Commodity navigation path planning method, computer readable storage medium, and electronic device

Abstract

This application discloses a product navigation path planning method, a computer-readable storage medium, and an electronic device. The method includes: obtaining a preset layout map of a physical store, a measured environment map, and a product display information table; the preset layout map includes shelf identifiers and placement locations of multiple shelves in the physical store; the measured environment map includes store spatial environment information collected during movement within the physical store; the information table stores product identifiers and placement locations of multiple products, with the placement location including at least the shelf identifier of the shelf where the product is located; registering the preset layout map and the measured environment map to establish a coordinate mapping relationship between them; determining the spatial coordinates of different products based on the placement locations of multiple products in the information table and the placement locations of multiple shelves in the preset layout map; and converting the spatial coordinates into corresponding environmental coordinates based on the coordinate mapping relationship to obtain the correspondence between product identifiers and environmental coordinates, used for path planning of the target product.

Description

Technical Field

[0001] This application relates to the field of commodity information service technology, and in particular to a commodity navigation path planning method, a computer-readable storage medium, an electronic device, and a computer program product. Background Technology

[0002] With the rapid development of the retail industry and the continuous expansion of offline physical stores, stores typically offer a wide variety of goods to meet consumer shopping needs. These goods are displayed using various methods such as shelf displays and floor displays, significantly increasing the overall complexity of the store space. When customers search for items of interest within the store, the complex zoning and frequent adjustments to product placement often lead to time-consuming and inefficient searches, negatively impacting the customer shopping experience.

[0003] Given the complex spatial layout, diverse products, and frequent changes in display locations of physical stores, providing an efficient product search solution has become a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] This application provides a product navigation path planning method and apparatus, a computer-readable storage medium, an electronic device, and a computer program product, which can realize efficient product search in physical store scenarios.

[0005] This application provides the following solution: A product navigation route planning method is used to provide route guidance services to consumers through smart devices provided by physical stores. The method includes: The system obtains a preset layout diagram, a measured environment map, and a product display information table for a physical store. The preset layout diagram includes shelf labels and locations of multiple shelves in the physical store. The measured environment map includes store space environment information collected during movement within the physical store, which is used for smart device positioning and path planning. The product display information table stores product labels and display locations of multiple products provided by the physical store, and the display location includes at least the shelf label of the shelf where the product is located. The preset layout map and the measured environment map are registered to establish a coordinate mapping relationship between them; Based on the display positions of multiple products in the information table and the layout positions of multiple shelves in the preset layout diagram, determine the spatial coordinates of different products in the preset layout diagram. Based on the coordinate mapping relationship, the spatial coordinates are converted into environmental coordinates corresponding to different products in the measured environment map. The correspondence between product identifiers and environmental coordinates is obtained and saved in the product knowledge base. When the smart device provides path guidance services for target products to consumer users, the target environmental coordinates of the target product can be obtained by querying the product knowledge base, and path planning can be performed based on the target environmental coordinates.

[0006] The method further includes: If there are products whose display positions have been changed in the physical store, the product display information table is updated according to the product identifier of the changed product and the changed display position, so as to obtain a new correspondence related to the changed product and update it to the product knowledge base.

[0007] The method further includes: If there are changes in the placement of shelves in the physical store, a new preset layout map and / or a new measured environment map after the store layout changes are obtained, and re-registered to update the coordinate mapping relationship and obtain a new correspondence relationship related to the products displayed on the changed shelves, which is then updated to the product knowledge base.

[0008] The change in the placement of the shelves indicates a localized adjustment to the shelf distribution in the physical store. Based on the newly collected store space environment information, the new measured environment map is obtained; Using the new measured environment map as a reference, the preset layout map is registered with the new measured environment map to obtain the updated coordinate mapping relationship.

[0009] The aforementioned partial adjustment involves adding new shelves in the physical store, and the method further includes: The newly added products displayed on the newly added shelves are identified, and the product identifiers and display positions of the newly added products are updated to the product display information table. In order to obtain new correspondences related to the newly added products and update them to the product knowledge base based on the updated product display information table and the updated coordinate mapping relationship.

[0010] The change in the placement of the shelves indicates a global adjustment to the distribution of shelves in the physical store. Obtain a new preset layout diagram for the global adjustment design and a new measured environment map generated by re-collection; The new preset layout map is registered with the new measured environment map to obtain the updated coordinate mapping relationship.

[0011] A product navigation route planning method is applied to smart devices provided by physical stores to provide route guidance services to consumers. The method includes: Obtain a measured environment map of the physical store, which includes store space environment information collected by moving within the physical store; The system receives a product search request submitted by a consumer user via human-computer interaction and sends it to the server. The server then queries the product knowledge base to obtain the target environment coordinates of the target product on the actual test environment map. The product knowledge base stores the correspondence between product identifiers and environment coordinates, which is obtained based on the product display information table of the physical store and the coordinate mapping relationship between the preset layout diagram of the physical store and the actual test environment map. The product display information table stores the product identifiers and display positions of multiple products provided by the physical store, and the display position includes at least the shelf identifier of the shelf where the product is located. The preset layout diagram includes the shelf identifiers and layout positions of multiple shelves set up in the physical store. The system obtains the target environment coordinates returned by the server and the positioning coordinates determined by the smart device based on the measured environment map, and generates a navigation path from the positioning coordinates to the target environment coordinates so as to guide the consumer user to find the target product according to the navigation path.

[0012] Wherein, the target product is displayed on multiple different shelves, and after obtaining the coordinates of the target product in multiple target environments on the measured environment map, the method further includes: From the plurality of target environment coordinates, a target environment coordinate to be used is determined, and a navigation path from the positioning coordinates to the target environment coordinate to be used is generated.

[0013] A product navigation path planning method, applied on the server side, is used to provide path guidance services to consumer users through smart devices provided by physical stores. The method includes: A product knowledge base for the physical store is obtained, which stores the correspondence between product identifiers and environmental coordinates. This correspondence is obtained based on the product display information table of the physical store and the coordinate mapping relationship between the preset layout diagram of the physical store and the measured environment map. The product display information table stores the product identifiers and display positions of multiple products provided by the physical store, and the display position includes at least the shelf identifier of the shelf where the product is located. The preset layout diagram includes the shelf identifiers and layout positions of multiple shelves set up in the physical store. The measured environment map includes store space environment information collected by moving within the physical store. The system receives a search request for a target product from a smart device during human-computer interaction with a consumer user, determines the product identifier of the target product, and obtains the target environmental coordinates of the target product in the measured environment map based on the correspondence between the product identifier and environmental coordinates. The target environment coordinates are sent to the smart device so that the smart device can perform path planning based on the target environment coordinates.

[0014] Wherein, if a consumer submits a request to find a target product by inputting a natural language command, then determining the product identifier of the target product includes: Using the natural language instruction and preset model prompts as input, a semantic recognition model is invoked. The model performs intent recognition, and if it is determined that the natural language instruction has a navigation intent, the product identifier of the target product is parsed out and standardized output according to the instructions of the preset model prompts. The product identifier of the target product is determined based on the output of the model.

[0015] A product navigation route planning device is used to provide route guidance services to consumers through smart devices provided by physical stores. The device includes: The store information acquisition unit is used to acquire a preset layout map, a measured environment map, and a product display information table of a physical store. The preset layout map includes shelf labels and locations of multiple shelves set up in the physical store. The measured environment map includes store space environment information collected by moving within the physical store, which is used for intelligent device positioning and path planning. The product display information table stores product labels and display locations of multiple products provided by the physical store, and the display location includes at least the shelf label of the shelf where the product is located. The coordinate mapping unit is used to register the preset layout map with the measured environment map and establish a coordinate mapping relationship between the two. The spatial coordinate determination unit is used to determine the spatial coordinates of different products in the preset layout diagram based on the display positions of multiple products in the information table and the layout positions of multiple shelves in the preset layout diagram. An environmental coordinate transformation unit is used to convert the spatial coordinates into environmental coordinates corresponding to different products in the measured environmental map according to the coordinate mapping relationship, obtain the correspondence between product identifiers and environmental coordinates and save it to the product knowledge base, so that when the smart device provides path guidance services for target products to consumer users, it can query the product knowledge base to obtain the target environmental coordinates of the target products and perform path planning based on the target environmental coordinates.

[0016] A product navigation route planning device is applied to smart devices provided in physical stores, providing route guidance services to consumers through the smart devices. The device includes: An environment map acquisition unit is used to acquire a measured environment map of a physical store, wherein the measured environment map includes store space environment information collected by moving within the physical store. The product search request receiving unit is used to receive product search requests submitted by consumer users through human-computer interaction, and send them to the server so that the server can query the product knowledge base to obtain the target environment coordinates of the target product in the actual test environment map. The product knowledge base stores the correspondence between product identifiers and environment coordinates, and the correspondence is obtained based on the product display information table of the physical store and the coordinate mapping relationship between the preset layout diagram of the physical store and the actual test environment map. The product display information table stores the product identifiers and display positions of multiple products provided by the physical store, and the display position includes at least the shelf identifier of the shelf where the product is located. The preset layout diagram includes the shelf identifiers and layout positions of multiple shelves set up in the physical store. The navigation path generation unit is used to obtain the target environment coordinates returned by the server and the positioning coordinates determined by the smart device based on the measured environment map, and generate a navigation path from the positioning coordinates to the target environment coordinates, so as to guide the consumer user to find the target product according to the navigation path.

[0017] A product navigation route planning device, applied on a server side, is used to provide route guidance services to consumers through smart devices provided by physical stores. The device includes: The knowledge base acquisition unit is used to acquire the product knowledge base of the physical store. The product knowledge base stores the correspondence between product identifiers and environmental coordinates. The correspondence is obtained based on the product display information table of the physical store and the coordinate mapping relationship between the preset layout diagram of the physical store and the measured environment map. The product display information table stores the product identifiers and display positions of multiple products provided by the physical store. The display position includes at least the shelf identifier of the shelf where the product is located. The preset layout diagram includes the shelf identifiers and layout positions of multiple shelves set up in the physical store. The measured environment map includes store space environment information collected by moving within the physical store. The product identification unit is used to receive a search request for a target product obtained by a smart device during human-computer interaction with a consumer user, and to determine the product identification of the target product. An environmental coordinate acquisition unit is used to obtain the target environmental coordinates of the target product in the measured environmental map based on the correspondence between the product identifier and the environmental coordinates. An environmental coordinate sending unit is used to send the target environmental coordinates to the smart device so that the smart device can perform path planning based on the target environmental coordinates.

[0018] A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of any of the preceding methods.

[0019] An electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of any of the preceding methods.

[0020] A computer program product includes a computer program / computer executable instructions that, when executed by a processor in an electronic device, implement the steps of any of the preceding methods.

[0021] According to the specific embodiments provided in this application, the following technical effects are disclosed: In this embodiment, by decoupling the store layout represented by the preset layout diagram and the measured environment map from the product display location represented by the product display information table, independent updating and maintenance of store layout information and product location information are achieved. This helps reduce maintenance costs and improve maintenance efficiency, and can better adapt to the complex and ever-changing usage scenarios of stores. Based on this, a three-level mapping method is used to establish a correspondence between product identifiers and environmental coordinates. Subsequently, based on this correspondence, the target environmental coordinates of the user's target product can be determined, and a navigation path guiding the user to the target environmental coordinates can be generated, achieving efficient product search in physical store scenarios.

[0022] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the product navigation path planning system provided in the embodiments of this application; Figure 2 This is a flowchart of the product knowledge base creation method provided in the embodiments of this application; Figure 3 This is a flowchart of the product navigation path planning method provided in the embodiments of this application; Figures 4-6 This is a schematic diagram of the product navigation path planning device provided in the embodiments of this application; Figure 7 This is a schematic diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0026] To enhance the shopping experience for consumers in physical stores, we can try using smart devices with shopping guide capabilities, such as navigation robots, to provide customers with product search services.

[0027] However, during the actual research and development process, the inventors discovered that most common navigation robots adopt a single static map mode, which pre-couples the navigation target with geographical coordinates. In this way, after determining the destination, the navigation route can be planned based on the pre-bound coordinates of the destination. This static pre-binding solution cannot adapt to the product retrieval needs in physical store scenarios.

[0028] On the one hand, the display location of goods in a store is dynamic. For example, during daily sales, operations such as moving shelves, changing zones, adding or removing items from shelves, displaying in multiple locations, and temporary display changes during specific events are performed, resulting in complex and frequently changing product display locations. If the product display location is pre-bound to geographical coordinates, the location needs to be re-marked and associated when the display location changes, which is costly and inefficient.

[0029] On the other hand, store layouts are also dynamic. For example, during daily sales, shelf layouts may be adjusted, and temporary locations may be changed for specific events. In other words, the placement of shelves within the store is not fixed. Thus, even if the shelves displaying goods remain the same, changes in shelf placement will cause changes to the geographical coordinates pre-assigned to those product locations. However, store layout changes are relatively infrequent; store adjustments, for example, are a type of phased layout adjustment. Nevertheless, such adjustments often trigger numerous changes in product locations. Therefore, when store layouts change, significant manpower is required to re-mark and associate locations, resulting in high maintenance costs and low efficiency.

[0030] To address the need for efficient product navigation in physical stores, especially large supermarkets and shopping malls, this application provides a novel product locator solution. This solution decouples the infrequently changing store layout from the frequently changing product display locations, and establishes a correspondence between product identifiers and environmental coordinates through a three-level mapping method. The environmental coordinates are used for path planning. This correspondence then enables subsequent path navigation in product locator scenarios.

[0031] Specifically, from a system architecture perspective, the product navigation path planning system of this application embodiment can be as follows: Figure 1 As shown, it includes: a server and at least one smart device.

[0032] The smart devices can be deployed in physical stores to provide route guidance services to consumers who need product navigation. As an example, the smart devices can be autonomous navigation robots, handheld devices that are easy for users to carry, wearable devices, etc. This application embodiment does not specifically limit the form of the smart devices. They can interact with users, receive product search requests submitted by users for target products and send them to the server, and generate navigation paths based on the target environment coordinates of the target products returned by the server.

[0033] Correspondingly, the server can access the physical store's product knowledge base, which stores the correspondence between product identifiers and environmental coordinates. When the server receives a product search request submitted by a smart device, it can determine the target product's identifier, query the target product's target environmental coordinates from the product knowledge base, and return them to the smart device to generate a navigation path.

[0034] As one aspect of this application, an implementation scheme for establishing the correspondence between product identifiers and environmental coordinates based on a three-level mapping method can be provided.

[0035] The implementation process of the product knowledge base creation method in this application embodiment will be explained below with specific examples. See [link to relevant documentation]. Figure 2 The flowchart shown may include: S201: Obtain the preset layout map, actual test environment map, and product display information table of the physical store.

[0036] In this embodiment of the application, considering that the product display position and store layout in physical stores are dynamic, the store layout and product display position can be decoupled and updated and maintained independently.

[0037] For store layout, it can be reflected in the store's preset layout map and the actual test environment map.

[0038] The preset layout diagram may include shelf labels and corresponding placement locations for multiple shelves in the physical store.

[0039] As an example, a pre-designed layout can be represented as a store CAD drawing (Computer-Aided Design). The drawing can indicate the shelf label and its corresponding location for each shelf in the store. The shelf location can be represented by its spatial coordinates within the layout drawing. Optionally, the drawing can also indicate different store sections, such as a fruit section, vegetable section, standard product section, and food section, thus clarifying the relationship between shelves and sections. Taking the standard product section as an example, shelves 1, 2, 3, and 4 placed side-by-side can be marked within this section, along with the spatial coordinates of each shelf.

[0040] The measured environment map can include store space environment information collected during movement within the physical store, showing the layout of shelves, aisles, walls, and other environmental elements. Specifically, the environmental information can be used to reconstruct the outline of shelves, clarifying their actual location within the store; it can also be used to reconstruct the outline of aisles between shelves, clarifying the passable areas of the store for path planning and dynamic obstacle avoidance.

[0041] As an example, the measured environment map can be represented as an environmental geometric map created based on the SLAM (Simultaneous Localization and Mapping) algorithm. In this embodiment, a smart device providing path guidance services can collect the measured environment map and save it locally. For example, mapping commands can be issued to a navigation robot, controlling the robot to move freely within a physical store. The device's sensors scan the store in real time to generate a high-precision point cloud map as the measured environment map. Alternatively, a dedicated mapping device can collect the measured environment map and send it to a smart device for local storage. This embodiment does not limit the method of obtaining the measured environment map.

[0042] As for the product display location, it can be reflected in the store's product display information sheet, which stores the product labels and corresponding display locations of multiple products provided by the physical store.

[0043] The display location may include at least the shelf label of the shelf where the product is located, for example, product A is displayed on shelf 3. Thus, when providing route guidance to consumers for a target product, users can be navigated to the shelf where the target product is located. Optionally, the display location may also include the shelf location label of the product's shelf position, for example, product A is displayed on the 2nd shelf, 6th shelf position of shelf 3, based on which users can be navigated to the shelf position where the target product is located. The specific navigation accuracy can be flexibly configured according to usage needs, and this application embodiment does not limit this.

[0044] In this embodiment, the product display information table can be obtained in different ways. For example, if the store has previously maintained information related to product identification and their display locations, this information can be updated in the product display information table of this application. Another example is that the display locations of products can be automatically obtained and saved to the product display information table using visual recognition technology. Specifically, store images can be obtained in real time from devices with image acquisition capabilities, such as store cameras and inspection robots. Through image analysis and recognition, the display locations of different products can be determined. Yet another example is that the display locations of different products can be determined and saved to the product display information table using electronic shelf labels. Specifically, the product identification displayed on the electronic shelf label can be read, and the deployment location of the electronic shelf label can be used as the display location of that product.

[0045] S202: Register the preset layout map with the actual environment map and establish the coordinate mapping relationship between the two.

[0046] In this embodiment of the application, the measured environment map and the preset layout map can be registered and aligned to establish a coordinate mapping relationship between the spatial coordinates of the layout map and the environmental coordinates of the environment map, providing a technical basis for subsequent three-level mapping.

[0047] As an example, the preset layout map and the actual environment map can be registered based on environmental features such as pillars, borders, and shelves in the store, and a coordinate mapping function from spatial coordinates to environmental coordinates can be established as the coordinate mapping relationship of this application.

[0048] S203: Based on the display positions of multiple products in the product display information table and the layout positions of multiple shelves in the preset layout diagram, determine the spatial coordinates of different products in the preset layout diagram.

[0049] S204: Based on the coordinate mapping relationship, convert the spatial coordinates into environmental coordinates corresponding to different products in the actual test environment map, obtain the correspondence between product identifiers and environmental coordinates, and save it to the product knowledge base.

[0050] Based on the three-level mapping approach, when establishing the correspondence between product labels and environmental coordinates, we can first establish a first-level mapping between product labels and shelf labels based on the product display information table; then, based on the preset layout diagram, we can convert the shelf labels into spatial coordinates of the shelf placement location to form a second-level mapping; finally, based on the coordinate mapping relationship, we can convert the spatial coordinates of the shelf into the environmental coordinates of the shelf to complete the third-level mapping.

[0051] Among them, the spatial coordinates of the shelf can be used to represent the location information of the shelf in the planned space; the environmental coordinates of the shelf can be used to represent the location information of the shelf in the real environment, and intelligent devices can perform device positioning and navigation path generation based on the environmental coordinates. After performing three-level mapping according to the scheme of this application, the environmental coordinates of the shelf can be used as the environmental coordinates of the product in the measured environment map, establishing a correspondence between product identification and environmental coordinates. Subsequently, the environmental coordinates corresponding to the product can be determined based on this correspondence, and a navigation path for finding the product can be generated.

[0052] Taking the shelf label representing the location of a product as an example, for the example of product A above, the following mapping relationship can be obtained: Product A Shelf 3 Spatial coordinates of shelf 3: W3 The environmental coordinates of shelf 3 are E3. Thus, the correspondence between product A and environmental coordinates E3 can be saved to the product knowledge base. Understandably, if the display location also includes shelf location markers, the mapping relationship can be represented as: Product A... 3 shelving units, 6 storage locations Spatial coordinates W of shelf 3, location 6 36 Environmental coordinates E for shelf 3, location 6 36 Product A can be compared with environmental coordinates E. 36 The corresponding relationships are saved to the product knowledge base.

[0053] In summary, this application aligns and registers the preset layout map with the actual test environment map, and performs a three-level mapping to obtain the environmental coordinates of the product in the actual test environment map. This eliminates the need to label shelves or products on the actual test environment map, quickly establishing a correspondence between product labels and environmental coordinates, and better adapting to complex scenarios with numerous store shelves and dense product placement.

[0054] Furthermore, this solution can efficiently update the corresponding relationships when there are changes in the product display location and / or store layout. The following example illustrates the process of updating the corresponding relationships.

[0055] Scenario 1: The location of the merchandise display has changed. In this embodiment of the application, when it is determined that the product display location has changed, the product display information table can be updated independently, and then the corresponding relationship can be updated by combining it with the three-level mapping scheme mentioned above.

[0056] Specifically, if there are products in a physical store whose display positions have been changed, the product display information table can be updated based on the product identification of the changed products and the changed display positions, so as to obtain new correspondences related to the changed products and update them to the product knowledge base.

[0057] As an example, changes in product display location can manifest as updates to the product's position when it is moved to a different shelf or area. For instance, moving product A from shelf 3 to shelf 5. Alternatively, changes can manifest as deletion of a product's location when it is removed from the shelf. For example, removing product B from shelf 2. Or, changes can manifest as addition of a new product location when a new product is introduced. For instance, adding a new product C to shelf 4.

[0058] Taking product A as an example, after updating the display location of product A from shelf 3 to shelf 5 in the product display information table, the corresponding three-level mapping can be updated to: Product A Shelf 5 Spatial coordinates W5 Environment coordinates E5. Thus, by updating the correspondence between product A and environment coordinates E3 stored in the product knowledge base to the correspondence between product A and environment coordinates E5, the correspondence update of product A can be completed. The update process is simple, convenient, and efficient.

[0059] For products whose locations have been deleted, simply remove the relevant information from both the product display information table and the product knowledge base. For products whose locations have been added, add and save their new display locations to the product display information table, and then perform a three-level mapping according to the scheme in this application to obtain the corresponding relationship of the products and save it to the product knowledge base. The specific implementation process can be referred to the above description, and will not be illustrated here.

[0060] Scenario 2: Changes in store layout In this embodiment of the application, when it is determined that the store layout has changed, the coordinate mapping relationship between the preset layout map and the actual environment map can be updated independently, and then the corresponding relationship can be updated by combining it with the three-level mapping scheme mentioned above.

[0061] Specifically, if there are changes in the placement of shelves in a physical store, a new preset layout map and / or a new measured environment map after the store layout changes can be obtained, and the maps can be re-registered to update the coordinate mapping relationship and obtain a new correspondence related to the products displayed on the changed shelves, which is then updated to the product knowledge base.

[0062] In one example, changes to the store layout might involve partial adjustments to the distribution of shelves in the physical store. For instance, if a shelf shifts in position due to human impact or other reasons during use, causing a significant change in the environmental coordinates of the shifted shelf, this can be considered a partial adjustment to the shifted shelf. Similarly, adding, removing, or relocating shelves within certain areas of the store can also be considered a partial adjustment to the shelf distribution.

[0063] In this example, the coordinate mapping relationship can be updated as follows: Based on the newly collected store space environment information, a new measured environment map is obtained; using the new measured environment map as a reference, the preset layout map and the new measured environment map are registered to obtain the updated coordinate mapping relationship.

[0064] Re-collecting store spatial environment information can be manifested as re-scanning within the store to obtain complete store spatial environment information and generate a new measured environment map. Alternatively, it can be manifested as re-scanning specific areas that have changed, collecting spatial environment information of the changed areas, and updating the original measured environment map to obtain a new measured environment map.

[0065] In practical applications, if after making local adjustments, without rescanning the environmental information in the actual environment, but instead obtaining a new preset layout map after the local adjustments, this application can still use the new preset layout map as a reference to register it with the measured environment map to obtain the updated coordinate mapping relationship. This is because when adding, removing, or relocating shelves, a layout design is usually performed first to generate a new preset layout map, and then the shelves are adjusted according to the new preset layout map. In other words, if a new preset layout map can be easily obtained, even without actually scanning to obtain a new measured environment map, feature matching and alignment can still be performed using the new preset layout map as a reference, which helps improve registration efficiency.

[0066] The following example, using the addition of a new shelf, illustrates the process of updating the corresponding relationship in this example.

[0067] Specifically, if the adjustment involves adding new shelves in a physical store, the new products displayed on the new shelves can be identified, and the product identification and display position of the new products can be updated in the product display information table. Subsequently, based on the updated product display information table and the updated coordinate mapping relationship, a three-level mapping can be performed to obtain a new correspondence related to the new products and update it in the product knowledge base.

[0068] The newly added products can be new items that are not yet available in the store. For example, new product D can be displayed on a new shelf n. Alternatively, the newly added products can be products that are already available in the store. By adding new shelves, the products can be displayed in multiple locations. For example, in the case above where product C is displayed on shelf 4, when making partial adjustments to the store, product C can also be displayed on a new shelf m. In other words, users can purchase product C on both shelf 4 and shelf m.

[0069] When making partial adjustments to the store layout and adding new shelves, it is necessary to update the map to ensure that the new shelves can be found on the map and that their coordinate mapping is clear. On the other hand, it is necessary to update the merchandise display information table to ensure that the new products placed on the new shelves can be identified and the corresponding relationships of these new products are updated.

[0070] Taking the addition of product C on shelf m as an example, we can first add product C and its display location shelf m in the product display information table, and then perform a three-level mapping: Product C Shelf m Spatial coordinates W m Environmental coordinates E m Obtain the coordinates of product C and environment E. m The corresponding relationships are saved to the product knowledge base. In this way, the process of updating the corresponding relationships of the products C displayed on a newly added shelf m can be completed.

[0071] Understandably, newly added shelves can be shelves that remain fixed for a period of time, or temporary shelves set up for specific events. For example, temporary displays or promotional counters set up in a store for specific products or during events on specific dates can be considered as newly added shelves.

[0072] Furthermore, if during the partial adjustment process it is determined that there are shelves in the store that need to be removed, this application can update the map to identify the location of the removed shelves as a passable area, and can also delete information related to the products displayed on the removed shelves from the product display information table and the product knowledge base, respectively.

[0073] If, during partial adjustments, it is determined that some shelves in the store have changed positions, this application can update the map to ensure that the changes in shelf positions are clearly visible on the map. For example, if the spatial coordinates of shelf 5 change from spatial coordinate W5 to spatial coordinate W5′, the corresponding environmental coordinates change from environmental coordinate E5 to environmental coordinate E5′. If the product's display position on the shelf remains unchanged, the product display information table can be maintained, and a three-level mapping can be performed based on the changed coordinates to obtain a new correspondence and update the product knowledge base. Taking product A displayed on shelf 5 as an example, the three-level mapping can be reflected as: Product A Shelf 5 Spatial coordinates W5′ The environment coordinate E5′ can update the correspondence between product A and environment coordinate E5 stored in the product knowledge base to the correspondence between product A and environment coordinate E5′, achieving a simple, convenient and efficient update of the correspondence.

[0074] In another example, a change in store layout might be a global adjustment to the distribution of shelves in a physical store.

[0075] Correspondingly, the coordinate mapping relationship can be updated in the following way: obtain a new preset layout map designed for global adjustment and a new measured environment map generated by re-collection; register the new preset layout map and the new measured environment map to obtain the updated coordinate mapping relationship.

[0076] This is because a global adjustment may require a complete redesign of the store's aisles, walls, shelves, etc., resulting in a significant change in the store's spatial environment structure. A new preset layout map and a new measured environment map can be obtained and re-registered so that the corresponding relationships can be updated based on the updated coordinate mapping relationship.

[0077] In summary, this application decouples store layout information from product location information in physical store scenarios and performs targeted independent updates and maintenance on both based on the dynamic changes of the store, which can effectively reduce maintenance costs and improve maintenance efficiency.

[0078] As another aspect of the embodiments of this application, an implementation scheme for generating navigation paths based on the correspondence between product identifiers and environmental coordinates can be provided.

[0079] The implementation process of the product navigation path planning method in this application will be explained below with specific examples. See [link to relevant documentation]. Figure 3 The flowchart shown may include: S301: Smart devices obtain a real-world environmental map of physical stores.

[0080] As mentioned above, the measured environment map can be collected by a smart device and saved locally, or it can be collected by a dedicated mapping device and provided to a smart device for local saving.

[0081] Taking the creation of a real-world environment map by a smart device as an example, the smart device can be controlled to scan the store environment through timed triggering to ensure the accuracy of the real-world environment map used for path generation, that is, to restore and represent the current real-world layout of the store as much as possible. Alternatively, if it is determined that the store layout has changed, the smart device can be controlled to scan the store environment to obtain the latest real-world environment map.

[0082] Understandably, the measured environment map stored locally on a smart device is usually consistent with the measured environment map used to establish the coordinate mapping relationship. This helps ensure the availability of the generated navigation path when planning a path based on the correspondence established by the coordinate mapping relationship.

[0083] S302: The smart device receives a customer's request to find a target product submitted by the customer through human-computer interaction and sends it to the server.

[0084] In this embodiment, when a user is shopping in a store and has a navigation need for a specific product, they can interact with the smart device provided by the store to submit a search request for that product. Understandably, submitting a search request through human-computer interaction reduces the difficulty of operating the device and improves user convenience; furthermore, it allows the device's current location to be used as the user's current location, reducing the difficulty of determining the user's location.

[0085] As an example, users can describe their navigation needs using natural language. For instance, a user might input "Where's the Coke?" during the interaction. After the smart device collects the user's voice, it can directly submit the user's voice as a search request to the server; alternatively, it can convert the user's voice into text before submitting it to the server. Optionally, the smart device can also display the voice-to-text message for the user to confirm their needs before submitting the text to the server, ensuring the accuracy of the recognition of the user's navigation request.

[0086] S303: The server receives a product search request sent by a smart device and determines the product identifier of the target product from it.

[0087] As shown in the example above, if a consumer submits a request to find a target product by inputting natural language commands, the product identifier of the target product can be determined from the request through a semantic recognition model.

[0088] Specifically, the server can take natural language commands and preset model prompts as input, call the semantic recognition model, and the model will perform intent recognition. If it determines that the natural language command has a navigation intent, it will parse out the product identifier of the target product and output it in a standardized manner according to the instructions of the preset model prompts. In this way, the server can determine the product identifier of the target product based on the model's output.

[0089] In this embodiment, a preset model prompt can guide the semantic recognition model to output standardized navigation instructions, achieving a reliable conversion from semantics to actions. As an example, the preset prompt may include: a preset output format, such as parsing a user request into JSON format; an action, i.e., the execution of the intent, which in this example could be product navigation; and parameters, i.e., the parameters required to execute the action, which in this example could be the product identifier of the target product.

[0090] S304: The server obtains the target environment coordinates of the target product in the actual test environment map based on the correspondence between the product identifier and the environment coordinates, and sends it to the smart device.

[0091] In this embodiment of the application, the server can obtain Figure 2 The product knowledge base generated by the scheme shown determines the target environment coordinates of the target product based on the correspondence between product identifiers and environment coordinates stored in the knowledge base. The product knowledge base can be generated by a server or by other devices; this embodiment does not limit this, as long as the server has access to the product knowledge base when it is necessary to query the product environment coordinates.

[0092] After the server queries the product knowledge base to determine the target environment coordinates of the target product, it can directly send the information to the smart device. Alternatively, the query results can be provided to a content generation model, which will then generate response information that matches the query results and send the response information to the smart device.

[0093] For example, if the query result is that the target product was not found, the generated response information may include a message indicating that the target product does not exist, as well as recommended products related to the target product.

[0094] For example, the query results might contain multiple fuzzy matches. In the example above searching for cola, there might be multiple brands and sizes of cola available. These can all be considered fuzzy matches, and the generated response can include these fuzzy matches for user confirmation. In other words, the process of querying the environmental coordinates of a target product may involve multiple rounds of interaction with the user to determine the unique target product, and then obtain the target environmental coordinates of that product and send them to the smart device.

[0095] In this application, the semantic recognition model and the content generation model can be represented as an integrated model, which has both semantic recognition and content generation capabilities. Alternatively, the semantic recognition model and the content generation model can be represented as two independent models, which the server can call separately according to usage requirements.

[0096] S305: The smart device obtains the target environment coordinates returned by the server and the positioning coordinates determined by the smart device based on the measured environment map, and generates a navigation path from the positioning coordinates to the target environment coordinates so as to guide the consumer user to find the target product according to the navigation path.

[0097] In this embodiment of the application, the smart device can collect environmental information of its current location through its own sensors, match it with the measured environmental map, realize the positioning of the smart device, and obtain the positioning coordinates of the smart device's current location.

[0098] When generating navigation paths, the device's current location can be used as the user's current location. Therefore, the device's location coordinates can be used as the starting point, and the target environment coordinates returned by the server can be used as the ending point. A navigation path from the device's location coordinates to the target environment coordinates is generated based on the measured environment map. Subsequently, the smart device can guide the consumer to the display location of the target product according to this navigation path.

[0099] In practical applications, a target product may be displayed on multiple different shelves, corresponding to multiple target environmental coordinates for that product. As in the example of product C above, the multiple target environmental coordinates returned by the server could include: environmental coordinates E4 for shelf 4, environmental coordinates E for shelf m, etc. m .

[0100] Correspondingly, a smart device can determine a target environment coordinate from multiple target environment coordinates and generate a navigation path from the positioning coordinates to the target environment coordinate.

[0101] As an example, based on the principle of the shortest navigation path, the target environment coordinates that are closest to the positioning coordinates among multiple target environment coordinates can be determined as the target environment coordinates to be used, and a navigation path from the positioning coordinates to the closest target environment coordinates can be generated.

[0102] As another example, the target environmental coordinates can be determined based on user needs. Specifically, multiple target environmental coordinates corresponding to physical locations can be provided to the user for confirmation, allowing the user to select one based on their needs. The physical location represented by the environmental coordinates can be represented by the shelf identifier of the corresponding shelf, such as providing the identifiers of shelf 4 and shelf m to the user. Alternatively, the physical location represented by the environmental coordinates can be represented by the zone identifier of the zone to which the environmental coordinates belong. If shelf 4 is located in the standard product zone and shelf m is located in the dining area, then the identifiers of the standard product zone and the dining area can be provided to the user. In this example, if the user wants to dine in the dining area, they can select the environmental coordinates of shelf m in the dining area as the target environmental coordinates.

[0103] In summary, this embodiment of the application decouples the store layout represented by the preset layout diagram and the measured environment map from the product display location represented by the product display information table. This enables independent updating and maintenance of store layout information and product location information, helping to reduce maintenance costs and improve maintenance efficiency, and better adapting to the complex and ever-changing usage scenarios of stores. Furthermore, a three-level mapping method is used to establish a correspondence between product identifiers and environmental coordinates. Subsequently, based on this correspondence, the target environmental coordinates of the user's intended product can be determined, generating a navigation path guiding the user to the target environmental coordinates, thus achieving efficient product search in physical store scenarios.

[0104] It should be noted that the embodiments of this application may involve the use of user data. In practical applications, user-specific personal data may be used in the scheme described herein within the scope permitted by applicable laws and regulations, provided that it complies with the applicable laws and regulations of the country (e.g., with the user's explicit consent, with the user being properly notified, etc.).

[0105] Corresponding to the foregoing method embodiments, this application also provides a product navigation path planning device for providing path guidance services to consumers through smart devices provided by physical stores. See also Figure 4 The device may include: The store information acquisition unit 401 is used to acquire a preset layout diagram, a measured environment map, and a product display information table of a physical store; the preset layout diagram includes shelf labels and placement locations of multiple shelves set up in the physical store; the measured environment map includes store space environment information collected during movement within the physical store, used for intelligent device positioning and path planning; the product display information table stores product labels and display locations of multiple products provided by the physical store, and the display location includes at least the shelf label of the shelf where the product is located. The coordinate mapping unit 402 is used to register the preset layout map with the measured environment map and establish a coordinate mapping relationship between the two. The spatial coordinate determination unit 403 is used to determine the spatial coordinates of different products in the preset layout diagram based on the display positions of multiple products in the information table and the layout positions of multiple shelves in the preset layout diagram. The environmental coordinate transformation unit 404 is used to convert the spatial coordinates into environmental coordinates corresponding to different products in the measured environmental map according to the coordinate mapping relationship, obtain the correspondence between product identifiers and environmental coordinates and save it to the product knowledge base, so that when the smart device provides path guidance services for target products to consumer users, it can query the product knowledge base to obtain the target environmental coordinates of the target product and perform path planning based on the target environmental coordinates.

[0106] The device further includes: The correspondence update unit is used to update the product display information table according to the product identifier of the modified product and the changed display position when there is a change in the display position of the product in the physical store, so as to obtain a new correspondence related to the modified product and update it to the product knowledge base.

[0107] The device further includes: The correspondence update unit is used to obtain a new preset layout map and / or a new measured environment map after the change of the store layout when there is a change in the placement of shelves in the physical store, and to re-register in order to update the coordinate mapping relationship and obtain a new correspondence related to the products displayed on the changed shelves and update it to the product knowledge base.

[0108] The change in the placement of the shelves indicates a localized adjustment to the shelf distribution in the physical store. The correspondence update unit can be used to: obtain the new measured environment map based on the newly collected store space environment information; and register the preset layout map with the new measured environment map based on the new measured environment map to obtain the updated coordinate mapping relationship.

[0109] The partial adjustment involves adding new shelves in the physical store. The correspondence update unit can also be used to: determine the new products displayed on the new shelves, update the product identifier and display position of the new products to the product display information table, so as to obtain a new correspondence related to the new products and update it to the product knowledge base based on the updated product display information table and the updated coordinate mapping relationship.

[0110] The change in the placement of the shelves indicates a global adjustment to the distribution of shelves in the physical store. The correspondence update unit can be specifically used to: obtain a new preset layout map designed for the global adjustment and a new measured environment map generated by re-collection; register the new preset layout map and the new measured environment map to obtain the updated coordinate mapping relationship.

[0111] Corresponding to the foregoing method embodiments, this application also provides a product navigation path planning device, applied to smart devices provided in physical stores, which provides path guidance services to consumers. See also Figure 5 The device may include: The environment map acquisition unit 501 is used to acquire a measured environment map of the physical store, wherein the measured environment map includes store space environment information collected by moving within the physical store. The product search request receiving unit 502 is used to receive product search requests submitted by consumer users through human-computer interaction, and send them to the server so that the server can query the product knowledge base to obtain the target environment coordinates of the target product in the actual test environment map. The product knowledge base stores the correspondence between product identifiers and environment coordinates, and the correspondence is obtained based on the product display information table of the physical store and the coordinate mapping relationship between the preset layout diagram of the physical store and the actual test environment map. The product display information table stores the product identifiers and display positions of multiple products provided by the physical store, and the display position includes at least the shelf identifier of the shelf where the product is located. The preset layout diagram includes the shelf identifiers and layout positions of multiple shelves set up in the physical store. The navigation path generation unit 503 is used to obtain the target environment coordinates returned by the server and the positioning coordinates determined by the smart device based on the measured environment map, and generate a navigation path from the positioning coordinates to the target environment coordinates, so as to guide the consumer user to find the target product according to the navigation path.

[0112] Wherein, the target product is displayed on multiple different shelves, and after obtaining multiple target environment coordinates corresponding to the target product in the measured environment map, the navigation path generation unit is further used to: determine a target environment coordinate to be used from the multiple target environment coordinates, and generate a navigation path from the positioning coordinates to the target environment coordinate to be used.

[0113] Corresponding to the foregoing method embodiments, this application also provides a product navigation path planning device, applied on a server side, for providing path guidance services to consumer users through smart devices provided by physical stores. See also Figure 6 The device may include: The knowledge base acquisition unit 601 is used to acquire a product knowledge base of the physical store. The product knowledge base stores the correspondence between product identifiers and environmental coordinates. The correspondence is obtained based on the product display information table of the physical store and the coordinate mapping relationship between the preset layout diagram of the physical store and the measured environment map. The product display information table stores the product identifiers and display positions of multiple products provided by the physical store. The display position includes at least the shelf identifier of the shelf where the product is located. The preset layout diagram includes the shelf identifiers and layout positions of multiple shelves set up in the physical store. The measured environment map includes store space environment information collected by moving within the physical store. The product identification determination unit 602 is used to receive a product search request for a target product obtained by a smart device during human-computer interaction with a consumer user, and to determine the product identification of the target product. The environmental coordinate acquisition unit 603 is used to obtain the target environmental coordinates of the target product in the measured environmental map according to the correspondence between the product identifier and the environmental coordinates. The environmental coordinate sending unit 604 is used to send the target environmental coordinates to the smart device so that the smart device can perform path planning based on the target environmental coordinates.

[0114] Specifically, if a consumer submits a request to find a target product by inputting a natural language command, the product identifier determination unit can be used to: take the natural language command and preset model prompt words as input, call a semantic recognition model, have the model perform intent recognition, and if it is determined that the natural language command has a navigation intent, parse out the product identifier of the target product from it, and perform standardized output according to the instructions of the preset model prompt words; determine the product identifier of the target product based on the output of the model.

[0115] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0116] And an electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.

[0117] A computer program product includes a computer program / computer executable instructions that, when executed by a processor in an electronic device, implement the steps of the method described in the foregoing method embodiments.

[0118] in, Figure 7 The architecture of an electronic device is illustrated by example. For instance, device 700 could be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, aircraft, etc.

[0119] Reference Figure 7 The device 700 may include one or more of the following components: a processing component 702, a memory 704, a power supply component 706, a multimedia component 708, an audio component 710, an input / output (I / O) interface 712, a sensor component 714, and a communication component 716.

[0120] Processing component 702 typically controls the overall operation of device 700, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 702 may include one or more processors 720 to execute instructions to perform all or part of the steps of the methods provided in this disclosure. Furthermore, processing component 702 may include one or more modules to facilitate interaction between processing component 702 and other components. For example, processing component 702 may include a multimedia module to facilitate interaction between multimedia component 708 and processing component 702.

[0121] Memory 704 is configured to store various types of data to support the operation of device 700. Examples of this data include instructions for any application or method operating on device 700, contact data, phonebook data, messages, pictures, videos, etc. Memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0122] Power supply component 706 provides power to various components of device 700. Power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 700.

[0123] Multimedia component 708 includes a screen that provides an output interface between device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 708 includes a front-facing camera and / or a rear-facing camera. When device 700 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0124] Audio component 710 is configured to output and / or input audio signals. For example, audio component 710 includes a microphone (MIC) configured to receive external audio signals when device 700 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 704 or transmitted via communication component 716. In some embodiments, audio component 710 also includes a speaker for outputting audio signals.

[0125] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0126] Sensor assembly 714 includes one or more sensors for providing state assessments of various aspects of device 700. For example, sensor assembly 714 may detect the on / off state of device 700, the relative positioning of components such as the display and keypad of device 700, changes in the position of device 700 or a component of device 700, the presence or absence of user contact with device 700, the orientation or acceleration / deceleration of device 700, and temperature changes of device 700. Sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 714 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0127] Communication component 716 is configured to facilitate wired or wireless communication between device 700 and other devices. Device 700 can access wireless networks based on communication standards, such as WiFi, or mobile communication networks such as 2G, 7G, 4G / LTE, and 7G. In one exemplary embodiment, communication component 716 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 716 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0128] In an exemplary embodiment, device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0129] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, which can be executed by a processor 720 of device 700 to perform the method provided by the present disclosure. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0130] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0131] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0132] The solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A product navigation path planning method, characterized in that, The method for providing route guidance services to consumers through smart devices provided in physical stores includes: The system obtains a preset layout diagram, a measured environment map, and a product display information table for a physical store. The preset layout diagram includes shelf labels and locations of multiple shelves in the physical store. The measured environment map includes store space environment information collected during movement within the physical store, which is used for smart device positioning and path planning. The product display information table stores product labels and display locations of multiple products provided by the physical store, and the display location includes at least the shelf label of the shelf where the product is located. The preset layout map and the measured environment map are registered to establish a coordinate mapping relationship between them; Based on the display positions of multiple products in the information table and the layout positions of multiple shelves in the preset layout diagram, determine the spatial coordinates of different products in the preset layout diagram. Based on the coordinate mapping relationship, the spatial coordinates are converted into environmental coordinates corresponding to different products in the measured environment map. The correspondence between product identifiers and environmental coordinates is obtained and saved in the product knowledge base. When the smart device provides path guidance services for target products to consumer users, the target environmental coordinates of the target product can be obtained by querying the product knowledge base, and path planning can be performed based on the target environmental coordinates.

2. The method according to claim 1, characterized in that, The method further includes: If there are products whose display positions have been changed in the physical store, the product display information table is updated according to the product identifier of the changed product and the changed display position, so as to obtain a new correspondence related to the changed product and update it to the product knowledge base.

3. The method according to claim 1, characterized in that, The method further includes: If there are changes in the placement of shelves in the physical store, a new preset layout map and / or a new measured environment map after the store layout changes are obtained, and re-registered to update the coordinate mapping relationship and obtain a new correspondence relationship related to the products displayed on the changed shelves, which is then updated to the product knowledge base.

4. The method according to claim 3, characterized in that, The change in the placement of the shelves indicates a localized adjustment to the shelf distribution in the physical store. Based on the newly collected store space environment information, the new measured environment map is obtained; Using the new measured environment map as a reference, the preset layout map is registered with the new measured environment map to obtain the updated coordinate mapping relationship.

5. The method according to claim 4, characterized in that, The localized adjustment involves adding new shelves in the physical store, and the method further includes: The newly added products displayed on the newly added shelves are identified, and the product identifiers and display positions of the newly added products are updated to the product display information table. In order to obtain new correspondences related to the newly added products and update them to the product knowledge base based on the updated product display information table and the updated coordinate mapping relationship.

6. The method according to claim 3, characterized in that, The change in the placement of the shelves indicates a global adjustment to the distribution of shelves in the physical store. Obtain a new preset layout diagram for the global adjustment design and a new measured environment map generated by re-collection; The new preset layout map is registered with the new measured environment map to obtain the updated coordinate mapping relationship.

7. A product navigation path planning method, characterized in that, A method for providing route guidance services to consumers using smart devices provided in physical stores includes: Obtain a measured environment map of the physical store, which includes store space environment information collected by moving within the physical store; The system receives a product search request submitted by a consumer user via human-computer interaction and sends it to the server. The server then queries the product knowledge base to obtain the target environment coordinates of the target product on the actual test environment map. The product knowledge base stores the correspondence between product identifiers and environment coordinates, which is obtained based on the product display information table of the physical store and the coordinate mapping relationship between the preset layout diagram of the physical store and the actual test environment map. The product display information table stores the product identifiers and display positions of multiple products provided by the physical store, and the display position includes at least the shelf identifier of the shelf where the product is located. The preset layout diagram includes the shelf identifiers and layout positions of multiple shelves set up in the physical store. The system obtains the target environment coordinates returned by the server and the positioning coordinates determined by the smart device based on the measured environment map, and generates a navigation path from the positioning coordinates to the target environment coordinates so as to guide the consumer user to find the target product according to the navigation path.

8. The method according to claim 7, characterized in that, The target product is displayed on multiple different shelves. After obtaining the coordinates of the target product in multiple target environments on the measured environment map, the method further includes: From the plurality of target environment coordinates, a target environment coordinate to be used is determined, and a navigation path from the positioning coordinates to the target environment coordinate to be used is generated.

9. A product navigation path planning method, characterized in that, Applied to the server side, and used to provide route guidance services to consumer users through smart devices provided by physical stores, the method includes: A product knowledge base for the physical store is obtained, which stores the correspondence between product identifiers and environmental coordinates. This correspondence is obtained based on the product display information table of the physical store and the coordinate mapping relationship between the preset layout diagram of the physical store and the measured environment map. The product display information table stores the product identifiers and display positions of multiple products provided by the physical store, and the display position includes at least the shelf identifier of the shelf where the product is located. The preset layout diagram includes the shelf identifiers and layout positions of multiple shelves set up in the physical store. The measured environment map includes store space environment information collected by moving within the physical store. The system receives a search request for a target product from a smart device during human-computer interaction with a consumer user, determines the product identifier of the target product, and obtains the target environmental coordinates of the target product in the measured environment map based on the correspondence between the product identifier and environmental coordinates. The target environment coordinates are sent to the smart device so that the smart device can perform path planning based on the target environment coordinates.

10. The method according to claim 9, characterized in that, If a consumer submits a request to find a target product by inputting natural language commands, then determining the product identifier of the target product includes: Using the natural language instruction and preset model prompts as input, a semantic recognition model is invoked. The model performs intent recognition, and if it is determined that the natural language instruction has a navigation intent, the product identifier of the target product is parsed out and standardized output according to the instructions of the preset model prompts. The product identifier of the target product is determined based on the output of the model.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method described in any one of claims 1 to 10.

12. An electronic device, characterized in that, include: One or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method according to any one of claims 1 to 10.

13. A computer program product comprising a computer program / computer executable instructions, characterized in that, When the computer program / computer-executable instructions are executed by a processor in an electronic device, they implement the steps of the method according to any one of claims 1 to 10.

Images