Logistics subject matching method, device and computer equipment based on logistics information

Abstract

The present application relates to a logistics subject matching method, device, computer equipment and storage medium based on logistics information, including: obtaining the target address information of the logistics subject, and obtaining multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban area information and a custom address; extracting corresponding character strings from the target address information and the custom addresses of multiple waybill address information respectively; obtaining the similarity between the corresponding character strings in the target address information and the waybill address information, and obtaining the similarity between the target address information and the waybill address information; determining the waybill address information that matches the logistics subject from multiple waybill address information whose similarity with the target address information reaches a preset threshold. The present application improves the processing efficiency of address information; by calculating the similarity between the target address information and the waybill address information, the efficiency of matching the waybill address information with the logistics subject is improved.

Description

Technical Field

[0001] The present application relates to the field of logistics information technology, and in particular to a logistics subject matching method, device, computer equipment and storage medium based on logistics information. Background Art

[0002] In the field of logistics, a logistics entity usually reaches a cooperative relationship with multiple senders and receives logistics packages sent by multiple senders; therefore, in the logistics information, a logistics entity may correspond to multiple address information, resulting in redundant logistics information and low efficiency in processing logistics information.

[0003] Currently, a corpus is usually used to train a natural language model. After obtaining a usable word segmenter, similarity calculations are performed on multiple address information to determine the match with the logistics entity. However, this method requires a lot of manpower and material resources to obtain a huge amount of address rules and address dictionaries, and requires continuous maintenance, resulting in poor address information matching efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a logistics entity matching method, device, computer equipment and storage medium based on logistics information to address the above technical problems.

[0005] A logistics subject matching method based on logistics information, the method comprising:

[0006] Obtaining the target address information of the logistics entity, and obtaining multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban area information and a custom address;

[0007] Extracting corresponding character strings from the target address information and the custom addresses of the plurality of waybill address information respectively;

[0008] Acquire the similarity between the corresponding character strings in the target address information and the waybill address information to obtain the similarity between the target address information and the waybill address information;

[0009] From a plurality of waybill address information whose similarity with the target address information reaches a preset threshold, determine the waybill address information that matches the logistics entity.

[0010] In one of the embodiments, after obtaining the target address information of the logistics entity and obtaining multiple waybill address information to be matched from the logistics information, it also includes: obtaining a preset address information dictionary file; identifying the urban area information from the target address information and the waybill address information respectively through the address information dictionary file; and using the address information in the target address information and the waybill address information, except the urban area information, as the custom address.

[0011] In one embodiment, the character string includes a text character string and a numeric character string; the obtaining the similarity between the corresponding character strings in the target address information and the waybill address information to obtain the similarity between the target address information and the waybill address information includes: determining a first similarity between the character string in the target address information and the custom address of the waybill address information; determining a second similarity between the numeric character string in the custom address of the target address information and the waybill address information; determining a similarity adjustment coefficient between the target address information and the waybill address information based on the name of the logistics entity; and determining the similarity between the target address information and the waybill address information based on the first similarity, the second similarity and the similarity adjustment coefficient.

[0012] In one embodiment, determining the first similarity between the text strings in the custom address of the target address information and the waybill address information includes: extracting multiple strings that do not contain numbers and have the same first and last characters as the text strings from the custom addresses of the target address information and the waybill address information, respectively; and determining the first similarity of the text strings based on the Levenshtein ratio of the multiple text strings.

[0013] In one of the embodiments, before determining the first similarity between the target address information and the text string in the custom address of the waybill address information, it includes: calculating the edit distances of multiple text strings; the edit distance of the replacement operation in the edit distance is not equal to the edit distances between the insertion operation and the deletion operation; selecting the largest edit distance from the multiple edit distances as the target edit distance; the target edit distance is used to determine the Levenshtein ratio of the text string.

[0014] In one embodiment, determining the second similarity between the digital character strings in the target address information and the custom address of the waybill address information includes: extracting multiple digital feature values ​​from the digital character strings respectively; performing weighted operation on the multiple digital feature values ​​according to weights corresponding to the multiple digital feature values ​​to obtain the second similarity of the digital character strings.

[0015] In one of the embodiments, determining the similarity adjustment coefficient between the target address information and the waybill address information based on the name of the logistics entity includes: obtaining the number of strokes of the name of the logistics entity; performing a weighted operation on the number of strokes according to a weight corresponding to the number of strokes to obtain the similarity adjustment coefficient.

[0016] A logistics subject matching device based on logistics information, the device comprising:

[0017] An address information acquisition module is used to acquire the target address information of the logistics entity, and to acquire multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban area information and a custom address;

[0018] A character string extraction module, used to extract corresponding character strings from the target address information and the custom addresses of the plurality of waybill address information respectively;

[0019] A similarity determination module, used to obtain the similarity between the corresponding character strings in the target address information and the waybill address information, and obtain the similarity between the target address information and the waybill address information;

[0020] The address information matching module is used to determine the waybill address information that matches the logistics entity from multiple waybill address information whose similarity with the target address information reaches a preset threshold.

[0021] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0022] Obtaining the target address information of the logistics entity, and obtaining multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban area information and a custom address;

[0023] Extracting corresponding character strings from the target address information and the custom addresses of the plurality of waybill address information respectively;

[0024] Acquire the similarity between the corresponding character strings in the target address information and the waybill address information to obtain the similarity between the target address information and the waybill address information;

[0025] From a plurality of waybill address information whose similarity with the target address information reaches a preset threshold, determine the waybill address information that matches the logistics entity.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0027] Obtaining the target address information of the logistics entity, and obtaining multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban area information and a custom address;

[0028] Extracting corresponding character strings from the target address information and the custom addresses of the plurality of waybill address information respectively;

[0029] Acquire the similarity between the corresponding character strings in the target address information and the waybill address information to obtain the similarity between the target address information and the waybill address information;

[0030] From a plurality of waybill address information whose similarity with the target address information reaches a preset threshold, determine the waybill address information that matches the logistics entity.

[0031] The above-mentioned logistics subject matching method, device, computer equipment and storage medium based on logistics information, the method includes: obtaining the target address information of the logistics subject, and obtaining multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban information and custom addresses; extracting corresponding character strings from the target address information and the custom addresses of multiple waybill address information respectively; obtaining the similarity between the corresponding character strings in the target address information and the waybill address information, and obtaining the similarity between the target address information and the waybill address information; determining the waybill address information that matches the logistics subject from the multiple waybill address information whose similarity with the target address information reaches a preset threshold. The present application reduces the amount of data to be processed and improves the processing efficiency of address information by dividing the logistics information into urban information and custom addresses; calculating the similarity between the target address information and the waybill address information through custom addresses, and determining the waybill address information that matches the logistics subject based on the similarity, thereby improving the efficiency of matching multiple waybill address information with the logistics subject. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is an application environment diagram of a logistics subject matching method based on logistics information in one embodiment;

[0033] Figure 2 A schematic diagram of a flow chart of a logistics subject matching method based on logistics information in one embodiment;

[0034] Figure 3 A flowchart of a step of identifying a custom address from target address information and waybill address information in one embodiment;

[0035] Figure 4 It is a flowchart of the step of obtaining the similarity between the target address information and the waybill address information in one embodiment;

[0036] Figure 5 A schematic flow chart of a step of determining a first similarity between target address information and a text string in a custom address of waybill address information in one embodiment;

[0037] Figure 6 A schematic diagram of a flow chart of a method for calculating edit distances of multiple text strings in one embodiment;

[0038] Figure 7 It is a structural block diagram of a logistics subject matching device based on logistics information in one embodiment;

[0039] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] The logistics subject matching method based on logistics information provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 11 communicates with the server 12 through the network. The server 12 obtains the target address information of the logistics subject sent by the terminal 11, and obtains multiple waybill address information to be matched from the logistics information provided by the terminal 11; the target address information and the waybill address information include urban information and a custom address; the server 12 extracts corresponding character strings from the target address information and the custom addresses of multiple waybill address information respectively; the server 12 obtains the similarity between the corresponding character strings in the target address information and the waybill address information, and obtains the similarity between the target address information and the waybill address information; the server 12 determines the waybill address information that matches the logistics subject from the multiple waybill address information whose similarity with the target address information reaches a preset threshold, and returns the information to the terminal 11.

[0042] Among them, the terminal 11 can be but is not limited to various express smart POS devices, express smart PDA devices, personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 12 can be implemented by an independent server or a server cluster composed of multiple servers.

[0043] In one embodiment, Figure 2As shown in the figure, a logistics subject matching method based on logistics information is provided, and the method is applied to Figure 1 Taking the server 12 in the example as an example, the following steps are included:

[0044] Step 21, obtain the target address information of the logistics entity, and obtain multiple waybill address information to be matched from the logistics information; the target address information and waybill address information include urban area information and custom address.

[0045] Among them, with the gradual improvement of the logistics network, the filling of logistics information has gradually become standardized. Under normal circumstances, the format requirements are: consignee, mobile phone number (telephone number), region and detailed address; among them, the region is usually the province, city, and district information, such as Nanshan District, Shenzhen City, Guangdong Province; and the detailed address is usually the road, street, house number, community, building, unit number, etc.; the specific detailed address is difficult to unify, and is usually customized by the recipient according to his own cognition, which is subject to the recognition of the logistics system or logistics personnel. Therefore, the address information except the province, city, district information can be defined as a "custom address".

[0046] For example, the registered address of Company A is "Room 1203, No. 123 Xuefu Road, Nanshan District, Shenzhen, Guangdong Province". In the course of business activities, Company A will exchange letters and goods with the outside world. Due to the different recipients and senders, the specific logistics information may be "Room 301, 12th Floor, No. 123 Xuefu Road, Nanshan District, Shenzhen, Guangdong Province", "Company A, No. 123 Xuefu Road, Nanshan District, Shenzhen, Guangdong Province", "Room 1203, No. 123 Haitian 1st Road, Nanshan District, Shenzhen, Guangdong Province", etc. Among them, Company A is the logistics entity, and the registered address of Company A is the target address information. The specific logistics information actually generated can be used as multiple waybill address information to be matched.

[0047] It can be seen that multiple logistics information actually correspond to the same logistics entity, and the province, city, and district information in the address information is usually relatively unified, that is, there is no difference if the city and district information is the same; but the customized parts such as "Room 301, 12th Floor, No. 123 Xuefu Road", "Company A, No. 123 Xuefu Road", and "Room 1203, No. 123 Haitian 1st Street" will be different in specific use, resulting in one logistics entity corresponding to multiple waybill address information.

[0048] Specifically, the terminal selects the logistics entity, and the corresponding identification carried by the logistics entity can be automatically associated with the target address information; the address information can be the registered business address, or the default contact address specified for the logistics entity, etc. The terminal then selects multiple waybill address information from the logistics information, and sends the logistics entity, the target address information of the logistics entity, and multiple waybill address information selected from the logistics information to the server for matching; the server can identify the urban area information and the custom address from the target address information and the waybill address information, and match it with the logistics information selected by the terminal, and return it to the terminal after obtaining the matching result.

[0049] In this step, the server can obtain the target address information of the logistics entity and obtain multiple waybill address information to be matched from the logistics information, thereby clarifying the logistics entity and the waybill address information that needs to be matched with the logistics entity.

[0050] Step 22, extract corresponding character strings from the target address information and the custom addresses of the multiple waybill address information respectively.

[0051] Specifically, since the target address information and multiple waybill address information are basically unified in format, they can be divided into a city information part and a custom address part, and the custom address part is usually composed of text, numbers, letters and symbols. Therefore, the server needs to extract different types of character strings from the target address information and the custom address part of multiple waybill address information.

[0052] In the specific extraction process, corresponding extraction rules can be set according to different character types. For example, first find the character string with the same beginning and end, that is, in "No. 1, Citizen Center, Fuzhong 3rd Road" and "No. 1, Citizen Square, Fuzhong 3rd Road", the character string with the same beginning and end found can be "Fuzhong 3rd Road Citizen".

[0053] The server first identifies the target address information and the custom addresses in the multiple waybill address information, determines the character type of each character in the custom address, identifies the characters of the same character type and consecutively as strings, and extracts the identified strings after all the custom addresses are identified to obtain multiple strings.

[0054] In this step, the corresponding strings are extracted from the target address information and the custom addresses of multiple waybill address information according to the characteristics of the strings. The strings are easier to compare, and the data processing difficulty is relatively small and the processing speed is relatively fast, which improves the efficiency of matching the waybill address information with the logistics entity.

[0055] Step 23, obtaining the similarity between the corresponding character strings in the target address information and the waybill address information, and obtaining the similarity between the target address information and the waybill address information.

[0056] Specifically, the similarity between character strings can be calculated by respectively setting similarity calculation methods according to the type of the character string, the length of the character string, and the importance of the character string in the address information.

[0057] Commonly used similarity calculation methods include the edit distance algorithm (also known as the Levenshtein distance), which refers to the minimum number of edit operations required to convert two strings from one to another. The greater the distance between them, the more different they are. There are only three types of edit operations: insertion, deletion, and replacement. The similarity between two strings can be determined by the cost of obtaining two identical strings after inserting, deleting, or replacing one of the two strings. Usually, the cost of each edit, that is, each insertion, deletion, or replacement, is set to 1.

[0058] Other commonly used similarity calculation methods include Jaccard similarity, which refers to the number of words in the intersection of text A and text B divided by the number of words in the union. Jaccard similarity is independent of the position and order of the text. It is suitable for texts that are not sensitive to the order of words or for texts with a large number of characters.

[0059] This step can further determine the overall similarity between the target address information and the waybill address information by calculating the similarity between the corresponding character strings in the custom address of the target address information and the waybill address information.

[0060] Step 24, determining the waybill address information that matches the logistics entity from the multiple waybill address information whose similarity with the target address information reaches a preset threshold.

[0061] Specifically, after similarity calculation, the server can determine multiple waybill address information that are similar to the target address information, and the similarity between each waybill address information and the target address information is different; it is generally believed that the one with the greatest similarity is more likely to be the same logistics entity, and the smaller the similarity is, the less likely it is to be the same logistics entity; therefore, a preset threshold value related to similarity can be set to filter multiple waybill address information, and the waybill address information with a similarity that is significantly less than a certain value can be filtered out, leaving multiple waybill address information with a similarity that reaches a preset threshold. Then, the waybill address information that matches the logistics entity is determined from the multiple waybill address information with a similarity that reaches the preset threshold.

[0062] The server can set the preset threshold in the form of a ratio, for example, taking the similarity corresponding to the top 20% of the similarity of all waybill address information as the basis for setting the preset threshold; the preset threshold can also be set in the form of a quantity, for example, arranging multiple waybill address information from large to small according to the similarity, and taking the first 10 as the multiple waybill address information that reach the preset threshold, that is, after arranging from large to small according to the similarity, the similarity corresponding to the 10th waybill address information is the preset threshold.

[0063] By setting preset thresholds, waybill address information that does not meet the preset threshold requirements can be quickly excluded, reducing the server's computing workload; and during the calculation process, when the number of waybill address information that reaches the preset threshold has reached a certain amount, subsequent calculations can be stopped, thereby speeding up the efficiency of matching multiple waybill address information with logistics entities.

[0064] After determining multiple waybill address information whose similarity with the target address information reaches a preset threshold, the server can take the first n waybill address information from the multiple waybill address information that reaches the preset threshold as the waybill address information matching the logistics entity according to parameters such as similarity size and ratio.

[0065] The above-mentioned logistics subject matching method, device, computer equipment and storage medium based on logistics information, the method includes: obtaining the target address information of the logistics subject, and obtaining multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban area information and custom addresses; extracting corresponding character strings from the target address information and the custom addresses of multiple waybill address information respectively; obtaining the similarity between the corresponding character strings in the target address information and the waybill address information, and obtaining the similarity between the target address information and the waybill address information; determining the waybill address information that matches the logistics subject from the multiple waybill address information whose similarity with the target address information reaches a preset threshold. The present application reduces the amount of data to be processed and improves the processing efficiency of address information by dividing the logistics information into urban area information and custom addresses; calculating the similarity between the target address information and the waybill address information through the custom address, and determining the waybill address information that matches the logistics subject based on the similarity, thereby improving the efficiency of matching multiple waybill address information with the logistics subject.

[0066] In one embodiment, Figure 3 As shown, after obtaining the target address information of the logistics entity and obtaining multiple waybill address information to be matched from the logistics information, it also includes:

[0067] Step 31, obtaining a preset address information dictionary file;

[0068] Step 32, identifying the urban area information from the target address information and the waybill address information respectively through the address information dictionary file;

[0069] Step 33: The address information in the target address information and the waybill address information, except the urban area information, is used as the custom address.

[0070] Specifically, the preset address information dictionary file mainly consists of province, city, and district information. Through the preset address information dictionary file, the city information can be identified from the target address information and the waybill address information; after the server identifies the city information, the remaining part can be used as the custom address of the target address information and the waybill address information.

[0071] This embodiment can divide the target address information and waybill address information into custom address and urban area information through a preset address information dictionary file, thereby improving the efficiency of matching multiple waybill address information with logistics entities.

[0072] In one embodiment, the character string includes a text character string and a numeric character string.

[0073] like Figure 4 As shown, the similarity between the corresponding character strings in the target address information and the waybill address information is obtained, and the similarity between the target address information and the waybill address information is obtained, including:

[0074] Step 41, determining a first similarity between the target address information and the text string in the custom address of the waybill address information;

[0075] Step 42, determining a second similarity between the target address information and the numeric character string in the custom address of the waybill address information;

[0076] Step 43, determining a similarity adjustment coefficient between the target address information and the waybill address information according to the name of the logistics entity;

[0077] Step 44: Determine the similarity between the target address information and the waybill address information based on the first similarity, the second similarity and the similarity adjustment coefficient.

[0078] Specifically, the server extracts text strings and numeric strings from the custom addresses of the target address information and the waybill address information, respectively; then the similarity between the text strings is calculated as the first similarity, and the similarity between the numeric strings is calculated as the second similarity; then the adjustment coefficient is determined using the name of the logistics entity to balance the complexity of the logistics entity name; finally, the first similarity, the second similarity and the similarity adjustment coefficient are integrated and calculated, and the final calculation result is determined as the similarity between the target address information and the waybill address information.

[0079] This embodiment calculates the similarity between the target address information and the waybill address information, taking into account the characteristics of text characters and numeric characters, and makes adjustments to the complexity of the name of the logistics entity, thereby obtaining a calculation result that can reflect the similarity between the target address information and the waybill address information.

[0080] In one embodiment, Figure 5 As shown, determining the first similarity between the target address information and the text string in the custom address of the waybill address information includes:

[0081] Step 51, extracting a plurality of character strings without numbers and with the same first and last characters from the custom addresses of the target address information and the waybill address information as text character strings;

[0082] Step 52: determining a first similarity of the text strings according to the Levenshtein ratio of the plurality of text strings.

[0083] Specifically, the server extracts multiple text strings that do not contain numbers and have the same first and last characters from the custom addresses of the target address information and the waybill address information; calculates the edit distance of all these text strings, that is, the minimum number of single-word editing operations required to convert one of the two strings into another; there are only three single-character editing operations defined here: insert, delete, and replace; takes the maximum edit distance as d; calculates the ratio of the Levenshtein distances of the two, and obtains the Levenshtein ratio R as R = (sum-d) / sum.

[0084] In one embodiment, Figure 6 As shown, before determining the first similarity between the target address information and the text string in the custom address of the waybill address information, it includes:

[0085] Step 61, calculating the edit distances of the plurality of character strings; the edit distance of the replacement operation in the edit distance is not equal to the edit distances between the insertion operation and the deletion operation;

[0086] Step 62 , selecting the largest edit distance from the plurality of edit distances as the target edit distance; the target edit distance is used to determine the Levenshtein ratio of the text string.

[0087] Specifically, when performing edit distance calculation, the quasi-edit distance is used for calculation; the quasi-edit distance refers to the situation in which, in the conventional edit distance calculation, the cost of the replacement operation is set differently from that of the insertion and deletion operations, for example, the cost of insertion and deletion is 1, while the cost of the replacement operation is 2; the edit distance calculated in this way is the quasi-edit distance.

[0088] In one embodiment, determining a second similarity between the target address information and the digital string in the custom address of the waybill address information includes: respectively extracting a plurality of digital feature values from the digital string; performing a weighted operation on the plurality of digital feature values according to the weights corresponding to the plurality of digital feature values to obtain the second similarity of the digital string.

[0089] Specifically, the extraction method and specific values of the digital features can be determined after analyzing the numbers in a large number of waybill address information; specifically, they can be obtained through the following methods:

[0090] D = e w1×h+w2×a ;

[0091]

[0092] Wherein, D is the second similarity of the digital string, h is the number of equal numbers before the character "hao", c is the remaining identical numbers other than those before the character "hao", length is the number of digits, and a is the digit number adjustment coefficient. The "hao" is the "hao" in the commonly used XX Road XX Hao in the address information. w1, w2, and w3 are the weight adjustment coefficients corresponding to h, a, and c respectively, and this coefficient is obtained by analyzing a large number of logistics information;

[0093] Further, w1, w2, and w3 can be set to 0.15, 0.03, and 1.6 respectively; that is:

[0094] D = e 0.15×h+0.03×a ;

[0095]

[0096] Through the above formula, the second similarity D of the digital string can be calculated.

[0097] In one embodiment, determining a similarity adjustment coefficient between the target address information and the waybill address information according to the name of the logistics entity includes: obtaining the number of strokes of the name of the logistics entity; performing a weighted operation on the number of strokes according to the weight corresponding to the number of strokes to obtain the similarity adjustment coefficient.

[0098] Specifically, the similarity adjustment coefficient can be determined according to the name of the logistics entity; specifically, it is calculated through the following method:

[0099] N = 20.02×(N 1 -20);

[0100] Wherein, N1 is the number of strokes of the name of the logistics entity; the name of the logistics entity can be the name of an enterprise legal person; N is the similarity adjustment coefficient. The similarity adjustment coefficient and each coefficient therein can be obtained after continuous adjustment by analyzing a large number of logistics information.

[0101] In one embodiment, the similarity between the target address information and the waybill address information can be obtained by the similarity between the corresponding character strings in the target address information and the waybill address information:

[0102] S = min(R × D × N, 100);

[0103] Among them, S is the similarity between the target address information and the waybill address information; R is the first similarity between the text strings; D is the second similarity between the numeric strings; and N is the similarity adjustment coefficient determined based on the name of the logistics entity.

[0104] It should be understood that although Figure 2-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-6 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0105] In one embodiment, Figure 7 As shown, a logistics subject matching device based on logistics information is provided, comprising: an address information acquisition module 71, a string extraction module 72, a similarity determination module 73 and an address information matching module 74, wherein:

[0106] The address information acquisition module 71 is used to acquire the target address information of the logistics entity, and to acquire multiple waybill address information to be matched from the logistics information; the target address information and waybill address information include urban area information and custom address;

[0107] A character string extraction module 72, used to extract corresponding character strings from the target address information and the custom addresses of the plurality of waybill address information respectively;

[0108] A similarity determination module 73 is used to obtain the similarity between the corresponding character strings in the target address information and the waybill address information, and obtain the similarity between the target address information and the waybill address information;

[0109] The address information matching module 74 is used to determine the waybill address information that matches the logistics entity from multiple waybill address information whose similarity with the target address information reaches a preset threshold.

[0110] In one embodiment, the address information acquisition module 71 is also used to obtain a preset address information dictionary file; identify the urban area information from the target address information and the waybill address information respectively through the address information dictionary file; and use the address information in the target address information and the waybill address information except the urban area information as a custom address.

[0111] In one embodiment, the similarity determination module 73 is also used to determine a first similarity between the text strings in the target address information and the custom address of the waybill address information; determine a second similarity between the numeric strings in the target address information and the custom address of the waybill address information; determine a similarity adjustment coefficient between the target address information and the waybill address information based on the name of the logistics entity; and determine the similarity between the target address information and the waybill address information based on the first similarity, the second similarity and the similarity adjustment coefficient.

[0112] In one embodiment, the similarity determination module 73 is further used to extract multiple character strings that do not contain numbers and have the same first and last characters as text strings from the custom addresses of the target address information and the waybill address information respectively; and determine the first similarity of the text strings based on the Levenshtein ratio of the multiple text strings.

[0113] In one embodiment, the similarity determination module 73 is also used to calculate the edit distances of multiple text strings; the edit distance of the replacement operation in the edit distance is not equal to the edit distances between the insertion operation and the deletion operation; the largest edit distance is selected from the multiple edit distances as the target edit distance; the target edit distance is used to determine the Levenshtein ratio of the text string.

[0114] In one embodiment, the similarity determination module 73 is further configured to extract multiple digital feature values ​​from the digital character string respectively; perform weighted operation on the multiple digital feature values ​​according to weights corresponding to the multiple digital feature values ​​to obtain a second similarity of the digital character string.

[0115] In one embodiment, the similarity determination module 73 is further used to obtain the number of strokes of the name of the logistics entity; perform a weighted operation on the number of strokes according to the weight corresponding to the number of strokes to obtain a similarity adjustment coefficient.

[0116] For the specific definition of the logistics subject matching device based on logistics information, please refer to the definition of the logistics subject matching method based on logistics information above, which will not be repeated here. Each module in the above-mentioned logistics subject matching device based on logistics information can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0117] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store logistics subject matching data based on logistics information. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a logistics subject matching method based on logistics information is implemented.

[0118] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0119] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0120] Obtain the target address information of the logistics entity, and obtain multiple waybill address information to be matched from the logistics information; the target address information and waybill address information include urban area information and custom address;

[0121] Extract corresponding character strings from the target address information and the custom addresses of multiple waybill address information respectively;

[0122] Obtain the similarity between the corresponding character strings in the target address information and the waybill address information to obtain the similarity between the target address information and the waybill address information;

[0123] From multiple waybill address information whose similarity with the target address information reaches a preset threshold, determine the waybill address information that matches the logistics entity.

[0124] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining a preset address information dictionary file; identifying urban area information from the target address information and the waybill address information respectively through the address information dictionary file; and using the address information in the target address information and the waybill address information, except for the urban area information, as a custom address.

[0125] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining a first similarity between the text character strings in the target address information and the custom address of the waybill address information; determining a second similarity between the numeric character strings in the target address information and the custom address of the waybill address information; determining a similarity adjustment coefficient between the target address information and the waybill address information based on the name of the logistics entity; determining the similarity between the target address information and the waybill address information based on the first similarity, the second similarity and the similarity adjustment coefficient.

[0126] In one embodiment, when the processor executes the computer program, the following steps are also implemented: extracting multiple character strings that do not contain numbers and have the same first and last characters from the custom addresses of the target address information and the waybill address information as text strings; and determining the first similarity of the text strings based on the Levenshtein ratio of the multiple text strings.

[0127] In one embodiment, when the processor executes the computer program, the following steps are also implemented: calculating the edit distances of multiple text strings; the edit distance of the replacement operation in the edit distance is not equal to the edit distances between the insertion operation and the deletion operation; selecting the largest edit distance from the multiple edit distances as the target edit distance; the target edit distance is used to determine the Levenshtein ratio of the text string.

[0128] In one embodiment, when the processor executes the computer program, the following steps are further implemented: extracting multiple digital feature values ​​from the digital character string respectively; performing weighted operation on the multiple digital feature values ​​according to weights corresponding to the multiple digital feature values ​​to obtain a second similarity of the digital character string.

[0129] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining the number of strokes of the name of the logistics entity; performing a weighted operation on the number of strokes according to the weight corresponding to the number of strokes to obtain a similarity adjustment coefficient.

[0130] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0131] Obtain the target address information of the logistics entity, and obtain multiple waybill address information to be matched from the logistics information; the target address information and waybill address information include urban area information and custom address;

[0132] Extract corresponding character strings from the target address information and the custom addresses of multiple waybill address information respectively;

[0133] Obtain the similarity between the corresponding character strings in the target address information and the waybill address information to obtain the similarity between the target address information and the waybill address information;

[0134] From multiple waybill address information whose similarity with the target address information reaches a preset threshold, determine the waybill address information that matches the logistics entity.

[0135] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining a preset address information dictionary file; identifying urban area information from the target address information and the waybill address information respectively through the address information dictionary file; and using the address information in the target address information and the waybill address information, except for the urban area information, as a custom address.

[0136] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining a first similarity between the text strings in the target address information and the custom address of the waybill address information; determining a second similarity between the numeric strings in the target address information and the custom address of the waybill address information; determining a similarity adjustment coefficient between the target address information and the waybill address information based on the name of the logistics entity; determining the similarity between the target address information and the waybill address information based on the first similarity, the second similarity and the similarity adjustment coefficient.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: extracting multiple character strings that do not contain numbers and have the same first and last characters from the custom addresses of the target address information and the waybill address information as text strings; determining the first similarity of the text strings based on the Levenshtein ratio of the multiple text strings.

[0138] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: calculating the edit distances of multiple text strings; the edit distance of the replacement operation in the edit distance is not equal to the edit distances between the insertion operation and the deletion operation; selecting the largest edit distance from the multiple edit distances as the target edit distance; the target edit distance is used to determine the Levenshtein ratio of the text string.

[0139] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: extracting multiple digital feature values ​​from the digital character string respectively; performing weighted operation on the multiple digital feature values ​​according to the weights corresponding to the multiple digital feature values ​​to obtain the second similarity of the digital character string.

[0140] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the number of strokes of the name of the logistics entity; performing a weighted operation on the number of strokes according to the weight corresponding to the number of strokes to obtain a similarity adjustment coefficient.

[0141] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0142] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0143] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A logistics subject matching method based on logistics information, characterized in that: The method comprises: Obtaining the target address information of the logistics entity, and obtaining multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban area information and a custom address; the custom address is the address information filled in by custom filling in the target address information and the waybill address information, except for the urban area information; Extracting corresponding character strings from the target address information and the custom addresses of the plurality of waybill address information respectively; the character strings include text character strings and numeric character strings; Acquire the similarity between the corresponding character strings in the target address information and the waybill address information to obtain the similarity between the target address information and the waybill address information; Determining the waybill address information matching the logistics entity from the multiple waybill address information whose similarity with the target address information reaches a preset threshold; The obtaining the similarity between the corresponding character strings in the target address information and the waybill address information to obtain the similarity between the target address information and the waybill address information includes: Determining a first similarity between the target address information and the text string in the custom address of the waybill address information; Determining a second similarity between the target address information and the numeric character string in the custom address of the waybill address information; Acquire the number of strokes of the name of the logistics entity, and perform a weighted operation on the number of strokes according to a weight corresponding to the number of strokes to obtain the similarity adjustment coefficient; The similarity between the target address information and the waybill address information is determined according to the first similarity, the second similarity, and the similarity adjustment coefficient.

2. The method according to claim 1, characterized in that After obtaining the target address information of the logistics entity and obtaining multiple waybill address information to be matched from the logistics information, it also includes: Get the preset address information dictionary file; Using the address information dictionary file, identifying the urban area information from the target address information and the waybill address information respectively; The address information filled in by user-defined in the target address information and the waybill address information, except for the urban area information, is used as the custom address.

3. The method according to claim 1, characterized in that The determining of the first similarity between the target address information and the text string in the custom address of the waybill address information includes: Extracting a plurality of character strings without numbers and with the same first and last characters from the custom addresses of the target address information and the waybill address information as the text character strings; A first similarity of the text strings is determined based on the Levenshtein ratio of the plurality of text strings.

4. The method according to claim 3, characterized in that Before determining the first similarity between the target address information and the text string in the custom address of the waybill address information, the method includes: Calculating the edit distances of the plurality of text strings; wherein the edit distance of the replacement operation in the edit distance is not equal to the edit distances between the insertion operation and the deletion operation; The largest edit distance is selected from the plurality of edit distances as a target edit distance; the target edit distance is used to determine the Levenshtein ratio of the text string.

5. The method according to claim 1, characterized in that The determining of the second similarity between the target address information and the digital character string in the custom address of the waybill address information includes: Extracting multiple digital feature values ​​from the digital character strings respectively; A weighted operation is performed on the multiple digital feature values ​​according to the weights corresponding to the multiple digital feature values ​​to obtain a second similarity of the digital character string.

6. A logistics subject matching device based on logistics information, characterized in that: The device comprises: The address information acquisition module is used to acquire the target address information of the logistics entity, and to acquire multiple waybill address information to be matched from the logistics information; the target address information and the waybill address information include urban area information and a custom address; the custom address is the address information filled in by custom filling in the target address information and the waybill address information, except for the urban area information; A character string extraction module, used to extract corresponding character strings from the target address information and the custom addresses of the plurality of waybill address information respectively; the character strings include text character strings and numeric character strings; A similarity determination module, used to obtain the similarity between the corresponding character strings in the target address information and the waybill address information, and obtain the similarity between the target address information and the waybill address information; An address information matching module, used to determine the waybill address information matching the logistics entity from a plurality of waybill address information whose similarity with the target address information reaches a preset threshold; The similarity determination module is further used to determine a first similarity between the target address information and the text string in the custom address of the waybill address information; determine a second similarity between the target address information and the numeric string in the custom address of the waybill address information; obtain the number of strokes of the name of the logistics entity, perform a weighted operation on the number of strokes according to the weight corresponding to the number of strokes, and obtain the similarity adjustment coefficient; determine the similarity between the target address information and the waybill address information based on the first similarity, the second similarity and the similarity adjustment coefficient.

7. The device according to claim 6, characterized in that The address information matching module is further used to obtain a preset address information dictionary file; and identify the urban area information from the target address information and the waybill address information respectively through the address information dictionary file; The address information filled in by user-defined in the target address information and the waybill address information, except for the urban area information, is used as the custom address.

8. The device according to claim 6, characterized in that The similarity determination module is also used to extract multiple character strings that do not contain numbers and have the same first and last characters as the text character strings from the custom addresses of the target address information and the waybill address information respectively; and determine the first similarity of the text character strings based on the Levenshtein ratio of the multiple text character strings.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images