Method, device and electronic equipment for entering information of freight waybill

Abstract

The present invention relates to the field of computer technology, and provides a method, device and electronic device for entering information of a cargo waybill. The method for entering information of a cargo waybill comprises: obtaining inbound cargo station information, outbound cargo station information and outbound cargo information recorded in a target waybill; determining candidate inbound cargo information matching the inbound cargo station information, outbound cargo station information and outbound cargo information based on a pre-established knowledge graph; outputting the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; and entering the inbound cargo information in the target waybill according to a received selection operation for the entry option of the inbound cargo information. The method improves the efficiency of entering cargo waybill information.

Description

Technical Field

[0001] The present invention relates to the field of computer science and technology, and in particular to a method, device and electronic equipment for entering information of a freight waybill. Background Art

[0002] The cargo name information of air cargo is usually entered once at the outbound cargo terminal, and needs to be entered again at the inbound cargo terminal after the cargo arrives at the destination. Moreover, for the same cargo, the cargo name and code at the outbound terminal and the cargo name and code at the inbound terminal are completely different naming systems.

[0003] The shipping agent information of the goods is usually entered before the goods leave the port, but in most cases the consignee agent information after entering the port is not entered. The consignee agent information is entered after the goods arrive at the destination.

[0004] In view of the huge volume of air cargo and the wide variety of cargo, in the process of entering information into the cargo waybill, there are problems such as the large workload of re-entering the information after entering the port and the easy error of entry. Summary of the invention

[0005] The present invention provides a method, device and electronic device for inputting information of a cargo waybill, which are used to solve the problems of heavy workload and easy error in re-entering information after entering a port in the existing cargo waybill information input process.

[0006] The present invention provides a method for entering information of a cargo waybill, comprising: obtaining inbound cargo station information, outbound cargo station information and outbound cargo information recorded in a target waybill; determining candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information based on a pre-established knowledge graph, wherein the knowledge graph is established based on historical waybill data, the knowledge graph comprises nodes and lines between nodes, the nodes represent entities or attributes of entities, the lines represent relationships between nodes, the nodes comprise waybill nodes, and the attribute nodes of the waybill nodes comprise inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes and outbound cargo information nodes; outputting the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; and entering the inbound cargo information in the target waybill according to a received selection operation for the entry option for the inbound cargo information.

[0007] According to a method for entering information into a cargo waybill provided by the present invention, it is characterized in that the candidate inbound cargo information includes candidate inbound product names, the outbound cargo information includes outbound product names, the inbound cargo information includes inbound product names, the outbound cargo information nodes include outbound product name nodes, the inbound cargo information nodes include inbound product name nodes, the knowledge graph also includes standard product name nodes that are synonymous or have a superior-subordinate relationship with the outbound product name nodes; the candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information is determined based on a pre-established knowledge graph, including The method comprises: performing entity recognition on the outbound product name; retrieving candidate outbound product name nodes matching the recognized entities in the knowledge graph; scoring the candidate outbound product name nodes according to the similarity between a subgraph starting from the outbound product name node and the inbound cargo terminal node and the outbound cargo terminal information, the outbound cargo terminal information and the outbound product name in the knowledge graph; selecting a preset number of candidate outbound product name nodes according to the scores; obtaining the standard product name recorded in the standard product name node that has a synonymous or superior-subordinate relationship with the selected candidate outbound product name node as the candidate inbound product name.

[0008] According to a method for entering information into a cargo waybill provided by the present invention, it is characterized in that the entity recognition of the outbound product name includes: determining a word vector representation of the outbound product name; inputting the word vector representation of the outbound product name into a pre-trained named entity recognition model to obtain entities recognized in the outbound product name; wherein the named entity recognition model is trained by using historical data of outbound product names from different cargo terminals with annotations.

[0009] According to a method for entering information into a cargo waybill provided by the present invention, it is characterized in that the candidate inbound cargo information also includes a candidate inbound product name code, the outbound cargo information also includes an outbound product name code, the inbound cargo information also includes an inbound product name code, the outbound cargo information node also includes an outbound product name code node, the inbound cargo information node also includes an inbound product name code node, the attribute node of the waybill node also includes a consignor node and a consignee node, the knowledge graph also includes a product name code system node, a cargo station node and an agent node, the outbound product name code node and the inbound product name code have a belonging relationship with the product name code system node, the standard product name node has a belonging relationship with the product name code system node, the attribute node of the cargo station node includes a cargo station name node, the cargo station name node has an association relationship with the product name code system node, the attribute node of the agent node includes an agent code node, the inbound cargo station node and the outbound cargo station node are connected to the cargo station node through the cargo station name node, the agent node has a belonging relationship with the cargo station node, and the agent code node is connected to the consignee node through the consignor node. The node or consignee node is connected to the waybill node; after the standard product name recorded by the standard product name node that has a synonymous or superior-subordinate relationship with the selected candidate outbound product name node is obtained as the candidate inbound product name, the candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information is determined based on the pre-established knowledge graph, and further includes: querying the cargo station name node connected to the inbound cargo station node matching the inbound cargo station information; determining the candidate inbound cargo information matching the inbound cargo station information according to the product name code system node that has an associated relationship with the queried cargo station name node. Determine the product name code corresponding to the candidate inbound product name in the product name code system, wherein the product name code system node records the correspondence between the product name and the product name code; obtain the outbound agent information recorded in the target waybill; retrieve the agent code node in the knowledge graph starting from the queried cargo station name node, through the inbound cargo station node, the waybill node and the consignor node; and select a preset number of product name codes from the product name codes corresponding to the candidate inbound product name as the candidate inbound product name codes according to the matching degree between the outbound agent information and the retrieved agent code node.

[0010] According to a method for entering information into a cargo waybill provided by the present invention, the method further comprises: querying a subgraph in which an agent code node in the knowledge graph matches the outbound agent information recorded in the target waybill, and an inbound cargo station node matches the inbound cargo station information recorded in the target waybill; obtaining the inbound agent code node included in the queried subgraph; determining the number of times and time at which the obtained inbound agent code node appears in the knowledge graph; selecting a candidate inbound agent code from the obtained inbound agent code nodes according to the determined number of times and time; outputting the candidate inbound agent code as an entry option for the inbound agent code in the target waybill; and entering the inbound agent code in the target waybill according to the received selection operation for the entry option for the inbound agent code.

[0011] A method for entering information on a cargo waybill according to the present invention is characterized in that, after entering the inbound cargo information in the target waybill according to the received selection operation for the entry option for the inbound cargo information, the method further comprises: updating the knowledge graph based on the entered information.

[0012] The present invention also provides an information entry device for a cargo waybill, comprising: an acquisition module, configured to acquire inbound cargo station information, outbound cargo station information and outbound cargo information recorded in a target waybill; a determination module, configured to determine candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information based on a pre-established knowledge graph, wherein the knowledge graph is established based on historical waybill data, the knowledge graph comprises nodes and lines between nodes, the nodes represent entities or attributes of entities, the lines represent relationships between nodes, the nodes comprise waybill nodes, the attribute nodes of the waybill nodes comprise inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes and outbound cargo information nodes; an output module, configured to output the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; an entry module, configured to enter the inbound cargo information in the target waybill according to a received selection operation for the entry option for the inbound cargo information.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for entering information of a freight waybill as described above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for entering information into a freight waybill as described in any one of the above.

[0015] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for entering information into a freight waybill.

[0016] The cargo waybill information entry method, device and electronic device provided by the present invention determine candidate inbound cargo information based on a pre-established knowledge graph, and output the candidate inbound cargo information as an entry option for the inbound cargo information in a target waybill. Finally, based on the received selection operation for the entry option for the inbound cargo information, the inbound cargo information in the target waybill is entered, thereby improving the efficiency of cargo waybill information entry. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the method for entering information of a freight waybill provided by the present invention.

[0019] Figure 2 It is one of the local schematic diagrams of the knowledge graph provided by the present invention.

[0020] Figure 3 This is the second structural schematic diagram of the knowledge graph provided by the present invention.

[0021] Figure 4 This is the third structural diagram of the knowledge graph provided by the present invention.

[0022] Figure 5 It is a structural schematic diagram of the information entry device for a cargo waybill provided by the present invention.

[0023] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Combine the following Figure 1-Figure 6The invention describes a method, device and electronic device for inputting information of a freight waybill.

[0026] Figure 1 is a flow chart of a method for entering information of a freight waybill provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0027] Step 101: Obtain inbound cargo station information, outbound cargo station information, and outbound cargo information recorded in the target waybill.

[0028] In this embodiment, the target waybill may be a waybill that needs to be re-entered at the inbound cargo station after the goods arrive at the destination. The inbound cargo station information, the outbound cargo station information and the outbound cargo information in the target waybill have been entered at the outbound cargo station, but the inbound cargo information and the consignee agent information have not yet been entered.

[0029] Step 102: Based on the pre-established knowledge graph, candidate inbound cargo information matching the inbound cargo terminal information, the outbound cargo terminal information, and the outbound cargo information is determined.

[0030] In this embodiment, the knowledge graph is established based on historical waybill data. As an example, the knowledge graph can be established through steps such as data cleaning, entity recognition, relationship extraction, and data storage.

[0031] See also Figure 2 , Figure 2 This is one of the partial schematic diagrams of the knowledge graph provided by the present invention. It should be noted that in practice, the knowledge graph includes several Figure 2 The knowledge graph structure shown in Figure 1 is shown in Figure 2. In addition, the knowledge graph can also include nodes such as flights, events, and time as needed.

[0032] Figure 2 The knowledge graph includes nodes and links between nodes. Nodes represent entities or attributes of entities, and links represent relationships between nodes. Nodes include waybill nodes. Attribute nodes or field nodes of waybill nodes include inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes, and outbound cargo information nodes. Inbound cargo station information and outbound cargo station information may include the name of the cargo station and the code of the cargo station, and outbound cargo information may include the name of the cargo and the code of the cargo. Inbound cargo station nodes and outbound cargo station nodes themselves may record cargo station name or cargo station code nodes, and may also be associated with cargo station name or cargo station code nodes that represent their attributes.

[0033] Based on the pre-established knowledge graph, the candidate inbound cargo information that matches the inbound cargo station information, the outbound cargo station information, and the outbound cargo information is determined. This can be done by querying the subgraph that matches the inbound cargo station information, the outbound cargo station information, and the outbound cargo information in the pre-established knowledge graph, and determining the candidate inbound cargo information through the inbound cargo information node in the subgraph. The criteria for judging whether there is a match can be divided into two categories: one is based on complete consistency, that is, when there is no difference in any aspect between two objects or data, it is considered a match; the other is based on similarity evaluation, that is, when the similarity between the two reaches or exceeds a specific numerical limit set in advance (that is, a preset threshold), it is also considered a match. The similarity can be calculated based on the semantic vector, and can also be calculated based on triples in combination with the relationship features in the knowledge graph.

[0034] Step 103: Output candidate inbound cargo information as an entry option for inbound cargo information in the target waybill.

[0035] In this embodiment, on the front-end interface for inputting waybill information, candidate inbound cargo information can be output as input options for the inbound cargo information in the target waybill through a drop-down menu or the like, for selection by the input personnel.

[0036] Step 104: Enter the inbound cargo information in the target waybill according to the received selection operation for the entry option of the inbound cargo information.

[0037] In this embodiment, according to the selection operation of the input personnel for the input option of the inbound cargo information, the input option selected by the input personnel can be input as the inbound cargo information in the target waybill. The selection operation can also include not selecting, that is, the input personnel can also not select the input option and input the inbound cargo information in the target waybill by themselves.

[0038] The cargo waybill information entry method provided by the present invention determines candidate inbound cargo information based on a pre-established knowledge graph, and outputs the candidate inbound cargo information as an entry option for the inbound cargo information in a target waybill. Finally, according to the received selection operation for the entry option for the inbound cargo information, the inbound cargo information in the target waybill is entered, thereby improving the efficiency of cargo waybill information entry.

[0039] In some optional implementations, the candidate inbound cargo information includes candidate inbound product names, the outbound cargo information includes outbound product names, and the inbound cargo information includes inbound product names, see Figure 3 , Figure 3 This is the second partial schematic diagram of the knowledge graph provided by the present invention. Compared with Figure 2 , Figure 3In the data graph, the outbound cargo information node includes the outbound product name node, the inbound cargo information node includes the inbound product name node, and the knowledge graph also includes the standard product name node that has a synonymous or superior-subordinate relationship with the outbound product name node.

[0040] In some optional implementations, based on a pre-established knowledge graph, candidate inbound cargo information matching the inbound cargo terminal information, the outbound cargo terminal information and the outbound cargo information is determined, including: entity recognition of the outbound product name; retrieving the candidate outbound product name nodes matching the identified entity in the knowledge graph; scoring the candidate outbound product name nodes according to the similarity between the subgraph starting from the outbound product name node and the inbound cargo terminal information, the outbound cargo terminal information and the outbound product name in the knowledge graph; selecting a preset number of candidate outbound product name nodes according to the scores; obtaining the standard product name recorded in the standard product name node that has a synonymous or superior-subordinate relationship with the selected candidate outbound product name node as the candidate inbound product name.

[0041] The final similarity can be determined based on the overlap between the text information or triple information of the node in the subgraph and the inbound cargo station information, the outbound cargo station information and the outbound product name, or the semantic similarity. For example, the outbound product name: hats, shoes, and circuit boards. The calculated standard product names as candidate inbound product names can include the following three groups: 1. Clothing; Clothing; Integrated Circuits; 2. Clothing; Accessories; Luggage; 3. Clothes; Clothes; Null. In addition to selecting a preset number of candidate outbound product name nodes based on the score, a score threshold can also be set to determine the standard product name corresponding to the candidate outbound product name node that exceeds the score threshold as the candidate inbound product name.

[0042] In addition, based on the data of historical waybills recorded in the knowledge graph, a standard product name entity tag library can be established. The standard product name entity tag library can maintain standard product names and synonyms of standard product names, for example, standard product name entity tag: dog; synonyms: dog, dog, pet dog, and words with a superior-subordinate relationship between standard product names and standard product names, for example, first-level standard product name: clothing; second-level standard product name: hat, pants, T-shirt, etc. Through the established standard product name entity tag library, the standard product name recorded in the standard product name node that has a synonymous or superior-subordinate relationship with the selected candidate outbound product name node can be directly queried as the candidate inbound product name.

[0043] In some optional implementations, entity recognition is performed on the name of the outbound product, including: determining a word vector representation of the name of the outbound product; inputting the word vector representation of the name of the outbound product into a pre-trained named entity recognition model to obtain the entity recognized in the name of the outbound product; wherein the named entity recognition model is trained by the annotated historical data of the outbound product names of different cargo stations. The named entity recognition model may be a BIO annotation model, which is a method of sequence annotation of units in a given sentence, and is used to extract meaningful phrases consisting of continuous words / word blocks from a given sentence, such as named entities (NE). The BIO annotation method annotates each element as "BX", "IX" or "O". Among them, "BX" indicates that the segment where this element is located belongs to type X and this element is at the beginning of this segment, "IX" indicates that the segment where this element is located belongs to type X and this element is in the middle of this segment, and "O" indicates that it does not belong to any type. The model trained by the annotated historical data of the outbound product names of different cargo stations is closer to the use scenario of waybill input and has higher annotation efficiency. In addition, after the outbound product noun vector is processed, named entity recognition can be performed based on the dictionary (the above-mentioned standard product name entity tag library) and BIOTagging (the above-mentioned named entity recognition model) to match the standard product name entity.

[0044] In some optional implementations, the candidate inbound cargo information also includes the candidate inbound commodity name code, the outbound cargo information also includes the outbound commodity name code, and the inbound cargo information also includes the inbound commodity name code, see Figure 4 , Figure 4 This is the third partial schematic diagram of the knowledge graph provided by the present invention. Compared with Figure 3 , Figure 4 The outbound cargo information node also includes an outbound product name code node, the inbound cargo information node also includes an inbound product name code node, the attribute nodes of the waybill node also include a consignor node and a consignee node, the knowledge graph also includes a product name code system node, a cargo station node and an agent node, the outbound product name code node and the inbound product name code have a belonging relationship with the product name code system node, the standard product name node has a belonging relationship with the product name code system node, the attribute node of the cargo station node includes a cargo station name node, the cargo station name node has an association relationship with the product name code system node, the attribute node of the agent node includes an agent code node, the inbound cargo station node and the outbound cargo station node are connected to the cargo station node through the cargo station name node, the agent node has a belonging relationship with the cargo station node, and the agent code node is connected to the waybill node through the consignor node or the consignee node.

[0045] In some optional implementations, after obtaining the standard product name recorded in the standard product name node that is synonymous or in a superior-subordinate relationship with the selected candidate outbound product name node as the candidate inbound product name, determining the candidate inbound cargo information that matches the inbound cargo station information, the outbound cargo station information and the outbound cargo information based on the pre-established knowledge graph, further includes: querying the cargo station name node connected to the inbound cargo station node that matches the inbound cargo station information; determining the product name code corresponding to the candidate inbound product name in the product name code system according to the product name code system node that is associated with the queried cargo station name node, the product name code system node recording the correspondence between the product name and the product name code; obtaining the outbound agent information recorded in the target waybill; retrieving the agent code node that takes the queried cargo station name node as the starting point, passes through the inbound cargo station node, the waybill node and the consignor node in the knowledge graph; and selecting a preset number of product name codes from the product name codes corresponding to the candidate inbound product name as the candidate inbound product name code according to the matching degree between the outbound agent information and the retrieved agent code node. The entry of product name codes reflects the entry habits of the port agent to a certain extent. According to the matching degree between the port agent information and the retrieved agent code node, a preset number of product name codes are selected from the product name codes corresponding to the candidate inbound product names, making the entry of cargo manifest information more accurate.

[0046] In some optional implementations, the method further includes: querying the subgraph in which the agent code node in the knowledge graph matches the outbound agent information recorded in the target waybill, and the inbound cargo terminal node matches the inbound cargo terminal information recorded in the target waybill; obtaining the inbound agent code node included in the queried subgraph; determining the number of times and time the obtained inbound agent code node appears in the knowledge graph; selecting a candidate inbound agent code from the obtained inbound agent code node according to the determined number of times and time; outputting the candidate inbound agent code as an entry option for the inbound agent code in the target waybill; and entering the inbound agent code in the target waybill according to the received selection operation for the entry option of the inbound agent code. Selecting a candidate inbound agent code from the obtained inbound agent code node according to the determined number of times and time may be selecting an inbound agent code whose number of times or frequency in the waybill data of a recent period exceeds a preset value.

[0047] In some optional implementations, after the inbound cargo information in the target waybill is entered according to the received selection operation for the entry option for the inbound cargo information, the method further includes: updating the knowledge graph based on the entered information. For the entered inbound cargo information, such as the inbound product name, the inbound product name code, and the entered inbound agent code, the knowledge graph can be updated together with the pre-acquired inbound cargo station information, the outbound cargo station information, and the outbound cargo information. Considering the limitations of storage space or computing power, the knowledge graph can be updated only when the outbound agent code is new information. When updating the knowledge graph, considering the accuracy of the data, the new knowledge verification module of the knowledge graph can be fed back first, and the knowledge can be updated after the manual confirmation of the verification data. In this way, the knowledge graph is continuously improved, which can further improve the efficiency of entering the waybill information.

[0048] Figure 5 A schematic diagram of the structure of the information entry device for the cargo waybill provided in the embodiment of the present application, such as Figure 5 As shown, it specifically includes: an acquisition module 501, which is configured to acquire the inbound cargo station information, the outbound cargo station information and the outbound cargo information recorded in the target waybill; a determination module 502, which is configured to determine the candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information based on a pre-established knowledge graph, wherein the knowledge graph is established based on historical waybill data, the knowledge graph includes nodes and lines between nodes, the nodes represent entities or attributes of entities, the lines represent relationships between nodes, the nodes include waybill nodes, and the attribute nodes of the waybill nodes include inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes and outbound cargo information nodes; an output module 503, which is configured to output the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; an entry module 504, which is configured to enter the inbound cargo information in the target waybill according to the received selection operation for the entry option of the inbound cargo information.

[0049] In some optional implementations, the candidate inbound cargo information includes candidate inbound product names, the outbound cargo information includes the outbound product names, the inbound cargo information includes the inbound product names, the outbound cargo information nodes include the outbound product name nodes, the inbound cargo information nodes include the inbound product name nodes, and the knowledge graph also includes the standard product name nodes that are synonymous or have a superior-subordinate relationship with the outbound product name nodes; the determination module 502 is further configured to: perform entity recognition on the outbound product names; retrieve candidate outbound product name nodes that match the identified entities in the knowledge graph; score the candidate outbound product name nodes based on the similarity between the subgraph starting from the outbound product name node and the inbound cargo station node and the outbound cargo station node in the knowledge graph and the inbound cargo station information, the outbound cargo station information and the outbound product names; select a preset number of candidate outbound product name nodes based on the scores; obtain the standard product name recorded in the standard product name node that is synonymous or has a superior-subordinate relationship with the selected candidate outbound product name node as the candidate inbound product name.

[0050] In some optional implementations, the determination module 502 is further configured to: determine the word vector representation of the outbound product name; input the word vector representation of the outbound product name into a pre-trained named entity recognition model to obtain entities recognized in the outbound product name; wherein the named entity recognition model is trained through historical data of outbound product names from different cargo terminals with annotations.

[0051] In some optional implementations, the candidate inbound cargo information also includes candidate inbound product name codes, the outbound cargo information also includes the outbound product name code, the inbound cargo information also includes the inbound product name code, the outbound cargo information node also includes the outbound product name code node, the inbound cargo information node also includes the inbound product name code node, the attribute node of the waybill node also includes the consignor node and the consignee node, the knowledge graph also includes the product name code system node, the cargo station node and the agent node, the outbound product name code node and the inbound product name code have a belonging relationship with the product name code system node, the standard product name node has a belonging relationship with the product name code system node, the attribute node of the cargo station node includes the cargo station name node, the cargo station name node has an association relationship with the product name code system node, the attribute node of the agent node includes the agent code node, the inbound cargo station node and the outbound cargo station node are connected to the cargo station node through the cargo station name node, and the agent The agent node and the cargo station node have a belonging relationship, and the agent code node is connected to the waybill node through the consignor node or the consignee node; the determination module 502 is further configured to: query the cargo station name node connected to the inbound cargo station node matching the inbound cargo station information; determine the product name code corresponding to the candidate inbound product name in the product name code system according to the product name code system node that has an associated relationship with the queried cargo station name node, and the product name code system node records the correspondence between the product name and the product name code; obtain the outbound agent information recorded in the target waybill; retrieve the agent code node in the knowledge graph starting from the queried cargo station name node, through the inbound cargo station node, the waybill node and the consignor node; select a preset number of product name codes from the product name codes corresponding to the candidate inbound product name as the candidate inbound product name code according to the matching degree between the outbound agent information and the retrieved agent code node.

[0052] In some optional implementations, the determination module 502 is further configured to: query the subgraph in which the agent code node in the knowledge graph matches the outbound agent information recorded in the target waybill, and the inbound cargo terminal node matches the inbound cargo terminal information recorded in the target waybill; obtain the inbound agent code node included in the queried subgraph; determine the number of times and time when the acquired inbound agent code node appears in the knowledge graph; select a candidate inbound agent code from the acquired inbound agent code nodes based on the determined number of times and time; the output module 503 is further configured to output the candidate inbound agent code as an entry option for the inbound agent code in the target waybill; the entry module 504 is further configured to enter the inbound agent code in the target waybill based on the received selection operation for the entry option for the inbound agent code.

[0053] In some optional implementations, the device also includes an updating unit configured to: update the knowledge graph based on the input information.

[0054] In this embodiment, the specific processing of the acquisition module 501, the determination module 502, the output module 503 and the input module 504 of the cargo waybill information input device can be referred to. Figure 1 This corresponds to step 101, step 102, step 103 and step 104 in the embodiment.

[0055] The cargo waybill information entry device provided by the present invention improves the efficiency of cargo waybill information entry.

[0056] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor (processor) 610 , a communication interface (Communications Interface) 620 , a memory (memory) 630 and a communication bus 640 , wherein the processor 610 , the communication interface 620 , and the memory 630 communicate with each other through the communication bus 640 . The processor 610 can call the logic instructions in the memory 630 to execute the information entry method of the cargo waybill, which includes: obtaining the inbound cargo station information, the outbound cargo station information and the outbound cargo information recorded in the target waybill; based on the pre-established knowledge graph, determining the candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information, wherein the knowledge graph is established based on the historical waybill data, the knowledge graph includes nodes and lines between nodes, the nodes represent entities or attributes of entities, the lines represent the relationship between nodes, the nodes include waybill nodes, and the attribute nodes of the waybill nodes include inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes and outbound cargo information nodes; outputting the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; and entering the inbound cargo information in the target waybill according to the received selection operation for the entry option of the inbound cargo information.

[0057] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of software function modules and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0058] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the information entry method of the cargo waybill provided by the above methods, the method including: obtaining the inbound cargo station information, the outbound cargo station information and the outbound cargo information recorded in the target waybill; based on a pre-established knowledge graph, determining candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information, wherein the knowledge graph is established based on historical waybill data, the knowledge graph includes nodes and lines between nodes, the nodes represent entities or attributes of entities, the lines represent relationships between nodes, the nodes include waybill nodes, and the attribute nodes of the waybill nodes include inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes and outbound cargo information nodes; outputting the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; and entering the inbound cargo information in the target waybill according to the received selection operation for the entry option for the inbound cargo information.

[0059] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the information entry method for a cargo waybill provided by the above methods, the method comprising: obtaining the inbound cargo station information, the outbound cargo station information and the outbound cargo information recorded in the target waybill; determining, based on a pre-established knowledge graph, candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information, wherein the knowledge graph is established based on historical waybill data, the knowledge graph comprises nodes and lines between nodes, the nodes represent entities or attributes of entities, the lines represent relationships between nodes, the nodes comprise waybill nodes, the attribute nodes of the waybill nodes comprise inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes and outbound cargo information nodes; outputting the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; and entering the inbound cargo information in the target waybill according to the received selection operation for the entry option for the inbound cargo information.

[0060] The device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0061] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for entering information on a freight bill, characterized in that: include: Obtain the inbound cargo station information, outbound cargo station information, and outbound cargo information recorded in the target waybill; Based on a pre-established knowledge graph, determine candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information, and the outbound cargo information, wherein the knowledge graph is established based on historical waybill data, the knowledge graph includes nodes and links between nodes, the nodes represent entities or attributes of entities, the links represent relationships between nodes, the nodes include waybill nodes, and the attribute nodes of the waybill nodes include inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes, and outbound cargo information nodes; Outputting the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; Entering the inbound cargo information in the target waybill according to the received selection operation for the entry option of the inbound cargo information; The candidate inbound cargo information includes candidate inbound product names, the outbound cargo information includes outbound product names, the inbound cargo information includes inbound product names, the outbound cargo information nodes include outbound product name nodes, the inbound cargo information nodes include inbound product name nodes, and the knowledge graph also includes standard product name nodes that are synonymous or have a superior-subordinate relationship with the outbound product name nodes; the determining, based on the pre-established knowledge graph, the candidate inbound cargo information that matches the inbound cargo station information, the outbound cargo station information, and the outbound cargo information includes: Perform entity recognition on the name of the outbound product; Retrieving candidate outbound product name nodes matching the identified entity in the knowledge graph; Scoring the candidate outbound product name node according to the similarity between the subgraph starting from the outbound product name node and the inbound cargo terminal node and the outbound cargo terminal information, the outbound cargo terminal information and the outbound product name in the knowledge graph; A preset number of candidate outbound commodity name nodes are selected according to the scores; Obtain the standard product name of the standard product name node record that has a synonymous or superior-subordinate relationship with the selected candidate outbound product name node as the candidate inbound product name; Among them, the candidate inbound cargo information also includes candidate inbound product name codes, the outbound cargo information also includes outbound product name codes, the inbound cargo information also includes inbound product name codes, the outbound cargo information node also includes outbound product name code nodes, the inbound cargo information node also includes inbound product name code nodes, the attribute nodes of the waybill node also include consignor nodes and consignee nodes, the knowledge graph also includes product name code system nodes, cargo station nodes and agent nodes, the outbound product name code node and the inbound product name code have a belonging relationship with the product name code system node, the standard product name node has a belonging relationship with the product name code system node, the attribute nodes of the cargo station node include cargo station name nodes, the The cargo station name node is associated with the product name code system node, the attribute node of the proxy node includes an agent code node, the inbound cargo station node and the outbound cargo station node are connected to the cargo station node through the cargo station name node, the proxy node and the cargo station node are in a belonging relationship, and the agent code node is connected to the waybill node through the consignor node or the consignee node; after obtaining the standard product name recorded in the standard product name node that is synonymous or in a superior-subordinate relationship with the selected candidate outbound product name node as the candidate inbound product name, the candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information based on the pre-established knowledge graph is determined, and further includes: Querying the cargo station name node connected to the inbound cargo station node matching the inbound cargo station information; Determine the commodity name code corresponding to the candidate inbound commodity name in the commodity name code system according to the commodity name code system node associated with the queried cargo station name node, wherein the commodity name code system node records the corresponding relationship between the commodity name and the commodity name code; Obtaining the outbound agent information recorded in the target waybill; Retrieve the agent code node in the knowledge graph starting from the queried cargo station name node, via the inbound cargo station node, the waybill node and the consignor node; According to the matching degree between the outbound agent information and the retrieved agent code node, a preset number of product name codes are selected from the product name codes corresponding to the candidate inbound product names as candidate inbound product name codes.

2. The method for entering information of a freight waybill according to claim 1, characterized in that: The entity identification of the outbound product name includes: Determine the word vector representation of the outbound product name; The word vector representation of the outbound product name is input into a pre-trained named entity recognition model to obtain entities recognized in the outbound product name; wherein the named entity recognition model is trained by using historical data of outbound product names from different cargo terminals with annotations.

3. The method for entering information of a freight waybill according to claim 1, characterized in that: The method further comprises: Querying the subgraph in which the agent code node in the knowledge graph matches the outbound agent information recorded in the target waybill, and the inbound cargo station node matches the inbound cargo station information recorded in the target waybill; Get the port agent code node included in the queried subgraph; Determine the number of times and time at which the acquired port entry agent code node appears in the knowledge graph; According to the determined number and time, a candidate port entry agent code is selected from the acquired port entry agent code nodes; Outputting the candidate port entry agent code as an entry option for the port entry agent code in the target waybill; According to the received selection operation for the entry option of the port entry agent code, the port entry agent code in the target waybill is entered.

4. The method for entering information of a freight bill according to claim 1, characterized in that: After entering the inbound cargo information in the target waybill according to the received selection operation for the entry option of the inbound cargo information, the method further includes: Based on the entered information, the knowledge graph is updated.

5. A device for inputting information of a cargo waybill, characterized in that: include: An acquisition module is configured to acquire inbound cargo station information, outbound cargo station information, and outbound cargo information recorded in a target waybill; a determination module configured to determine candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information, and the outbound cargo information based on a pre-established knowledge graph, wherein the knowledge graph is established based on historical waybill data, the knowledge graph includes nodes and links between nodes, the nodes represent entities or attributes of entities, the links represent relationships between nodes, the nodes include waybill nodes, and the attribute nodes of the waybill nodes include inbound cargo station nodes, outbound cargo station nodes, inbound cargo information nodes, and outbound cargo information nodes; an output module configured to output the candidate inbound cargo information as an entry option for the inbound cargo information in the target waybill; An input module is configured to input the inbound cargo information in the target waybill according to the received selection operation of the input option for the inbound cargo information; The candidate inbound cargo information includes candidate inbound product names, the outbound cargo information includes outbound product names, the inbound cargo information includes inbound product names, the outbound cargo information nodes include outbound product name nodes, the inbound cargo information nodes include inbound product name nodes, and the knowledge graph also includes standard product name nodes that are synonymous or have a superior-subordinate relationship with the outbound product name nodes; the determining, based on the pre-established knowledge graph, the candidate inbound cargo information that matches the inbound cargo station information, the outbound cargo station information, and the outbound cargo information includes: Perform entity recognition on the name of the outbound product; Retrieving candidate outbound product name nodes matching the identified entity in the knowledge graph; Scoring the candidate outbound product name node according to the similarity between the subgraph starting from the outbound product name node and the inbound cargo terminal node and the outbound cargo terminal information, the outbound cargo terminal information and the outbound product name in the knowledge graph; A preset number of candidate outbound commodity name nodes are selected according to the scores; Obtain the standard product name of the standard product name node record that has a synonymous or superior-subordinate relationship with the selected candidate outbound product name node as the candidate inbound product name; Among them, the candidate inbound cargo information also includes candidate inbound product name codes, the outbound cargo information also includes outbound product name codes, the inbound cargo information also includes inbound product name codes, the outbound cargo information node also includes outbound product name code nodes, the inbound cargo information node also includes inbound product name code nodes, the attribute nodes of the waybill node also include consignor nodes and consignee nodes, the knowledge graph also includes product name code system nodes, cargo station nodes and agent nodes, the outbound product name code node and the inbound product name code have a belonging relationship with the product name code system node, the standard product name node has a belonging relationship with the product name code system node, the attribute nodes of the cargo station node include cargo station name nodes, the The cargo station name node is associated with the product name code system node, the attribute node of the proxy node includes an agent code node, the inbound cargo station node and the outbound cargo station node are connected to the cargo station node through the cargo station name node, the proxy node and the cargo station node are in a belonging relationship, and the agent code node is connected to the waybill node through the consignor node or the consignee node; after obtaining the standard product name recorded in the standard product name node that is synonymous or in a superior-subordinate relationship with the selected candidate outbound product name node as the candidate inbound product name, the candidate inbound cargo information matching the inbound cargo station information, the outbound cargo station information and the outbound cargo information based on the pre-established knowledge graph is determined, and further includes: Querying the cargo station name node connected to the inbound cargo station node matching the inbound cargo station information; Determine the commodity name code corresponding to the candidate inbound commodity name in the commodity name code system according to the commodity name code system node associated with the queried cargo station name node, wherein the commodity name code system node records the corresponding relationship between the commodity name and the commodity name code; Obtaining the outbound agent information recorded in the target waybill; Retrieve the agent code node in the knowledge graph starting from the queried cargo station name node, via the inbound cargo station node, the waybill node and the consignor node; According to the matching degree between the outbound agent information and the retrieved agent code node, a preset number of product name codes are selected from the product name codes corresponding to the candidate inbound product names as candidate inbound product name codes.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for entering information of a freight waybill as described in any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for entering information into a freight bill as claimed in any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for entering information into a freight bill as claimed in any one of claims 1 to 4 is implemented.

Images