushed commodity code from the to-be-selected container commodity set according to the historical commodity code set includes: Determine whether any element in the to-be-selected container commodity set exists in the historical commodity code set; If it exists, the same commodity code in the historical commodity code set and the commodity set to be selected is used as the commodity code element in the commodity set to be pushed; At least one pushed commodity code is selected from the set of commodities to be pushed.

8. The store intelligent shopping guidance method according to claim 7, characterized in that: The method further includes: selecting at least one push commodity code from the to-be-selected container commodity set according to the historical commodity code set; If it does not exist, determine the reference value p based on the quantity of goods in each historical purchase order associated with the customer ID; Determine the sampling value m in the projectable range 1~b according to the reference value p, where b is a positive integer and m is a positive integer; Randomly select 1 to a elements in the historical commodity code set, and randomly select 1 to m elements in the commodity code associated with the container code to form an associated commodity set, and traverse the combination to obtain multiple sets of associated commodity sets; Count the number of times each group of associated product sets appears in historical orders; Calculate the recommendation value D of each group of associated product sets; it is calculated as follows: ; Where i is the number of elements in the associated product set, n is the number of times the associated product set appears in historical orders; α is the recommendation index, β is the penalty coefficient, and m is the sampling value.

Images