Industry classification method and device, computer equipment and storage medium
By analyzing the shipping data of logistics target objects, determining commonly used slaughter objects and using industry mapping information, the problem of lack of industry identification methods for target objects in the logistics field is solved, and the accuracy and efficiency of industry classification are improved.
Patent Information
- Application Number
- CN202311667495.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-05
- Publication Date
- 2025-06-06
AI Technical Summary
The existing technology lacks special target object industry identification methods in the logistics field, resulting in low accuracy of industry classification, insufficient objectivity and reference, and cannot meet personalized needs.
By analyzing the delivery data of the target object within a given time period, determining common entrusted objects, and classifying them into enterprise or individual target objects according to attributes, the target industry is determined using the first industry mapping information and the second industry mapping information.
It improves the accuracy, logic and efficiency of the industry classification of target objects, can better fit the business and habits of target objects, and meets personalized needs in logistics scenarios.
Smart Images
Figure CN120106699A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of logistics technology, and in particular to an industry classification method, device, computer equipment and storage medium. Background Art
[0002] With the surge in the number of express delivery targets and the increasing complexity of the cooperation network, logistics parties face greater challenges in meeting diverse needs. As the link between the supply chain and the cooperation targets, logistics parties need to better adapt to cross-industry service needs. In this context, it is crucial to accurately identify the industry to which the target object belongs in order to promote customized logistics services and provide accurate industry analysis reports.
[0003] However, the current technology is to classify the target objects by industry by manual classification with reference to the general classification standards, but there is a lack of industry identification methods for target objects in the logistics field. Direct reuse of general industry classification standards has limitations, and manual classification methods are also highly subjective, making the existing industry classification methods for target objects less accurate, less objective and less referenceable, and unable to meet the personalized needs in logistics scenarios. Summary of the invention
[0004] Based on this, it is necessary to provide an industry classification method, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy, logic and efficiency of industry classification of target objects in response to the above technical problems.
[0005] In the first aspect, the present application provides an industry classification method, including:
[0006] Determine the target object's frequently used consignments according to the target object's consignment data within a given period of time;
[0007] Obtaining the attribute classification of the target object;
[0008] If the attribute classification of the target object is an enterprise target object, one of the first industry mapping information and the second industry mapping information is determined as the target industry mapping information, and the target industry corresponding to the target object is determined based on the target industry mapping information; the first industry mapping information represents the mapping relationship between the commonly used consignments and the industry; the target object includes sub-objects, and the second industry mapping information represents the mapping relationship between the sub-objects and the industry.
[0009] In one embodiment, the determining one of the first industry mapping information and the second industry mapping information as the target industry mapping information, and determining the target industry corresponding to the target object based on the target industry mapping information, includes:
[0010] Obtaining the first shipping amount of the commonly used consignment within the given time period, and the second shipping amount of the sub-object within the preset shipping duration, taking the second shipping amount with the largest value as the comparison shipping amount, and taking the sub-object corresponding to the comparison shipping amount as the target sub-object;
[0011] If the first shipping amount is greater than or equal to the compared shipping amount, determining the first industry mapping information as the target industry mapping information, and searching the industry corresponding to the commonly used consignment as the target industry according to the first industry mapping information;
[0012] If the first mailing amount is less than the compared mailing amount, the second industry mapping information is determined to be the target industry mapping information, and the industry corresponding to the target sub-object is searched according to the second industry mapping information as the target industry.
[0013] In one embodiment, the method further comprises:
[0014] If the target object is the first target object, a sub-classification operation is performed on the target industry corresponding to the target object to obtain an updated industry.
[0015] In one embodiment, the method of determining that the target object is the first target object includes:
[0016] Acquire the importance of the target object, and if the importance is greater than a first threshold, determine the target object as the first target object;
[0017] The target industry corresponding to the target object is subdivided into categories to obtain an updated industry, including:
[0018] The information of the target industry of the target object is reviewed, and the target industry of the target object that needs to be modified is updated to obtain an updated industry of the target object.
[0019] In one embodiment, the method of determining that the target object is the first target object includes:
[0020] Obtaining a third shipping amount and shipping frequency of the target object within a first given time period, and determining the target object whose third shipping amount is less than a second threshold or whose shipping frequency is less than a third threshold as the first target object;
[0021] The target industry corresponding to the target object is subdivided into categories to obtain an updated industry, including:
[0022] A first target industry matching the target object is constructed, and the first target industry is determined as an updated industry of the target object.
[0023] In one embodiment, the method further comprises:
[0024] If the attribute classification of the target object is an individual target object, the target industry corresponding to the target object is determined according to the first industry mapping information.
[0025] In one embodiment, determining the frequently used consignments of the target object according to the consignment data of the target object in a given period of time includes:
[0026] According to the mailing data, obtaining a fourth mailing amount or a second mailing number of the plurality of consignments within the given time period;
[0027] The consignment with the fourth highest shipping amount or the consignment with the second highest shipping frequency is determined as the frequently used consignment.
[0028] In a second aspect, the present application further provides an industry classification device, the device comprising:
[0029] A commonly used consignment module, used to determine the commonly used consignments of a target object according to the consignment data of the target object in a given period of time;
[0030] An attribute classification module, used to obtain the attribute classification of the target object;
[0031] The target industry determination module is used to determine the target industry corresponding to the target object according to the first industry mapping information or the second industry mapping information if the target object is an enterprise target object; the second industry mapping information represents the mapping relationship between the sub-object and the industry.
[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0033] Determine the target object's frequently used consignments according to the target object's consignment data within a given period of time;
[0034] Obtaining the attribute classification of the target object;
[0035] If the attribute classification of the target object is an enterprise target object, one of the first industry mapping information and the second industry mapping information is determined as the target industry mapping information, and the target industry corresponding to the target object is determined based on the target industry mapping information; the first industry mapping information represents the mapping relationship between the commonly used consignments and the industry; the target object includes sub-objects, and the second industry mapping information represents the mapping relationship between the sub-objects and the industry.
[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:
[0037] Determine the target object's frequently used consignments according to the target object's consignment data within a given period of time;
[0038] Obtaining the attribute classification of the target object;
[0039] If the attribute classification of the target object is an enterprise target object, one of the first industry mapping information and the second industry mapping information is determined as the target industry mapping information, and the target industry corresponding to the target object is determined based on the target industry mapping information; the first industry mapping information represents the mapping relationship between the commonly used consignments and the industry; the target object includes sub-objects, and the second industry mapping information represents the mapping relationship between the sub-objects and the industry.
[0040] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0041] Determine the target object's frequently used consignments according to the target object's consignment data within a given period of time;
[0042] Obtaining the attribute classification of the target object;
[0043] If the attribute classification of the target object is an enterprise target object, one of the first industry mapping information and the second industry mapping information is determined as the target industry mapping information, and the target industry corresponding to the target object is determined based on the target industry mapping information; the first industry mapping information represents the mapping relationship between the commonly used consignments and the industry; the target object includes sub-objects, and the second industry mapping information represents the mapping relationship between the sub-objects and the industry.
[0044] The above-mentioned industry classification method, apparatus, computer equipment, storage medium and computer program product determine the target object's commonly used consignments according to the target object's mailing data within a given time period; obtain the attribute classification of the target object; if the attribute classification of the target object is an enterprise target object, determine one of the first industry mapping information and the second industry mapping information as the target industry mapping information, and determine the target industry corresponding to the target object based on the target industry mapping information; the first industry mapping information represents the mapping relationship between commonly used consignments and industries; the target object includes sub-objects, and the second industry mapping information represents the mapping relationship between sub-objects and industries. Based on the analysis of mailing data, the embodiments of the present invention can mine the mailing behavior characteristics of the enterprise target object, match more appropriate industry classification logic for the enterprise target object, and obtain the industry classification results that are more in line with the business and habits of the target object itself, thereby improving the accuracy, logic and efficiency of the target object classification. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0046] Figure 1 An application environment diagram of an industry classification method in an embodiment;
[0047] Figure 2 A schematic diagram of a process flow of an industry classification method in one embodiment;
[0048] Figure 3 A schematic diagram of a flow chart of a step of determining a target industry of a target object in an embodiment;
[0049] Figure 4 A schematic diagram of the overall process of industry classification of target objects in one embodiment;
[0050] Figure 5 is a structural block diagram of an industry classification device in an embodiment;
[0051] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0053] With the surge in the number of express delivery targets and the continuous expansion of cooperation networks, logistics companies are facing more complex challenges in meeting the ever-diversifying needs. As the key link between the supply chain and cooperation targets, logistics companies need to better adapt to the service needs of different industries. In this context, it becomes crucial to accurately identify the industry to which the target object belongs in order to promote the provision of customized logistics services and generate accurate industry analysis reports.
[0054] The problem with traditional technology is that it mainly manually classifies the target objects by referring to the general classification standards. In the field of logistics, there is still a lack of specialized target object industry identification methods. There are some limitations in directly using the general industry classification standards, and the manual classification method is easily affected by subjective factors, resulting in low accuracy of the existing industry classification methods for target objects, and lack of sufficient objectivity and reference, which cannot meet the personalized needs in logistics scenarios.
[0055] The industry classification method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.
[0056] In the application scenario of the present application, the terminal 102 determines the target object's commonly used consignments based on the target object's mailing data within a given time period; obtains the attribute classification of the target object; the attribute classification is used to indicate that the target object is an individual target object or an enterprise target object; if the target object is an individual target object, the target industry corresponding to the target object is determined based on the first industry mapping information; the first industry mapping information represents the mapping relationship between commonly used consignments and the industry; if the target object is an enterprise target object, the target industry corresponding to the target object is determined based on the first industry mapping information or the second industry mapping information; the second industry mapping information represents the mapping relationship between the sub-object and the industry.
[0057] In an exemplary embodiment, Figure 2 As shown, a method of industry classification is provided, which can be applied to Figure 1The terminal 102 in FIG. 1 is used as an example to illustrate the method, which includes the following steps S202 to S208, wherein:
[0058] Step S202: Determine the target object's frequently used consignments according to the target object's shipment data within a given period of time.
[0059] The mailing data may be the types of consignments sent by the target object and the corresponding amounts. In some embodiments, the mailing data may be analyzed to identify the types of consignments with the highest total amount of consignments sent by the target object in a given period of time, and the types of consignments with the highest total amount of consignments are used as common consignments. For example, common consignments may be food, daily necessities, books, electronic products, etc.
[0060] In some embodiments, the given time period can be set according to demand, for example, it can be one week, one month or one year, etc. In some embodiments, in addition to the amount of mailings in a given time period, the commonly used consignments of the target object can also be determined by referring to the mailing frequency, mailing urgency, insurance amount, etc. of different consignments in a given time period. The embodiments of the present application do not limit the given time period and the specific method of determining the commonly used consignments.
[0061] In this way, the preferences and behavior patterns of the target objects can be identified from their large amount of mailing data, so as to better understand their needs, thereby providing basic data for the subsequent industry classification of the target objects and improving the accuracy and logic of the industry classification.
[0062] Step S204: Obtain the attribute classification of the target object.
[0063] Among them, the attribute classification can be used to indicate that the target object is an individual target object or an enterprise target object. In some embodiments, the sender name of the target object can be obtained from the mailing data, and the attribute classification of the target object can be identified by the sender name. For example, if the sender name is "Zhang San", it can be identified that the sender name is a name, and the attribute classification of the target object is determined to be an individual target object. For another example, if the sender name is "Company A", it can be identified that the sender name is a corporate name, and the attribute classification of the target object is determined to be a corporate target object.
[0064] In some embodiments, in addition to determining the attribute classification of the target object by the name of the sender, the attribute classification of the target object can also be determined by the total mailing amount, mailing frequency, and mailing item types of all consignments of the target object in a given period of time. For example, the total mailing amount and mailing frequency of the corporate target object are higher than those of the individual target object, so different thresholds can be set for the total mailing amount and mailing frequency, respectively. If the total mailing amount or mailing frequency in the mailing data of the target object exceeds the threshold, it means that the target object is a corporate target object.
[0065] In some embodiments, different weights can be assigned to the sender name, total mailing amount and mailing frequency, and a score for determining the attribute classification can be calculated by weighted summation. The final attribute classification of the target object can be determined based on the score. For example, a target object with a higher score can be determined as an enterprise target object, and a target object with a lower score can be determined as an individual target object.
[0066] Step S206: If the attribute classification of the target object is an enterprise target object, one of the first industry mapping information and the second industry mapping information is determined as the target industry mapping information, and the target industry corresponding to the target object is determined based on the target industry mapping information.
[0067] The first industry mapping information represents the mapping relationship between commonly used consignments and industries, the target object includes sub-objects, and the second industry mapping information represents the mapping relationship between sub-objects and industries.
[0068] In some embodiments, if the attribute of the target object is classified as an enterprise target object, the system may consider using two mapping information tables when determining the target industry mapping information: a first industry mapping information table and a second industry mapping information table.
[0069] In some embodiments, the first industry mapping information table may be based on the perspective of the corporate entity. For example, Company A may include many subsidiaries. The total mailing data of Company A may be used to determine which type of consignment has the highest mailing amount, so that the first industry mapping information table mainly focuses on the mailing data and business conditions at the company level, mapping the relationship between commonly used consignments and industries.
[0070] In some embodiments, the second industry mapping information table can be mapped based on the branch ID of the enterprise, and different branch IDs correspond to different sub-objects, that is, the subsidiaries of the enterprise. For example, as mentioned above, Company A can include mobile phone subsidiary b and automobile subsidiary c, etc. Each subsidiary can correspond to a branch ID, and each branch ID can be a series of numbers or characters, etc. The system can compare the mailing amounts of different branch IDs, and select the industry of the subsidiary corresponding to the branch ID with the highest mailing amount as the industry classification of the entire company. For example, through mailing data analysis, it is found that the mailing amount of branch ID 6677 is the highest, and branch ID 6677 corresponds to mobile phone subsidiary b, then the mobile phone industry corresponding to mobile phone subsidiary b can be determined as the target industry of Company A. The second industry mapping information table mainly focuses on the business conditions of each subsidiary of the enterprise, and maps the relationship between the industry of the sub-object and the target industry.
[0071] The above-mentioned industry classification method, apparatus, computer equipment, storage medium and computer program product determine the target object's commonly used consignments according to the target object's mailing data within a given time period; obtain the attribute classification of the target object; if the attribute classification of the target object is an enterprise target object, determine one of the first industry mapping information and the second industry mapping information as the target industry mapping information, and determine the target industry corresponding to the target object based on the target industry mapping information; the first industry mapping information represents the mapping relationship between commonly used consignments and industries; the target object includes sub-objects, and the second industry mapping information represents the mapping relationship between sub-objects and industries. Based on the analysis of mailing data, the embodiments of the present invention can mine the mailing behavior characteristics of the enterprise target object, match more appropriate industry classification logic for the enterprise target object, and obtain the industry classification results that are more in line with the business and habits of the target object itself, thereby improving the accuracy, logic and efficiency of the target object classification.
[0072] In an exemplary embodiment, Figure 3 As shown, step S206 includes the following steps:
[0073] Step S302, obtaining the first shipping amount of commonly used consignments within a given period of time, and the second shipping amount of the sub-object within a preset shipping time, taking the second shipping amount with the largest value as the comparison shipping amount, and taking the sub-object corresponding to the comparison shipping amount as the target sub-object.
[0074] In some embodiments, the first shipping amount and the second shipping amount can be obtained from the shipping data, and the second shipping amount with the largest value is used as the comparison shipping amount, and the sub-object corresponding to the comparison shipping amount is used as the target sub-object. In some embodiments, the first shipping amount can be the shipping amount of the target object for sending common consignments within a given period. Assuming that the common consignments are invoices and the given period is one month, the first shipping amount can be the amount spent by the target object for sending one or more invoices within one month, for example, the first shipping amount is 1,000 yuan in total.
[0075] In some embodiments, the second consignment amount may be the consignment amount of the first consignment belonging to the sub-object. Assuming that the sub-object is mobile phone subsidiary b, and the given time period is also one month, the first consignment may be items sent by mobile phone subsidiary b within one month, such as mobile phones and mobile phone accessories. Assuming that the mobile phone subsidiary b sends out mobile phones with a consignment amount of 800 yuan and sends out mobile phone accessories with a consignment amount of 500 yuan within one month, the second consignment amount of mobile phone subsidiary b may be the sum of the consignment amounts of mobile phones and mobile phone accessories, which is 1,300 yuan. The above operation is performed on different sub-objects (such as automobile subsidiary c), and the sub-object with the highest second consignment amount is used as the target sub-object. For example, when the second consignment amount of automobile subsidiary c is 1,000 yuan, mobile phone subsidiary b is used as the target sub-object.
[0076] Step S304: if the first mailing amount is greater than or equal to the compared mailing amount, the first industry mapping information is determined as the target industry mapping information, and the industry corresponding to the commonly used consignments is searched according to the first industry mapping information as the target industry.
[0077] It is understandable that since the scale of corporate target objects is larger than that of individual target objects, especially corporate target objects with a large number of people, the number and types of consignments involved are both large. Therefore, the industry classification of corporate target objects cannot be determined solely based on the shipping amount of the consignments as basic data. It is also necessary to further compare the shipping amount between commonly used consignments and the first consignment to improve the accuracy of industry classification for corporate target objects.
[0078] In some embodiments, Figure 4 As shown, after determining that the target object is an enterprise target object, the first shipping amount and the comparison shipping amount can be compared. If the first shipping amount is greater than the comparison shipping amount, it means that the commonly used consignments have a greater impact on the shipping behavior of the enterprise target object. The first industry mapping information can be determined as the target industry mapping information corresponding to the enterprise target object, and the target industry corresponding to the enterprise target object can be found according to the first industry mapping information.
[0079] Still referring to the example in step S302, assuming that the commonly used consignments are invoices, and the first consignment amount of invoices in a given period is 2,000 yuan. Still taking the first consignment corresponding to the sub-object as a mobile phone and mobile phone accessories as an example, assuming that the comparison consignment amount is 1,300 yuan, it can be seen that the first consignment amount is greater than the comparison consignment amount. This indicates that the consignment amount spent by the enterprise target object on invoices alone exceeds the multiple first consignments of other sub-objects, making the enterprise target object more inclined to belong to the industry related to invoices. Then, the industry corresponding to the invoice can be further found through the first industry mapping information as the target industry of the enterprise target object. For example, the target industry of the enterprise target object can be the business service industry or the financial accounting service industry.
[0080] Step S306: If the first mailing amount is less than the compared mailing amount, the second industry mapping information is determined as the target industry mapping information, and the industry corresponding to the target sub-object is searched as the target industry according to the second industry mapping information.
[0081] Still referring to the example in step S304, assume that the commonly used consignments are invoices, and the first consignment amount of the invoice within a given time period is 1,000 yuan. Still taking the first consignment corresponding to the sub-object as a mobile phone and mobile phone accessories as an example, assuming that the comparison consignment amount is 1,300 yuan, it can be seen that the first consignment amount is less than the comparison consignment amount. This indicates that the consignment amount spent by the enterprise target object on multiple first consignments of the sub-object is higher than the consignment amount spent on a certain commonly used consignment. This makes the enterprise target object more inclined to belong to the electronic product industry, and then further, the industry corresponding to the electronic product industry can be found through the second industry mapping information as the target industry of the enterprise target object. For example, the target industry of the enterprise target object can be the technology electronics industry, the consumer electronics industry, etc.
[0082] It can be understood that this method introduces multiple first consignments of sub-objects to compare the first shipping amount and the comparison shipping amount, which can avoid the situation where the first shipping amount for the enterprise target object to mail commonly used consignments is large, resulting in misjudgment of the industry classification of the enterprise target object, thereby improving the accuracy, logic and efficiency of industry classification of the target object.
[0083] In an exemplary embodiment, step S201 may further include:
[0084] According to the mailing data, obtaining a fourth mailing amount or a second mailing number of the plurality of consignments within the given time period;
[0085] The consignment with the fourth highest shipping amount or the consignment with the second highest shipping frequency is determined as the frequently used consignment.
[0086] In some embodiments, the shipping amount or shipping frequency of multiple consignments in a given period can be extracted from the shipping data, that is, the fourth shipping amount and the second shipping frequency in the first given period, and the commonly used consignments can be determined by two standards, for example, the consignment with the highest fourth shipping amount can be determined as a commonly used consignment, and for another example, the consignment with the highest second shipping frequency can be determined as a commonly used consignment. It can be understood that the specific item determined as a commonly used consignment can be used as an important feature for subsequent target object classification and industry mapping.
[0087] In this way, the most commonly used or important consignments of the target object can be determined according to the target object's mailing behavior in a given period of time, which serves as an important basis for subsequent industry classification of the target object. This can help the system understand the target object's mailing habits and behaviors more accurately, and improve the accuracy of industry classification and mapping of the target object.
[0088] In some embodiments, Figure 4 As shown, when performing the sub-classification operation, the importance of the classified target objects can be evaluated to determine the first target object whose importance is greater than the first threshold. In some embodiments, the system can send the relevant information of the target industry of the determined target object to the review end to further review the information of the target industry of the target object to obtain the updated industry of the target object.
[0089] In some embodiments, the importance of the target object can be evaluated in a variety of ways. In a specific implementation, the importance of the target object can be determined by evaluating factors such as the transaction frequency between the target object and the logistics party, the historical mailing amount, the years of cooperation, the size of the enterprise, and the geographical location. It can be understood that the larger the four values of transaction frequency, historical mailing amount, years of cooperation, and enterprise size, the higher the importance of the corresponding target object. The geographical location of the target object can also be used to evaluate its importance. For example, a target object in a specific area can be more important than users in other areas. For example, a specific area can be an economically developed area, an area where mailing discount activities are carried out, etc.
[0090] In the specific implementation process, a set of evaluation rules can be formulated by converting these importance evaluation factors into specific values, performing weighted combination, and performing threshold comparison. For example, if the importance evaluation value of a target object is higher than the set threshold, it is considered to be an important target object (i.e., the first target object).
[0091] In some embodiments, the review end may review the received target industry information of the target object. In specific implementations, the review end may review the target industry by manual review, automatic review or other review methods to ensure the accuracy of the target industry.
[0092] In some embodiments, if the review end finds that the target industry of the target object needs to be modified during the review process, the review end can perform corresponding update operations, such as correcting format errors of the target industry, adjusting the classification of the target industry, etc., to ensure that the updated industry of the target object after modification is more accurate and objective than the target industry before modification.
[0093] In some embodiments, after the review is completed, the system can update the industry of the target object so as to match the target object with a more accurate industry by correcting or updating the target industry of the target object.
[0094] Through the above methods, the purpose of this series of steps is to improve the accuracy of industry classification for target objects with higher importance through the combination of automatic classification and review operations of the system, with special attention paid to those important target objects that have a greater impact on the overall accuracy of the system. This is conducive to the continuous learning and optimization of the industry classification system, so as to perform more accurate industry classification operations for target objects based on the changing business environment and target object behavior.
[0095] It is understandable that in the above embodiment, the important target object is used as the first target object to improve the accuracy of the industry classification of the important target object. It is understandable that according to actual needs, the target object that has not been cooperated with, has been lost or has no shipping information can also be used as the first target object. This situation is explained below.
[0096] In an exemplary embodiment, a method for determining that the target object is the first target object includes:
[0097] Obtaining a third shipping amount and shipping frequency of the target object within the first given time period, and determining the target object whose third shipping amount is less than a second threshold or whose shipping frequency is less than the third threshold as the first target object;
[0098] The target industry corresponding to the target object is subdivided into categories to obtain an updated industry, including:
[0099] A first target industry matching the target object is constructed, and the first target industry is determined as an updated industry of the target object.
[0100] In some embodiments, the target objects that have not been cooperated with, have been lost, and target objects that have no shipping information in the recent period (for example, in the first given period) can be identified by analyzing the shipping data of the target objects. In a specific implementation, it can be determined which target objects in the target object set meet the requirement that the shipping amount is less than the second threshold value or the number of shipments is less than the third threshold value in the first given period. It can be understood that in order to ensure the accuracy of the industry classification of the target objects, the first given period is usually a longer period, such as one month, half a year, one year, etc. If the shipping amount or shipping frequency of the target object is at a relatively small value in the first given period, it means that the target object is most likely the aforementioned target object that has not been cooperated with, has been lost, or has no shipping information.
[0101] In some embodiments, a catch-all mapping relationship may be designed for these relatively special target objects. The catch-all mapping relationship may be a default industry mapping, which classifies these target objects into a common industry classification to prevent these target objects from being ignored or lost in subsequent industry classification operations.
[0102] In some embodiments, the system can generate corresponding SQL code for this catch-all mapping relationship, and apply the SQL code of this catch-all mapping relationship to the big data platform to ensure that the system can correctly classify the above special target objects according to the catch-all mapping relationship.
[0103] Through the above methods, we can ensure that the system has a reasonable way to deal with those target objects that have not cooperated, have been lost, or have no recent shipping information, so as to prevent them from being ignored or misjudged in subsequent industry classification operations. Through the bottom-line mapping relationship, the system can ensure that the classification of these special case target objects can still be carried out, and can be launched on the big data platform to cope with large-scale data processing needs.
[0104] In an exemplary embodiment, the method of the present application further includes:
[0105] If the attribute classification of the target object is an individual target object, the target industry corresponding to the target object is determined according to the first industry mapping information.
[0106] Among them, the first industry mapping information can characterize the mapping relationship between commonly used consignments and industries. That is, using the first industry mapping information, the commonly used consignments of individual target objects can be mapped to the corresponding target industries. For example, if the commonly used consignments of an individual target object are books, and the first industry mapping information indicates that books correspond to the culture and media industry, then the target object will be classified into the culture and media industry. In some embodiments, the first industry mapping information can be stored as a first industry mapping information table, for example, the first industry information mapping table can be named: consignment-industry mapping information table.
[0107] It can be understood that the first industry mapping information is helpful to more accurately understand the characteristics of individual target objects in business, and to classify the individual target objects to be classified into appropriate target industry classifications.
[0108] In some embodiments, the industry mapping information may be updated regularly according to a preset time interval. In a specific implementation, the first industry mapping information and / or the second industry mapping information may be adjusted to ensure that the industry mapping information can reflect the latest business and industry changes of the target object.
[0109] In some embodiments, during the update process, the system may consider the latest business situation of the target object and make adjustments based on new market trends, the target object's mailing behavior, or other relevant information, thereby ensuring that the industry classification system can more accurately capture changes in the target object's business environment.
[0110] In some embodiments, after updating the mapping information, the system can automatically generate a report to report some target objects whose industry classifications have changed during the iteration process, thereby facilitating understanding of adjustments to the industry classification system and providing timely feedback or further optimization.
[0111] Through the above methods, we can ensure that the industry classification system remains sensitive and adapts to the ever-changing business environment and market needs in a timely manner. Through regular, automated iterative updates, the system can maintain accuracy and accurately understand and respond to changes in the target object's industry classification by updating industry mapping information.
[0112] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0113] Based on the same inventive concept, the embodiment of the present application also provides an industry classification device for implementing the industry classification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more industry classification device embodiments provided below can refer to the limitations on the industry classification method above, and will not be repeated here.
[0114] In an exemplary embodiment, Figure 5 As shown, an industry classification device is provided, including: a common consignment module 410, an attribute classification module 420 and a target industry determination module 430, wherein:
[0115] Common consignments module 410, for determining common consignments of a target object according to the consignment data of the target object in a given period of time;
[0116] An attribute classification module 420 is used to obtain the attribute classification of the target object;
[0117] The target industry determination module 430 is used to determine one of the first industry mapping information and the second industry mapping information as the target industry mapping information if the target object is an enterprise target object, and determine the target industry corresponding to the target object based on the target industry mapping information; the second industry mapping information represents the mapping relationship between the sub-object and the industry.
[0118] Each module in the above industry classification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0119] Figure 6In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an industry classification method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0120] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0121] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0122] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0123] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0124] It should be noted that the target object information (including but not limited to the target object device information, target object personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the target object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0125] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium 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, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0126] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0127] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method of industry classification, It is characterized in that The method comprises: Determine the target object's frequently used consignments according to the target object's consignment data within a given period of time; Obtaining the attribute classification of the target object; If the attribute classification of the target object is an enterprise target object, one of the first industry mapping information and the second industry mapping information is determined as the target industry mapping information, and the target industry corresponding to the target object is determined based on the target industry mapping information; the first industry mapping information represents the mapping relationship between the commonly used consignments and the industry; the target object includes sub-objects, and the second industry mapping information represents the mapping relationship between the sub-objects and the industry.
2. The method according to claim 1, It is characterized in that The determining one of the first industry mapping information and the second industry mapping information as the target industry mapping information, and determining the target industry corresponding to the target object based on the target industry mapping information, includes: Obtaining the first shipping amount of the commonly used consignment within the given time period, and the second shipping amount of the sub-object within the preset shipping duration, taking the second shipping amount with the largest value as the comparison shipping amount, and taking the sub-object corresponding to the comparison shipping amount as the target sub-object; If the first shipping amount is greater than or equal to the compared shipping amount, determining the first industry mapping information as the target industry mapping information, and searching the industry corresponding to the commonly used consignment as the target industry according to the first industry mapping information; If the first mailing amount is less than the compared mailing amount, the second industry mapping information is determined to be the target industry mapping information, and the industry corresponding to the target sub-object is searched according to the second industry mapping information as the target industry.
3. The method according to claim 1, It is characterized in that The method further comprises: If the target object is the first target object, a sub-classification operation is performed on the target industry corresponding to the target object to obtain an updated industry.
4. The method according to claim 3, It is characterized in that The method of determining that the target object is the first target object includes: Acquire the importance of the target object, and if the importance is greater than a first threshold, determine the target object as the first target object; The target industry corresponding to the target object is subdivided into sub-categories to obtain an updated industry, including: The information of the target industry of the target object is reviewed, and the target industry of the target object that needs to be modified is updated to obtain an updated industry of the target object.
5. The method according to claim 3, It is characterized in that The method of determining that the target object is the first target object includes: Obtaining a third shipping amount and shipping frequency of the target object within a first given time period, and determining the target object whose third shipping amount is less than a second threshold or whose shipping frequency is less than a third threshold as the first target object; The target industry corresponding to the target object is subdivided into sub-categories to obtain an updated industry, including: A first target industry matching the target object is constructed, and the first target industry is determined as an updated industry of the target object.
6. The method according to claim 1, It is characterized in that The method further comprises: If the attribute classification of the target object is an individual target object, the target industry corresponding to the target object is determined according to the first industry mapping information.
7. The method according to any one of claims 1 to 6, It is characterized in that The step of determining the target object's frequently used consignments according to the target object's consignment data within a given period of time includes: According to the mailing data, obtaining a fourth mailing amount or a second mailing number of the plurality of consignments within the given time period; The consignment with the fourth highest shipping amount or the consignment with the second highest shipping frequency is determined as the frequently used consignment.
8. An industry classification device, It is characterized in that The device comprises: A commonly used consignment module, used to determine the commonly used consignments of a target object according to the consignment data of the target object in a given period of time; An attribute classification module, used to obtain the attribute classification of the target object; A target industry determination module is used to determine one of the first industry mapping information and the second industry mapping information as the target industry mapping information if the attribute classification of the target object is an enterprise target object, and determine the target industry corresponding to the target object based on the target industry mapping information; the first industry mapping information represents the mapping relationship between the commonly used consignment and the industry; the target object includes a sub-object, and the second industry mapping information represents the mapping relationship between the sub-object and the industry.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
11. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.