Similar item identification methods, devices, readable storage media and electronic devices

Abstract

This disclosure relates to a method, apparatus, readable storage medium, and electronic device for identifying similar items. The method includes: acquiring attribute information of the item to be identified and a similar item knowledge graph, wherein the similar item knowledge graph is updated at least based on a list of frequently mistakenly issued items; identifying similar items from the items to be identified based on the attribute information of the item to be identified and the similar item knowledge graph; and marking the similar items. Updating the similar item knowledge graph at least based on the list of frequently mistakenly issued items enriches the similar item groups stored in the similar item knowledge graph, thus improving the accuracy of similar item identification when automatically identifying similar items from the items to be identified using the similar item knowledge graph. Furthermore, after identifying similar items, they can be automatically marked, prompting staff to scan the barcodes of the similar items for verification, thereby improving the accuracy of similar item operations and the efficiency of non-similar item operations.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a method, apparatus, readable storage medium, and electronic device for identifying similar items. Background Technology

[0002] In e-commerce logistics, central warehouses often store similar items. For example, different flavors of the same brand of cookies are similar, as are different weights of the same item (e.g., different weights of ginger). These similar items frequently cause confusion and errors when being sorted by warehouse staff. For instance, if a customer orders a certain flavor of cookie A online, a staff member might mistakenly retrieve a different flavor of the same cookie based on the order information, resulting in the customer receiving something different from what they ordered, leading to a poor online shopping experience. Therefore, it is necessary to identify similar items among those awaiting or already stored in the central warehouse. This allows staff to accurately retrieve the customer's order, ensuring the customer receives the correct item and improving their online shopping experience. Summary of the Invention

[0003] The purpose of this disclosure is to provide a method, apparatus, readable storage medium, and electronic device for identifying similar items, in order to solve the problems existing in the related technologies.

[0004] To achieve the above objectives, the first aspect of this disclosure provides a method for identifying similar items, comprising:

[0005] Obtain the attribute information of the item to be identified and the knowledge graph of similar items, wherein the knowledge graph of similar items is at least updated based on the list of items prone to being sent incorrectly, and the list of items prone to being sent incorrectly includes the identifiers of the original purchased items and the actual items sent, for which the return or exchange was due to the wrong item being sent.

[0006] Based on the attribute information of the item to be identified and the knowledge graph of similar items, similar items are identified from the item to be identified; and

[0007] Mark the similar items.

[0008] Optionally, the attribute information of the item to be identified includes the identifier of the item to be identified; the method further includes:

[0009] Obtain the list of items prone to error;

[0010] Based on the identifier of the item to be identified and the identifiers of the items included in the list of items prone to misdelivery, determine whether there is a group of items prone to misdelivery among the items to be identified;

[0011] If the group of items prone to misdelivery exists among the items to be identified, then the similar items are identified from the items to be identified based on the group of items prone to misdelivery.

[0012] Optionally, the step of identifying the similar item from the items to be identified based on the group of easily mistaken items if the group of easily mistaken items exists includes:

[0013] If the group of items prone to being sent is present among the items to be identified, then the complaint rate of each group of items prone to being sent is determined.

[0014] Each group of items with a complaint rate greater than or equal to a preset threshold that is prone to being mistakenly sent is identified as a group of similar items.

[0015] Optionally, the attribute information includes the item's identifier; the method further includes:

[0016] Send a prompt message to the target staff member's terminal to prompt the target staff member to identify whether there are similar items among the items to be identified;

[0017] The system receives the identifier of a similar item sent by the target worker's terminal and identifies the similar item among the items to be identified based on the identifier.

[0018] Optionally, the method further includes:

[0019] The similar item knowledge graph is updated using the attribute information of the identified similar items to obtain an updated similar item knowledge graph.

[0020] Optionally, marking the similar items includes:

[0021] Record the attribute information of similar items among the items to be identified in the list of similar items;

[0022] The method further includes:

[0023] Obtain the central warehouse identifier and date where the item to be identified is stored;

[0024] The list of similar items, the central warehouse identifier, and the date are associated and stored.

[0025] Optionally, the similar item knowledge graph includes multiple groups of similar items, and the step of identifying similar items from the item to be identified based on the attribute information of the item to be identified and the similar item knowledge graph includes:

[0026] For any item among the items to be identified, determine whether the item is located in the similar item knowledge graph based on the item's attribute information. If it is located, determine the similar item group to which the item belongs. Also, determine whether there are other items in the similar item group among the items to be identified. If there are, identify the item and the other items among the items to be identified as a group of similar items.

[0027] A second aspect of this disclosure provides a similar item identification device, comprising:

[0028] The first acquisition module is used to acquire attribute information of the item to be identified and a knowledge graph of similar items. The knowledge graph of similar items is at least updated based on a list of items prone to being sent incorrectly. The list of items prone to being sent incorrectly includes multiple sets of original purchased items and the identifiers of the items actually sent that were returned or exchanged due to incorrect delivery.

[0029] The first identification module is used to identify similar items from the items to be identified based on the attribute information of the items to be identified and the similar items knowledge graph; and

[0030] A tagging module is used to tag the similar items.

[0031] Optionally, the attribute information of the item to be identified includes the identifier of the item to be identified; the device further includes:

[0032] The second acquisition module is used to acquire the list of items prone to error in delivery;

[0033] The determination module is used to determine whether there is a group of items prone to being sent out among the items to be identified, based on the identifier of the item to be identified and the identifiers of the items included in the list of items prone to being sent out.

[0034] The second identification module is used to identify the similar items from the items to be identified if the group of items prone to misdelivery exists among the items to be identified.

[0035] Optionally, the second identification module includes:

[0036] The first determining submodule is used to determine the complaint rate of each of the error-prone item groups if the error-prone item group exists among the items to be identified.

[0037] The second determining submodule is used to determine each group of error-prone items with a complaint rate greater than or equal to a preset threshold as a group of similar items.

[0038] Optionally, the attribute information includes the item's identifier; the device further includes:

[0039] The sending module is used to send a prompt message to the terminal of the target staff member to prompt the target staff member to identify whether there are similar items among the items to be identified;

[0040] The receiving module is used to receive the identifier of similar items sent by the terminal of the target worker, and to identify similar items among the items to be identified based on the identifier.

[0041] Optionally, the device further includes:

[0042] The update module is used to update the similar item knowledge graph using the attribute information of the identified similar items, so as to obtain the updated similar item knowledge graph.

[0043] Optionally, the marking module is used to: record attribute information of similar items among the items to be identified in a list of similar items; the device further includes:

[0044] The third acquisition module is used to acquire the central warehouse identifier and date of the item to be identified;

[0045] The storage module is used to associate and store the list of similar items, the central warehouse identifier, and the date.

[0046] Optionally, the identification module is configured to: for any item among the items to be identified, determine whether the item is located in the similar item knowledge graph based on the attribute information of the item; if it is located, determine the similar item group to which the item belongs; and determine whether there are other items in the similar item group among the items to be identified; if there are, identify the item and the other items among the items to be identified as a group of similar items.

[0047] A third aspect of this disclosure provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects of this disclosure.

[0048] A fourth aspect of this disclosure provides an electronic device, comprising:

[0049] A memory on which computer programs are stored;

[0050] A processor for executing the computer program in the memory to implement the steps of the method according to any of the first aspects of this disclosure.

[0051] By adopting the above technical solution, the knowledge graph of similar items is updated at least according to the list of frequently mistakenly sent items, enriching the similar item groups stored in the knowledge graph. This improves the accuracy of similar item identification when automatically recognizing similar items from the items to be identified using the similar item knowledge graph. Furthermore, after identifying similar items, they are automatically marked, prompting staff to scan their barcodes for verification, thereby improving the accuracy of similar item processing and the efficiency of non-similar item processing.

[0052] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0053] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0054] Figure 1 This is a flowchart illustrating a method for identifying similar items according to an exemplary embodiment.

[0055] Figure 2 This is a flowchart illustrating another method for identifying similar items according to an exemplary embodiment.

[0056] Figure 3 This is a flowchart illustrating another method for identifying similar items according to an exemplary embodiment.

[0057] Figure 4 This is a flowchart illustrating another method for identifying similar items according to an exemplary embodiment.

[0058] Figure 5 This is a block diagram illustrating a similar item identification device according to an exemplary embodiment.

[0059] Figure 6 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0060] To avoid frequent sorting confusion and errors by staff, similar items are typically identified manually. In this technology, when receiving goods, the central warehouse receiving team manually checks the receiving list to determine if there are any items with similar appearances or product names. If so, the items with similar appearances and product names are identified as similar items. Then, the receiving staff manually records the identification of similar items in an Excel spreadsheet (i.e., a list of similar items). After receiving the goods, the list of similar items is synchronized to the central warehouse sorting team through the work group, and the latter refers to the list of similar items during the sorting process to avoid the risk of sorting confusion and errors.

[0061] It's worth noting that the similar items recorded in the similar items list are all groups of similar items. For example, if the receiving list includes cowpeas and garlic scapes, because cowpeas and garlic scapes look similar, the receiving staff will identify them as a group of similar items and record them as such in the similar items list to indicate their similarity. Similarly, if the receiving list includes a brand of lime-flavored, strawberry-flavored, and chocolate-flavored cookies, the receiving staff can record the lime-flavored cookies, strawberry-flavored cookies, and chocolate-flavored cookies as a group of similar items in the similar items list.

[0062] However, the above method relies heavily on the experience and judgment of the receiving team staff. If the staff are not familiar with the items included in the receiving list, they may identify incorrect similar items, resulting in low accuracy in identifying similar items. Furthermore, manual identification of similar items is also slow.

[0063] In view of this, in order to improve the efficiency of similar item identification, this disclosure provides a similar item identification method, apparatus, readable storage medium and electronic device.

[0064] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0065] Figure 1 This is a flowchart illustrating a similar item identification method according to an exemplary embodiment, wherein the similar item identification method can be applied to the operating system of a central warehouse. For example... Figure 1 As shown, the method may include the following steps.

[0066] In step S11, the attribute information of the item to be identified and the knowledge graph of similar items are obtained.

[0067] An item knowledge graph is a structured and semantic knowledge graph that uses AI (Artificial Intelligence) and machine learning technologies to represent item information and its attributes, such as category, brand, appearance, packaging, images, origin, and preparation methods, as nodes according to human-understandable dimensions. Different products with the same attributes are connected by edges, thus representing a massive number of items as a structured and semantic knowledge graph. Specifically, when constructing an item knowledge graph, for perishable goods, information such as item name, local name, and specifications (weight) are described as nodes. For standard goods, SPU (standard product unit) information can be described as nodes. The specific implementation method for constructing an item knowledge graph can refer to methods for constructing knowledge graphs in related technologies, and this disclosure does not impose specific limitations on it. Similar item knowledge graphs can be determined based on the item knowledge graph; specifically, similar item knowledge graphs can be determined based on the dimension of attribute information similarity.

[0068] It's worth noting that the similar item knowledge graph is updated based on at least the list of items prone to errors in delivery. This list includes multiple sets of identifiers for the original purchased items and the actual items shipped when returns or exchanges were due to incorrect delivery. Thus, the list of items prone to errors in delivery enriches the similar item groups stored in the similar item knowledge graph, thereby improving the accuracy of similar item identification when using this richer knowledge graph.

[0069] In this disclosure, the item to be identified may be an item to be received in the central warehouse, an item stored in the central warehouse, an item to be shipped out, etc. This disclosure does not limit the item to be identified.

[0070] In step S12, similar items are identified from the items to be identified based on the attribute information of the items to be identified and the knowledge graph of similar items.

[0071] In this disclosure, similar items refer to multiple items that are similar to each other. The similar item knowledge graph records multiple groups of similar items, and each group of similar items includes at least two items. Therefore, the similar items determined in step S12 refer to a group of similar items, rather than a single item.

[0072] In step S13, similar items are marked.

[0073] For example, after identifying similar items, a label can be automatically printed on them. This label can be used throughout the entire logistics process within the central warehouse: receiving, shelving, storage, and outbound operations, prompting staff to handle the item differently. For instance, when outbound, staff need to use a PDA (Personal Digital Assistant) to scan the item's barcode to double-check its accuracy. Unlabeled, dissimilar items can be shipped directly without needing to scan the barcode again. Thus, staff only need to double-check labeled items, improving the accuracy of handling similar items and the efficiency of handling dissimilar items.

[0074] By adopting the above technical solution, the knowledge graph of similar items is updated at least according to the list of frequently misplaced items, enriching the similar item groups stored in the knowledge graph. This improves the accuracy of similar item identification when automatically recognizing similar items from the list of items to be identified using the similar item knowledge graph. Furthermore, after identifying similar items, they can be automatically marked, prompting staff to scan their barcodes for verification, thereby improving the accuracy of operations involving similar items and the efficiency of operations involving dissimilar items.

[0075] To facilitate a better understanding of the similar item identification method provided in this disclosure by those skilled in the art, the specific implementation of the similar item identification method provided in this disclosure is described below with a complete embodiment.

[0076] In one possible manner, the specific implementation of step S12 above, which identifies similar items from the items to be identified based on the attribute information of the items to be identified and the knowledge graph of similar items, is as follows:

[0077] For any item among the items to be identified, determine whether the item is located in the similar item knowledge graph based on the item's attribute information. If it is, determine the similar item group to which the item belongs. Also, determine whether there are other items in the similar item group among the items to be identified. If there are, identify the item and the other items among the items to be identified as a group of similar items.

[0078] As mentioned above, the similar item knowledge graph records multiple groups of similar items, each group containing at least two items. Therefore, to identify similar items from the item to be identified, for each item in the item to be identified, it is first determined whether the item is located within the similar item knowledge graph. If it is, it indicates that the item is included in at least one similar item group within the similar item knowledge graph. At this point, the similar item group to which the item belongs can be further determined within the similar item knowledge graph. All other items within the determined similar item group are similar to the item in question. Then, it is determined whether other items in the similar item group exist within the item to be identified. If they do, the other items in the item to be identified, along with the item itself, are identified as a similar item group.

[0079] For example, suppose the items to be identified include garlic sprouts, spinach, ginger, lime-flavored C-brand cookies, and strawberry-flavored C-brand cookies. The similarity item knowledge graph records similar item groups for lime-flavored C-brand cookies, strawberry-flavored C-brand cookies, and chocolate-flavored C-brand cookies, as well as a similar item group for garlic sprouts and cowpeas. For instance, regarding the garlic sprouts in the items to be identified, based on their attribute information, it is determined that the garlic sprouts are located in the similarity item knowledge graph, and the similar item group to which the garlic sprouts belong is the similar item group for garlic sprouts and cowpeas. Since there are no other items (cowpeas) in this similar item group in the items to be identified, the garlic sprouts are not similar items in the items to be identified. For example, regarding the lime-flavored C-brand biscuits among the items to be identified, based on their attribute information, it is determined that the lime-flavored C-brand biscuits are located within the similar item knowledge graph, and the similar item group to which the lime-flavored C-brand biscuits belong is the group of similar items consisting of lime-flavored C-brand biscuits, strawberry-flavored C-brand biscuits, and chocolate-flavored C-brand biscuits. Since other items in this similar item group (i.e., strawberry-flavored C-brand biscuits) exist among the items to be identified, the lime-flavored C-brand biscuits and strawberry-flavored C-brand biscuits among the items to be identified can be identified as a group of similar items.

[0080] Since an item knowledge graph is trained by continuously absorbing external item information data based on technologies such as AI and machine learning, a similar item knowledge graph is also obtained by utilizing rich item information based on AI and machine learning technologies. Therefore, identifying similar items based on a similar item knowledge graph improves the ability and efficiency of identifying similar items.

[0081] In the field of e-commerce applications, considering that similar items are easily confused, merchants or sorting staff may send other items similar to the items originally purchased by users to users via express delivery. Therefore, in addition to using similar item knowledge graphs to identify similar items, after-sales data of users after purchasing items online can also be used to identify similar items.

[0082] Figure 2 This is a flowchart illustrating another similar item identification method according to an exemplary embodiment. In this embodiment, the attribute information of the item to be identified includes the item's identifier. For example... Figure 2 As shown, the method may include the following steps.

[0083] In step S21, a list of items prone to being sent by mistake is obtained.

[0084] In step S22, based on the identifier of the item to be identified and the identifiers of the items included in the list of items prone to misdelivery, it is determined whether there is a group of items prone to misdelivery among the items to be identified.

[0085] It's worth noting that when users are dissatisfied with the items they receive during online shopping, they typically file online complaints and contact the seller to request a return or exchange. When applying for a return or exchange, users usually need to specify the reason. If the item received is different from the original purchase due to the seller sending the wrong item, the user will state "wrong item sent" as the reason for the return or exchange. Therefore, based on after-sales data, the original purchased item and the actual item sent can be identified as a group of items prone to error-shipping when the reason for return or exchange is "wrong item sent."

[0086] For example, a list of items prone to being mistakenly sent can be pre-built based on after-sales data. This list includes multiple sets of identifications of the original purchased items and the actual items sent, where the return or exchange was due to the wrong item being sent.

[0087] It is worth noting that, referring to the above method of identifying similar items based on similar item indicator maps, we can determine whether there is a group of items prone to being mistakenly sent among the items to be identified, based on the identifier of the item to be identified and the identifier of the items included in the list of items prone to being mistakenly sent. This will not be elaborated on here.

[0088] In step S23, if there is a group of items that are prone to being mistakenly sent among the items to be identified, then similar items are identified from the items to be identified based on the group of items that are prone to being mistakenly sent.

[0089] In step S24 (S13), similar items are marked.

[0090] In one possible approach, the group of error-prone items among the items to be identified is directly identified as similar items.

[0091] However, considering that merchants or sorting personnel might mistakenly send dissimilar items, such as cookies and yogurt, directly classifying a group of items prone to misdelivery as similar items could lead to the identification of incorrect similar items. Therefore, in another possible approach, the similarity of a group of items prone to misdelivery can be determined based on the number of times multiple items within that group are mistakenly sent. A low number of misdeliveries indicates that the items within the group are dissimilar, while a high number of misdeliveries indicates that the items within the group are likely similar. Thus, in this approach, the similarity of a group of items prone to misdelivery can be determined based on its complaint rate. For example, if a group of items prone to misdelivery exists among the items to be identified, the complaint rate of each group is determined, and groups with a complaint rate greater than or equal to a preset threshold are classified as a group of similar items.

[0092] By adopting the above technical solution, after identifying the group of items prone to misdelivery among the items to be identified, the group of items prone to misdelivery with a complaint rate greater than or equal to a preset threshold is identified as a group of similar items, thereby improving the accuracy of similar item identification.

[0093] In one embodiment, similar items can be identified manually. The attribute information includes the item's identifier, such as... Figure 3 As shown, the similar item identification method may include the following steps.

[0094] In step S31, the attribute information of the item to be identified is obtained.

[0095] In step S32, a prompt message is sent to the target worker's terminal to prompt the target worker to identify whether there are similar items among the items to be identified.

[0096] It's worth noting that the work of staff in different work areas within the central warehouse differs. For example, in the receiving area, staff receive items stored in the central warehouse. In the picking area, staff sort items purchased by users from the central warehouse according to their orders, and so on. Therefore, the target staff in step S32 will also differ depending on whether the item to be identified corresponds to an item in a different work area of ​​the central warehouse. For instance, assuming the item to be identified is an item to be received in the central warehouse, the target staff is the central warehouse receiving staff. Assuming the item to be identified corresponds to an item in a user order, the target staff is the picking staff.

[0097] In step S33, the system receives the identifier of similar items sent by the target worker's terminal and identifies similar items among the items to be identified based on the identifier.

[0098] In step S34, similar items are marked.

[0099] For example, after receiving the prompt message on their terminal, the target worker uses their PDA to scan the item's barcode to obtain item information, and then identifies similar items among the items to be identified based on the scanned item information. As another example, after receiving the prompt message on their terminal, the target worker identifies similar items among the items to be identified based on the item's appearance, packaging, product name, etc. After identifying similar items in either of the above methods, the target worker can send the identifier of the identified similar item to the operating system executing the similar item identification method, so that the operating system, upon receiving the similar item identifier sent from the target worker's terminal, can identify the similar item among the items to be identified.

[0100] It is worth noting that the above descriptions separately cover identifying similar items using knowledge graphs, error-prone item groups, and manual methods. However, in practical applications, these three methods can be freely combined to identify similar items. For example, any two of the above methods can be used sequentially to identify similar items. For instance, the knowledge graph method can be used first, followed by error-prone item groups or manual methods. Alternatively, error-prone item groups can be used first, followed by the knowledge graph method or manual methods. Another example is that manual methods can be used first, followed by the knowledge graph method or error-prone item groups. Furthermore, all three methods can be used sequentially. The order of these three methods is not limited.

[0101] Figure 4 This is a flowchart illustrating another method for identifying similar items according to an exemplary embodiment. Figure 4 As shown, the method may include the following steps.

[0102] In step S41 (S11), the attribute information of the item to be identified and the knowledge graph of similar items are obtained.

[0103] In step S42, based on the attribute information of the item to be identified and the knowledge graph of similar items, it is determined whether there are similar items among the items to be identified.

[0104] The method described above for identifying similar items based on a knowledge graph of similar items can be used to determine whether similar items exist among the items to be identified; this will not be repeated here. If it is determined that similar items exist among the items to be identified, proceed to step S43; otherwise, proceed to step S44.

[0105] In step S43 (S13), similar items are marked.

[0106] In step S44, it is determined whether there is a group of items prone to being sent incorrectly among the items to be identified. If there is a group of items prone to being sent incorrectly, steps S45 and S43 are executed sequentially; otherwise, steps S46, S47, and S43 are executed sequentially.

[0107] In step S45, each group of error-prone items is identified as a group of similar items.

[0108] In step S46, a prompt message is sent to the target worker's terminal. This prompt message is used to guide the target worker to identify whether there are similar items among the items to be identified.

[0109] In step S47, the system receives the identifier of a similar item sent by the target worker's terminal, and identifies the similar item among the items to be identified based on the identifier.

[0110] The specific implementation methods for each step have been described in detail above and will not be repeated here.

[0111] By adopting the above technical solution, similar items are identified by using a knowledge graph of similar items, a group of items prone to errors, and manual methods in sequence, which improves the comprehensiveness of identifying similar items and avoids missing similar items.

[0112] Furthermore, similar items can be identified from the items to be identified using a similar item knowledge graph, error-prone item groups, and manual methods, respectively. Then, the intersection of the similar items identified by these three methods is calculated to obtain the final list of similar items. This further improves the accuracy of similar item identification.

[0113] In one embodiment, step S13, marking similar items, includes recording attribute information of similar items among the items to be identified in a list of similar items. The similar item identification method may further include obtaining the identifier and date of the central warehouse storing the items to be identified, and storing the list of similar items, the central warehouse identifier, and the date in association.

[0114] For example, after storing the list of similar items, the central warehouse identifier, and the date together, the resulting file can be named: "T-day X-Central Warehouse Similar Item List". Here, T represents the date, and X is the central warehouse identifier.

[0115] By adopting the above technical solution, the list of similar items, the central warehouse identifier, and the date are stored together, which makes it easier for staff to process similar items in the central warehouse on the date specified in the list of similar items, thereby improving the accuracy of similar item operations.

[0116] In addition, the associated stored files can be uploaded to the server, which makes it easier for downstream staff to obtain the associated stored files in a timely manner, avoids information delays, and improves the speed and accuracy of information transmission.

[0117] In another embodiment, the similar item identification method may further include updating the similar item knowledge graph using the attribute information of the identified similar items to obtain an updated similar item knowledge graph. In this embodiment, after identifying similar items, the similar item knowledge graph is updated using the identified similar items, thereby enriching the similar item groups stored in the similar item knowledge graph. This improves the comprehensiveness and accuracy of similar item identification based on the similar item knowledge graph.

[0118] Based on the same inventive concept, this disclosure also provides a similar item identification device. Figure 5 This is a block diagram illustrating a similarity item identification device according to an exemplary embodiment. Figure 5 As shown, the similar item identification device 500 may include:

[0119] The first acquisition module 501 is used to acquire attribute information of the item to be identified and a knowledge graph of similar items. The knowledge graph of similar items is at least updated based on a list of items prone to being sent incorrectly. The list of items prone to being sent incorrectly includes multiple sets of identifiers of the original purchased items and the actual items sent, for which the return or exchange was due to incorrect delivery.

[0120] The first identification module 502 is used to identify similar items from the items to be identified based on the attribute information of the items to be identified and the similar items knowledge graph; and

[0121] The marking module 503 is used to mark the similar items.

[0122] Optionally, the attribute information of the item to be identified includes the identifier of the item to be identified; the device further includes:

[0123] The second acquisition module is used to acquire the list of items prone to error in delivery;

[0124] The determination module is used to determine whether there is a group of items prone to being sent out among the items to be identified, based on the identifier of the item to be identified and the identifiers of the items included in the list of items prone to being sent out.

[0125] The second identification module is used to identify the similar items from the items to be identified if the group of items prone to misdelivery exists among the items to be identified.

[0126] Optionally, the second identification module includes:

[0127] The first determining submodule is used to determine the complaint rate of each of the error-prone item groups if the error-prone item group exists among the items to be identified.

[0128] The second determining submodule is used to determine each group of error-prone items with a complaint rate greater than or equal to a preset threshold as a group of similar items.

[0129] Optionally, the attribute information includes the item's identifier; the device further includes:

[0130] The sending module is used to send a prompt message to the terminal of the target staff member to prompt the target staff member to identify whether there are similar items among the items to be identified;

[0131] The receiving module is used to receive the identifier of similar items sent by the terminal of the target worker, and to identify similar items among the items to be identified based on the identifier.

[0132] Optionally, the device further includes:

[0133] The update module is used to update the similar item knowledge graph using the attribute information of the identified similar items, so as to obtain the updated similar item knowledge graph.

[0134] Optionally, the marking module 503 is used to: record attribute information of similar items among the items to be identified in a list of similar items; the device further includes:

[0135] The third acquisition module is used to acquire the central warehouse identifier and date of the item to be identified;

[0136] The storage module is used to associate and store the list of similar items, the central warehouse identifier, and the date.

[0137] Optionally, the identification module 502 is configured to: for any item among the items to be identified, determine whether the item is located in the similar item knowledge graph based on the attribute information of the item; if it is located, determine the similar item group to which the item belongs; and determine whether there are other items in the similar item group among the items to be identified; if there are, determine the item and the other items among the items to be identified as a group of similar items.

[0138] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0139] Figure 6 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Figure 6 As shown, the electronic device 700 may include a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0140] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in the aforementioned similar item identification method. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 702 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. Multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals. I / O interface 704 provides an interface between processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0141] In an exemplary embodiment, the electronic 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 aforementioned similar item identification method.

[0142] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the similar item identification method described above. For example, the computer-readable storage medium may be the memory 702 including the program instructions described above, which may be executed by the processor 701 of the electronic device 700 to complete the similar item identification method described above.

[0143] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a programmable device, the computer program having a code portion for performing the above-described similar item identification method when executed by the programmable device.

[0144] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0145] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0146] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method of identifying similar items, characterized by, The method comprises: obtaining attribute information of a to-be-identified article and a similar article knowledge graph, wherein the similar article knowledge graph is at least updated according to a mistaken-delivery article list, and the mistaken-delivery article list comprises a plurality of groups of mistaken-delivery articles and actual delivery articles whose identification is mistaken; identifying a similar article from the to-be-identified article according to the attribute information of the to-be-identified article and the similar article knowledge graph; and labeling the similar article. The attribute information of the to-be-identified article comprises an identification of the to-be-identified article, and the method further comprises: obtaining the mistaken-delivery article list; determining whether there is a mistaken-delivery article group in the to-be-identified article according to the identification of the to-be-identified article and the identification of the articles included in the mistaken-delivery article list; if the mistaken-delivery article group exists in the to-be-identified article, identifying the similar article from the to-be-identified article according to the mistaken-delivery article group.

2. The method of claim 1, wherein, If the mistaken-delivery article group exists in the to-be-identified article, the method of identifying the similar article from the to-be-identified article according to the mistaken-delivery article group comprises: if the mistaken-delivery article group exists in the to-be-identified article, determining a complaint rate of each mistaken-delivery article group; determining a mistaken-delivery article group with a complaint rate greater than or equal to a preset threshold as a group of similar articles.

3. The method according to claim 1 or 2, characterized in that, The attribute information comprises an identification of an article, and the method further comprises: sending prompt information to a terminal of a target worker to prompt the target worker to identify whether there is a similar article in the to-be-identified article; receiving an identification of a similar article sent by the terminal of the target worker, and identifying a similar article in the to-be-identified article according to the identification.

4. The method of claim 3, wherein, The method further comprises: updating the similar article knowledge graph by using the attribute information of the identified similar article to obtain an updated similar article knowledge graph.

5. The method of claim 1 or 2, wherein, The method of labeling the similar article comprises: recording attribute information of a similar article in the to-be-identified article in a similar article list; The method further comprises: obtaining a central warehouse identification and a date of storing the to-be-identified article; storing the similar article list, the central warehouse identification, and the date in association.

6. The method of claim 1 or 2, wherein, The similar article knowledge graph comprises a plurality of groups of similar articles, and the method of identifying a similar article from the to-be-identified article according to the attribute information of the to-be-identified article and the similar article knowledge graph comprises: for any article in the to-be-identified article, determining whether the article is located in the similar article knowledge graph according to the attribute information of the article, if so, determining a similar article group where the article is located, and determining whether there is another article in the similar article group in the to-be-identified article, if so, determining the article and the another article in the to-be-identified article as a group of similar articles.

7. An identical article identifying device characterized by comprising: The method comprises: The first obtaining module is configured to obtain attribute information of a to-be-identified item and a similar item knowledge graph, wherein the similar item knowledge graph is obtained at least according to an error-prone item list, the error-prone item list includes a plurality of groups of identification of original purchase items and actual delivery items that are delivered in error due to reasons for return and exchange, and the attribute information of the to-be-identified item includes identification of the to-be-identified item; and the second obtaining module is configured to obtain the error-prone item list. The first identifying module is configured to identify a similar item from the to-be-identified item according to the attribute information of the to-be-identified item and the similar item knowledge graph; the determining module is configured to determine whether there is an error-prone item group in the to-be-identified item according to the identification of the to-be-identified item and the identification of the items included in the error-prone item list; the second identifying module is configured to identify the similar item from the to-be-identified item according to the error-prone item group if the error-prone item group exists in the to-be-identified item; and The marking module is configured to mark the similar item.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of any one of claims 1-6.

9. An electronic device, comprising: The program is executed by the processor to implement the steps of the method of any one of claims 1-6. The memory has a computer program stored thereon; The processor is configured to execute the computer program in the memory to implement the steps of the method of any one of claims 1-6.

Images