Scene construction method and device for commodity recommendation

Abstract

The invention provides a scene construction method and device for commodity recommendation, and relates to the technical field of commodity recommendation. The invention discloses a scene construction method for commodity recommendation. The scene construction method comprises the following steps: extracting scene feature variables influencing a scene construction target from a preset reference scene to form an initial formula; expanding selectable items of scene feature variables in the initial formula, and binding intervention contents corresponding to the selectable items to obtain a scene formula; a scene formula is selected according to the to-be-processed scene construction task, and a target scene formula is obtained; according to the to-be-processed scene construction task, performing option filling on scene feature variables in the target scene formula to obtain target scene feature variables; scene factors are selected according to the target scene feature variables and the intervention content thereof, and target scene factors are obtained; and combining the target scene factors to obtain a target scene. According to the technical scheme, scene production can be completed by selecting the target scene factor, operation is easy, and the starting cost is low.

Description

Technical Field

[0001] This application relates to the technical field of product recommendation, and specifically relates to a method and device for constructing a scenario for product recommendation. Background Art

[0002] Currently, in the fields of e-commerce and retail, scenarios that are online for a long time and have a certain mentality, such as flash sales, 8 pm promotions, physical stores, lists, and split treasure, are not sufficient to meet the needs of all buyers. Consumers' shopping habits, preferences, and expectations are constantly changing, and a single or fixed scenario is difficult to adapt to the complexity of actual applications.

[0003] In the traditional scenario construction process, some AB tests are usually configured for the assumed scenarios for verification. However, this experimental method requires a large amount of manual participation and a long experimental cycle, resulting in an extended overall development cycle of the scenario. In addition, due to a large amount of manual participation, the interpretability of the experimental results is poor, and sometimes it is difficult to accurately determine which factors have caused changes in the scenario construction goals. At the same time, with the changes in internal positions and the adjustment of business goals within the enterprise, the maintenance and optimization of the scenario become more difficult.

[0004] The prior art usually trains professional operation personnel to perform relevant operations, but the onboarding cost is high and the operation is difficult.

[0005] In summary, the prior art has the problem of difficult scenario construction operations. Summary of the Invention

[0006] Based on this, this application provides a method and device for constructing a scenario for product recommendation, realizing the construction of an easy-to-operate scenario for product recommendation.

[0007] According to one aspect of this application, a method for constructing a scenario for product recommendation is proposed, including: extracting scenario feature variables that affect the scenario construction goal from a preset reference scenario to form an initial formula; expanding the optional items of the scenario feature variables in the initial formula and binding the intervention content corresponding to the optional items to obtain a scenario formula; selecting a scenario formula according to the to-be-processed scenario construction task to obtain a target scenario formula; filling the optional items of the scenario feature variables in the target scenario formula according to the to-be-processed scenario construction task to obtain target scenario feature variables; selecting scenario factors according to the target scenario feature variables and their intervention content to obtain target scenario factors; combining the target scenario factors to obtain a target scenario.

[0008] According to some embodiments, the scenario formula includes a daily sales scenario formula and a major promotion marketing theme scenario formula; among them, the scenario feature variables of the daily sales scenario formula include: scenario goal, target population, merchandise threshold, visual decision factor, and / or scenario gameplay; the scenario feature variables of the major promotion marketing theme scenario formula include: population portrait, seasonal festival, scenario mentality, merchandise splitting dimension, product life cycle, and / or scenario gameplay.

[0009] According to some embodiments, after combining the target scenario factors to obtain the target scenario, it further includes: formulating a grid multi-scenario feature variable experiment strategy according to the target scenario; conducting a comparative experiment according to the grid multi-scenario feature variable experiment strategy to obtain an experimental result; and performing attribution analysis based on the experimental result and the target scenario feature variables to obtain a scenario construction target attribution conclusion.

[0010] According to some embodiments, selecting scenario factors according to the target scenario feature variables and their intervention content to obtain target scenario factors includes: determining scenario factor selection conditions according to the attributes of the target scenario feature variables and the intervention content, where the scenario factor selection conditions include product selection conditions, visual template selection conditions, and / or scenario gameplay selection conditions; and screening from a preset scenario factor sequence according to the scenario factor selection conditions to obtain target scenario factors.

[0011] According to some embodiments, screening from a preset scenario factor sequence according to the scenario factor selection conditions to obtain target scenario factors includes: selecting a merchandise pool for the target selection plan from the preset scenario factor sequence according to the product selection conditions to obtain a target product selection planning pool; selecting a visual template from the preset scenario factor sequence according to the visual template selection conditions to obtain a target visual template; and / or selecting scenario components from the preset scenario factor sequence according to the scenario gameplay selection conditions to obtain target scenario components.

[0012] According to some embodiments, combining the target scenario factors to obtain the target scenario includes: combining the target product selection planning pool, the target visual template, and / or the target scenario components to obtain a scenario protocol; and deploying the scenario on the rendering side according to the scenario protocol to obtain the target scenario.

[0013] According to some embodiments, the method further includes: saving the historical scenario construction strategy of the historical to-be-processed scenario construction task, where the historical scenario construction strategy includes the association relationship of the target scenario factors; generating a target scenario construction strategy according to the to-be-processed scenario construction task based on the historical scenario construction strategy; and constructing the target scenario according to the target scenario construction strategy.

[0014] According to one aspect of the present application, a scenario construction device for product recommendation includes: a first formula module for extracting scenario feature variables that affect the scenario construction goal from a preset reference scenario to form an initial formula; a second formula module for expanding the options of the scenario feature variables in the initial formula and binding the intervention content corresponding to the options to obtain a scenario formula; a formula selection module for selecting a scenario formula according to the to-be-processed scenario construction task to obtain a target scenario formula; a variable filling module for filling the options of the scenario feature variables in the target scenario formula according to the to-be-processed scenario construction task to obtain target scenario feature variables; a factor intervention module for selecting scenario factors according to the target scenario feature variables and their intervention content to obtain target scenario factors; an assembly result module for combining the target scenario factors to obtain a target scenario.

[0015] According to one aspect of the present application, an electronic device is provided, which includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described above.

[0016] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method as described above is implemented.

[0017] Through the above-mentioned embodiments provided by the present application, scenario formulas are constructed using a preset reference scenario to standardize the definition of scenarios. During the application process, only the selection of target scenario factors is required, and scenario production can be fully automated through engineering capabilities. It is easy to operate, and at the same time, it reduces the onboarding learning cost and the risk of misconfiguration for operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the present application.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can also obtain other drawings based on these drawings without exceeding the scope of protection required by the present application.

[0020] Figure 1 It is a flowchart of the scenario construction method for product recommendation provided by the embodiment of the present application;

[0021] Figure 2 It is a flowchart of selecting scenario factors according to the target scenario feature variables and their intervention content to obtain target scenario factors provided by the embodiment of the present application;

[0022] Figure 3 This is a flowchart for combining target scenario factors to obtain a target scenario provided by an embodiment of the present application;

[0023] Figure 4 This is another flowchart for a scenario construction method for product recommendation provided by an embodiment of the present application;

[0024] Figure 5 This is a block diagram of an open-set fine-grained recognition device provided by an embodiment of the present application;

[0025] Figure 6 This is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0026] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0027] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will realize that the technical solutions of the present application may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be used. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of the present application.

[0028] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0029] The flowcharts shown in the drawings are only illustrative and do not necessarily include all the content and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps may be decomposed, and some operations / steps may be combined or partially combined. Therefore, the actual execution order may be changed according to the actual situation.

[0030] It should be understood that although terms such as first, second, and third may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Thus, the first component discussed below may be referred to as the second component without departing from the teachings of the concepts of this application. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more of them.

[0031] In order to realize the construction of a self-iterative shopping guide scenario, it is necessary to digitalize the scenario. In the prior art, there is no mature solution for scenario digitalization ability. Usually, the scenario construction plan is deconstructed into a building plan, and through the modularization and building of components, the rapid generation of the scenario is realized. However, the building plan requires professional operation for module configuration, which has a certain learning cost, and since it is manually executed, it is easy to make mistakes in the manual intervention link.

[0032] Based on this, this application proposes a scenario construction method and device for product recommendation.

[0033] For better illustration of this application, the terms mentioned in this application are explained as follows:

[0034] Scenario merchandise tray: The collection of products on the e-commerce shelf.

[0035] Scenario component: The card slots used to display products. The components can be configured independently and can be built and reused on multiple e-commerce shelf pages.

[0036] Scenario (visual) template: The page component specification of the e-commerce shelf, which stipulates that fixed components can be displayed in fixed blocks on the page with the template.

[0037] Scenario component pool: The collection of components that can be used in advance.

[0038] Scenario factor: The variables used to describe the "construction elements", "construction processes" and "construction capabilities" of the scenario, such as the scenario features of product recall, component vision, and banner main picture.

[0039] Merchandise tray threshold: The basic condition for constructing the scenario, which is used to ensure a certain characteristic of a batch of scenario merchandise trays, such as all meeting the "7-day return without reason".

[0040] Scenario construction strategy: By assembling scenario factors, describe the scenario construction characteristics, such as "merchandise tray threshold", "merchandise grouping method", "scenario (visual) template", "scenario component pool", "scenario algorithm strategy", to form a scenario construction strategy. Among them, the merchandise grouping method refers to splitting the merchandise tray into multiple parts through logic, and each part can be constructed into a scenario page for delivery; the algorithm strategy refers to the personalized display logic of e-commerce shelf products, and selects the products that users prefer more in the product pool.

[0041] Arrangement factor: By flexibly selecting and combining scenario factors, a scenario construction strategy is formed.

[0042] The specific implementation method can refer to the following embodiments.

[0043] Figure 1 It is a flowchart of the scenario construction method for product recommendation provided by the embodiments of this application. As Figure 1 shown, this method includes steps S110 - S160.

[0044] In step S110, scenario feature variables that affect the scenario construction goal are extracted from a preset reference scenario to form an initial formula.

[0045] This application constructs a scenario formula to define the scenario in a standardized manner. During the construction of the scenario formula, scenario feature variables that affect the scenario construction goal are extracted from a preset reference scenario to form an initial formula.

[0046] Specifically, the features in the preset reference scenario are analyzed, and variables related to the features that the operation is concerned about (i.e., those that will affect the scenario construction goal) are extracted as scenario feature variables, and at least one scenario feature variable forms an initial formula.

[0047] The type of the preset reference scenario determines the applicable scenario for the constructed formula. According to the exemplary embodiment, the type of the preset reference scenario is determined based on scenario features and goals.

[0048] For example, if the type of the preset reference scenario is the daily sales channel scenario, then the scenario formula constructed based on this preset reference scenario is applicable to the scenario construction task of the daily sales channel scenario. Correspondingly, if the type of the preset reference scenario is the large promotion and marketing activity scenario, then the scenario formula constructed based on this preset reference scenario is applicable to the scenario construction task of the large promotion and marketing activity scenario.

[0049] It can be understood that the selection of the preset reference scenario can be based on historical experience, or the shopping guide scenarios can be classified first, and the scenarios can be selected through the constructed evaluation indicators. This application does not limit this.

[0050] According to the exemplary embodiment, the scenario feature variables that affect the scenario construction goal are, for example, scenario product assortments, scenario visuals, scenario gameplay strategies, etc.

[0051] In a specific embodiment, the currently online shopping guide scenarios on 1688 are used as the preset reference scenario. Through feature analysis and variable extraction of the product assortments, visuals, and gameplay of the shopping guide scenarios, an initial formula is finally obtained.

[0052] In step S120, the options of the scenario feature variables in the initial formula are expanded, and the intervention content corresponding to the options is bound to obtain a scenario formula.

[0053] In the actual operation process, it is necessary to continuously expand the scenario feature variables in the initial formula to obtain multiple options corresponding to each variable, and bind the intervention content behind the options of the variables, that is, to obtain a scenario formula suitable for practical use. For example, enumerate the scenario feature variables in the initial formula, iterate the real design criteria and product threshold conditions, and complete the standardized definition of the scenario.

[0054] According to the example embodiment, the intervention content includes the conditions for each option to intervene in the engineering node, such as product selection conditions and visual template selection conditions.

[0055] Through the superposition of variable conditions in the formula, it is possible to accurately deconstruct the scenario features for the target scenario and realize the automated production of the scenario.

[0056] Furthermore, according to some embodiments, the scenario formula includes a daily sales scenario formula and a major promotion marketing theme scenario formula.

[0057] Specifically, this embodiment includes a total of 2 sets of scenario formulas, namely the daily sales scenario formula and the major promotion marketing theme scenario formula. It can be understood that the daily sales scenario formula is applicable to the scenario construction task of the daily sales channel scenario, and the major promotion marketing theme scenario formula is applicable to the scenario construction task of the major promotion marketing activity scenario.

[0058] Furthermore, the scenario feature variables of the daily sales scenario formula include: scenario goal, target population, product offering threshold, visual decision factor, and / or scenario gameplay.

[0059] According to the example embodiment, the daily sales scenario formula can be described as: Daily sales scenario formula = ${Scenario goal} x ${Target population} x ${Product offering threshold} x ${Visual decision factor} x ${Scenario gameplay}.

[0060] It should be noted that ${} represents the scenario feature variable.

[0061] Furthermore, the scenario feature variables of the major promotion marketing theme scenario formula include: population portrait, seasonal festival, scenario mindset, product offering split dimension, product life cycle, and / or scenario gameplay.

[0062] According to the example embodiment, the major promotion marketing theme scenario formula can be described as: Major promotion marketing & fully automated theme scenario formula = ${Population portrait} x ${Seasonal festival} x ${Scenario mindset} x ${Product offering split dimension} x ${Product life cycle} x ${Scenario gameplay}.

[0063] Based on the above embodiments, according to the exemplary embodiments, the optional items of some scenario feature variables in the daily sales scenario formula can be extended as follows: For the scenario feature variable of pallet threshold, the optional items include: shipping within 24 hours, shipping within 48 hours, shipping within 72 hours; For the scenario feature variable of visual decision factor, the optional items include: visual template 1, visual template 2; For the scenario feature variable of scenario gameplay, the optional items include: getting a sample for one cent, adding to cart within the scenario.

[0064] Further, according to the exemplary embodiments, the optional items of some scenario feature variables in the daily sales scenario formula can also be extended as shown in Table 1.

[0065] Table 1 Optional items of some scenario feature variables in the daily sales scenario formula

[0066]

[0067] Based on the above embodiments, according to the exemplary embodiments, the optional items of some scenario feature variables in the major promotion marketing theme scenario formula can be extended as shown in Table 2.

[0068] Table 2 Optional items of some scenario feature variables in the major promotion marketing theme scenario formula

[0069]

[0070] According to the exemplary embodiments, bind the intervention content corresponding to the optional items. For example: If the scenario feature variable "population portrait" selects "mothers and infants", during the dynamic construction process, "pallet adapted to mothers and infants population", "design draft adapted to mothers and infants population", and "scenario marketing gameplay for mothers and infants population" will be automatically selected.

[0071] In step S130, select a scenario formula according to the to-be-processed scenario construction task to obtain a target scenario formula.

[0072] During the application process, according to the to-be-processed scenario construction task, select a target scenario formula from multiple pre-constructed scenario formulas. The to-be-processed scenario construction task needs to at least describe the type of the to-be-constructed scenario, and select the scenario formula that adapts to the type of the to-be-constructed scenario as the target scenario formula.

[0073] Based on the above embodiments, the to-be-processed scenario construction task includes relevant descriptions of the scenario features and objectives of the to-be-constructed scenario.

[0074] Based on the above embodiments, for example, if the to-be-processed scenario construction task is: need to construct a scenario for a catering physical store, then select the daily sales scenario formula as the target scenario formula.

[0075] In step S140, according to the to-be-processed scenario construction task, fill in the optional items for the scenario feature variables in the target scenario formula to obtain target scenario feature variables.

[0076] During the application process, the scenario feature variables in the target scenario formula are filled according to the scenario to be processed, that is, the optional items of the scenario feature variables are filled.

[0077] On this basis, in order to fill the scenario feature variables more accurately, the task of constructing the scenario to be processed may also include relevant descriptions of the sales strategy of the scenario to be constructed.

[0078] In addition, it should be noted that the filling of optional items is actually based on the matching of optional items, and the next-level variables are refined for each scenario feature variable. For example, for the scenario feature variable of pallet threshold, the filled content of the optional item can be any one of shipping within 24 hours, shipping within 48 hours, and shipping within 72 hours. For the scenario feature variable of visual decision factor, the filled content of the optional item can be any one of visual template 1 and visual template 2. For the scenario feature variable of scenario gameplay, the filled content of the optional item can be any one of getting a sample for one cent and adding to cart within the scenario.

[0079] In step S150, according to the target scenario feature variables and their intervention contents, the scenario factors are selected to obtain the target scenario factors.

[0080] The intervention contents of the target scenario feature variables mainly include pallet structure and overall visual tone.

[0081] In step S160, the target scenario factors are combined to obtain the target scenario.

[0082] Combining the target scenario factors can realize the online launch of the target scenario.

[0083] According to the embodiment, the target scenario factors are assembled to obtain a scenario protocol, and the online launch of the target scenario is realized according to the obtained scenario protocol.

[0084] This application constructs a scenario formula through a preset reference scenario to standardize the definition of the scenario. During the application process, only the selection of the target scenario factors is required, and the scenario production can be fully automated through engineering capabilities. It is easy to operate and reduces the onboarding learning cost and the risk of misconfiguration for operations.

[0085] According to some embodiments, after step S160, steps S170 - S190 are further included.

[0086] In step S170, a grid-based multi-scenario feature variable experiment strategy is formulated according to the target scenario.

[0087] Specifically, for each scenario feature variable, different scenario factors are selected as the target scenario factors, and multiple groups of target scenarios corresponding to the target scenario factors are obtained through permutation and combination.

[0088] For example, the scenario factors that can be selected for ${pallet threshold} include: "ship within 24 hours, ship within 48 hours, ship within 72 hours"; the scenario factors that can be selected for ${visual decision factor} include: "visual template 1, visual template 2"; the scenario factors that can be selected for ${scenario gameplay} include: "get a sample for one cent, add to cart within the scenario". Through permutation and combination of the above variables, a total of 12 scenarios of catering physical stores with multiple variables can be constructed.

[0089] By conducting experiment AB (i.e., comparative experiment analysis) on these target scenarios, a grid-based (multi-variable) experimental strategy can be obtained.

[0090] In step S180, a comparative experiment is conducted according to the grid-based multi-scenario feature variable experimental strategy to obtain the experimental results.

[0091] According to the grid-based (multi-variable) experimental strategy, a comparative experiment is conducted to obtain the experimental results.

[0092] In step S190, attribution analysis is performed based on the experimental results and the target scenario feature variables to obtain the attribution conclusion of the scenario construction target.

[0093] Based on the experimental results and relevant features, attribution analysis is performed, and the improvement of the scenario construction target can be attributed to specific variables, thereby obtaining a white-boxed attribution conclusion of the scenario construction target.

[0094] The present application aims to decompose the capabilities and features of each core link of scenario construction (such as product recall, component vision, banner main image) into factor variables, and realize the digitization of scenarios through the arrangement of scenario factors. Specifically, through the standardized definition of scenarios, scenario feature variables such as "scenario pallet", "scenario design pattern", and "scenario construction strategy" are decomposed to realize the semi-automated production of scenarios. At the same time, preset reference scenario assets are precipitated, and combined with personalized distribution, grid-based experiments, and white-boxed attribution capabilities, AI control and scientific operation of scenarios are realized.

[0095] According to some embodiments, referring to Figure 2 , in step S150, according to the target scenario feature variables and their intervention contents, scenario factors are selected to obtain the target scenario factors, which can be specifically realized through steps S210 - S220.

[0096] In step S210, according to the attributes of the target scenario feature variables and the intervention content, determine the scenario factor selection conditions, where the scenario factor selection conditions include product selection conditions, visual template selection conditions, and / or scenario gameplay selection conditions;

[0097] Specifically, the attributes of the scenario feature variables in the scenario formula may include page-level variables and block-level variables. The intervention content of the page-level variables includes at least one of intervening in the product threshold at the page level and the visual expression at the page level; the intervention content of the block-level variables includes at least one of the interactive gameplay of the block components, the vision and merchandise display of the block components, and the characterization of the product / promotion components.

[0098] For example, based on the above embodiment, in the scenario formula of the big promotion marketing theme, the page-level variables include: population portrait, seasonal festivals, and scenario mentality; the block-level variables include: merchandise display split dimension, product life cycle, and scenario gameplay.

[0099] It should be emphasized that ${scenario mentality} affects the merchandise display threshold and visual design, and ${merchandise display method} affects the merchandise display assembly method.

[0100] To further illustrate the target scenario feature variables and their intervention content, an embodiment is given to illustrate the target scenario formula, target scenario feature variables, and their intervention content related to the physical catering store scenario as follows.

[0101] The to-be-processed scenario construction task is: It is necessary to construct a scenario for a physical catering store.

[0102] The target scenario formula is: Physical catering store = Purchase GMV × Physical catering store owner × Service & 48-hour delivery × Highlight product specifications × Sample for one cent / Add to cart within the scenario.

[0103] Among them, the intervention content of the target scenario feature variable Purchase GMV: Intervene in the product selection conditions (for example, high-purchase-frequency consumables and / or high-unit-price products);

[0104] The intervention content of the target scenario feature variable Physical catering store owner: Intervene in the product selection conditions (for example, catering consumables, pre-prepared dishes, fresh produce, etc.); Intervene in the visual template (for example, a visual design template suitable for a restaurant);

[0105] The intervention content of the target scenario feature variable Service & 48-hour delivery: Intervene in the product selection conditions (for example, merchants can deliver within 48 hours);

[0106] The intervention content of the target scenario feature variable Highlight product specifications: Intervene in the component selection (for example, the component expressing the product specification field);

[0107] Target scenario feature variable: One-cent sample taking / Intervention content within the scenario: Selection of intervention components (e.g., one-cent sample taking component or in-scenario add-to-cart component).

[0108] Based on the superposition of the conditions included in the intervention content, determine the scenario factor selection conditions. The scenario factor selection conditions include product selection conditions, visual template selection conditions, and / or scenario gameplay selection conditions.

[0109] In step S220, according to the scenario factor selection conditions, screen from the preset scenario factor sequence to obtain the target scenario factor.

[0110] Based on the determined scenario factor selection conditions, select the target scenario factor from the preset scenario factor sequence.

[0111] The preset scenario factor sequence includes optional scenario factors, that is, it can be understood as including the further refined content of the optional items. It can be obtained by transforming the optional items of the scenario feature variable, or by using pre-constructed scenario factors.

[0112] According to some embodiments, in step S220, according to the scenario factor selection conditions, screen from the preset scenario factor sequence to obtain the target scenario factor, which can be specifically implemented through steps S221 - S223.

[0113] Step S221: Select the scenario product pool bottom from the preset scenario factor sequence according to the product selection conditions to obtain the target product selection planning bottom pool;

[0114] Step S222: Select the visual template from the preset scenario factor sequence according to the visual template selection conditions to obtain the target visual template; and / or

[0115] Step S223: Select the scenario component from the preset scenario factor sequence according to the scenario gameplay selection conditions to obtain the target scenario component.

[0116] Specifically, in step S221, first select the scenario product pool bottom according to the product selection conditions to obtain the target product selection planning bottom pool (e.g., 1688 product selection planning bottom pool). It should be noted that the product selection planning bottom pool refers to the pool of product IDs that can be launched.

[0117] After that, in step S222, select the visual template according to the visual template selection conditions, such as selecting visual template 1 or visual template 2, to obtain the target visual template.

[0118] In step S223, according to the scenario gameplay selection conditions, select the scenario component from, for example, the scenario component pool, such as the one-cent sample taking component or the in-scenario add-to-cart component, to obtain the target scenario component.

[0119] Based on the above embodiments, according to some embodiments, referring to Figure 3 , in step S160, the target scenario factors are combined to obtain a target scenario, which can be specifically implemented through steps S310 - S320.

[0120] In step S310, the target product selection planning pool, the target visual template, and / or the target scenario components are combined to obtain a scenario protocol.

[0121] Specifically, the target product selection planning pool, the target visual template, and / or the target scenario components obtained in steps S221 - S223 are assembled to obtain a scenario protocol.

[0122] In step S320, according to the scenario protocol, scenario deployment is performed on the rendering side to obtain a target scenario.

[0123] According to the scenario protocol, deployment is carried out on the rendering side to realize the online launch of the scenario, that is, a target scenario is obtained.

[0124] It should be emphasized that the variables of the scenario formula in the scenario production stage are all dynamic. In the scenario delivery stage, some variables of the scenario formula are static, and the dynamic variables affect scenario experiment delivery and data attribution. For example, in the scenario formula of the big promotion marketing theme, the population portrait and seasonal festivals at the same time and space are relatively determined, and other variables affect scenario experiment delivery and data attribution.

[0125] According to some embodiments, referring to Figure 4 , the method further includes steps S410 - S430.

[0126] In step S410, the historical scenario construction strategy of the historical to-be-processed scenario construction task is saved, where the historical scenario construction strategy includes the association relationship of the target scenario factors.

[0127] This application quickly realizes the digital construction of scenarios through the orchestration of scenario factors, and during the construction process, the scenario construction strategy is precipitated for subsequent calls.

[0128] In step S420, based on the historical scenario construction strategy, a target scenario construction strategy is generated according to the to-be-processed scenario construction task.

[0129] The target scenario construction strategy is generated by reusing the historical scenario construction strategy that has been docked.

[0130] According to the exemplary embodiments, the nodes are personalized distributed according to the to-be-processed scenario construction task, and the scenarios are personalized matched through the scenario features that the to-be-processed scenario construction task may involve. For example, the construction strategy of the "catering physical store scenario" will be distributed more preferentially to the population with the "purchase preference for the catering category".

[0131] In step S430, a target scenario is constructed according to the target scenario construction policy.

[0132] The construction of the target scenario is completed by using the target scenario construction policy.

[0133] In the embodiments of the present application, the technical historical scenario construction policy can be reused, or the scenario can be dynamically constructed by selecting scenario construction elements, further realizing the rapid production of scenarios, and quickly realizing the production of daily marketing activities and push scenarios.

[0134] The present application deconstructs the scenario construction process into factor variables, and then forms a scenario policy through the assembly of factors to complete the digitization of the scenario. Through flexible factors and scenario construction protocols, the pluggability of the overall scenario construction process and the dynamic assembly of scenario policies are realized, laying a solid foundation for future scenario intelligence in practical applications, improving the efficiency of future marketing and daily sales work, and at the same time better meeting the long-tail needs of buyers.

[0135] The device embodiments of the present application are described below, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, reference may be made to the method embodiments of the present application.

[0136] Figure 5 The block diagram of a scenario construction device for product recommendation according to an exemplary embodiment is shown.

[0137] Figure 5 The device shown can execute the scenario construction method for product recommendation according to the embodiments of the present application described above.

[0138] As Figure 5 shown, the open-set fine-grained recognition device may include:

[0139] See Figure 5 And referring to the previous description, the first formula module 510 is used to extract scenario feature variables that affect the scenario construction target from a preset reference scenario to form an initial formula.

[0140] The second formula module 520 is used to expand the optional items of the scenario feature variables in the initial formula and bind the intervention content corresponding to the optional items to obtain a scenario formula.

[0141] The formula selection module 530 is used to select a scenario formula according to the scenario construction task to be processed to obtain a target scenario formula.

[0142] The variable filling module 540 is used to fill the optional items of the scenario feature variables in the target scenario formula according to the scenario construction task to be processed to obtain target scenario feature variables.

[0143] The factor intervention module 550 is used to select scene factors according to the target scene feature variables and their intervention contents, so as to obtain the target scene factors.

[0144] The assembly result module 560 is used to combine the target scene factors to obtain the target scene.

[0145] The device performs functions similar to the methods provided above. For other functions, please refer to the previous description and will not be elaborated here.

[0146] Figure 6 An electronic device according to an exemplary embodiment of the present application is shown. The following will refer to Figure 6 to describe the electronic device 600 according to this embodiment of the present application. Figure 6 The shown electronic device 600 is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0147] As Figure 6 shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0148] Among them, the storage unit stores program codes, and the program codes can be executed by the processing unit 610, so that the processing unit 610 executes the methods according to various exemplary embodiments of the present application described in this specification. For example, the processing unit 610 can execute the methods as described above.

[0149] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0150] The storage unit 620 may further include a program / utilities 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples.

[0151] The bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0152] The electronic device 600 can also communicate with one or more external devices 300 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 650. Moreover, the electronic device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 through the bus 630. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0153] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or can be implemented by the way of software combined with necessary hardware. The technical solutions according to the embodiments of the present application can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiments of the present application.

[0154] The software product can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0155] A computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable storage medium may also be any readable medium other than the readable storage medium, which may send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0156] The program code for performing the operations of this application may be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0157] The above computer-readable medium carries one or more programs, which when executed by one of the devices, cause the computer-readable medium to implement the foregoing functions.

[0158] Those skilled in the art can understand that the above-mentioned modules can be distributed in the device according to the description of the embodiments, or can be correspondingly changed in one or more devices that are uniquely different from this embodiment. The modules of the above embodiments can be combined into one module, or can be further split into multiple sub-modules.

[0159] According to an embodiment of the present application, a computer program is proposed, including a computer program or instruction, which when executed by a processor, can execute the method described above.

[0160] Those skilled in the art can understand that the above-mentioned modules can be distributed in the device according to the description of the embodiments, or can be correspondingly changed in one or more devices that are uniquely different from this embodiment. The modules of the above embodiments can be combined into one module, or can be further split into multiple sub-modules.

[0161] The above has introduced the embodiments of the present application in detail. Specific examples are used herein to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only for helping to understand the method of the present application and its core idea. At the same time, any changes or deformations made by those skilled in the art based on the idea of the present application, within the specific implementation manner and application scope of the present application, all belong to the scope protected by the present application. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A scenario construction method for product recommendation, characterized in that: include: Extracting scene feature variables that affect the scene construction target from the preset reference scene to form an initial formula; Expanding the optional items of the scenario characteristic variables in the initial formula and binding the intervention content corresponding to the optional items to obtain a scenario formula; Select a scenario formula according to the scenario construction task to be processed to obtain a target scenario formula; According to the to-be-processed scene construction task, the scene characteristic variables in the target scene formula are filled with optional items to obtain the target scene characteristic variables; According to the target scenario characteristic variables and the intervention content thereof, the scenario factors are selected to obtain the target scenario factors; The target scene factors are combined to obtain a target scene.

2. The method according to claim 1, characterized in that The scenario formulas include daily sales scenario formulas and big promotion marketing theme scenario formulas; The scenario characteristic variables of the daily sales scenario formula include: scenario target, target group, pallet threshold, visual decision factor and / or scenario gameplay; The scenario characteristic variables of the big promotion marketing theme scenario formula include: crowd portrait, seasonal festivals, scenario mentality, pallet splitting dimensions, product life cycle and / or scenario gameplay.

3. The method according to claim 1, characterized in that After combining the target scene factors to obtain the target scene, the method further includes: Formulate a gridded multi-scenario characteristic variable experimental strategy according to the target scenario; Conduct comparative experiments according to the grid-based multi-scenario characteristic variable experimental strategy to obtain experimental results; Attribution analysis is performed based on the experimental results and the target scene characteristic variables to obtain a scene construction target attribution conclusion.

4. The method according to claim 1, characterized in that: The step of selecting a scenario factor according to the target scenario characteristic variable and its intervention content to obtain the target scenario factor includes: Determine the scene factor selection condition according to the attribute of the target scene feature variable and the intervention content, wherein the scene factor selection condition includes a product selection condition, a visual template selection condition and / or a scene play method selection condition; According to the scene factor selection condition, the target scene factor is obtained by screening from a preset scene factor sequence.

5. The method according to claim 4, characterized in that The step of screening from a preset scene factor sequence according to the scene factor selection condition to obtain the target scene factor comprises: Select a scene pallet pool from the preset scene factor sequence according to the product selection conditions to obtain a target product selection planning pool; Selecting a visual template from the preset scene factor sequence according to the visual template selection condition to obtain a target visual template; and / or A scene component is selected from the preset scene factor sequence according to the scene play selection condition to obtain a target scene component.

6. The method according to claim 5, characterized in that The step of combining the target scene factors to obtain the target scene includes: Combining the target product selection planning pool, the target visual template and / or the target scene component to obtain a scene protocol; The scene is deployed on the rendering side according to the scene protocol to obtain the target scene.

7. The method according to claim 1, characterized in that The method further comprises: Saving the historical scene construction strategy of the historical scene construction task to be processed, wherein the historical scene construction strategy includes the association relationship of the target scene factors; Based on the historical scene construction strategy, generating a target scene construction strategy according to the scene construction task to be processed; The target scene is constructed according to the target scene construction strategy.

8. A scene construction device for commodity recommendation, characterized in that: include: The first formula module is used to extract scene feature variables that affect the scene construction target from a preset reference scene to form an initial formula; A second formula module is used to expand the optional items of the scenario characteristic variables in the initial formula and bind the intervention content corresponding to the optional items to obtain a scenario formula; A formula selection module is used to select a scenario formula according to the scenario construction task to be processed to obtain a target scenario formula; A variable filling module is used to fill in optional items of the scene characteristic variables in the target scene formula according to the task of constructing the scene to be processed, so as to obtain the target scene characteristic variables; A factor intervention module, used to select scenario factors according to the target scenario characteristic variables and their intervention contents to obtain target scenario factors; The assembly result module is used to combine the target scene factors to obtain the target scene.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. 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 is implemented.

Images