Express parcel-free matching method and device and electronic equipment

Abstract

The invention provides an express parcel-free matching method and apparatus, and an electronic device. The method comprises the steps of obtaining feature information of a parcel-free to be processed; performing multi-dimensional matching on the feature information and feature matching factors in a pre-constructed feature matching factor library, and when the matching succeeds, obtaining a no-contact document number corresponding to the matching features in the feature matching factor library; whether the to-be-processed non-attached piece corresponds to the non-attached piece number or not is confirmed, if yes, the to-be-processed non-attached piece and the non-attached piece number are pushed to a network point center, and after the network point center confirms the to-be-processed non-attached piece and the corresponding piece number, an express sheet is printed for the non-attached piece and continues to be transported; according to the method, the matching efficiency and the retrieval rate of the non-contact parts can be effectively improved, and the customer experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a method, device and electronic device for matching undelivered express items. Background Art

[0002] In the express delivery industry, during the transportation or transit sorting process, express parcels may have missing delivery information due to the falling off of the delivery bill, contamination or fading of the delivery bill, incomplete delivery bill number, damaged outer packaging, and partial falling off of the inner parts. The delivery bill number and the parcel cannot be matched one-to-one, resulting in the inability to continue transportation or delivery, resulting in undelivered parcels. When undelivered parcels occur, the system generally enters the parcel-related information, including but not limited to the residual delivery bill information, pictures of the outer packaging of the parcel, pictures of the contents of the parcel, item weight, item description, and other related information into the system.

[0003] When customers report problems with packages, the courier company’s customer service will search in the undelivered system based on the courier number and picture information provided by the customer. However, the above method is inefficient in finding packages, as it takes more than 10 minutes to search for one number. The recovery rate is low, with only about 20% of packages being recoverable. The customer experience is poor, and customers are required to actively report problems. Summary of the invention

[0004] The present invention provides a method, device and electronic device for matching undelivered express items, so as to at least solve the above technical problems existing in the prior art.

[0005] According to a first aspect of the present disclosure, a method for matching undelivered express items is provided, the method comprising:

[0006] Obtain feature information of unprocessed items;

[0007] Perform multi-dimensional matching of the feature information with the feature matching factors in a pre-built feature matching factor library, and when the match is successful, obtain the undelivered item number corresponding to the matching feature in the feature matching factor library;

[0008] Confirm whether the undelivered item to be processed corresponds to the undelivered item order number. If so, push the undelivered item to be processed and the undelivered item order number to the network center. After the network center confirms the undelivered item to be processed and the corresponding order number, it prints a label for the undelivered item and continues transportation.

[0009] In one possible implementation, constructing a feature matching factor library includes:

[0010] When obtaining the unattached item, obtaining characteristic information of the unattached item;

[0011] Determine whether the characteristic information has a corresponding undelivered item number, and if so, associate the characteristic information with the undelivered item number;

[0012] The feature information and the corresponding unattached item number are stored in a feature matching factor library.

[0013] In one possible implementation, the multi-dimensional matching of the feature information with the feature matching factors in a pre-built feature matching factor library includes:

[0014] The feature information of the unprocessed item is cross-matched with the feature matching factors in the feature matching factor library for multiple rounds, so as to compare and verify the feature information with the feature matching factors.

[0015] In one possible implementation, the characteristic information includes at least one of the following: appearance information, item description information, brand information, item name, item picture, packaging color, weight, primary category, current node, and shipping company;

[0016] The feature matching factor includes at least one of: reporting time, reporting organization, weight, brand, item category, suspected organization, routing node, description, picture, packaging color and feature keyword.

[0017] In one possible implementation, the multi-dimensional matching of the feature information with the feature matching factors in a pre-built feature matching factor library includes:

[0018] A suspected stagnant package collection pool is established for the stagnant nodes of the waybill routing transit operation; the stagnant package collection pool is used to match the original order number for the undelivered items;

[0019] Matching the drop-off points, arrival points, and pick-up points of the undelivered parcels to be processed with the reporting points and the nodes in the suspected stagnant parcel collection pool to obtain a first matching result set;

[0020] Matching the weight of the unattached piece to be processed with the weight of the objects in the first matching result set to obtain a second matching result set;

[0021] Matching the item description features of the unprocessed items with the item description features in the second matching result set to obtain a third matching result set;

[0022] Matching the types of the unprocessed items with the types of items in the third matching result set to obtain a fourth matching result set;

[0023] Segmenting the names of the unmarked items to be processed, and then matching the segmented words with the segmented words of the item names in the fourth matching result set to obtain a fifth matching result set;

[0024] Matching the brand of the unprocessed item with the brand of the item in the fifth matching result set to obtain a sixth matching result set;

[0025] Matching the shape and color of the unattached item to be processed with the shape and color of the items in the sixth matching result set to obtain a seventh matching result set;

[0026] Matching the mutually exclusive words of the unprocessed items with the mutually exclusive words in the seventh matching result set to obtain an eighth matching result set;

[0027] Matching the unprocessed image with the object images in the eighth matching result set to obtain a ninth matching result set;

[0028] Calculate the matching scores corresponding to the unmatched items in the ninth matching result set based on the preset weights of the matching factors, and obtain the unmatched item result set whose matching scores are higher than a preset threshold;

[0029] Based on the description information of the unmarked items to be processed, the unmarked item result set is identified using a large model to obtain a final matching result set.

[0030] In one possible implementation, the establishment of a suspected stagnant package collection pool for the stagnant nodes of the waybill routing transit operation includes:

[0031] In the express delivery process, if the previous routing node has completed the sending scan, and the next routing node has not recorded the corresponding arrival scan information within the first preset time period, it indicates that there is a delay or disconnection in the logistics chain;

[0032] In the express delivery circulation link, if the next routing node receives it now and does not scan it within the second preset time period, it indicates that the express delivery is forced to stagnate in the transfer center.

[0033] In one possible implementation, the time during which the express delivery is forced to stop is obtained by calculating the operation time required for each order number.

[0034] In one possible implementation manner, obtaining characteristic information of the unprocessed items includes:

[0035] Receiving characteristic information of the undelivered items to be processed inputted by the network center;

[0036] The unprocessed items are photographed, and feature information is acquired based on the pictures of the unprocessed items.

[0037] According to a second aspect of the present disclosure, a matching device for express delivery without a delivery item is provided, the device comprising:

[0038] An acquisition module is used to acquire characteristic information of unprocessed items;

[0039] A matching module, used to perform multi-dimensional matching of the feature information with feature matching factors in a pre-built feature matching factor library, and when the matching is successful, obtain the undelivered item number corresponding to the matching feature in the feature matching factor library;

[0040] The push module is used to confirm whether the undelivered item to be processed corresponds to the undelivered item order number. If so, the undelivered item to be processed and the undelivered item order number are pushed to the network center. After the network center confirms the undelivered item to be processed and the corresponding order number, it prints a label for the undelivered item and continues transportation.

[0041] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0042] at least one processor; and

[0043] a memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present disclosure.

[0045] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the present disclosure.

[0046] The method, device and electronic device for matching undelivered express items disclosed herein can effectively improve the matching efficiency and retrieval rate of undelivered items and enhance customer experience.

[0047] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0049] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0050] Figure 1 The schematic diagram shows the implementation process of the matching method of express delivery without delivery in the embodiment of the present disclosure. Figure 1 ;

[0051] Figure 2The schematic diagram shows the implementation process of the matching method of express delivery without delivery in the embodiment of the present disclosure. Figure 2 ;

[0052] Figure 3 The schematic diagram shows the implementation process of the matching method of express delivery without delivery in the embodiment of the present disclosure. Figure 3 ;

[0053] Figure 4 The schematic diagram shows the implementation process of the matching method of express delivery without delivery in the embodiment of the present disclosure. Figure 4 ;

[0054] Figure 5 The schematic diagram shows the implementation process of the matching method of express delivery without delivery in the embodiment of the present disclosure. Figure 5 ;

[0055] Figure 6 A schematic diagram of the structure of a matching device for express delivery without a delivery item according to an embodiment of the present disclosure is shown;

[0056] Figure 7 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0057] In order to make the purpose, features, and advantages of the present disclosure more obvious and easy to understand, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0058] At present, the main implementation methods of the express delivery company's no-delivery system include:

[0059] 1. Reporting of unclaimed items:

[0060] When an express delivery company outlet or center encounters an express delivery waybill that has fallen off or the waybill information is incomplete, the remaining waybill information, pictures of the package outer packaging, pictures of the package contents, item weight, and item description will be entered into the system.

[0061] 2. No claim for the item:

[0062] When customers report express delivery issues, the company's customer service staff will search the undelivered system based on the express delivery number reported by the customer, and based on the logistics track, item information, weight and other information.

[0063] However, the above method has several obvious disadvantages, mainly including:

[0064] (1) The description of item characteristics is insufficient when reporting, key information is insufficient, and there is a lot of interference from human factors; (2) The search is difficult and the search results are not accurate enough. It is necessary to compare each item based on the information provided by the customer. Sometimes, the customer is even unwilling to provide package information; (3) The recovery rate is low and completely relies on manual matching; (4) Due to untimely claiming, some packages have already been compensated and the value of the package has been lost.

[0065] A method and device for matching undelivered express items provided by the present application are described below in conjunction with the accompanying drawings.

[0066] like Figure 1 As shown, the present application provides a method for matching undelivered express items, the method comprising:

[0067] S101, obtaining characteristic information of unattached items to be processed;

[0068] In some embodiments, the step of obtaining characteristic information of the unprocessed items includes:

[0069] Receiving characteristic information of the undelivered items to be processed inputted by the network center;

[0070] The unprocessed items are photographed, and feature information is acquired based on the pictures of the unprocessed items.

[0071] It is understandable that the undeliverable items to be processed can be undeliverable items found by the outlet center, or undeliverable items that customers have not received and are looking for. The feature information of the undeliverable items can be text information input by the outlet, or feature information of the undeliverable items obtained by photographing the undeliverable items.

[0072] The characteristic information includes at least one of the following: appearance information, item description information, brand information, item name, item picture, packaging color, weight, first-level category, current node and shipping company.

[0073] This application will regularly query the image information of historically reported undelivered items, perform OCR analysis to extract text information, and extract large-model product names, colors, and brand information through text information and reported descriptions to form a rich express delivery feature data set.

[0074] When an undelivered item is reported, the trained large model is called to perform semantic understanding and recognition analysis on the undelivered item images and description data, extract key attributes of the package, including item name, brand, appearance, features and other information, and store this key information in the search engine database to provide a basis for subsequent queries and matching.

[0075] S102, performing multi-dimensional matching of the feature information with feature matching factors in a pre-built feature matching factor library, and obtaining the undelivered item number corresponding to the matching feature in the feature matching factor library when the matching is successful;

[0076] It is understandable that the feature matching factor library in this application is pre-built. The specific construction method is to extract item feature information based on the reported basic information, pictures, descriptions of unattached items, brands, etc., using the feature information recognition capabilities of the large model; for example, identifying item categories, name information, colors, brands, etc. through pictures, extracting keywords through descriptions and graphics, and storing them in the feature matching factor library. Then, multiple similarity searches and matches can be performed on the unattached items to be processed through the item names or key information.

[0077] Specifically, the non-target matching performs multiple rounds of cross-matching in the non-target feature library based on the extracted high-recognition feature information, and conducts in-depth comparison and verification of the high-recognition feature set extracted from the target object with the extensive, unrestricted data set in the feature library.

[0078] S103, confirm whether the undelivered item to be processed corresponds to the undelivered item order number. If so, push the undelivered item to be processed and the undelivered item order number to the network center. After the network center confirms the undelivered item to be processed and the corresponding order number, it prints a label for the undelivered item and continues transportation.

[0079] Specifically, Figure 2 As shown, this application obtains the set of undeliverable items corresponding to the order number through matching and filtering in each dimension. If the undeliverable item has been matched multiple times, it will not continue to push the outlets. This is because there may be deviations in the result set after multiple matching. Here, a maximum of 10 order numbers are pushed for an undeliverable item, otherwise it will be pushed to the corresponding undeliverable item reporting center or outlet. The center or outlet conducts a secondary review and confirmation based on the push list. If an undeliverable item has multiple corresponding waybill numbers, the most matching waybill is screened out and manually pushed to the corresponding shipping company. The shipping company receives the pushed undeliverable item, and confirms the information with the shipping customer in combination with the parcel lost after the company sends it out. If it is correct, it will claim it. When the shipping company takes the initiative to claim it, it will find the most similar and accurate parcel by searching and filtering in multiple dimensions in the undeliverable item list, such as matching by commodity feature words and matching by image search. After the reporting center or outlet of the undeliverable item receives the confirmation of the undeliverable item claimed by the shipping company, it will reprint the waybill and continue the subsequent transportation and delivery.

[0080] The present application provides a method for matching undelivered express parcels, which matches a known delayed parcel set with an undelivered parcel set, extracts key information from known parcel information using a large model, calculates and filters multi-dimensional features and keyword similarity, and simultaneously considers content exclusivity, parcel trajectory outlets or centers, parcel operation time period, weight, etc., to generate the most similar parcel matching list, assembles prompt words in the matching list and gives them to the large model to calculate the most accurate result, and automatically recommends them to relevant outlets or centers for claiming.

[0081] It can effectively improve the matching efficiency and retrieval rate of unavailable items and enhance customer experience.

[0082] In some embodiments, constructing a feature matching factor library includes:

[0083] When obtaining the unattached item, obtaining characteristic information of the unattached item;

[0084] Determine whether the characteristic information has a corresponding undelivered item number, and if so, associate the characteristic information with the undelivered item number;

[0085] The feature information and the corresponding unattached item number are stored in a feature matching factor library.

[0086] Specifically, Figure 3 As shown, this application requires reporting of each unmarked item, and based on the reported basic information, pictures, unmarked item descriptions, brands and other information, the feature information recognition capability of the large model is used to extract item feature information; such as identifying item category, name information, color, brand and other information through pictures, extracting keywords through descriptions and graphics, and storing them in a database, which is a feature matching factor library.

[0087] In some embodiments, the multi-dimensional matching of the feature information with the feature matching factors in a pre-built feature matching factor library includes:

[0088] The feature information of the unprocessed item is cross-matched with the feature matching factors in the feature matching factor library for multiple rounds, so as to compare and verify the feature information with the feature matching factors.

[0089] like Figure 4 As shown, the characteristic information includes at least one of the following: appearance information, item description information, brand information, item name, item picture, packaging color, weight, first-level category, current node and shipping company;

[0090] The feature matching factor includes at least one of: reporting time, reporting organization, weight, brand, item category, suspected organization, routing node, description, picture, packaging color and feature keyword.

[0091] Specifically, in the present application, based on the extracted high-recognition feature information, multiple rounds of cross-matching are performed in the feature library without any specific restrictions, and the high-recognition feature set extracted from the target object is deeply compared and verified with the extensive and unrestricted data set in the feature library.

[0092] In some embodiments, the multi-dimensional matching of the feature information with the feature matching factors in a pre-built feature matching factor library includes:

[0093] A suspected stagnant package collection pool is established for the stagnant nodes of the waybill routing transit operation; the stagnant package collection pool is used to match the original order number for the undelivered items;

[0094] Matching the drop-off points, arrival points, and pick-up points of the undelivered parcels to be processed with the reporting points and the nodes in the suspected stagnant parcel collection pool to obtain a first matching result set;

[0095] Matching the weight of the unattached piece to be processed with the weight of the objects in the first matching result set to obtain a second matching result set;

[0096] Matching the item description features of the unprocessed items with the item description features in the second matching result set to obtain a third matching result set;

[0097] Matching the types of the unprocessed items with the types of items in the third matching result set to obtain a fourth matching result set;

[0098] Segmenting the names of the unmarked items to be processed, and then matching the segmented words with the segmented words of the item names in the fourth matching result set to obtain a fifth matching result set;

[0099] Matching the brand of the unprocessed item with the brand of the item in the fifth matching result set to obtain a sixth matching result set;

[0100] Matching the shape and color of the unattached item to be processed with the shape and color of the items in the sixth matching result set to obtain a seventh matching result set;

[0101] Matching the mutually exclusive words of the unprocessed items with the mutually exclusive words in the seventh matching result set to obtain an eighth matching result set;

[0102] Matching the unprocessed image with the object images in the eighth matching result set to obtain a ninth matching result set;

[0103] Calculate the matching scores corresponding to the unmatched items in the ninth matching result set based on the preset weights of the matching factors, and obtain the unmatched item result set whose matching scores are higher than a preset threshold;

[0104] Based on the description information of the unmarked items to be processed, the unmarked item result set is identified using a large model to obtain a final matching result set.

[0105] In some embodiments, the step of establishing a suspected stagnant package collection pool for a stagnant node in a waybill routing transit operation includes:

[0106] In the express delivery process, if the previous routing node has completed the sending scan, and the next routing node has not recorded the corresponding arrival scan information within the first preset time period, it indicates that there is a delay or disconnection in the logistics chain;

[0107] In the express delivery circulation link, if the next routing node receives it now and does not scan it within the second preset time period, it indicates that the express delivery is forced to stagnate in the transfer center.

[0108] Specifically, Figure 5 As shown, first of all, when establishing a suspected stagnant package collection pool, it should be noted that in the express delivery circulation link, the stagnant node phenomenon of the waybill routing transit operation can be divided into two categories: one is the "sent but not arrived" state, that is, the current processing node has completed the dispatch scan, but the next routing node has not been able to record the corresponding vehicle arrival scan information in the system, which usually indicates that there may be a delay or disconnection in a certain link in the logistics chain; the other is the "arrived but not sent" situation, which means that although the next routing node has shown that the goods have been received (confirmed by the vehicle arrival scan), the current processing node has not performed the dispatch scan operation.

[0109] Based on the above situation, by monitoring the operation track of the waybill of the entire network and calculating the next operation time of the order number in real time, the order number that has no subsequent operation record for more than 40 hours or even 72 hours is regarded as a high-risk item, because these order numbers are very likely to be forced to stay in the transfer center due to damage, loss or other abnormal conditions of the goods, and may become undeliverable items; therefore, a collection pool of stagnant packages is established as the source of original order numbers for matching undeliverable items.

[0110] Based on the image information in the reported unclaimed items, OCR is performed to parse the text information, and the large model product name, color, and brand information are extracted through the text information + reported description and stored in the unclaimed item feature library. The reported image is stored in the unclaimed image retrieval library (vector database), and the image name is uniquely named using the unclaimed item number (image similarity search uses the confirmed unclaimed item).

[0111] Specific matching calculation process:

[0112] (1) Order number routing node and / or time matching: When the transport link has arrived but not shipped, the pick-up and arrival points are matched with the reporting points for the undelivered items. When the link has shipped but not arrived, the loading and unloading points are matched with the reporting points. At the same time, the corresponding vehicle registration number and discovery place of the undelivered items reported within 3 days of the stagnation time are used to preliminarily filter out the result set related to the order number location and time, narrowing the scope to avoid interference in subsequent matching.

[0113] (2) Parcel weight matching: The weighed weight of the parcel is compared with the reported weight of the undelivered item. The weight may fluctuate up or down by 30% (there may be a certain deviation between the actual parcel weight and the undelivered item due to reasons such as loss of goods on the waybill, etc.).

[0114] (3) Product information feature extraction: Based on the product information obtained from the order number, call the big model to extract the product, brand, and color (the prompt word given to the big model here is very important. For example, if you are a keyword extraction tool, your task is to accurately extract the brand, item, and color from the item description. The item must be included in the description and must be returned, and related adjectives must be removed. Finally, it is output in Json format, and the key name must be brand, item, or color. No other content is allowed to be output).

[0115] (4) Extraction of synonyms and / or item categories: Based on the product information extraction results, request the AI ​​model to obtain the synonyms and categories of the item.

[0116] (5) Word segmentation query matching: Construct ES word segmentation query conditions, use the feature information and categories extracted by the large model as the hard filtering search conditions, and use the ik_smart word segmenter in ES to perform matching queries (preliminarily collect and maintain all item names in the ES vocabulary, and limit the word segmentation results to those already in the vocabulary to avoid too many word segmentations affecting the search results).

[0117] (6) Brand matching: Based on the maintained brand set, perform fuzzy query on the product information of the package and the product information reported by the undelivered item. If there is no brand, use the brand results extracted by the large model. If the maintained brand is included, obtain the brand of the undelivered item and the brand of the product to determine whether they are the same. If they are not the same, filter them out (brand filtering is very important. For example, laundry detergent can easily produce undelivered items, but there are many corresponding brands. Adding the brand will filter out a lot of irrelevant data).

[0118] (7) Color and size matching: Currently, this is only applicable to clothing categories. If both the color and size of the unavailable item and the product information exist, a comparison filter will be performed. If one of the two does not exist, no filtering will be performed to avoid filtering out possible unavailable items.

[0119] (8) Mutually exclusive word matching: ES may return similar words when segmenting words, which may lead to biased results. Therefore, a mutually exclusive word library is maintained for filtering. For example, if the item description word includes cat litter, then the product information must include cat litter, because cat litter may match cat food, resulting in query matching errors.

[0120] (9) Image similarity matching: When there is a merchant display picture in the item, search it in the image retrieval library. If found, match the result set with the result set filtered above (items with obvious appearance features and high recognition have better results when searching images).

[0121] Then the matching score threshold is set. Specifically, the score of es is controlled by adjusting the weight of each search condition during the query. In word segmentation matching, the "item" query condition is the most important, so the item weight is set higher, and the score threshold is set to perform score filtering. Currently, 100 points are set (the result obtained through continuous verification), and results below 100 points are discarded to obtain the result set.

[0122] Finally, the big model makes a judgment: the result set (list of undelivered items) and the key information of the order number items are given to the big model, and the final most reasonable and similar undelivered result set is calculated by giving the prompt words.

[0123] In some embodiments, the time that the express delivery is forced to stop is obtained by calculating the operation time for each order number.

[0124] This application adds the calculation of the suspected stagnant package pool, integrates the data of each operation link of the whole network package, calculates the operation time of each order number according to the route transportation time configuration, and determines the stagnation time of the package, providing a basic order number pool for active matching of undelivered items and narrowing the matching scope.

[0125] like Figure 6 As shown, an embodiment of the present application provides a matching device for express delivery without a delivery item, the device comprising:

[0126] An acquisition module 601 is used to acquire characteristic information of unattached items to be processed;

[0127] A matching module 602 is used to perform multi-dimensional matching of the feature information with feature matching factors in a pre-built feature matching factor library, and when the matching is successful, obtain the undelivered item number corresponding to the matching feature in the feature matching factor library;

[0128] The push module 603 is used to confirm whether the undelivered item to be processed corresponds to the undelivered item order number. If so, the undelivered item to be processed and the undelivered item order number are pushed to the network center. After the network center confirms the undelivered item to be processed and the corresponding order number, it prints a label for the undelivered item and continues transportation.

[0129] An embodiment of the present application provides an electronic device, including:

[0130] at least one processor; and

[0131] a memory communicatively connected to the at least one processor; wherein,

[0132] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

[0133] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0134] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0135] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0136] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0137] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the matching method for express delivery without a delivery item. For example, in some embodiments, the matching method for express delivery without a delivery item may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the matching method for express delivery without a delivery item described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the matching method for express delivery without a destination in any other appropriate manner (eg, by means of firmware).

[0138] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0139] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0140] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0141] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0142] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0143] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0144] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0145] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0146] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for matching undelivered express items, characterized in that: The method comprises: Obtain feature information of unprocessed items; Perform multi-dimensional matching of the feature information with the feature matching factors in a pre-built feature matching factor library, and when the match is successful, obtain the undelivered item number corresponding to the matching feature in the feature matching factor library; Confirm whether the undelivered item to be processed corresponds to the undelivered item order number. If so, push the undelivered item to be processed and the undelivered item order number to the network center. After the network center confirms the undelivered item to be processed and the corresponding order number, it prints a label for the undelivered item and continues transportation.

2. The method according to claim 1, characterized in that: Construct a feature matching factor library, including: When obtaining the unattached item, obtaining characteristic information of the unattached item; Determine whether the characteristic information has a corresponding undelivered item number, and if so, associate the characteristic information with the undelivered item number; The feature information and the corresponding unattached item number are stored in a feature matching factor library.

3. The method according to claim 1, characterized in that The multi-dimensional matching of the feature information with the feature matching factors in the pre-built feature matching factor library includes: The feature information of the unprocessed item is cross-matched with the feature matching factors in the feature matching factor library for multiple rounds, so as to compare and verify the feature information with the feature matching factors.

4. The method according to claim 1, characterized in that The characteristic information includes at least one of the following: appearance information, item description information, brand information, item name, item picture, packaging color, weight, first-level category, current node and shipping company; The feature matching factor includes at least one of: reporting time, reporting organization, weight, brand, item category, suspected organization, routing node, description, picture, packaging color and feature keyword.

5. The method according to claim 1, characterized in that The multi-dimensional matching of the feature information with the feature matching factors in the pre-built feature matching factor library includes: A suspected stagnant package collection pool is established for the stagnant nodes of the waybill routing transit operation; the stagnant package collection pool is used to match the original order number for the undelivered items; Matching the drop-off points, arrival points, and pick-up points of the undelivered parcels to be processed with the reporting points and the nodes in the suspected stagnant parcel collection pool to obtain a first matching result set; Matching the weight of the unattached piece to be processed with the weight of the objects in the first matching result set to obtain a second matching result set; Matching the item description features of the unprocessed items with the item description features in the second matching result set to obtain a third matching result set; Matching the types of the unprocessed items with the types of items in the third matching result set to obtain a fourth matching result set; Segmenting the names of the unmarked items to be processed, and then matching the segmented words with the segmented words of the item names in the fourth matching result set to obtain a fifth matching result set; Matching the brand of the unprocessed item with the brand of the item in the fifth matching result set to obtain a sixth matching result set; Matching the shape and color of the unattached item to be processed with the shape and color of the items in the sixth matching result set to obtain a seventh matching result set; Matching the mutually exclusive words of the unprocessed items with the mutually exclusive words in the seventh matching result set to obtain an eighth matching result set; Matching the unprocessed image with the object images in the eighth matching result set to obtain a ninth matching result set; Calculate the matching scores corresponding to the unmatched items in the ninth matching result set based on the preset weights of the matching factors, and obtain the unmatched item result set whose matching scores are higher than a preset threshold; Based on the description information of the unmarked items to be processed, the unmarked item result set is identified using a large model to obtain a final matching result set.

6. The method according to claim 5, characterized in that The establishment of a suspected stagnant package collection pool for the stagnant nodes of the waybill routing transit operation includes: In the express delivery process, if the previous routing node has completed the sending scan, and the next routing node has not recorded the corresponding arrival scan information within the first preset time period, it indicates that there is a delay or disconnection in the logistics chain; In the express delivery circulation link, if the next routing node receives it now and does not scan it within the second preset time period, it indicates that the express delivery is forced to stagnate in the transfer center.

7. The method according to claim 6, characterized in that The time that express delivery is forced to stop is obtained by calculating the operation time for each order number.

8. The method according to claim 1, characterized in that: The step of obtaining characteristic information of unprocessed items includes: Receiving characteristic information of the undelivered items to be processed inputted by the network center; The unprocessed items are photographed, and feature information is acquired based on the pictures of the unprocessed items.

9. A matching device for express delivery without a delivery item, characterized in that: The device comprises: An acquisition module is used to acquire characteristic information of unprocessed items; A matching module, used to perform multi-dimensional matching of the feature information with feature matching factors in a pre-built feature matching factor library, and when the matching is successful, obtain the undelivered item number corresponding to the matching feature in the feature matching factor library; The push module is used to confirm whether the undelivered item to be processed corresponds to the undelivered item order number. If so, the undelivered item to be processed and the undelivered item order number are pushed to the network center. After the network center confirms the undelivered item to be processed and the corresponding order number, it prints a label for the undelivered item and continues transportation.

10. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

Images