Target category object recognition method and device, computer device, and storage medium
By dividing regions based on order addresses and performing similarity matching, the problem of being unable to identify enterprise orders in logistics services has been solved, achieving efficient identification and processing of target category objects.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SF DIGITAL TECH (SHENZHEN) TECH SERVICE CO LTD
- Filing Date
- 2021-05-25
- Publication Date
- 2026-06-09
AI Technical Summary
Logistics service providers are unable to effectively identify corporate logistics orders submitted in the name of individuals, resulting in low processing efficiency.
By dividing the order object into regional groups based on the address information, and matching them with the regional information of the target category object, similarity matching technology is used to determine whether the order object belongs to the target category object.
This improves the efficiency of identifying target categories of objects, ensuring the accuracy and efficiency of logistics order processing.
Smart Images
Figure CN115392603B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of information processing technology, and in particular to a method, apparatus, computer device, and storage medium for identifying target category objects. Background Technology
[0002] In user services, taking logistics services as an example, logistics orders can be divided into different categories, such as individual users and corporate organizations. Different categories of users have different needs for order services. Therefore, service providers will provide differentiated services for different users to meet the service needs of all parties.
[0003] However, in real-world applications, service recipients may submit orders under different identities. For example, a company member may submit a logistics order for the company in their personal capacity. In this case, the logistics service provider cannot provide services that meet the actual needs of these service recipients, resulting in low processing efficiency for these logistics orders. Therefore, there is an urgent need for a method that can identify whether the object corresponding to the order is a target category object based on the order information. Summary of the Invention
[0004] Therefore, it is necessary to provide a method, apparatus, computer device, and storage medium for identifying target category objects that can effectively identify the aforementioned technical problems.
[0005] A method for identifying target category objects, the method comprising:
[0006] Based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, order objects belonging to the same region are grouped into the same group according to the region to which the address belongs, resulting in multiple order object groups;
[0007] Extract the target category objects and region information contained in each target category information obtained, and group the target category objects with the same region information into the same group to obtain multiple target category object groups;
[0008] Based on the regional information corresponding to each order object group and each target category object group, the order object groups and target category object groups belonging to the same region are selected from the multiple order object groups and the multiple target category object groups respectively.
[0009] The similarity of the order objects in the group of order objects to be matched with the target category objects in the group of target category objects to be matched is performed, and the order objects are determined to be new target category objects based on the matching results.
[0010] In one embodiment, the method further includes:
[0011] The object group of orders to be matched is matched with the object group of target categories to be matched to obtain the object group matching result;
[0012] The step of performing similarity matching between order objects in the group of order objects to be matched and target category objects in the group of target category objects to be matched, and determining whether the order object is a newly added target category object based on the matching result, includes:
[0013] When the object group matching result meets the object group matching condition, the order object in the order object group to be matched is matched with the target category object in the target category object group to be matched, and the order object is determined to be a newly added target category object based on the matching result.
[0014] In one embodiment, the step of performing object group matching between the group of order objects to be matched and the group of target category objects to be matched, to obtain object group matching results, includes:
[0015] The object identifiers in the group of order objects to be matched are matched with the object identifiers in the group of target category objects to be matched, and the successfully matched object identifier groups are determined.
[0016] When the object group matching result meets the object group matching condition, the order objects in the order object group to be matched are matched with the target category objects in the target category object group to be matched for similarity. Based on the matching result, it is determined whether the order object is a newly added target category object, including:
[0017] When the number of successfully matched object identifier groups meets the quantity condition, the order objects corresponding to the successfully matched object identifier groups and the target category objects are matched for similarity. Based on the matching results, it is determined whether the corresponding order object is a newly added target category object.
[0018] In one embodiment, the step of grouping order objects belonging to the same region according to the region to which the address belongs into the same group, resulting in multiple order object groups, includes:
[0019] The address is format-standardized, the obtained format-standardized address data is converted into latitude and longitude, and multiple regional units are obtained by dividing the preset area into units according to latitude and longitude.
[0020] Based on the regional unit to which the address belongs, the order objects corresponding to addresses belonging to the same regional unit are grouped into the same group, resulting in multiple order object groups.
[0021] In one embodiment, the plurality of region units have equal areas.
[0022] In one embodiment, the step of extracting the target category objects and region information contained in each acquired target category information, and grouping target category objects with the same region information into the same group to obtain multiple target category object groups includes:
[0023] Extract the target category object and target category code from each piece of target category information obtained;
[0024] Based on the position of the region code in the target category code, the region code is extracted from the target category code;
[0025] Target category objects with the same region code are grouped together to obtain multiple target category object groups.
[0026] In one embodiment, the method further includes:
[0027] Based on the object information corresponding to the newly added target category objects, construct a new target category object table;
[0028] The object information in the newly added target category object table is matched with the obtained target category object sample data, and the number of newly added target category objects that fail to match in the newly added target category object table is counted.
[0029] The availability of the new target category object table is determined based on the proportion of the number of newly added target category objects that failed to match to the total number of newly added target category objects in the new target category object table.
[0030] A device for identifying target category objects, the device comprising:
[0031] The order object group construction module is used to divide the order objects corresponding to the target order and the addresses corresponding to the order objects extracted from the target order into the same group according to the region to which the address belongs, thereby obtaining multiple order object groups;
[0032] The target category object group construction module is used to extract the target category objects and region information contained in each piece of target category information obtained, and to divide the target category objects with the same region information into the same group to obtain multiple target category object groups;
[0033] The object group filtering module is used to filter out the order object groups and target category object groups that belong to the same region from the multiple order object groups and the multiple target category object groups based on the regional information corresponding to each order object group and each target category object group.
[0034] The object matching module is used to perform similarity matching between the order objects in the order object group to be matched and the target category objects in the target category object group to be matched, and to determine whether the order object is a newly added target category object based on the matching result.
[0035] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:
[0036] Based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, order objects belonging to the same region are grouped into the same group according to the region to which the address belongs, resulting in multiple order object groups;
[0037] Extract the target category objects and region information contained in each target category information obtained, and group the target category objects with the same region information into the same group to obtain multiple target category object groups;
[0038] Based on the regional information corresponding to each order object group and each target category object group, the order object groups and target category object groups belonging to the same region are selected from the multiple order object groups and the multiple target category object groups respectively.
[0039] The similarity of the order objects in the group of order objects to be matched with the target category objects in the group of target category objects to be matched is performed, and the order objects are determined to be new target category objects based on the matching results.
[0040] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0041] Based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, order objects belonging to the same region are grouped into the same group according to the region to which the address belongs, resulting in multiple order object groups;
[0042] Extract the target category objects and region information contained in each target category information obtained, and group the target category objects with the same region information into the same group to obtain multiple target category object groups;
[0043] Based on the regional information corresponding to each order object group and each target category object group, the order object groups and target category object groups belonging to the same region are selected from the multiple order object groups and the multiple target category object groups respectively.
[0044] The similarity of the order objects in the group of order objects to be matched with the target category objects in the group of target category objects to be matched is performed, and the order objects are determined to be new target category objects based on the matching results.
[0045] The aforementioned method, apparatus, computer equipment, and storage medium for identifying target category objects, based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, group order objects belonging to the same region according to the region to which the address belongs, resulting in multiple order object groups; extracting the target category object and region information contained in each piece of target category information, grouping target category objects with the same region information into the same group, resulting in multiple target category object groups, thereby realizing the grouping of order objects and target category objects by region; based on the region information corresponding to each order object group and each target category object group, filtering out order object groups and target category object groups belonging to the same region from multiple order object groups and multiple target category object groups respectively; performing similarity matching between the order objects in the order object group to be matched and the target category objects in the target category object group to be matched, and determining whether the order object is a newly added target category object based on the matching result. Based on order information and target category information, and by utilizing the relationship between the corresponding areas of order objects and target category objects, it is possible to determine whether an order object in the order information is a newly added target category object, thereby improving the efficiency of identifying target category objects. Attached Figure Description
[0046] Figure 1 This is an application environment diagram of a target category object recognition method in one embodiment;
[0047] Figure 2 This is a flowchart illustrating a method for identifying target category objects in one embodiment;
[0048] Figure 3 This is a flowchart illustrating a method for identifying target category objects in another embodiment;
[0049] Figure 4 This is a flowchart illustrating the method for identifying target category objects in another embodiment;
[0050] Figure 5 This is a flowchart illustrating the method for identifying target category objects in yet another embodiment;
[0051] Figure 6 Here is a flowchart illustrating the method for identifying target category objects in one embodiment;
[0052] Figure 7 This is a structural block diagram of a target category object recognition device in one embodiment;
[0053] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0055] The target category object identification method provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. Server 104, based on the order objects corresponding to the target orders provided by terminal 102 and the addresses corresponding to the order objects extracted from the target orders, groups order objects belonging to the same region according to the region of the address, resulting in multiple order object groups. Server 104 extracts the target category objects and region information contained in each piece of target category information, groups target category objects with the same region information into the same group, resulting in multiple target category object groups. Based on the region information corresponding to each order object group and each target category object group, server 104 filters out order object groups and target category object groups belonging to the same region from the multiple order object groups and multiple target category object groups, respectively. Server 104 performs similarity matching between the order objects in the order object groups and the target category objects in the target category object groups, determines whether the order object is a newly added target category object based on the matching result, and feeds back the determination result to terminal 102.
[0056] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets and portable wearable devices, and the server 104 can be implemented by a standalone server or a server cluster consisting of multiple servers.
[0057] In one embodiment, such as Figure 2 As shown, a method for identifying target category objects is provided, which can be applied to... Figure 1 Taking the server in the example, the following steps are included:
[0058] Step 202: Based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, the order objects belonging to the same region are grouped into the same group according to the region to which the address belongs, resulting in multiple order object groups.
[0059] The target order can be an order whose order object needs to be determined to belong to a target category object. A target category is a category for which the order service provider offers a specific service to the service recipient. The server stores a set of target category objects, consisting of order objects corresponding to target category orders, to record order objects belonging to the target category. It should be noted that, based on the target category object identification method, it is possible to determine whether order objects corresponding to the target order that are not in the target category object set belong to a newly added target category object. For ease of description, the following embodiments use the example of an individual user as the target order object, an enterprise as the target category, and an enterprise user as the target category object to illustrate the target category object identification method. It can be understood that in other embodiments, the order object and the target category object can also be other categories.
[0060] Order information for individual users can be encrypted and anonymized, containing information that reflects the individual user's characteristics. This information includes both user and item information; for example, in a food delivery order, user information might include the orderer's name, phone number, and delivery address, while item information might include the specific food name, quantity, and price. Similarly, in a logistics order, user information might include the sender's / recipient's name, phone number, and sender / recipient's address, while item information might include the specific name, quantity, and weight of the items being sent or received.
[0061] Taking a logistics order as an example, the order objects corresponding to the target order include the recipient and the sender. The addresses extracted from the target order that correspond to the order objects include the recipient's receiving address and the sender's sending address. It should be noted that the recipient and receiving address in the same order belong to the same set of user information, while the sender's name and sending address belong to another set of user information. In this application, all embodiments use the same set of user information as an example for illustration.
[0062] Furthermore, based on the region to which the address belongs, order objects belonging to the same region are grouped into the same group, resulting in multiple order object groups.
[0063] Among them, the region can be a geographical unit that is pre-divided into a certain range according to the address location. Specifically, the region can be an administrative region, a street area, a community jurisdiction, or a region limited by latitude and longitude. The pre-defined region can be determined according to the approximate area where the enterprise members to be identified are located.
[0064] In this embodiment, the resulting geographical units can be of equal or unequal size. The geographical units should be as small as possible to facilitate the aggregation of order information based on user addresses and the identification of the corresponding enterprise users within each geographical unit. If the preset region is an administrative district, the regional unit can be an area formed between streets, or it can be an office building or industrial park, etc.
[0065] In a specific application, based on the characteristics of a preset area and the registered or actual operating addresses of businesses within that area, the preset area is divided into as small and independent as possible regional units, such as an office building or a technology park. Based on user addresses, all user information corresponding to the same area is grouped into the same group, resulting in multiple user information groups.
[0066] Step 204: Extract the target category objects and region information contained in each target category information obtained, and group the target category objects with the same region information into the same group to obtain multiple target category object groups.
[0067] The server can acquire multiple pieces of target category information, which can be obtained from a publicly available system for specified category information. A target category object refers to an object recorded in the target category information that can generate order transactions with the order service provider under different identities. For example, a corporate member generating order transactions with the order service provider under an individual identity and a corporate member identity.
[0068] Taking enterprise registration information as an example, the target category of information refers to the registration and operation information of an enterprise that can be obtained from public systems, including annual reports, news, credit information, company directories, and shareholder information. From enterprise registration information, one can identify the company name, enterprise code (such as the unified social credit code), company address, names, positions, and contact information of company members.
[0069] Since a single enterprise may include multiple members, and the goal of this solution is to identify these members, to ensure accuracy during information processing, the corresponding member information is determined separately for each member included in the enterprise's business registration information. For example, if an enterprise's business registration information includes President A, General Manager B, and Business Department Supervisor C, then corresponding member information is created for President A, General Manager B, and Business Department Supervisor C respectively. The member information corresponding to President A, General Manager B, and Business Department Supervisor C may have the same enterprise code and address, but their names will be different.
[0070] In a specific application, the server groups enterprise member information with the same regional information into the same group based on the regional information carried in the target category information, resulting in an enterprise member information table that includes multiple enterprise member information groups.
[0071] Specifically, enterprise registration information includes the enterprise code. Taking the Unified Social Credit Code as an example, the Unified Social Credit Code is the "identity card" of legal persons and other organizations. For instance, the standard stipulates that the Unified Social Credit Code is represented by 18 Arabic numerals or uppercase English letters, namely, 1 digit of the registration management department code, 1 digit of the organization category code, 6 digits of the administrative division code of the registration management authority, 9 digits of the subject identification code, and 1 digit of the check code. Among them, the regional information carried by the enterprise code can be the 6-digit administrative division code of the registration management authority. By grouping enterprise member information with the same regional information into the same group, the classification of enterprise member information with the same administrative division code of the registration management authority is realized, thus obtaining an enterprise member information table including multiple enterprise member information groups.
[0072] Step 206: Based on the regional information corresponding to each order object group and each target category object group, select the order object groups and target category object groups that belong to the same region from multiple order object groups and multiple target category object groups.
[0073] Specifically, the region information corresponding to the order object group refers to the region information of the common region to which the addresses corresponding to the order objects in the order object group belong. The region information corresponding to the target category object group refers to the region information of the target category objects in the target category object group. Order object groups and target category object groups to be matched that belong to the same region refer to order object groups and target category object groups that have the same region information.
[0074] It should be noted that the regions corresponding to the order object group and the target category object group can be regions divided based on latitude and longitude, regions divided based on administrative regions, or regions defined in other ways, as long as the same regional division standard is used for the regions corresponding to the order objects in the order object group and the regions corresponding to the target category objects in the target category object group.
[0075] Step 208: Perform similarity matching between the order objects in the order object group to be matched and the target category objects in the target category object group to be matched, and determine whether the order object is a newly added target category object based on the matching result.
[0076] Specifically, the similarity comparison between order objects and target category objects can be carried out from multiple perspectives. For example, the same type of information content in the order objects and target category objects, or the number of objects with the same name in the order object group to be matched and the target category object group to be matched.
[0077] In a specific application, the server can filter user information corresponding to a user address and enterprise member information corresponding to an enterprise by using user addresses and enterprises with the same region. By comparing the similarity between user information and enterprise member information, it can determine whether the user information corresponds to a newly added enterprise member.
[0078] The aforementioned method for identifying target category objects is based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order. Order objects belonging to the same address region are grouped together, resulting in multiple order object groups. From each piece of target category information, the target category object and region information are extracted, and target category objects with the same region information are grouped together, resulting in multiple target category object groups. This achieves grouping of order objects and target category objects by region. Based on the region information corresponding to each order object group and each target category object group, matching order object groups and matching target category object groups belonging to the same region are selected from the multiple order object groups and multiple target category object groups. Similarity matching is performed between the order objects in the matching order object groups and the target category objects in the matching target category object groups. The matching result determines whether the order object is a newly added target category object. Using order information and target category information as a foundation, and leveraging the relationship between the regions corresponding to order objects and target category objects, the method determines whether an order object in the order information is a newly added target category object, improving the efficiency of target category object identification.
[0079] In one embodiment, the method further includes: performing object group matching between the order object group to be matched and the target category object group to be matched, to obtain the object group matching result;
[0080] The similarity matching process involves comparing order objects in the group of order objects to be matched with target category objects in the group of target category objects to be matched. Based on the matching results, it is determined whether an order object belongs to a newly added target category object, including:
[0081] When the object group matching result meets the object group matching condition, the order object in the order object group to be matched is matched with the target category object in the target category object group to be matched, and the similarity is matched. Based on the matching result, it is determined whether the order object is a newly added target category object.
[0082] Among them, object group matching can be performed by matching the object identifiers in the object group of the order to be matched with the object identifiers in the object group of the target category to be matched, and determining the object identifier group that is successfully matched.
[0083] In this embodiment, matching is first performed according to object groups. If the object group matching result meets the object group matching conditions, further object matching is performed. By setting multiple conditions, it is determined whether the order object is a newly added target category object, which improves the accuracy of the determination result.
[0084] In a specific application, multiple user information groups constitute a user information table, and multiple enterprise member information groups constitute an enterprise member information table. When the user information table and the enterprise member information table contain target user addresses and target enterprise addresses with the same region, the user information group containing the target user address matches the enterprise member information group containing the target enterprise address, and the user information corresponding to the target user address matches the enterprise member information corresponding to the target enterprise address, the user corresponding to the user information corresponding to the target user address is determined as a new enterprise member.
[0085] To determine whether a user is a new enterprise member, several conditions must be met. First, the user information table and the enterprise member information table must contain target user addresses and target enterprise addresses in the same region. Second, the user information group containing the target user address and the enterprise member information group containing the target enterprise address must meet information group matching criteria. This matching criterion can be the existence of at least two pairs of users and enterprise members with the same name, contact information, or other unique identification information. Third, the user information corresponding to the target user address and the enterprise member information corresponding to the target enterprise address must meet information matching criteria. This matching criterion can be the same type of information content in the user information and enterprise member information, or a similarity threshold. It should be noted that if all three conditions are met, the user is considered a new enterprise member; if any one condition is not met, the user is not considered a new enterprise member.
[0086] In this embodiment, multiple conditions are set to determine whether a user is a newly added enterprise member, thereby improving the accuracy of the determination results.
[0087] It should be noted that the above conditions can be judged sequentially or simultaneously. For example, the three conditions can be judged in the order of the first, second, and third conditions. If the first condition is not met, the second and third conditions are not judged. In another embodiment, two of the above conditions can be judged simultaneously, for example, the second and third conditions can be judged simultaneously.
[0088] In one embodiment, the object group to be matched is matched with the object group to be matched target category to obtain the object group matching result, including: matching the object identifiers in the object group to be matched with the object identifiers in the object group to be matched target category to determine the successfully matched object identifier group;
[0089] When the object group matching result meets the object group matching condition, the order objects in the order object group to be matched are matched with the target category objects in the target category object group to be matched. Based on the matching result, it is determined whether the order object is a newly added target category object. This includes: when the number of successfully matched object identifier groups meets the quantity condition, the order objects corresponding to the successfully matched object identifier groups are matched with the target category objects. Based on the matching result, it is determined whether the corresponding order objects are newly added target category objects.
[0090] In a specific application, when the server detects that there are target user addresses and target enterprise addresses with the same region in the user information table and the enterprise member information table, it retrieves the user names from the user information group containing the target user address and the enterprise member names from the enterprise member information group containing the target enterprise address. If there are at least two pairs of users and enterprise members with the same names in both the user information group containing the target user address and the enterprise member information group containing the target enterprise address, it extracts the user information corresponding to the target user address and the enterprise member information corresponding to the target enterprise address. It then calculates the similarity between the user information corresponding to the target user address and the enterprise member information corresponding to the target enterprise address. If the similarity meets a preset similarity condition, the user corresponding to the user information corresponding to the target user address is identified as a new enterprise member.
[0091] In one embodiment, based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, order objects belonging to the same region are grouped into the same group according to the region to which the address belongs, resulting in multiple order object groups. That is, step 202 includes steps 302 to 306.
[0092] Step 302: Determine the order object corresponding to the target order, and extract the address corresponding to the order object from the target order;
[0093] Step 304: Standardize the address format, convert the obtained standardized address data into latitude and longitude, and obtain multiple regional units by dividing the preset area according to latitude and longitude.
[0094] Step 306: Based on the regional unit to which the address belongs, the order objects corresponding to the addresses belonging to the same regional unit are divided into the same group, resulting in multiple order object groups.
[0095] Specifically, standardized address data is the result of standardizing addresses using the same format, such as expressing them in a standardized way like province-city-district-street-community format. Latitude and longitude information enables a unified data display format for addresses, allowing for accurate determination of the area unit to which an address belongs.
[0096] In one embodiment, the target category objects and region information contained in each target category information are extracted respectively, and the target category objects with the same region information are divided into the same group to obtain multiple target category object groups. Step 204 includes steps 402 to 406.
[0097] Step 402: Extract the target category object and target category code from each piece of target category information obtained;
[0098] Step 404: Extract the region code from the target category code based on the position of the region code in the target category code;
[0099] Step 406: Group target category objects with the same region code into the same group to obtain multiple target category object groups.
[0100] The target category code can be the enterprise code in the enterprise's business registration information. The position of the region code within the enterprise code is fixed. Based on the position of the region code within the enterprise code, the region code is extracted from the enterprise code. Enterprise member information with the same region code is grouped together, resulting in an enterprise member information table comprising multiple enterprise member information groups.
[0101] Taking the enterprise code as the unified social credit code as an example, the unified social credit code is 18 digits long and is represented by Arabic numerals or English letters. It consists of five parts: the first part (the first digit) is the registration management department code; the second part (the second digit) is the taxpayer category code such as enterprise; the third part (the third to the eighth digit) is the administrative division code of the registration management authority; the fourth part (the ninth to the seventeenth digit) is the main body identification code; and the fifth part (the eighteenth digit) is the check code, which is automatically generated by the system.
[0102] In this embodiment, based on the position of the regional code in the enterprise code as the 3rd to 8th digits, the regional code is obtained by extracting the 3rd to 8th digits of the unified social credit code. Then, the enterprise member information with the same regional code is divided into the same group, corresponding to an enterprise member information group, thereby obtaining an enterprise member information table including multiple enterprise member information groups.
[0103] In one embodiment, the method for identifying target category objects further includes steps 502 to 506.
[0104] Step 502: Construct a new target category object table based on the object information corresponding to the newly added target category object;
[0105] Step 504: Match the object information in the newly added target category object table with the obtained target category object sample data, and count the number of newly added target category objects that failed to match in the newly added target category object table;
[0106] Step 506: Determine the availability of the new target category object table based on the proportion of the number of newly added target category objects that failed to match to the total number of newly added target category objects in the new target category object table.
[0107] In a specific application, the server constructs a new enterprise member table based on the user information and enterprise member information corresponding to the new enterprise member. The new enterprise member table is then matched with the obtained sample data of enterprise member information, and the number of new enterprise member information that fails to match is counted. The availability of the new enterprise member table is determined based on the proportion of the number of new enterprise member information that fails to match to the total number of new enterprise member information in the new enterprise member table.
[0108] The sample data of enterprise member information includes a pre-selected batch of known and correct enterprise member information. The information types of the sample data of enterprise member information include the various information types in the new enterprise member table. For example, the new enterprise member table includes company name, unified social credit code, name, position, contact number and registered address; the sample data of enterprise member information includes company name, unified social credit code, name, position, contact number, registered address and email.
[0109] Each record in the newly added enterprise member table is compared one-to-one with the information in the enterprise member information sample data. If all the information in a record in the newly added enterprise member table can be completely matched with a record in the enterprise member information sample data, then the record in the newly added enterprise member table is considered correct; if any record does not match, then the record is considered incorrect. The number of correct and incorrect records is counted, and the proportion of incorrect newly added enterprise member information to the total number of newly added enterprise member information in the newly added enterprise member table is calculated to obtain the accuracy rate. If the accuracy rate is within a preset reasonable range, then the newly added enterprise member table is considered usable; otherwise, the newly added enterprise member table is considered unusable.
[0110] To facilitate understanding of this application by those skilled in the art, the following will be combined with Figure 6 The present invention provides another embodiment to illustrate the method for identifying the target category object of this application. This embodiment includes the following steps:
[0111] S1. Extract the names, phone numbers, and addresses of senders and recipients of waybills within a preset area from the logistics waybill database.
[0112] S2. For the name and phone number extracted from S1, retain only the complete name (name) and the phone number with the correct number of digits (tel); parse the address extracted from S1, output the address in a standardized format (address), and convert the address into latitude and longitude (gps).
[0113] S3. Based on S1 and S2, establish a relational structure table a1 with name, tel, address, and gps; where the logistics waybill database contains personal user order information, the sender's and recipient's names, phone numbers, and addresses correspond to the user's name, contact number, and address, respectively. The relational structure table a1 can be a data format of order information.
[0114] S4. Divide the preset area into multiple area units of the same size according to latitude and longitude, and group the data in Table a1 into the corresponding area units according to the latitude and longitude correspondence, to obtain N groups b1, b2, b3...bN; where the N groups b1, b2, b3...bN are multiple user information groups corresponding to multiple areas.
[0115] S5. Extract the company name (company_name), unified social credit code (code), senior executive name (name) and corresponding position information, and company registered address from the publicly available business registration information database. The unified social credit code (code), senior executive name (name), and company registered address correspond to the company code, company member name, and company address, respectively.
[0116] S6. Parse the enterprise registration address extracted in S5, output the address in a standardized format (reg_address), and convert the address into latitude and longitude (gps);
[0117] S7. Based on S5 and S6, establish a relational structure table a2 with company_name, code, name, position, reg_address, and gps;
[0118] S8. Group the data in table a2 according to the unified social credit code to obtain N groups c1, c2, c3...cN, which correspond to N enterprise member information groups;
[0119] S9. Compare the addresses in table a1 with the addresses in table a2. When addressX and reg_addressX belong to the same administrative region, compare all names in group bX where addressX is located with all senior executive names in group cX where reg_addressX is located. If two or more names are identical in a certain group X, extract the entire data in table a1 corresponding to addressX and the entire data in table a2 corresponding to reg_addressX.
[0120] S10. Based on the data extracted in S9, comprehensively evaluate the data in tables a1 and a2 according to name and address, compare the similarity between the two, and assign a value to the similarity.
[0121] S11. Set a similarity threshold. When the threshold is reached, the data in table a1 and the data in table a2 can be considered to be from the same company and the same executive.
[0122] S12. Merge all data that has reached the threshold into table a3, using "name+code" as the primary key, and merge the data from tables a1 and a2 into table a3, i.e., company_name, code, name, tel, position, reg_address.
[0123] S13. Evaluate the accuracy of the data in table A3 by selecting a batch of known and correct sample data. The data content includes the information in table A3, such as: company name, unified social credit code, name, position, contact number and registered address.
[0124] S14. Compare the data in table a3 with the sample data one by one. If all the information of a data can be completely matched with the sample data, the data is considered correct. If any data cannot be matched, the data is considered incorrect. Count the number of correct and incorrect data.
[0125] S15. Calculate the accuracy rate of the data in table A3. Accuracy rate = number of correct rows / (number of correct rows + number of incorrect rows). If the accuracy rate is within a reasonable range, the data in table A3 is considered usable.
[0126] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.
[0127] In one embodiment, such as Figure 7 As shown, a target category object identification device is provided, including: an order object group construction module 702, a target category object group construction module 704, an object group filtering module 706, and an object matching module 708, wherein:
[0128] The order object group construction module 702 is used to group order objects belonging to the same region into the same group based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, thereby obtaining multiple order object groups.
[0129] The target category object group construction module 704 is used to extract the target category objects and region information contained in each piece of target category information, and to group target category objects with the same region information into the same group to obtain multiple target category object groups.
[0130] The object group filtering module 706 is used to filter out the order object groups and target category object groups that belong to the same region from multiple order object groups and multiple target category object groups based on the regional information corresponding to each order object group and each target category object group.
[0131] The object matching module 708 is used to perform similarity matching between the order objects in the order object group to be matched and the target category objects in the target category object group to be matched, and to determine whether the order object is a newly added target category object based on the matching result.
[0132] The aforementioned target category object identification device, based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, groups order objects belonging to the same region according to the region to which the address belongs, resulting in multiple order object groups. It extracts the target category object and region information contained in each piece of target category information, groups target category objects with the same region information together, resulting in multiple target category object groups. This achieves grouping of order objects and target category objects by region. Based on the region information corresponding to each order object group and each target category object group, it filters out matching order object groups and matching target category object groups belonging to the same region from the multiple order object groups and multiple target category object groups. It then performs similarity matching between the order objects in the matching order object groups and the target category objects in the matching target category object groups, and determines whether the order object is a newly added target category object based on the matching result. Using order information and target category information as a foundation, and leveraging the relationship between the regions corresponding to order objects and target category objects, it achieves the determination of whether an order object in the order information is a newly added target category object, improving the efficiency of target category object identification.
[0133] In one embodiment, the target category object identification device further includes an object group matching module, which is used to perform object group matching between the order object group to be matched and the target category object group to be matched, and obtain the object group matching result;
[0134] The object matching module is also used to perform similarity matching between the order objects in the order object group to be matched and the target category objects in the target category object group to be matched when the object group matching result meets the object group matching condition, and to determine whether the order object is a newly added target category object based on the matching result.
[0135] In one embodiment, the object group matching module is further configured to perform identifier matching between the object identifiers in the order object group to be matched and the object identifiers in the target category object group to be matched, and determine the successfully matched object identifier groups; the object matching module is further configured to perform similarity matching between the order objects corresponding to the successfully matched object identifier groups and the target category objects when the number of successfully matched object identifier groups meets the quantity condition, and determine whether the corresponding order objects are newly added target category objects based on the matching results.
[0136] In one embodiment, the order object group construction module is further configured to standardize the address format, convert the obtained standardized address data into latitude and longitude, and obtain multiple regional units by dividing the preset area into units according to latitude and longitude; according to the regional unit to which the address belongs to the latitude and longitude, the order objects corresponding to the address belonging to the same regional unit are divided into the same group to obtain multiple order object groups.
[0137] In one embodiment, the areas of the multiple region units are equal.
[0138] In one embodiment, the target category object group construction module is further configured to extract the target category object and the target category code contained in each piece of target category information; extract the region code from the target category code based on the position of the region code in the target category code; and divide the target category objects with the same region code into the same group to obtain multiple target category object groups.
[0139] In one embodiment, the target category object identification device further includes a new target category object table construction and availability judgment module, which is used to construct a new target category object table based on the object information corresponding to the new target category object; match the object information in the new target category object table with the obtained target category object sample data, and count the number of new target category objects that fail to match in the new target category object table; and determine the availability of the new target category object table based on the proportion of the number of new target category objects that fail to match to the total number of new target category objects in the new target category object table.
[0140] Specific limitations regarding the target category object identification device can be found in the limitations of the target category object identification method described above, and will not be repeated here. Each module in the aforementioned target category object identification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.
[0141] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores target orders. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for identifying target category objects.
[0142] Those skilled in the art will understand that Figure 8The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0143] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.
[0144] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.
[0145] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, 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 storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.
[0146] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.
[0147] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. A method of identifying an object of a target class, characterized by, The method includes: Based on the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, order objects belonging to the same region are grouped into the same group according to the region to which the address belongs, resulting in multiple order object groups; Extract the target category objects and region information contained in each target category information obtained, and group the target category objects with the same region information into the same group to obtain multiple target category object groups; Based on the regional information corresponding to each order object group and each target category object group, the order object groups and target category object groups belonging to the same region are selected from the multiple order object groups and the multiple target category object groups respectively. The similarity of the order objects in the group of order objects to be matched with the target category objects in the group of target category objects to be matched is performed, and the order objects are determined to be new target category objects based on the matching results.
2. The method of claim 1, wherein, The method further includes: The object group of orders to be matched is matched with the object group of target categories to be matched to obtain the object group matching result; The step of performing similarity matching between order objects in the group of order objects to be matched and target category objects in the group of target category objects to be matched, and determining whether the order object is a newly added target category object based on the matching result, includes: When the object group matching result meets the object group matching condition, the order object in the order object group to be matched is matched with the target category object in the target category object group to be matched, and the order object is determined to be a newly added target category object based on the matching result.
3. The method according to claim 2, characterized in that, The step of performing object group matching between the group of order objects to be matched and the group of target category objects to be matched, to obtain the object group matching result, includes: The object identifiers in the group of order objects to be matched are matched with the object identifiers in the group of target category objects to be matched, and the successfully matched object identifier groups are determined. When the object group matching result meets the object group matching condition, the order objects in the order object group to be matched are matched with the target category objects in the target category object group to be matched for similarity. Based on the matching result, it is determined whether the order object is a newly added target category object, including: When the number of successfully matched object identifier groups meets the quantity condition, the order objects corresponding to the successfully matched object identifier groups and the target category objects are matched for similarity. Based on the matching results, it is determined whether the corresponding order object is a newly added target category object.
4. The method according to claim 1, characterized in that, The step involves grouping order objects belonging to the same region according to the region to which the address belongs, resulting in multiple order object groups, including: The address is format-standardized, the obtained format-standardized address data is converted into latitude and longitude, and multiple regional units are obtained by dividing the preset area into units according to latitude and longitude. Based on the regional unit to which the address belongs, the order objects corresponding to addresses belonging to the same regional unit are grouped into the same group, resulting in multiple order object groups.
5. The method according to claim 4, characterized in that, The areas of the multiple regional units are equal.
6. The method according to claim 1, characterized in that, The process involves extracting the target category objects and region information from each acquired target category information, grouping target category objects with the same region information into the same group, resulting in multiple target category object groups, including: Extract the target category object and target category code from each piece of target category information obtained; Based on the position of the region code in the target category code, the region code is extracted from the target category code; Target category objects with the same region code are grouped together to obtain multiple target category object groups.
7. The method according to claim 1, characterized in that, The method further includes: Based on the object information corresponding to the newly added target category objects, construct a new target category object table; The object information in the newly added target category object table is matched with the obtained target category object sample data, and the number of newly added target category objects that fail to match in the newly added target category object table is counted. The availability of the new target category object table is determined based on the proportion of the number of newly added target category objects that failed to match to the total number of newly added target category objects in the new target category object table.
8. A device for identifying target category objects, characterized in that, The device includes: The order object group construction module is used to divide the order objects corresponding to the target order and the addresses corresponding to the order objects extracted from the target order into the same group according to the region to which the address belongs, thereby obtaining multiple order object groups; The target category object group construction module is used to extract the target category objects and region information contained in each piece of target category information obtained, and to divide the target category objects with the same region information into the same group to obtain multiple target category object groups; The object group filtering module is used to filter out the order object groups and target category object groups that belong to the same region from the multiple order object groups and the multiple target category object groups based on the regional information corresponding to each order object group and each target category object group. The object matching module is used to perform similarity matching between the order objects in the order object group to be matched and the target category objects in the target category object group to be matched, and to determine whether the order object is a newly added target category object based on the matching result.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.