Address type identification method, correlation analysis method and device

Abstract

The invention discloses an address type identification method and a correlation analysis method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining historical logistics order data in response to a received address type identification request; according to a preset screening rule, order screening is carried out on the historical logistics order data to obtain effective logistics orders to be subjected to address type identification, address data in the effective logistics orders are extracted, and the address data have transaction item category labels; and determining the address type of the address data according to the pre-acquired planning data of the commercial place and the residence place and the transaction item type label of the address data. According to the embodiment, identification of the fine-grained address type is realized, computing resources are reduced, and the identification efficiency is improved; and a specific address can be accurately obtained, and high-quality data support is provided for subsequent commuting analysis.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an address type recognition method, a correlation analysis method and a device. Background Art

[0002] With the rapid development of the economy, the formulation of strategies such as urban industrial layout, transportation planning, and commercial site selection has become particularly important. Effectively identifying the geographical distribution of residents' workplace commercial addresses and residential addresses helps to understand the spatial characteristics of the city from the perspectives of work-residence balance and commuting behavior, and reasonably guides urban industrial layout, transportation planning, commercial site selection, and logistics station configuration. Existing technologies mainly determine the trajectory of personnel through signaling data, and identify whether the address type of the personnel's stay is a commercial address or a residential address by counting the length of stay.

[0003] In the process of implementing the present invention, the inventors found that the prior art has the following problems:

[0004] The signaling data receives a large amount of spatiotemporal reporting data through the base station. The data scale is large, and analysis and statistics require high computing resources. In addition, the type of location of a person determined by the base station signal is not accurate enough. It can only be determined to the grid block level of the geocoding, and cannot be accurate to the specific address granularity, which is not conducive to subsequent data analysis. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide an address type identification method, a related analysis method and a device, which realize economical, efficient and fine-grained identification of address types. Since Internet logistics order data is far less than mobile device report data, identifying the address type of address data in logistics orders not only reduces computing resources and improves identification efficiency; it can also be accurate to the specific address, providing high-quality data support for subsequent commuting analysis.

[0006] To achieve the objective, according to a first aspect of an embodiment of the present invention, a method for identifying an address type is provided, comprising:

[0007] In response to receiving the address type identification request, obtaining historical logistics order data;

[0008] According to the preset screening rules, the historical logistics order data is screened to obtain valid logistics orders for which address type identification is to be performed, and address data in the valid logistics orders is extracted, wherein the address data has a transaction item category label;

[0009] The address type of the address data is determined according to pre-acquired planning data of commercial and residential locations and a transaction item category label of the address data.

[0010] Optionally, after obtaining the historical logistics order data, the method further includes: standardizing the addresses in the historical logistics order data.

[0011] Optionally, before standardizing the addresses in the historical logistics order data, the method further includes: performing element segmentation on the address data of each order data in the historical logistics order data, and obtaining street elements and point of interest elements in each order data; performing text clustering on the street elements and point of interest elements in each order data, and identifying similar street elements representing the same street in each order data, and similar point of interest elements representing the same point of interest, so as to standardize the similar street elements and the similar point of interest elements.

[0012] Optionally, after identifying similar street elements representing the same street and similar point of interest elements representing the same point of interest in each of the order data, the method further includes: using the latitude and longitude information of the destination in each of the order data to verify the similar street elements and the similar point of interest elements.

[0013] Optionally, the historical logistics order data is screened according to preset screening rules, including: according to preset order quantity screening rules, taking the recipient as a dimension, screening the logistics orders whose order quantities meet the order quantity screening rules from the historical logistics order data; according to preset transaction item category screening rules, screening the logistics orders that meet the order quantity screening rules by transaction item category; and conducting self-purchase behavior verification on the logistics orders that meet the transaction item category screening rules, thereby screening out logistics orders with self-purchase behavior.

[0014] Optionally, the commercial and residential places defined in the planning data are based on the granularity of points of interest, and the address types include commercial addresses and residential addresses; the address type of the address data is determined based on the pre-acquired planning data of the commercial and residential places, and the transaction item category label of the address data, including: matching the points of interest in the address data and the planning data to obtain a reference type of the address data, the reference type having a corresponding transaction item category label set; judging whether the transaction item category label of the address data belongs to the transaction item category label set; in response to the transaction item category label of the address data belonging to the transaction item category label set, using the reference type as the address type of the address data; in response to the transaction item category label of the address data not belonging to the transaction item category label set, determining the address type of the address data according to the transaction item category label of the address data.

[0015] According to a second aspect of an embodiment of the present invention, a commuting analysis method based on address type is provided, comprising:

[0016] Taking the logistics order to which the identified address data having the address type belongs as an analysis sample, wherein the address type is determined according to any method of the first aspect of the embodiment of the present invention;

[0017] Based on the analysis sample, construct a workplace-residence address knowledge graph for characterizing workplace commercial addresses and residential addresses associated with personnel;

[0018] Based on the work-residence address knowledge graph, the work-residence commuting data of people in a specified geographical area is analyzed.

[0019] Optionally, based on the analysis sample, a work-residence-address knowledge graph is constructed, including: extracting recipient and address data from the analysis sample, taking the recipient and the address data as entities, and the order number as the associated edge between the entities, to form a personnel work-residence-address knowledge graph, wherein the address data has an address category label.

[0020] Optionally, after constructing the work-residence-address knowledge graph, the method further includes: searching whether there are identical entities in the work-residence-address knowledge graph; if there are identical entities in the work-residence-address knowledge graph, merging the identical entities to obtain a fused work-residence-address knowledge graph.

[0021] Optionally, after constructing the work-residence address knowledge graph, the method further includes: querying the number of address data with the same address category associated with each recipient in the work-residence address knowledge graph; when the recipient is associated with multiple address data with the same address category, retaining one address data according to the number of order numbers and order time of the associated edges.

[0022] Optionally, based on the work-residence address knowledge graph, the work-residence commuting data of people in a specified geographical area is analyzed, including: searching for entities in the work-residence address knowledge graph that fall within the specified geographical area, obtaining the persons to be analyzed in the knowledge graph subgraph, and the workplace commercial addresses and residential addresses associated with the persons to be analyzed; based on the workplace commercial addresses and the residential addresses, analyzing and calculating the commuting data of the persons to be analyzed.

[0023] According to a third aspect of an embodiment of the present invention, there is provided a device for identifying an address type, including:

[0024] An order acquisition module, for acquiring historical logistics order data in response to receiving an address type identification request;

[0025] An address extraction module, used to perform order screening on the historical logistics order data according to preset screening rules, obtain valid logistics orders to be identified by address type, and extract address data from the valid logistics orders, wherein the address data has a transaction item category label;

[0026] The address type identification module is used to determine the address type of the address data based on pre-acquired planning data of commercial and residential places and the transaction item category label of the address data.

[0027] According to a fourth aspect of an embodiment of the present invention, there is provided a commuting analysis device based on address type, comprising:

[0028] An analysis sample determination module, used to use the logistics order to which the identified address data having an address type belongs as an analysis sample, wherein the address type is determined according to any one of the methods according to claims 1 to 6;

[0029] A graph construction module, for constructing a knowledge graph of workplace and residential addresses corresponding to a person based on the analysis sample;

[0030] The commuting analysis module is used to analyze the work-residence commuting data of people in a specified geographical area based on the work-residence address knowledge graph.

[0031] According to a fifth aspect of an embodiment of the present invention, there is provided an electronic address type identification device and a related commuting analysis device, including:

[0032] one or more processors;

[0033] a storage device for storing one or more programs,

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the methods provided in the first aspect and the second aspect of the embodiments of the present invention.

[0035] According to a sixth aspect of an embodiment of the present invention, there is provided a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method provided by the first aspect and the second aspect of the embodiment of the present invention is implemented.

[0036] According to a seventh aspect of the embodiments of the present invention, a computer program product is provided. A computer program product of the embodiments of the present application includes a computer program, and when the program is executed by a processor, the method provided by the first and second aspects of the embodiments of the present invention is implemented.

[0037] An embodiment of the invention has the following advantages or beneficial effects: by responding to receiving an address type identification request, historical logistics order data is obtained; according to preset screening rules, the historical logistics order data is screened to obtain valid logistics orders to be subjected to address type identification, and the address data in the valid logistics orders is extracted, wherein the address data has a transaction item category label; according to the pre-acquired commercial and residential planning data, and the transaction item category label of the address data, a technical solution for determining the address type of the address data is implemented, thereby realizing an economical, efficient and fine-grained address type identification method. Since Internet logistics order data is far less than mobile device reporting data, address type identification of address data in logistics orders not only reduces computing resources and improves identification efficiency; but also can be accurate to the specific address, providing high-quality data support for subsequent commuting analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0039] Figure 1 is a schematic diagram of the main process of the method for identifying the address type according to an embodiment of the present invention;

[0040] Figure 2 is a schematic diagram of the main process of the commuting analysis method based on address type according to an embodiment of the present invention;

[0041] Figure 3 It is a schematic diagram of the overall process of the address type identification and commuting analysis method according to an embodiment of the present invention;

[0042] Figure 4 is a schematic diagram of main modules of an address type identification device according to an embodiment of the present invention;

[0043] Figure 5 is a schematic diagram of main modules of a commuting analysis device based on address type according to an embodiment of the present invention;

[0044] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0045] Figure 7 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0046] It should be noted that in the technical solution of the present invention, the collection / collection, update, analysis, use, transmission, storage and other aspects of user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside of these legal uses, and are subject to supervision and management by national regulatory authorities. Necessary measures should be taken for user personal information to selectively block the use or access to personal information data to prevent illegal access to such personal information data, ensure that persons who have access to personal information data comply with the provisions of relevant laws and regulations, and ensure the security of user personal information. In addition, once these user personal information data are no longer needed, the risks should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0047] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0048] The existing signaling data receives a large amount of spatiotemporal reporting data through base stations. The data scale is large, and analysis and statistics require high computing resources. In addition, the address type of the person's location determined by the base station signal is not accurate enough. It can only be determined to the grid block level of the geocoding, and cannot be accurate to the specific address granularity, which is not conducive to subsequent data analysis and cannot meet practical applications well.

[0049] In order to solve the above problems existing in the prior art, the present invention proposes a method for identifying address types, which uses the address data of valid logistics orders in the recent historical logistics order data, and identifies the address type of the address data according to the pre-acquired planning data and the transaction category label of the address data. An economical, efficient and fine-grained address type identification method is implemented. Since the Internet logistics order data is far less than the mobile device reporting data, the address type identification of the address data in the logistics order not only reduces the computing resources and improves the identification efficiency; but also can be accurate to the specific address, providing high-quality data support for subsequent commuting analysis.

[0050] In the introduction to the embodiments of the present invention, the terms and their meanings are as follows:

[0051] POI: The abbreviation of "Point of Interest". In a geographic information system, a POI can be a house, a shop, a mailbox, a bus stop, etc.

[0052] Figure 1FIG. 1 is a schematic diagram of the main process of the method for identifying the address type according to an embodiment of the present invention. Figure 1 As shown, the method for identifying the address type according to the embodiment of the present invention includes the following steps S101 to S103.

[0053] Step S101: In response to receiving an address type identification request, historical logistics order data is obtained.

[0054] Specifically, considering the rapid development of e-commerce in recent years, the scale of e-commerce users has continued to grow, and the coverage rate of express delivery stations has continued to increase. The embodiment of the present invention makes full use of Internet logistics order data, and uses the addresses in the logistics order data as the residents' stay, and then identifies the address type. When the system receives an address type identification request, it extracts the e-commerce logistics order data in the recent period through the interactive interface with the Internet logistics order database. The e-commerce logistics order data usually includes the name of the transaction item, the category of the transaction item, the user information of the ordering user, the name of the recipient, the mobile phone number of the recipient, the receiving address, and the longitude and latitude of the receiving place. The embodiment of the present invention uses all the logistics order data of all users on the entire network in the past 6 months as historical logistics order data.

[0055] According to one embodiment of the present invention, after acquiring the historical logistics order data, the method further includes: standardizing the addresses in the historical logistics order data.

[0056] Specifically, in order to facilitate the subsequent identification of address types and improve the identification efficiency, after obtaining the historical logistics order data, the addresses in the historical logistics order data need to be standardized. Specifically, standardization can be achieved by encoding the address text. First, the address data in the historical logistics order data is identified by elements, and the province, city, district, street, point of interest POI, and house number are identified. Then, the address is encoded according to the ID pre-defined for each element. In particular, for the house number, the house number can be extracted based on the textual expression content of the house number through pattern recognition according to the meaningful numbers in it for house number encoding. For example, BuildNum: 12 Building | Unit: 2 Unit | O: 1 | O: 6 | O: 0 | O: 5 | O: Room |, the house number encoding result is: 12_2_1605.

[0057] According to another embodiment of the present invention, before standardizing the addresses in the historical logistics order data, the method further includes: performing element segmentation on the address data of each order data in the historical logistics order data, and obtaining street elements and point of interest elements in each of the order data; performing text clustering on the street elements and point of interest elements in each of the order data, and identifying similar street elements representing the same street in each of the order data, and similar point of interest elements representing the same point of interest, so as to standardize the similar street elements and the similar point of interest elements.

[0058] Specifically, considering that the addresses in the logistics order data are edited by the ordering user personally, there may be non-standard wording, such as abbreviations of roads and community names, or individual typos. Therefore, before standardizing the addresses in the historical logistics order data, the address data of each order data in the historical logistics order data is segmented. The street elements and point of interest (POI) elements in the address data are extracted through the address entity extraction model; the street elements and POI elements extracted from each order data in the historical logistics order data are subjected to text clustering to determine whether each street element describes the same street object and whether each POI element describes the same POI object, so that the same ID can be used for subsequent address standardization coding. For example, A Home Community, A Home, A, A Home District 1, these segmented and extracted POI elements are clustered into similar point of interest elements through text clustering, and then the same ID is used for address standardization coding in the future.

[0059] According to another embodiment of the present invention, after identifying similar street elements representing the same street and similar point of interest elements representing the same point of interest in each of the order data, the method further includes: using the longitude and latitude information of the destination in each of the order data to verify the similar street elements and the similar point of interest elements.

[0060] Specifically, after identifying the same street elements representing the same street and the same point of interest elements representing the same point of interest in each order data, in order to ensure the accuracy of the clustering results, the longitude and latitude of the destination in the order data are used to verify the same street elements and the same point of interest elements obtained by clustering. Verify whether the longitude and latitude of the destination of the order data corresponding to the same street elements are located on the same street in the map, and verify whether the longitude and latitude of the destination of the order data corresponding to the same point of interest elements are located at the same point of interest in the map, such as a residential area, a shopping mall, an office building, etc.

[0061] Step S102: perform order screening on the historical logistics order data according to preset screening rules to obtain valid logistics orders for which address type identification is to be performed, and extract address data from the valid logistics orders, wherein the address data has a transaction item category label.

[0062] Specifically, considering that the present invention is mainly used to obtain the geographical distribution characteristics of the workplace commercial address and residential address of personnel, and the Internet logistics order data will have some noisy logistics order data, for example, the address data is too general and only involves the village or street name, and does not involve the logistics order data of the specific house number or street number. According to the address hierarchy screening rules, it is judged whether the address data in the historical logistics order data meets the hierarchy requirements, and the logistics orders corresponding to the address data that do not meet the hierarchy requirements are deleted, and the valid logistics orders that meet the address hierarchy screening rules are screened out, and the address data in the valid logistics orders are extracted. In addition, the transaction item category in the logistics order data is instructive for the identification of the address type. For example, the transaction item category of office supplies is usually used in the workplace, correspondingly, corresponding to the workplace commercial address, and the transaction item category of household goods is usually used for residential daily use, correspondingly, corresponding to the residential address, so the transaction item category in the valid logistics order is marked in the form of a label on the corresponding address data. It should be noted that usually one address data will have multiple logistics orders and, accordingly, multiple transaction item categories. The transaction item category label of the address data in an embodiment of the present invention selects the transaction item category with the largest proportion in all logistics orders of the address data as the transaction item category label of the address data.

[0063] According to one embodiment of the present invention, the historical logistics order data is screened according to preset screening rules, including: according to preset order quantity screening rules, with recipients as dimensions, screening the logistics orders whose order quantities meet the order quantity screening rules from the historical logistics order data; according to preset transaction item category screening rules, screening the logistics orders that meet the order quantity screening rules for transaction item category; and conducting self-purchase behavior verification on the logistics orders that meet the transaction item category screening rules, thereby screening out logistics orders with self-purchase behavior.

[0064] Specifically, in addition to the above-mentioned cases where the addresses are relatively general and not detailed enough, the historical logistics order data obtained may also involve malicious orders, or a small number of orders from individual inactive users; orders where the correlation between the transaction category and the address type is unclear, for example, if the office workplace type needs to be identified, then the correlation between orders for books and flowers and the workplace type is unclear; and orders for helping others place orders, or for sending gifts to others. For these orders that have no direct significance for the identification of the address type of the present invention, in order to improve the recognition efficiency, reduce the amount of calculation, and avoid the interference of invalid data, these orders with unclear office and home daily characteristics are ignored, and valid logistics orders that are directly meaningful to the present invention and can be used for address type identification are screened out from the historical logistics order data.

[0065] Furthermore, based on business experience, a reasonable order quantity threshold is set. For each recipient, the order quantity of the recipient in the historical logistics order data is counted. If the order quantity is within the order quantity threshold, it means that the order is a logistics order for a normal transaction. The embodiment of the present invention sets the order quantity threshold 5≤S≤500, that is, the orders of users with a small number of orders with less than 5 times and risky users with more than 500 orders are screened out, and the order data of normal users are retained.

[0066] Similarly, the transaction item categories with obvious correlation are determined according to the address type, and the determined transaction item categories are set as the screening rules. For example, orders of office supplies and daily necessities are used as the transaction item category screening rules, and orders of office supplies and daily necessities are screened out from the above-mentioned normal transaction logistics orders.

[0067] Similarly, it is also necessary to identify from the existing orders whether they are self-purchased orders. Specifically, this can be done by comparing the mobile phone number of the ordering account and the mobile phone number of the recipient, and treating orders with the same mobile phone number as self-purchased orders, thus filtering out orders of self-purchased behavior.

[0068] It is understandable that the order of the above three methods of screening orders can be arbitrarily changed as needed. The embodiment of the present invention only specifically describes one execution order. It is also possible to first screen the transaction item category, then screen the recipient's order quantity, and finally screen the self-purchase behavior; it is also possible to first screen the self-purchase behavior, then screen the order from the transaction item category, and finally screen the order from the recipient's order quantity. The present invention does not make specific limitations.

[0069] Step S103: Determine the address type of the address data according to the pre-acquired planning data of the commercial and residential areas and the transaction item category label of the address data.

[0070] Specifically, considering that municipal planning data has clear commercial and residential types, there are inevitably special cases, such as studios in residential areas, etc. Therefore, based on the transaction item category labels of planning data and address data, the real address type corresponding to the address data extracted from the valid logistics order can be accurately determined.

[0071] According to one embodiment of the present invention, the commercial and residential places defined in the planning data are based on the granularity of points of interest, and the address types include commercial addresses and residential addresses; the address type of the address data is determined based on the pre-acquired planning data of the commercial and residential places, and the transaction item category label of the address data, including: matching the points of interest in the address data and the planning data to obtain a reference type of the address data, the reference type having a corresponding transaction item category label set; determining whether the transaction item category label of the address data belongs to the transaction item category label set; in response to the transaction item category label of the address data belonging to the transaction item category label set, using the reference type as the address type of the address data; in response to the transaction item category label of the address data not belonging to the transaction item category label set, determining the address type of the address data according to the transaction item category label of the address data.

[0072] Specifically, text matching is performed between the points of interest POI of the address data in the above-mentioned valid logistics order and the planning data to obtain the reference type of the address data, that is, whether the POI in the address data is defined as a commercial address type or a residential address type in the planning data. For example, the point of interest POI of the address data is found to be a commercial location in the planning data, so the reference type is the commercial address type. It can be understood that each POI in the planning data may be defined in the form of a code, so the POI code after the above-mentioned standardized encoding of the address data can be used to match the code in the planning data to improve the matching efficiency. At this time, the reference type obtained is only the work-residence type of the POI, and the address data in the logistics order is refined to the next level house number of the POI, so it is also necessary to proofread the reference type in combination with the transaction item category label of the address data.

[0073] It can be understood that the reference type is a commercial address type or a residential address type. The embodiment of the present invention pre-assigns all corresponding matching transaction product category labels to the reference type of commercial address type, forming a transaction product category label set corresponding to the commercial address type; and assigns all corresponding matching transaction product category labels to the reference type of residential address type, forming a transaction product category label set corresponding to the residential address type. For example, the transaction product category label set corresponding to the residential address type includes: household daily necessities, clothing, beauty, toys, maternal and child products, pet products, etc.

[0074] Further, it is determined whether the transaction product category label of the address data belongs to the transaction product category label set corresponding to the reference type, that is, whether the transaction product category of the current address data is a subset of the transaction product category label set. If the transaction product category label of the address data belongs to the transaction product category label set, then the reference type can be directly used as the address type of the address data; otherwise, since the definition of the transaction product category label is determined by the type of transaction product with the largest purchase ratio in the address data, the corresponding address type is determined according to the transaction product category label at this time. For example, a studio in a residential community, the reference work-residence type of the community is a residential address, but the transaction product category label of the address data of the house number is office supplies, then the address data of the house number is determined to be a commercial address. It can be understood that since the definition of the transaction product category label is determined by the type of transaction product with the largest purchase ratio in the address data, and the workplace type POI has a settlement management mechanism, the transaction product category labels of the specific addresses of each company and unit in the workplace type POI are usually office supplies.

[0075] It can be understood that according to the recognition results of the above-mentioned address types, the corresponding address code is searched from the address codes that are standardized for the addresses in the historical logistics order data, and the recognition results are marked on the address code, so that the corresponding job-residence type can be directly queried through the standardized code of the address in the order data in the future.

[0076] Based on the above-mentioned address category identification method, the present invention also provides a commuting analysis method based on address type. Figure 2 FIG. 4 is a schematic diagram of the main process of the commuting analysis method based on address type according to an embodiment of the present invention. Figure 2 As shown, the commuting analysis method based on address type according to an embodiment of the present invention includes the following steps S201 to S203.

[0077] Step S201: taking the logistics orders to which the identified address data with the work-residence type belongs as analysis samples, wherein the address type is determined according to any one of the above-mentioned address type identification methods.

[0078] Specifically, based on the above-mentioned recognition results of the address type of the address data in the valid order data, the logistics orders to which the address data with the address type belongs are statistically identified, and these logistics orders are used as analysis samples for subsequent commuting analysis.

[0079] Step S202: construct a workplace-residence address knowledge graph for characterizing workplace commercial addresses and residential addresses associated with personnel based on the analysis sample.

[0080] Specifically, taking the recipient as the extraction unit, the recipient's corresponding workplace business address data and residential address data are extracted from the analysis sample, the workplace business address data and residential address data are combined into a knowledge graph subgraph of the recipient, and the corresponding order number is recorded on the address data. The knowledge graph subgraphs of all recipients constitute the workplace and residential address knowledge graph of the embodiment of the present invention.

[0081] According to one embodiment of the present invention, a work-residence-address knowledge graph is constructed based on the analysis sample, including: extracting recipient and address data from the analysis sample, taking the recipient and the address data as entities, and order numbers as associated edges between the entities, to form a personnel work-residence-address knowledge graph, wherein the address data has an address category label.

[0082] Specifically, the address data of the recipient and the recipient are extracted from the logistics order analysis sample, and the recipient and the corresponding address data are taken as entities, wherein the address data is marked with the above-identified address category, and the order number is the association edge between the two entities to construct the work-residence address knowledge graph. It should be noted that there is only one association edge between the two entities. When the recipient places an order to the address data multiple times before and after, multiple order numbers can be recorded on this association edge. It can be understood that in the work-residence knowledge graph, there will inevitably be individual personnel who are only associated with the workplace commercial address or only associated with the residential address. The knowledge graph subgraph, this incomplete knowledge graph subgraph can be used to assist in determining the address type when other personnel are associated with the same address entity. In addition, when constructing the work-residence knowledge graph, the determined workplace commercial address can also be used to construct the work-residence knowledge graph. Specifically, the workplace commercial address can be used to find the person associated with it, and then the residential address associated with the person can be found. This can effectively reduce the number of such incomplete knowledge graph subgraphs.

[0083] According to another embodiment of the present invention, after constructing the work-residence-address knowledge graph, the method further includes: searching whether there are identical entities in the work-residence-address knowledge graph; if there are identical entities in the work-residence-address knowledge graph, performing entity fusion on the identical entities to obtain a fused work-residence-address knowledge graph.

[0084] Specifically, based on the person entities and address entities in the work-residence-address knowledge graph constructed above, find out whether there are identical entities in the work-residence-address knowledge graph. For person entities, you can determine whether they are the same person entity by finding out whether the recipient's mobile phone number is the same. For address entities, you can determine whether they are the same address entity by finding out whether the standardized address codes of the address entities are the same. For identical entities found, merge the identical entities. For example, if Mr. Li and Li Si have the same mobile phone number, then Mr. Li and Li Si belong to the same entity. Mr. Li and Li Si, as well as the address entities associated with Mr. Li and Li Si, are merged. The specific name of the entity after the fusion can be determined by merging, selecting the best, or correcting errors according to the situation, and the embodiments of the present invention do not make specific limitations.

[0085] Through the above-mentioned entity fusion of the work-residence address knowledge graph, the work-residence address knowledge graph is streamlined, the complexity of the work-residence address knowledge graph is reduced, and the efficiency of subsequent commuting analysis is improved.

[0086] According to another embodiment of the present invention, after constructing the work-residence address knowledge graph, the method further includes: querying the number of address data with the same address category associated with each recipient in the work-residence address knowledge graph; when the recipient is associated with multiple address data with the same address category, retaining one address data according to the number of order numbers and order time of the associated edges.

[0087] Specifically, considering that the recipient may have multiple residential addresses or multiple workplace business addresses in the historical logistics orders due to relocation or job changes, after constructing the workplace and residence address knowledge graph, the number of residential addresses associated with each recipient in the graph and the number of workplace and business addresses are queried. If there are multiple residential addresses and / or multiple workplace and business addresses associated, the latest residential address and / or business address with more than a preset number of order numbers is retained according to the number of order numbers and order time of the associated edges, and the entities and associated edges of other uncommon address data are deleted. The preset number in the embodiment of the present invention is 3. Of course, if the number of order numbers does not reach 3, the address data of the latest order number is retained as the commonly used address data. It can be understood that this step can also be performed in the fused workplace and residence address knowledge graph after the above-mentioned entity fusion.

[0088] Step S203: Analyze the work-residence commuting data of people in a specified geographical area based on the work-residence address knowledge graph.

[0089] According to one embodiment of the present invention, based on the work-residence address knowledge graph, the work-residence commuting data of people in a specified geographical area is analyzed, including: searching the knowledge graph subgraph whose entities fall into the specified geographical area from the work-residence address knowledge graph, obtaining the persons to be analyzed in the knowledge graph subgraph, and the workplace commercial addresses and residential addresses associated with the persons to be analyzed; based on the workplace commercial addresses and residential addresses, analyzing and calculating the commuting data of the persons to be analyzed.

[0090] Specifically, based on the work-residence address knowledge graph constructed above, according to the designated geographic area in the received analysis request, the work-residence address knowledge graph is searched for the knowledge graph subgraph whose address entity falls within the designated geographic area, and the person entity to be analyzed in the knowledge graph subgraph is obtained, and then the workplace commercial address and residential address associated with the person to be analyzed are obtained. Based on the obtained workplace commercial address and residential address of the person, the commuting data between the work and residence of the person in the designated area, such as commuting distance and commuting time, is analyzed and calculated through relevant commuting data analysis tools, and then the work-residence balance analysis of the person is performed.

[0091] Exemplarily, the above-mentioned designated geographical area can also be a certain community, a certain POI, or even a company address. Taking the company's workplace address as the designated analysis object, the knowledge graph subgraph of the company's address is searched from the knowledge graph of the personnel's work and residence address to obtain the employees associated with the company's address and the employees' residential addresses. Then calculate the commuting distance of the company's employees, estimate the public transportation commuting time and commuting cost through the commuting data calculation tool, and obtain the commuting data between the work and residence. Based on the employees' work-residence commuting data, for communities with a large number of employees, longer average commuting distances and commuting times, and higher commuting costs, the employees' residences are clustered to obtain the main residential addresses, which are then used for the company's shuttle bus planning, employee carpooling, commuting subsidies, flexible office and other employee benefits.

[0092] Exemplarily, the residential area can also be used as the designated analysis object, and the knowledge graph subgraph of the residential address can be searched from the work-residence address knowledge graph to obtain the commuting residents associated with the residential address and the workplace and commercial addresses of each commuting resident. Then calculate the commuting data of the commuting residents, such as commuting distance and commuting time. Based on the work-residence commuting data of the commuting residents, for communities with a large number of commuting residents and longer average commuting distances and commuting times, the workplace and commercial addresses of the commuting residents in the community are clustered to obtain the main workplace and commercial addresses, which are then used to determine which communities need to add public transportation line stations or provide more convenient public transportation services to meet the commuting needs of residents.

[0093] Exemplarily, the work-residence address knowledge graph of the embodiment of the present invention can also be used to analyze the work-residence balance across geographical regions. According to the specified geographical area, the knowledge graph subgraph whose address entity falls into the geographical area is searched, and the associated person to be analyzed and another address data associated with the person to be analyzed are obtained to obtain the workplace commercial address and residential address of the person to be analyzed. Then count the proportion of people whose workplace commercial address and residential address are both in the geographical area, as well as the proportion of people who commute across regions. For areas with a relatively high proportion of cross-regional commuting, count the number of people flowing in (living in other areas, working in this area) and out (living in this area, working in other areas). This information can be used to optimize transportation services between designated areas during peak hours in the morning and evening, such as increasing commuter vehicles and other operations.

[0094] Figure 3 The present invention is a schematic diagram of the overall process of the address type identification and commuting analysis method of the embodiment of the present invention. According to the received address type identification request, the system extracts the historical logistics order data of the past 6 months from the Internet logistics data; by segmenting the address data of each order data in the historical logistics order data and performing text clustering processing, the same type of street elements and the same type of interest point elements are identified; at the same time, the house number of the element segmentation is identified and standardized; based on the same type of street elements and the same type of interest point elements, the address data in the order data is overall standardized. Valid logistics orders to be identified for address category are screened out from the historical logistics order data, and the address data in the valid logistics orders are extracted. According to the acquired planning data and the transaction item category label of the address data, the address data is identified as the workplace commercial address and the residential address, and the identification result is used as the address type of the address data. All logistics orders with address types in the valid logistics orders are used as analysis samples; according to the analysis samples, a knowledge graph of work-residence address is constructed; and then, according to the knowledge graph of work-residence address, the commuting data of people in the specified geographical area is calculated, and the balanced distribution analysis of the workplace and residence of the people is performed.

[0095] In summary, the embodiments of the present invention use historical logistics order data to identify whether a person's delivery address is a workplace commercial address or a residential address, and construct a workplace-residence address knowledge graph based on the identified address type, to obtain the workplace commercial address and residential address of the person in a specified geographical area, so as to conduct a balanced distribution analysis of the person's workplace and residence, providing a new method for address type identification and commuting analysis of personnel, which not only saves computing resources but also can be accurate to the specific address, so as to achieve more accurate correlation analysis of the person's workplace and residence.

[0096] Figure 4 FIG. 2 is a schematic diagram of the main modules of the device for identifying the address type according to an embodiment of the present invention. Figure 4As shown, the address type identification device 400 mainly includes an order acquisition module 401, an address extraction module 402 and an address type identification module 403.

[0097] The order acquisition module 401 is used to acquire historical logistics order data in response to receiving an address type identification request;

[0098] The address extraction module 402 is used to perform order screening on the historical logistics order data according to a preset screening rule, obtain a valid logistics order to be identified by address type, and extract address data from the valid logistics order, wherein the address data has a transaction item category label;

[0099] The address type identification module 403 is used to determine the address type of the address data according to the pre-acquired planning data of the commercial and residential places and the transaction item category label of the address data.

[0100] According to an embodiment of the present invention, the address type identification device 400 further includes an address standardization module (not shown in the figure), which is used to: after acquiring the historical logistics order data, perform standardization processing on the addresses in the historical logistics order data.

[0101] According to another embodiment of the present invention, the address type identification device 400 also includes an address preprocessing module (not shown in the figure), which is used to: before standardizing the addresses in the historical logistics order data, perform element segmentation on the address data of each order data in the historical logistics order data, and obtain the street elements and point of interest elements in each of the order data; perform text clustering on the street elements and point of interest elements in each of the order data, and identify similar street elements representing the same street in each of the order data, and similar point of interest elements representing the same point of interest, so as to standardize the similar street elements and the similar point of interest elements.

[0102] According to another embodiment of the present invention, the address type identification device 400 also includes a verification module (not shown in the figure) for verifying the same type of street elements and the same type of point of interest elements using the longitude and latitude information of the delivery location in each of the order data.

[0103] According to another embodiment of the present invention, the address extraction module 402 is further used for: according to a preset order quantity screening rule, taking the recipient as a dimension, screening the logistics orders whose order quantity meets the order quantity screening rule from the historical logistics order data; according to a preset transaction item category screening rule, screening the logistics orders that meet the order quantity screening rule for transaction item category; and conducting a self-purchase behavior check on the logistics orders that meet the transaction item category screening rule, to screen out logistics orders with self-purchase behavior.

[0104] According to another embodiment of the present invention, the commercial and residential places defined in the planning data are based on the granularity of points of interest, and the address types include commercial addresses and residential addresses; the address type identification module 403 is also used to: match the points of interest in the address data with the planning data to obtain a reference type of the address data, the reference type having a corresponding transaction item category label set; determine whether the transaction item category label of the address data belongs to the transaction item category label set; in response to the transaction item category label of the address data belonging to the transaction item category label set, use the reference type as the address type of the address data; in response to the transaction item category label of the address data not belonging to the transaction item category label set, determine the address type of the address data according to the transaction item category label of the address data.

[0105] Figure 5 FIG. 1 is a schematic diagram of the main modules of the commuting analysis device based on address type according to an embodiment of the present invention. Figure 5 As shown, the address type-based commuting analysis device 500 mainly includes an analysis sample determination module 501 , a graph construction module 502 and a commuting analysis module 503 .

[0106] An analysis sample determination module 501 is used to use the logistics order to which the identified address data with an address type belongs as an analysis sample, wherein the address type is determined according to any method according to claims 1 to 6;

[0107] A graph construction module 502, for constructing a knowledge graph of workplace and residence addresses for representing the workplace and residence addresses corresponding to the personnel according to the analysis sample;

[0108] The commuting analysis module 503 is used to analyze the work-residence commuting data of people in a specified geographical area based on the work-residence address knowledge graph.

[0109] According to one embodiment of the present invention, the graph construction module 502 is also used to: extract recipient and address data from the analysis sample, take the recipient and the address data as entities, and the order number as the associated edge between the entities to form a personnel work-residence-address knowledge graph, and the address data is marked with an address category.

[0110] According to another embodiment of the present invention, the address type-based commuting analysis device 500 also includes a fusion module (not shown in the figure), which is used to: after constructing the work-residence address knowledge graph, search whether there are identical entities in the work-residence address knowledge graph; if there are identical entities in the work-residence address knowledge graph, fuse the identical entities to obtain a fused work-residence address knowledge graph.

[0111] According to another embodiment of the present invention, the address type-based commuting analysis device 500 also includes an address number review module (not shown in the figure), which is used to: after constructing the work-residence address knowledge graph, query the number of address data with the same address category associated with each recipient in the work-residence address knowledge graph; when the recipient is associated with multiple address data with the same address category, retain one address data based on the number of order numbers and order time of the associated edges.

[0112] According to another embodiment of the present invention, the commuting analysis module 503 is further used to: search for entities in the knowledge graph subgraph that fall within the specified geographical area from the work-residence address knowledge graph, obtain the persons to be analyzed in the knowledge graph subgraph, and the workplace commercial addresses and residential addresses associated with the persons to be analyzed; and analyze and calculate the commuting data of the persons to be analyzed based on the workplace commercial addresses and the residential addresses.

[0113] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention can be applied.

[0114] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0115] Users can use terminal devices 601, 602, 603 to interact with server 605 through network 604 to receive or send messages, etc. Terminal devices 601, 602, 603 can be installed with various communication client applications, such as address type identification applications, etc. (only for example).

[0116] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0117] Server 605 may be a server that provides various services, such as a background management server that provides support for the identification and analysis of address types performed by users using terminal devices 601, 602, and 603 (for example only). The background management server may obtain historical logistics order data in response to receiving an address type identification request; perform order screening on the historical logistics order data according to preset screening rules to obtain valid logistics orders to be identified for address types, extract address data from the valid logistics orders, wherein the address data has a transaction item category label; determine the address type of the address data according to the pre-acquired planning data of the commercial and residential areas, and the transaction item category label of the address data, and feed back the processing results (such as address type, etc. - for example only) to the terminal device.

[0118] It should be noted that the address type identification method provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the address type identification device is generally set in the server 605 .

[0119] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0120] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. Figure 7 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0121] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 to a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0122] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0123] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0124] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0125] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be arranged in a processor, for example, it may be described as follows: a processor includes an order acquisition module, an address extraction module and an address type identification module.

[0127] The names of these modules do not, in some cases, constitute a limitation on the modules themselves. For example, the order acquisition module can also be described as "a module for acquiring historical logistics order data in response to receiving an address type identification request."

[0128] On the other hand, the present invention also provides a computer-readable medium, which may be included in the device described in the embodiment; or it may exist independently without being assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the device includes: in response to receiving an address type identification request, obtaining historical logistics order data; according to preset screening rules, performing order screening on the historical logistics order data to obtain valid logistics orders to be identified for address type, extracting address data from the valid logistics orders, wherein the address data has a transaction item category label; determining the address type of the address data according to the pre-acquired planning data of the commercial and residential places, and the transaction item category label of the address data.

[0129] The technical solution according to the embodiment of the present invention has the following advantages or beneficial effects: by responding to receiving an address type identification request, historical logistics order data is obtained; according to preset screening rules, the historical logistics order data is screened to obtain valid logistics orders to be subjected to address type identification, and the address data in the valid logistics orders is extracted, wherein the address data has a transaction item category label; according to the pre-acquired commercial and residential planning data, and the transaction item category label of the address data, the technical solution of determining the address type of the address data realizes an economical, efficient and fine-grained address type identification method. Since the Internet logistics order data is far less than the mobile device reporting data, the address type identification of the address data in the logistics order not only reduces the computing resources and improves the identification efficiency; but also can be accurate to the specific address, providing high-quality data support for subsequent commuting analysis.

[0130] The specific implementation methods described herein do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A method for identifying an address type, characterized in that: include: In response to receiving the address type identification request, obtaining historical logistics order data; According to the preset screening rules, the historical logistics order data is screened to obtain valid logistics orders for which address type identification is to be performed, and address data in the valid logistics orders is extracted, wherein the address data has a transaction item category label; The address type of the address data is determined according to pre-acquired planning data of commercial and residential places and a transaction item category label of the address data.

2. The method according to claim 1, characterized in that After obtaining the historical logistics order data, the method further includes: The addresses in the historical logistics order data are standardized.

3. The method according to claim 2, characterized in that Before standardizing the addresses in the historical logistics order data, the method further includes: Performing element segmentation on the address data of each order data in the historical logistics order data, and obtaining street elements and point of interest elements in each order data; Text clustering is performed on the street elements and point of interest elements in each of the order data to identify similar street elements representing the same street and similar point of interest elements representing the same point of interest in each of the order data, so as to standardize the similar street elements and similar point of interest elements.

4. The method according to claim 3, characterized in that After identifying the same type of street elements representing the same street and the same type of point of interest elements representing the same point of interest in each of the order data, the method further includes: The similar street elements and the similar point of interest elements are verified using the longitude and latitude information of the delivery location in each of the order data.

5. The method according to claim 1, characterized in that According to the preset screening rules, the historical logistics order data is screened, including: According to a preset order quantity screening rule, with the recipient as a dimension, screening the logistics orders whose order quantity meets the order quantity screening rule from the historical logistics order data; According to the preset transaction item category screening rules, the logistics orders that meet the order quantity screening rules are screened for transaction item categories; The selected logistics orders that meet the transaction item category screening rules are checked for self-purchase behavior, and the logistics orders with self-purchase behavior are screened out.

6. The method according to claim 1, characterized in that The commercial and residential areas defined in the planning data are based on points of interest as granularity, and the address types include commercial addresses and residential addresses; determining the address type of the address data according to the pre-acquired planning data of the commercial and residential areas and the transaction item category label of the address data includes: Matching the points of interest in the address data with the planning data to obtain a reference type of the address data, wherein the reference type has a corresponding transaction item category label set; Determine whether the transaction item category label of the address data belongs to the transaction item category label set; in response to the transaction item category label of the address data belonging to the transaction item category label set, use the reference type as the address type of the address data; in response to the transaction item category label of the address data not belonging to the transaction item category label set, determine the address type of the address data according to the transaction item category label of the address data.

7. A commuting analysis method based on address type, characterized in that: include: Taking the logistics order to which the identified address data with the address type belongs as an analysis sample, wherein the address type is determined according to any one of the methods according to claims 1 to 6; Based on the analysis sample, construct a workplace-residence address knowledge graph for characterizing workplace commercial addresses and residential addresses associated with personnel; Based on the work-residence address knowledge graph, the work-residence commuting data of people in a specified geographical area is analyzed.

8. The method according to claim 7, characterized in that Based on the analysis sample, a knowledge graph of work-residence address is constructed, including: Recipient and address data are extracted from the analysis sample, and the recipient and address data are used as entities, and the order number is used as the associated edge between the entities to form a personnel work-residence-address knowledge graph, and the address data is marked with an address category.

9. The method according to claim 8, characterized in that After constructing the work-residence address knowledge graph, the method further includes: Find out whether there is the same entity in the work-residence-address knowledge graph; When there are identical entities in the job-residence-address knowledge graph, the identical entities are fused to obtain a fused job-residence-address knowledge graph.

10. The method according to claim 8, characterized in that After constructing the work-residence-address knowledge graph, the method further includes: Querying the number of address data with the same address category associated with each recipient in the work-residence address knowledge graph; In the case where the recipient is associated with multiple address data with the same address category, one address data is retained according to the number of order numbers and order time of the associated edges.

11. The method according to claim 8, characterized in that According to the work-residence address knowledge graph, the work-residence commuting data of people in the specified geographical area is analyzed, including: Searching the knowledge graph subgraph whose entity falls within the specified geographical area from the work-residence address knowledge graph, obtaining the person to be analyzed in the knowledge graph subgraph, and the workplace business address and residential address associated with the person to be analyzed; The commuting data of the person to be analyzed is analyzed and calculated based on the workplace business address and the residential address.

12. A device for identifying an address type, characterized in that: include: An order acquisition module, for acquiring historical logistics order data in response to receiving an address type identification request; An address extraction module, used to perform order screening on the historical logistics order data according to preset screening rules, obtain valid logistics orders to be identified by address type, and extract address data from the valid logistics orders, wherein the address data has a transaction item category label; The address type identification module is used to determine the address type of the address data based on pre-acquired planning data of commercial and residential places and the transaction item category label of the address data.

13. A commuting analysis device based on address type, characterized in that: include: An analysis sample determination module, used to use the logistics order to which the identified address data having an address type belongs as an analysis sample, wherein the address type is determined according to any one of the methods according to claims 1 to 6; A graph construction module, for constructing a knowledge graph of workplace and residence addresses for representing the workplace and residence addresses corresponding to the personnel according to the analysis sample; The commuting analysis module is used to analyze the work-residence commuting data of people in a specified geographical area based on the work-residence address knowledge graph.

14. A mobile electronic device terminal, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 11.

15. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images