Offline shoe and clothing store inventory marketing methods and related components based on video behavior analysis

Abstract

The present invention discloses an offline shoe and clothing store inventory marketing method and related components based on video behavior analysis. The method includes: using an avatar recognition algorithm to identify whether a consumer is a member; if the consumer is a member, identifying the consumer's in-store try-on behavior, and updating the current consumer's try-on list based on the in-store try-on behavior; determining whether the consumer has placed an order; if the consumer has placed an order, obtaining the consumer's total consumption amount and determining whether the total consumption amount is greater than a preset value; if the total consumption amount is greater than the preset value, inputting the target product information with the highest number of tries in the try-on list into a marketing model for discount calculation. Outputting discount information for the target product and pushing the discount information to the consumer. Based on consumer preferences and product characteristics, the present invention establishes a marketing model that adaptively matches products and people, thereby effectively reducing inventory costs, increasing consumer repurchase rates, brand influence, and overall store profits.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an offline shoe and clothing store inventory marketing method based on video behavior analysis and related components. Background Art

[0002] In the e-commerce era, offline footwear and apparel stores still hold a significant market share due to their advantages, such as low customer acquisition costs, verifiable product quality, and on-site customer experience. Consumers can visit a nearby physical store to observe and analyze the quality of the products they desire, and even try on the styles they like. While some consumers ultimately choose to place an order and take the clothes home, others choose not to, leaving the clothes stagnant in warehouses. Consequently, offline stores accumulate a wealth of valuable consumer information every day, leaving them untapped. Furthermore, with the rapid pace and variety of consumer demand, high inventory levels at footwear and apparel stores are driving up costs.

[0003] On the one hand, traditional store marketing methods lack effective consumer marketing methods, resulting in low consumer retention rates, low brand loyalty and influence, and thus low store profits; on the other hand, the handling of existing shoe and clothing inventory does not effectively utilize offline consumer behavior information, resulting in passive and inefficient inventory promotion methods. Summary of the Invention

[0004] The embodiment of the present invention provides an offline shoe and clothing store inventory marketing method and related components based on video behavior analysis, aiming to solve the problem of store inventory.

[0005] In a first aspect, an embodiment of the present invention provides an offline shoe and clothing store inventory marketing method based on video behavior analysis, comprising:

[0006] Use profile picture recognition algorithms to identify whether consumers are members;

[0007] If the customer is a member, the customer's in-store try-on behavior is identified, and the current customer's try-on list is updated based on the in-store try-on behavior, wherein the try-on list includes the tried items and the number of tries;

[0008] Determine whether the consumer has placed an order;

[0009] If an order is placed, the consumer's total consumption is obtained and it is determined whether the total consumption is greater than a preset value, where the total consumption is the sum of the current order consumption and the previous order consumption;

[0010] If the total consumption amount is greater than a preset value, the target product information ranked first in the try-on list is input into the marketing model for discount calculation, the discount information of the target product is output, and the discount information is pushed to the consumer.

[0011] In a second aspect, an embodiment of the present invention provides an offline shoe and clothing store inventory marketing device based on video behavior analysis, comprising:

[0012] The first recognition unit is used to use a head portrait recognition algorithm to identify whether the consumer is a member;

[0013] The second identification unit is used to identify the consumer's in-store try-on behavior if the consumer is a member, and update the current consumer's try-on list according to the in-store try-on behavior, wherein the try-on list includes the tried-on items and the number of try-ons;

[0014] The first judgment unit is used to judge whether the consumer places an order;

[0015] A second judgment unit is configured to obtain the total consumption amount of the consumer if an order is placed, and to judge whether the total consumption amount is greater than a preset value, wherein the total consumption amount is the sum of the current order consumption and the previous order consumption;

[0016] The calculation unit is used to input the target product information ranked first in the number of tries in the try-on list into the marketing model for discount calculation if the total consumption amount is greater than the preset value, output the discount information of the target product, and push the discount information to the consumer.

[0017] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the offline shoe and clothing store inventory marketing method based on video behavior analysis as described in the first aspect is implemented.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the offline shoe and clothing store inventory marketing method based on video behavior analysis as described in the first aspect is implemented.

[0019] The present invention discloses an offline shoe and apparel store inventory marketing method and related components based on video behavior analysis. The method comprises: using an avatar recognition algorithm to identify whether a consumer is a member; if the consumer is a member, identifying the consumer's in-store try-on behavior, and updating the current consumer's try-on list based on the in-store try-on behavior, wherein the try-on list includes the tried-on items and the number of times they have been tried on; determining whether the consumer has placed an order; if the consumer has placed an order, obtaining the consumer's total consumption and determining whether the total consumption is greater than a preset value, wherein the total consumption is the sum of the current order consumption and historical order consumption; if the total consumption is greater than the preset value, inputting the target product information with the highest number of tries on times in the try-on list into a marketing model for discount calculation, outputting discount information for the target product, and pushing the discount information to the consumer. The present invention establishes a marketing model that adaptively matches products and people based on consumer preferences and product characteristics, thereby effectively reducing inventory costs, increasing consumer repurchase rates, brand influence, and overall store profits. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flowchart of an offline shoe and clothing store inventory marketing method based on video behavior analysis provided by an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a sub-process of an offline shoe and clothing store inventory marketing method based on video behavior analysis provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of another sub-process of the offline shoe and clothing store inventory marketing method based on video behavior analysis provided by an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of another sub-process of the offline shoe and clothing store inventory marketing method based on video behavior analysis provided by an embodiment of the present invention;

[0025] Figure 5 A schematic diagram of another sub-process of the offline shoe and clothing store inventory marketing method based on video behavior analysis provided by an embodiment of the present invention;

[0026] Figure 6 A schematic block diagram of an offline shoe and clothing store inventory marketing device based on video behavior analysis provided by an embodiment of the present invention;

[0027] Figure 7A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0029] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0030] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0031] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0032] See below Figure 1 , Figure 1 A flowchart of an offline shoe and clothing store inventory marketing method based on video behavior analysis provided by an embodiment of the present invention specifically includes: steps S101 to S106.

[0033] S101. Using a head portrait recognition algorithm to identify whether the consumer is a member;

[0034] Specifically, terminal devices that can capture consumers' facial information and track their in-store behavior are installed in stores. Considering that cameras can be found everywhere in offline physical stores, the terminal devices can be cameras or other terminal devices, and are not restricted here.

[0035] In some implementations, the camera is communicatively connected to a computer device, and a head portrait recognition algorithm is designed in the computer device. The camera uses the head portrait recognition algorithm to identify whether the consumer is a member. The computer device can be a desktop computer, or a tablet computer, mobile phone or other electronic product.

[0036] S102: If the customer is a member, identify the customer's in-store try-on behavior and update the current customer's try-on list based on the in-store try-on behavior, where the try-on list includes the items tried on and the number of times tried on. If the customer is not a member, jump to step S501;

[0037] It is understandable that each member has a corresponding member account on the computer device, which can save various information such as the consumer's name, phone number, and try-on list.

[0038] Specifically, after the consumer is identified as a member by the camera, the camera continues to track the consumer's movements. If the consumer tries on a product, the computer device will record the consumer's behavior of trying on the product and save it to the try-on list under the consumer's corresponding member account, and update the number of times the product has been tried on in the try-on list, that is, the number is accumulated as long as the consumer tries on the product once.

[0039] It is understood that by storing information about items tried on by consumers, the computer device can be used to analyze consumer preferences and, based on these preferences, recommend products that are suitable for them. For example, if a consumer enters a store and is identified as a member, and then tries on casual clothing, the computer device may determine that the consumer is interested in casual clothing. Based on this interest, similar products may be recommended to the consumer, thereby increasing their interest and boosting the shoe and apparel store's sales while reducing inventory levels.

[0040] S103, determining whether the consumer has placed an order;

[0041] S104: If an order is placed, the total amount of the consumer's consumption is obtained, and it is determined whether the total amount of consumption is greater than a preset value, where the total amount of consumption is the sum of the current order consumption and the previous order consumption. If no order is placed, jump to step S106;

[0042] Specifically, after each order is placed by a consumer, the computer device saves the order amount in the consumer's corresponding membership account and accumulates the order amounts to obtain a total order amount. After each order is placed, the accumulated amount is compared with a preset amount set by the computer device to facilitate subsequent discount calculations for the product.

[0043] S105. If the total consumption amount is greater than the preset value, the target product information ranked first in the try-on list is input into the marketing model for discount calculation, the discount information of the target product is output, and the discount information is pushed to the consumer.

[0044] Specifically, once a consumer's total purchase exceeds a preset limit, the computer identifies the product most frequently tried on in the consumer's membership account and inputs that product's information into the marketing model to calculate a discount for that product. This information includes the product type and the number of times the consumer has tried it on. The product type can be either a non-slow-moving item or a slow-moving item.

[0045] Furthermore, if the product type is a non-slow-moving product, the marketing model outputs discount information for the product based on the consumer's total consumption amount and pushes it to the consumer's membership account, where the greater the total consumption amount, the greater the discount.

[0046] Furthermore, if the product type is a slow-moving product, the marketing model directly outputs the gift information of the product and pushes the free gift information of the product to the consumer's membership account.

[0047] It is understandable that the user can obtain the gift information or discount information of the product through the mobile terminal bound to the member account.

[0048] S106. If no order is placed, delete the invalid stored data after the consumer leaves the store.

[0049] In steps S101 to S106, first, a member account is established. The member account stores various information corresponding to each consumer, such as the name, mobile phone number, avatar, and try-on list, and this information can be updated in real time, thereby realizing dynamic management of consumer information, which is conducive to understanding consumer preferences for products and timely pushing discount information of inventory products in the store to interested consumers, effectively reducing the store's inventory rate and increasing marketing revenue. Secondly, the pushed products are sold at a discount based on the consumer's member account information, thereby increasing consumer stickiness to the store and repurchase rate.

[0050] In some implementations, a membership account can be applied for online, such as through the store's mini-program and WeChat public account, or applied for through the store front desk after entering an offline physical store. A membership account can also be automatically generated based on the order information after placing the first order after entering an offline physical store.

[0051] In one embodiment, if Figure 2 As shown, step S101 includes: steps S201 to S204;

[0052] S201, using a head portrait recognition algorithm to identify consumers entering the store and obtain the consumer's head portrait information;

[0053] Specifically, cameras are used to obtain consumer portrait information. Multiple cameras can be installed as needed. The cameras can be installed above the store entrance. In this way, when a consumer enters the store, the camera can first collect the consumer's portrait information to identify whether the consumer is a member.

[0054] S202, searching and matching in the member database based on the avatar information;

[0055] Specifically, consumers register as members online or offline, and the consumer's profile picture information is saved in the consumer's corresponding membership account. After the camera recognizes the profile picture information of the consumer entering the store, the computer equipment will match the profile picture information recognized by the camera with the profile picture information in the entire membership database (including each consumer's membership account) to determine whether the consumer is a member.

[0056] In some implementations, after the camera recognizes the consumer's profile picture information, the historical profile picture information of the consumer's membership account is updated and replaced with the profile picture information recognized this time, so as to realize dynamic management of the consumer's profile picture information.

[0057] S203: If the profile picture information is matched in the member database, the consumer is determined to be a member;

[0058] S204: If the avatar information is not matched in the member database, the consumer is determined to be a non-member.

[0059] In this embodiment, if the camera recognizes that the similarity between the consumer's profile picture information and a profile picture information in all member accounts reaches a preset threshold, the computer device determines that the consumer is a member; otherwise, the consumer is not a member.

[0060] It can be understood that this application searches and matches the consumer portrait information recognized by the camera in all member accounts, which is fast and easy to implement, and is conducive to subsequent analysis and processing by computer equipment.

[0061] In one embodiment, if Figure 3 As shown, step S102 includes: steps S301 to S303;

[0062] S301, identifying and calculating the distance between the consumer's hand and the clothes in the store;

[0063] S302, identifying and calculating the distance between the consumer's body and the clothes in the store;

[0064] S303: Input the distance between the consumer's hand and the clothes in the store, and the distance between the consumer's body and the clothes in the store into the consumer trying-on model, and output the consumer's in-store trying-on behavior.

[0065] In this embodiment, consumers have different behavioral characteristics when entering a store. They may simply browse the clothes in the store; or directly touch the clothes with their hands to feel the fabric; or try on the clothes in the store to confirm whether the clothes are suitable for them. It can be understood that the different behavioral characteristics of consumers in the store clothes reflect the degree of interest in the clothes. Therefore, this application establishes a consumer try-on model based on the consumer's behavioral characteristics and the status of the goods, thereby obtaining consumer preference information.

[0066] Specifically, the image between the consumer and the clothes is obtained through the camera, and the distance between the consumer's hand and the store clothes and the distance between the consumer's body and the store clothes are calculated through the algorithm. These two distances are then input into the consumer try-on model. The consumer try-on model outputs the consumer's in-store try-on behavior, and ultimately obtains the consumer's preference information.

[0067] In one embodiment, if Figure 4 As shown, step S303 includes: steps S401 to S403;

[0068] S401: When the distance between the consumer's hand and the store's clothing is 0, it is determined that the consumer is touching the product;

[0069] S402: When the distance between the consumer's body and the clothes in the store is 0, it is determined that the consumer is trying on the goods;

[0070] S403. When the consumer touches the product, detect whether the distance between the consumer's body and the store's clothes is less than or equal to a preset length. If so, it is determined that the consumer is trying on the product; otherwise, the consumer is not trying on the product.

[0071] In this embodiment, the camera recognizes and calculates the distance between the consumer's hand and body and the store's clothing to determine the consumer's behavior with the store's clothing. Specifically, the camera recognizes the distance between the consumer's hand and the store's clothing. As will be apparent, when the distance between the consumer's hand and the store's clothing is zero, it is confirmed that the consumer has touched the store's clothing. The camera then performs subsequent analysis based on the consumer's touching of the store's clothing.

[0072] Furthermore, after a consumer touches a garment in the store, the camera continues to track the consumer's movement characteristics on the garment. If the distance between the consumer's body and the garment is less than or equal to a preset length, the consumer is confirmed to have tried on the garment. The preset length is the length of the consumer's arm.

[0073] Specifically, if the camera does not detect the consumer touching the clothing in the store, the camera recognizes and calculates the distance between the consumer's body and the clothing in the store. As will be apparent, in one case, when the distance between the consumer's body and the clothing in the store is zero, it is confirmed that the consumer has tried on the clothing. In another case, when the distance between the consumer's body and the clothing in the store is greater than zero and less than or equal to a preset length, it is confirmed that the consumer is gesturing at the clothing. In yet another case, when the distance between the consumer's body and the clothing in the store is greater than a preset length, it is confirmed that the consumer is viewing the clothing in the store.

[0074] In one embodiment, if Figure 5 As shown, after step S101, the following steps are further included: steps S501 to S504;

[0075] S501. If the consumer is not a member, track the consumer's ordering behavior;

[0076] S502: Determine whether the consumer has placed an order. If so, proceed to step S503; if not, jump to step S504.

[0077] S503, adding the consumer to the membership according to the consumer's order information;

[0078] S504: After the consumer leaves the store, delete the invalid stored data.

[0079] In this embodiment, when a consumer enters an offline physical store for the first time and has not registered a membership account online, the camera tracks the consumer's ordering behavior, the computer device receives the consumer's order information, and then opens a membership account for the consumer. The consumer's name, mobile phone number, profile picture information, and the consumption amount of this order are entered into the membership account.

[0080] In some implementations, the tracking of consumers' ordering behavior is the same as the above steps S102 to S105, that is, the inventory marketing method of the above embodiment is also used for newly joined members.

[0081] It can be understood that this embodiment adds non-member consumers to the membership through order information, which is conducive to improving consumers' stickiness to the store and the brand influence of the store, thereby attracting more consumers to shop in the store and increasing the store's operating income.

[0082] In one embodiment, step S105 includes:

[0083] The discount for the target product is calculated as follows:

[0084]

[0085] Among them, f (i)is the current store discount, Or is the total amount of consumer spending, SV is the preset value, T i is the number of times the consumer tries on the target product, i is the label corresponding to the target product, α i Represents any real number.

[0086] In this embodiment, i is the label corresponding to the target product, wherein the label information can be a slow-moving item or a non-slow-moving item in the store's clothing. When the label of the store's clothing is a slow-moving item, the α of the formula i The value is 0, and accordingly, the discount f of the clothes in this store (i) A value of 0 indicates that the store does not offer discounts on clothes and directly gives the clothes to consumers for free.

[0087] Furthermore, when the label of the store clothes is non-saleable, the α of the formula is i It is an arbitrary real number, and the specific value can be set according to actual conditions.

[0088] It can be understood that the above parameter values ​​are input into the marketing model, and the marketing model outputs a specific discount, then outputs the discount information, and pushes the discount information to the consumer's membership account. This embodiment can push different product marketing plans to different consumers through this formula, thereby improving consumer stickiness and repurchase rate, reducing inventory costs, and increasing the overall profit of the store.

[0089] In one embodiment, the preset value and the total consumption amount are both positively correlated with the discount of the target product, and the number of times the target product is tried on is negatively correlated with the discount of the target product.

[0090] In this embodiment, in one case, the more the total amount of consumer's spending in this store is, the greater the difference between the amount exceeding the preset value set by the store is, then the discount f calculated according to the above formula is (i) The larger the value, the greater the discount the store gives to the consumer. In another case, the larger the preset value set by the store, the greater the discount f calculated according to the above formula. (i) The larger the number, the greater the discount the store gives to the consumer, which is conducive to increasing the consumer's repurchase rate.

[0091] It is understandable that the more times a consumer tries on clothes in a store, the more interested the consumer is in the clothes and the more likely the consumer is to place an order for the clothes. The discount f calculated according to the above formula is (i) The smaller it is, the smaller the discount the store gives to the consumer, which is beneficial to increasing the store's operating profit.

[0092] Figure 6 This is a schematic block diagram of an offline shoe and clothing store inventory marketing device 600 based on video behavior analysis provided by an embodiment of the present invention. The device 600 includes:

[0093] The first recognition unit 601 is used to use a head portrait recognition algorithm to identify whether the consumer is a member;

[0094] The second identification unit 602 is used to identify the consumer's in-store try-on behavior if the consumer is a member, and update the current consumer's try-on list based on the in-store try-on behavior, where the try-on list includes the tried items and the number of tries;

[0095] The first judgment unit 603 is used to judge whether the consumer has placed an order;

[0096] The second judgment unit 604 is used to obtain the total consumption of the consumer if an order is placed, and to determine whether the total consumption is greater than a preset value, where the total consumption is the sum of the current order consumption and the previous order consumption;

[0097] The calculation unit 605 is used to input the target product information ranked first in the try-on list into the marketing model for discount calculation if the total consumption amount is greater than the preset value, output the discount information of the target product, and push the discount information to the consumer.

[0098] A member account is established through this device. The member account stores a variety of information corresponding to each consumer, such as the name, mobile phone number, avatar, and try-on list, and this information can be updated in real time, realizing dynamic management of consumer information, which is conducive to understanding consumer preferences for products and timely pushing discount information of inventory products in the store to interested consumers, effectively reducing the store's inventory rate and increasing marketing revenue. Secondly, the pushed products are sold at a discount based on the consumer's member account information, thereby increasing consumer stickiness to the store and repurchase rate.

[0099] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0100] The above-mentioned offline shoe and clothing store inventory marketing device based on video behavior analysis can be implemented in the form of a computer program. The computer program can be used in Figure 7 Runs on the computer equipment shown.

[0101] See also Figure 7 , Figure 7 Schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device 700 is a server, which can be an independent server or a server cluster composed of multiple servers.

[0102] See Figure 7The computer device 700 includes a processor 702 , a memory, and a network interface 705 connected via a system bus 701 , wherein the memory may include a non-volatile storage medium 703 and an internal memory 704 .

[0103] The non-volatile storage medium 703 can store an operating system 7031 and a computer program 7032. When the computer program 7032 is executed, the processor 702 can execute an offline shoe and clothing store inventory marketing method based on video behavior analysis.

[0104] The processor 702 is used to provide computing and control capabilities to support the operation of the entire computer device 700.

[0105] The internal memory 704 provides an environment for the operation of the computer program 7032 in the non-volatile storage medium 703. When the computer program 7032 is executed by the processor 702, the processor 702 can execute an offline shoe and clothing store inventory marketing method based on video behavior analysis.

[0106] The network interface 705 is used for network communication, such as providing data information transmission. Those skilled in the art will understand that Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device 700 to which the solution of the present invention is applied. The specific computer device 700 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0107] Those skilled in the art will understand that Figure 7 The embodiment of the computer device shown in the figure does not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and processor are the same as those in the figure. Figure 7 The embodiments shown are consistent and will not be described again here.

[0108] It should be understood that in the embodiment of the present invention, the processor 702 may be a central processing unit (CPU), and the processor 702 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0109] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the offline shoe and apparel store inventory marketing method based on video behavior analysis according to an embodiment of the present invention.

[0110] The storage medium is a physical, non-transient storage medium, for example, a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which can store program codes.

[0111] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the scope of protection of the claims of this application.

[0112] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

Claims

1. An offline shoe and clothing store inventory marketing method based on video behavior analysis, characterized in that: The method includes: Use profile picture recognition algorithms to identify whether consumers are members; If the customer is a member, the customer's in-store try-on behavior is identified, and the current customer's try-on list is updated based on the in-store try-on behavior, wherein the try-on list includes the tried items and the number of tries; Determine whether the consumer has placed an order; If an order is placed, the consumer's total consumption is obtained and it is determined whether the total consumption is greater than a preset value, where the total consumption is the sum of the current order consumption and the previous order consumption; If the total consumption amount is greater than a preset value, the target product information ranked first in the try-on list is input into the marketing model for discount calculation, the discount information of the target product is output, and the discount information is pushed to the consumer; If the consumer is a member, the consumer's in-store trying-on behavior is identified, and a current consumer's try-on list is updated based on the in-store trying-on behavior, wherein the try-on list includes the tried-on items and the number of tries, including: identifying and calculating the distance between the consumer's hand and the store's clothes; identifying and calculating the distance between the consumer's body and the store's clothes; inputting the distance between the consumer's hand and the store's clothes and the distance between the consumer's body and the store's clothes into a consumer try-on model, and outputting the consumer's in-store trying-on behavior; The distance between the consumer's hand and the store's clothes and the distance between the consumer's body and the store's clothes are input into the consumer fitting model, and the consumer's in-store fitting behavior is outputted, including: when the camera identifies that the distance between the consumer's hand and the store's clothes is 0, it is determined that the consumer is touching the goods; when the camera identifies that the distance between the consumer's body and the store's clothes is 0, it is determined that the consumer is trying on the goods; when the consumer touches the goods, it is detected whether the distance between the consumer's body and the store's clothes is less than or equal to a preset length, and if so, it is determined that the consumer is trying on the goods; If the total consumption amount is greater than a preset value, the target product information ranked first in the try-on list is input into the marketing model for discount calculation, the discount information of the target product is output, and the discount information is pushed to the consumer, including: The discount for the target product is calculated as follows: Among them, f (i) is the current store discount, Or is the total amount of consumer spending, SV is the preset value, T i is the number of times consumers try on the target product, i is the label corresponding to the target product, and when the label is a slow-moving product, α i The value is 0, when the label is non-saleable, α i is any real number.

2. The offline shoe and clothing store inventory marketing method based on video behavior analysis according to claim 1 is characterized in that: The use of a head portrait recognition algorithm to identify whether a consumer is a member includes: Use the head portrait recognition algorithm to identify consumers entering the store and obtain their head portrait information; Search and match the member database based on the avatar information; If the profile picture information is matched in the member database, the consumer is determined to be a member; If the profile picture information is not matched in the member database, the consumer is determined to be a non-member.

3. The offline shoe and clothing store inventory marketing method based on video behavior analysis according to claim 1 is characterized in that: After using the head recognition algorithm to identify whether the consumer is a member, it also includes: If the consumer is not a member, the consumer's ordering behavior will be tracked; Determine whether the consumer has placed an order. If so, add the consumer to the membership based on the consumer's order information.

4. The offline shoe and clothing store inventory marketing method based on video behavior analysis according to claim 1 is characterized by: The preset value and the total consumption amount are both positively correlated with the discount of the target product; The number of times the target product is tried on is negatively correlated with the discount of the target product.

5. An offline shoe and clothing store inventory marketing device based on video behavior analysis, characterized in that: include: The first recognition unit is used to use a head portrait recognition algorithm to identify whether the consumer is a member; The second identification unit is used to identify the consumer's in-store try-on behavior if the consumer is a member, and update the current consumer's try-on list according to the in-store try-on behavior, wherein the try-on list includes the tried-on items and the number of try-ons; The first judgment unit is used to judge whether the consumer places an order; A second judgment unit is configured to obtain the total consumption amount of the consumer if an order is placed, and to judge whether the total consumption amount is greater than a preset value, wherein the total consumption amount is the sum of the current order consumption and the previous order consumption; a calculation unit configured to input the target product information ranked first in the number of tries in the try-on list into a marketing model for discount calculation if the total consumption amount is greater than a preset value, output discount information for the target product, and push the discount information to the consumer; If the consumer is a member, the consumer's in-store trying-on behavior is identified, and a current consumer's try-on list is updated based on the in-store trying-on behavior, wherein the try-on list includes the tried-on items and the number of tries, including: identifying and calculating the distance between the consumer's hand and the store's clothes; identifying and calculating the distance between the consumer's body and the store's clothes; inputting the distance between the consumer's hand and the store's clothes and the distance between the consumer's body and the store's clothes into a consumer try-on model, and outputting the consumer's in-store trying-on behavior; The distance between the consumer's hand and the store's clothes and the distance between the consumer's body and the store's clothes are input into the consumer fitting model, and the consumer's in-store fitting behavior is outputted, including: when the camera identifies that the distance between the consumer's hand and the store's clothes is 0, it is determined that the consumer is touching the goods; when the camera identifies that the distance between the consumer's body and the store's clothes is 0, it is determined that the consumer is trying on the goods; when the consumer touches the goods, it is detected whether the distance between the consumer's body and the store's clothes is less than or equal to a preset length, and if so, it is determined that the consumer is trying on the goods; If the total consumption amount is greater than a preset value, the target product information ranked first in the try-on list is input into the marketing model for discount calculation, the discount information of the target product is output, and the discount information is pushed to the consumer, including: The discount for the target product is calculated as follows: Among them, f (i) is the current store discount, Or is the total amount of consumer spending, SV is the preset value, T i is the number of times consumers try on the target product, i is the label corresponding to the target product, and when the label is a slow-moving product, α i The value is 0, when the label is non-saleable, α i is any real number.

6. A computer device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the offline shoe and clothing store inventory marketing method based on video behavior analysis as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the offline shoe and clothing store inventory marketing method based on video behavior analysis as described in any one of claims 1 to 4.

Images