Account category identification method and apparatus, computer device, and storage medium

Abstract

The application relates to an account category identification method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a plurality of account data; the account data comprises a plurality of influence factors influencing the category to which the account belongs; for each influence factor, a plurality of initial assumption values corresponding to the influence factor are acquired; based on a plurality of threshold values corresponding to the influence factor, the plurality of initial assumption values are divided into a plurality of assumption value intervals; based on the plurality of initial assumption values in the assumption value interval, a plurality of key-value pairs are obtained; based on the key-value pairs, a target assumption value is assigned to the plurality of account data having the influence factor, the category value corresponding to each account data under each key-value pair is calculated, and the category of each account data is determined based on the category value; and based on the category of the plurality of account data under each key-value pair, the relationship between the influence factor with different values and the category of the account data is obtained. The method can improve the accuracy of account type identification results.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to an account category identification method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] In the field of big data risk control, the interpretability of the identification model is crucial to its stability and generalization ability during the process of account type identification. Since overfitting often occurs on trends that defy common sense, the elimination of abnormal influencing factors is particularly important during the process of account type identification.

[0003] In traditional techniques, gradient boosting algorithms provide an interface for calculating the gain importance of influencing factors, using the weight ratio of influencing factors to control the degree of influence of each influencing factor on the identification results.

[0004] However, traditional techniques only provide the weight of the influence factor in the identification model through the gain importance calculation interface of the influence factor, and cannot find abnormal influence factors, resulting in low accuracy of account type identification results. Summary of the Invention

[0005] Therefore, it is necessary to provide an account category identification method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of account type identification results in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for identifying account categories. The method includes:

[0007] Acquire data from multiple accounts; account data includes: multiple influencing factors that affect the category to which an account belongs;

[0008] For each impact factor, multiple initial hypothesis values ​​are obtained; based on multiple thresholds corresponding to the impact factor, the multiple initial hypothesis values ​​are divided into multiple hypothesis value intervals.

[0009] Based on multiple initial hypotheses within the hypotheses interval, multiple key-value pairs are obtained; each key-value pair consists of a target hypothesis within the hypotheses interval and an influence factor; the number of key-value pairs is the same as the number of initial hypotheses within the hypotheses interval.

[0010] Based on key-value pairs, the target hypothesis value is assigned to multiple account data with influence factors, the category value corresponding to each account data under each key-value pair is calculated, and the category of each account data is determined based on the category value;

[0011] Based on the categories of multiple account data under each key-value pair, the relationship between the influence factor with different values ​​and the category of account data is obtained.

[0012] In one embodiment, multiple key-value pairs are obtained based on multiple initial hypothesis values ​​within a hypothesis value range, including:

[0013] Select an initial hypothesis value that has not been selected within the hypothesis value range as the target hypothesis value, and obtain a key-value pair consisting of the target hypothesis value and the influence factor; repeat the above steps until the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value range.

[0014] In one embodiment, before dividing multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the impact factors, the above method further includes:

[0015] Retrieve multiple initial thresholds corresponding to the impact factors from the stored object;

[0016] For each impact factor, multiple initial thresholds are deduplicated and sorted to obtain a threshold list for the corresponding impact factor; the threshold list includes multiple thresholds corresponding to the impact factor.

[0017] In one embodiment, based on key-value pairs, the target hypothesis value is assigned to multiple account data with influence factors, including:

[0018] For each range of hypothetical values, select an initial hypothetical value that has not been selected before within the range as the target hypothetical value;

[0019] Based on the threshold list, determine the order of multiple hypothetical value intervals;

[0020] Based on the sorting of multiple hypothesis value intervals, determine the sorting of multiple target hypothesis values;

[0021] Based on the sorting of multiple target hypothesis values, the target hypothesis values ​​are assigned to multiple account data with influence factors in turn.

[0022] In one embodiment, the method further includes:

[0023] The relationship between influencing factors and the categories of account data is stored in a storage object.

[0024] In one embodiment, the relationship between influence factors and account data categories is stored in a storage object, including:

[0025] For each influencing factor, obtain the category values ​​of multiple account data with the target hypothesis value;

[0026] The system retrieves the average of the category values ​​from multiple account data and stores the influence factor, multiple hypothetical values, and multiple averages into a storage object.

[0027] Secondly, this application also provides an account category identification device. The device includes:

[0028] The account data acquisition module is used to acquire data from multiple accounts; the account data includes: multiple influencing factors that affect the category to which an account belongs;

[0029] The hypothesis value interval division module is used to obtain multiple initial hypothesis values ​​for each impact factor; and to divide the multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the impact factor.

[0030] The key-value pair acquisition module is used to obtain multiple key-value pairs based on multiple initial hypothesis values ​​within a hypothesis value interval; wherein, a key-value pair consists of a target hypothesis value and an influence factor within the hypothesis value interval; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value interval;

[0031] The category determination module is used to assign the target hypothesis value to multiple account data with influence factors based on key-value pairs, calculate the category value corresponding to each account data under each key-value pair, and determine the category of each account data based on the category value;

[0032] The category relationship determination module is used to determine the relationship between different values ​​of the influence factor and the category of the account data based on the categories of multiple account data under each key-value pair.

[0033] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any of the above embodiments.

[0034] Fourthly, this application also provides a computer device readable storage medium. The computer device readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0035] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0036] The aforementioned account category identification method, apparatus, computer equipment, storage medium, and computer program product first acquire multiple account data sets. These account data sets include multiple influence factors affecting the category to which an account belongs. For each influence factor, multiple initial hypothesis values ​​are acquired. Next, based on multiple thresholds corresponding to the influence factors, the multiple initial hypothesis values ​​are divided into multiple hypothesis value intervals. Then, based on the multiple initial hypothesis values ​​within the hypothesis value intervals, multiple key-value pairs are obtained. Each key-value pair consists of a target hypothesis value and an influence factor within the hypothesis value interval; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value interval. Further, based on the key-value pairs, the target hypothesis value is assigned to the multiple account data sets with influence factors. The category value corresponding to each account data set under each key-value pair is calculated, and the category of each account data set is determined based on the category value. Based on the categories of the multiple account data sets under each key-value pair, the relationship between influence factors of different values ​​and the categories of the account data is obtained. This application assigns the target hypothesis value to multiple account data with influence factors. By uniformly assigning the same influence factor to all account data, the impact of changes in the value of each influence factor on the category to which the account data belongs can be intuitively reflected. This is beneficial for removing abnormal influence factors during the account type identification process and can improve the accuracy of account type identification results. Attached Figure Description

[0037] Figure 1 This is an application environment diagram of the account category identification method in one embodiment;

[0038] Figure 2 This is a flowchart illustrating an account category identification method in one embodiment;

[0039] Figure 3 This is a schematic diagram illustrating the training and use of an account category recognition model in one embodiment;

[0040] Figure 4 This is a structural block diagram of an account category identification device in one embodiment;

[0041] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0042] 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.

[0043] The account category identification method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system stores the data that server 104 needs to process. The data storage system can be integrated on a server, or it can be located in the cloud or on another network server. Server 104 provides an environment for account category recognition to terminal 102. Server 104 communicates and interacts with terminal 102 to enter the account category recognition environment. First, server 104 can obtain multiple account data from multiple terminals 102 respectively; the account data includes: multiple influencing factors affecting the category to which the account belongs; for each influencing factor, multiple initial hypothesis values ​​corresponding to the influencing factor are obtained. Next, server 104 can divide the multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the influencing factors. Then, server 104 can obtain multiple key-value pairs based on the multiple initial hypothesis values ​​within the hypothesis value intervals; wherein, each key-value pair consists of a target hypothesis value and an influencing factor within the hypothesis value interval; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value interval. Furthermore, based on key-value pairs, server 104 can assign the target hypothesis value to multiple account data points with influence factors, calculate the category value corresponding to each account data point under each key-value pair, determine the category of each account data point based on the category value, and then obtain the relationship between different values ​​of influence factors and the categories of account data based on the categories of multiple account data points under each key-value pair. Furthermore, the server can feed back the category of each account data point to terminal 102 and store the relationship between different values ​​of influence factors and the categories of account data in the data storage system.

[0044] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0045] The account category identification method provided in this application can be implemented on a single side of a server or terminal, or it can be implemented in a system including a server and a terminal through the interaction between the server and the terminal.

[0046] In one embodiment, such as Figure 2 As shown, an account category identification method is provided. Taking the application of this method to a single-side server implementation as an example, the method includes the following steps 202 to 208.

[0047] Step 202: Obtain data for multiple accounts; the account data includes multiple influencing factors that affect the category to which the account belongs.

[0048] In this embodiment, account data may include, but is not limited to: account information and multiple influencing factors that affect the category to which the account belongs.

[0049] In this embodiment, the values ​​of multiple influencing factors corresponding to the same account data are independent of each other. That is, the values ​​of multiple influencing factors corresponding to the same account data can be the same, partially the same, or all different.

[0050] In this embodiment, the values ​​of the same influence factor in different account data are independent of each other. That is to say, the values ​​of the same influence factor in different account data can be the same, partially the same, or all different.

[0051] Step 204: For each impact factor, obtain multiple initial hypothesis values ​​corresponding to the impact factor; based on multiple thresholds corresponding to the impact factor, divide the multiple initial hypothesis values ​​into multiple hypothesis value intervals.

[0052] In this embodiment, the server can obtain multiple thresholds corresponding to the influencing factors from the stored object and generate multiple threshold intervals accordingly.

[0053] In this embodiment, the threshold interval can be left-open and right-closed. For example, when multiple thresholds are 3, 6, and 9, the server can generate corresponding threshold intervals based on the multiple thresholds: [3,6), [6,9).

[0054] In this embodiment, the server can use a threshold range as a hypothesis value range, and then, based on the numerical relationship between multiple initial hypothesis values ​​and multiple thresholds, divide the multiple initial hypothesis values ​​into different hypothesis value ranges. For example, when the initial hypothesis values ​​corresponding to the influence factor are 3, 4, 5, and 8, and the multiple thresholds are [3,6) and [6,9), the server can use [3,6) and [6,9) as hypothesis value ranges. Based on the numerical relationship between multiple initial hypothesis values ​​and multiple thresholds, the initial hypothesis values ​​3, 4, and 5 are divided into the hypothesis value range [3,6), and the initial hypothesis value 8 is divided into the hypothesis value range [6,9).

[0055] In another embodiment, the server may not be limited to forming a threshold interval by storing multiple thresholds corresponding to the influencing factor in the object. The server may also obtain multiple hypothetical value intervals based on multiple initial hypothetical values ​​by equal-frequency binning.

[0056] In another embodiment, the server may not be limited to forming a threshold interval by storing multiple thresholds corresponding to the influencing factor in the object. The server may also obtain the threshold interval by randomly selecting values, and then divide the multiple initial hypothesis values ​​into different hypothesis value intervals based on the numerical relationship between the multiple initial hypothesis values ​​and the multiple thresholds.

[0057] Step 206: Based on multiple initial hypotheses within the hypothesis value interval, obtain multiple key-value pairs; wherein, a key-value pair consists of a target hypothesis value and an influence factor within the hypothesis value interval; the number of key-value pairs is the same as the number of initial hypotheses within the hypothesis value interval.

[0058] In this embodiment, for each impact factor, the server can form a key-value pair with each of the multiple target hypothesis values ​​corresponding to that impact factor. For example, when the impact factor is A, and the target hypothesis values ​​corresponding to impact factor A are 1, 5, and 7, the server can form key-value pairs with each of the impact factor A and its corresponding target hypothesis values ​​(1, 5, and 7): A-1 (impact factor A and target hypothesis value 1), A-5 (impact factor A and target hypothesis value 5), and A-7 (impact factor A and target hypothesis value 7).

[0059] Step 208: Based on key-value pairs, assign the target hypothesis value to multiple account data with influence factors, calculate the category value corresponding to each account data under each key-value pair, and determine the category of each account data based on the category value.

[0060] In this embodiment, for each key-value pair, the server can use multiple account data containing the influence factor in the key-value pair as target account data, and use the influence factor in the key-value pair as the target influence factor.

[0061] In this embodiment, the server can assign the target hypothesis value in the key-value pair to the target influence factor in multiple target account data based on the key-value pair, calculate the category value corresponding to each account data under each key-value pair, and determine the category of each account data based on the category value.

[0062] Step 210: Based on the categories of multiple account data under each key-value pair, obtain the relationship between the influence factors of different values ​​and the categories of account data.

[0063] In this embodiment, each key-value pair corresponds to an impact factor and a target hypothesis value. By assigning the target hypothesis value to multiple account data with impact factors, and by uniformly assigning the same impact factor to all account data, the influence of the change in the value of each impact factor on the category to which the account data belongs can be intuitively reflected. The relationship between impact factors with different values ​​and the category of account data can be obtained, which is beneficial to removing abnormal impact factors in the process of account type identification.

[0064] In the aforementioned account category identification method, firstly, multiple account data are acquired. This data includes multiple influence factors affecting the category to which an account belongs. For each influence factor, multiple initial hypothesis values ​​are obtained. Next, based on multiple thresholds corresponding to the influence factors, the initial hypothesis values ​​are divided into multiple hypothesis value intervals. Then, based on the multiple initial hypothesis values ​​within each interval, multiple key-value pairs are obtained. Each key-value pair consists of a target hypothesis value and an influence factor within the interval; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the interval. Further, based on the key-value pairs, the target hypothesis value is assigned to the multiple account data with influence factors. The category value corresponding to each account data under each key-value pair is calculated, and the category of each account data is determined based on the category value. Based on the categories of the multiple account data under each key-value pair, the relationship between influence factors of different values ​​and the category of the account data is obtained. This application assigns the target hypothesis value to multiple account data with influence factors. By uniformly assigning the same influence factor to all account data, the impact of changes in the value of each influence factor on the category to which the account data belongs can be intuitively reflected. This is beneficial for removing abnormal influence factors during the account type identification process and can improve the accuracy of account type identification results.

[0065] In some embodiments, such as Figure 3 As shown, based on multiple initial hypotheses within the hypothesis value interval, multiple key-value pairs are obtained. This can include: selecting an initial hypotheses within the hypothesis value interval that has not been selected before as the target hypothesis value, and obtaining a key-value pair consisting of the target hypothesis value and the influence factor; repeating the above steps until the number of key-value pairs is the same as the number of initial hypotheses within the hypothesis value interval.

[0066] In this embodiment, the server can generate the same number of key-value pairs as the number of initial hypothesis values ​​within the hypothesis value range, based on multiple initial hypothesis values ​​within the hypothesis value range. The influence factors of each key-value pair are consistent, and the target hypothesis values ​​of each key-value pair are different.

[0067] In another embodiment, the server may also obtain the target hypothesis value sequentially from multiple initial hypothesis values ​​within the hypothesis value range in a preset order (from largest to smallest, from smallest to largest, or at intervals, etc.) until the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value range.

[0068] In some embodiments, before dividing multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the impact factor, the above method may further include: obtaining multiple initial thresholds corresponding to the impact factor from a storage object; for each impact factor, deduplicating and sorting the multiple initial thresholds to obtain a threshold list for the corresponding impact factor; wherein the threshold list includes multiple thresholds corresponding to the impact factor.

[0069] In this embodiment, the server can sort multiple initial thresholds in descending or ascending order.

[0070] In this embodiment, the server can first deduplicate multiple initial thresholds, then sort the deduplicated initial thresholds to obtain a threshold list for the corresponding influencing factors. Deduplication reduces the amount of data that needs to be processed during sorting, which improves the efficiency of obtaining the threshold list and reduces the computer resources required in the process.

[0071] In another embodiment, the server may first sort multiple initial thresholds, then remove duplicates from the sorted initial thresholds to obtain a threshold list for the corresponding influencing factors.

[0072] In some embodiments, such as Figure 3 As shown, assigning target hypothesis values ​​to multiple account data with impact factors based on key-value pairs can include: for each hypothesis value interval, selecting an initial hypothesis value that has not been selected before as the target hypothesis value; determining the order of multiple hypothesis value intervals based on a threshold list; determining the order of multiple target hypothesis values ​​based on the order of multiple hypothesis value intervals; and assigning the target hypothesis values ​​to the multiple account data with impact factors in sequence based on the order of multiple target hypothesis values.

[0073] In this embodiment, the server can use the threshold interval as the hypothesis value interval, that is, divide multiple initial hypothesis values ​​into different hypothesis value intervals (threshold intervals), and then determine the order of multiple hypothesis value intervals based on the threshold list (multiple sorted and non-repeating thresholds).

[0074] In this embodiment, as Figure 3 As shown, the server can traverse multiple hypothesis value intervals, select a target hypothesis value from each interval, determine the order of multiple target hypothesis values ​​based on the sorting of multiple hypothesis value intervals, and then assign the target hypothesis values ​​to multiple account data with influence factors in turn based on the sorting of multiple target hypothesis values.

[0075] In some embodiments, the above method may further include storing the relationship between the influence factor and the category of account data in a storage object.

[0076] In this embodiment, the storage object can be integrated into the account category identification model or the database corresponding to the account category identification model.

[0077] In some embodiments, such as Figure 3As shown, storing the relationship between impact factors and account data categories in a storage object can include: for each impact factor, obtaining the category values ​​of multiple account data with target hypothesis values; obtaining the average of the category values ​​of multiple account data; and storing the impact factor, multiple hypothesis values, and multiple average values ​​in a storage object.

[0078] In this embodiment, the server can determine the impact of each influencing factor on the category value of account data under different assumptions based on the influencing factor, multiple hypothetical values, and multiple average values. This is beneficial for predicting the changing trend of the category value of account data as the value of the influencing factor changes. It can intuitively reflect the impact of the change of each influencing factor value on the category to which the account data belongs. This is beneficial for removing abnormal influencing factors during the account type identification process and can improve the accuracy of the account type identification results.

[0079] It should be understood that although the steps in the flowcharts of the embodiments described above 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 embodiments described above 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 of other steps.

[0080] Based on the same inventive concept, this application also provides an account category identification device for implementing the account category identification method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more account category identification device embodiments provided below can be found in the limitations of the account category identification method described above, and will not be repeated here.

[0081] In one embodiment, such as Figure 4 As shown, an account category identification device is provided, including: an account data acquisition module 402, a hypothetical value interval division module 404, a key-value pair acquisition module 406, a category determination module 408, and a category relationship determination module 410, wherein:

[0082] The account data acquisition module 402 is used to acquire data from multiple accounts; the account data includes multiple influencing factors that affect the category to which an account belongs.

[0083] The hypothesis value interval division module 404 is used to obtain multiple initial hypothesis values ​​corresponding to each impact factor; and to divide the multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the impact factor.

[0084] The key-value pair acquisition module 406 is used to obtain multiple key-value pairs based on multiple initial hypothesis values ​​within the hypothesis value interval; wherein, a key-value pair consists of a target hypothesis value and an influence factor within the hypothesis value interval; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value interval.

[0085] The category determination module 408 is used to assign the target hypothesis value to multiple account data with influence factors based on key-value pairs, calculate the category value corresponding to each account data under each key-value pair, and determine the category of each account data based on the category value.

[0086] The category relationship determination module 410 is used to determine the relationship between the influence factors of different values ​​and the categories of account data based on the categories of multiple account data under each key-value pair.

[0087] In one embodiment, the key-value pair acquisition module 406 may include:

[0088] The key-value pair building submodule is used to select an initial hypothesis value that has not been selected within the hypothesis value range as the target hypothesis value, and obtain a key-value pair consisting of the target hypothesis value and the influence factor; repeat the above steps until the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value range.

[0089] In one embodiment, before dividing multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the influence factors, the above-mentioned apparatus may further include:

[0090] The initial threshold acquisition module is used to obtain multiple initial thresholds corresponding to the influence factors from the stored objects.

[0091] The threshold list acquisition module is used to deduplicate and sort multiple initial thresholds for each impact factor to obtain a threshold list for the corresponding impact factor; wherein, the threshold list includes multiple thresholds corresponding to the impact factor.

[0092] In one embodiment, the category determination module 408 may include:

[0093] The target hypothesis value acquisition submodule is used to select an initial hypothesis value that has not been selected before as the target hypothesis value for each hypothesis value interval.

[0094] The Hypothesis Value Interval Sorting Submodule is used to determine the sorting of multiple hypothesis value intervals based on a threshold list.

[0095] The target hypothesis sorting submodule is used to determine the sorting of multiple target hypothesis values ​​based on the sorting of multiple hypothesis value intervals.

[0096] The assignment submodule is used to assign target hypothesis values ​​to multiple account data with influence factors in sequence based on the sorting of multiple target hypothesis values.

[0097] In one embodiment, the above-described apparatus may further include:

[0098] The relational storage module is used to store the relationship between influence factors and the categories of account data into a storage object.

[0099] In one embodiment, the relational storage module may include:

[0100] The category value acquisition submodule is used to obtain the category values ​​of multiple account data with target hypothesis values ​​for each impact factor.

[0101] The storage submodule is used to obtain the average of the category values ​​of multiple account data and store the influence factors, multiple hypothesis values, and multiple averages into a storage object.

[0102] Each module in the aforementioned account category 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, or stored in the memory of a computer device as software, so that the processor can invoke and execute the corresponding operations of each module.

[0103] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational 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 the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data such as influence factors, initial hypothesis values, and target hypothesis values. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements an account category identification method.

[0104] Those skilled in the art will understand that Figure 5 The 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.

[0105] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring multiple account data; the account data includes multiple influence factors affecting the category to which an account belongs; for each influence factor, acquiring multiple initial hypothesis values ​​corresponding to the influence factor; dividing the multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the influence factors; obtaining multiple key-value pairs based on the multiple initial hypothesis values ​​within the hypothesis value intervals; wherein, a key-value pair consists of a target hypothesis value and an influence factor within the hypothesis value interval; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value intervals; assigning the target hypothesis value to the multiple account data with influence factors based on the key-value pairs, calculating the category value corresponding to each account data under each key-value pair, and determining the category of each account data based on the category value; and obtaining the relationship between influence factors with different values ​​and the category of account data based on the categories of multiple account data under each key-value pair.

[0106] In one embodiment, when the processor executes the computer program, it further implements the process of obtaining multiple key-value pairs based on multiple initial hypothesis values ​​within the hypothesis value range. This may include: selecting an initial hypothesis value within the hypothesis value range that has not been selected before as the target hypothesis value, and obtaining a key-value pair consisting of the target hypothesis value and the influence factor; repeating the above steps until the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value range.

[0107] In one embodiment, before the processor executes the computer program to divide multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the impact factors, the following steps may also be performed: obtaining multiple initial thresholds corresponding to the impact factors from a storage object; for each impact factor, deduplicating and sorting the multiple initial thresholds to obtain a threshold list for the corresponding impact factor; wherein the threshold list includes multiple thresholds corresponding to the impact factors.

[0108] In one embodiment, when the processor executes the computer program, it further implements assigning target hypothesis values ​​to multiple account data with influence factors based on key-value pairs. This may include: for each hypothesis value interval, selecting an initial hypothesis value that has not been selected before as the target hypothesis value; determining the order of multiple hypothesis value intervals based on a threshold list; determining the order of multiple target hypothesis values ​​based on the order of the multiple hypothesis value intervals; and assigning the target hypothesis values ​​to the multiple account data with influence factors sequentially based on the order of the multiple target hypothesis values.

[0109] In one embodiment, when the processor executes a computer program, it may also perform the following steps: storing the relationship between the influence factor and the category of account data into a storage object.

[0110] In one embodiment, when the processor executes the computer program, it further implements storing the relationship between the impact factor and the categories of account data into a storage object, which may include: for each impact factor, obtaining the category values ​​of multiple account data with target hypothesis values; obtaining the average of the category values ​​of the multiple account data; and storing the impact factor, the multiple hypothesis values, and the multiple average values ​​into the storage object.

[0111] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When executed by a processor, the computer program performs the following steps: acquiring multiple account data; the account data includes multiple influence factors affecting the category to which an account belongs; for each influence factor, acquiring multiple initial hypothesis values ​​corresponding to the influence factor; dividing the multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the influence factors; obtaining multiple key-value pairs based on the multiple initial hypothesis values ​​within the hypothesis value intervals; wherein, a key-value pair consists of a target hypothesis value and an influence factor within the hypothesis value interval; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value intervals; assigning the target hypothesis value to the multiple account data with influence factors based on the key-value pairs, calculating the category value corresponding to each account data under each key-value pair, and determining the category of each account data based on the category value; and obtaining the relationship between influence factors of different values ​​and the category of account data based on the categories of multiple account data under each key-value pair.

[0112] In one embodiment, when the computer program is executed by the processor, it further implements the process of obtaining multiple key-value pairs based on multiple initial hypothesis values ​​within the hypothesis value range. This may include: selecting an initial hypothesis value within the hypothesis value range that has not been selected before as the target hypothesis value, and obtaining a key-value pair consisting of the target hypothesis value and the influence factor; repeating the above steps until the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value range.

[0113] In one embodiment, before the computer program is executed by the processor to divide multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the impact factors, the following steps may also be performed: obtaining multiple initial thresholds corresponding to the impact factors from a storage object; for each impact factor, deduplicating and sorting the multiple initial thresholds to obtain a threshold list for the corresponding impact factor; wherein the threshold list includes multiple thresholds corresponding to the impact factors.

[0114] In one embodiment, when the computer program is executed by a processor, it further implements assigning target hypothesis values ​​to multiple account data with influence factors based on key-value pairs. This may include: for each hypothesis value interval, selecting an initial hypothesis value that has not been selected before as the target hypothesis value; determining the order of multiple hypothesis value intervals based on a threshold list; determining the order of multiple target hypothesis values ​​based on the order of the multiple hypothesis value intervals; and assigning the target hypothesis values ​​to the multiple account data with influence factors sequentially based on the order of the multiple target hypothesis values.

[0115] In one embodiment, when the computer program is executed by a processor, it may also perform the following steps: storing the relationship between the influence factor and the category of account data into a storage object.

[0116] In one embodiment, when the computer program is executed by the processor, it further implements storing the relationship between the impact factor and the categories of account data into a storage object, which may include: for each impact factor, obtaining the category values ​​of multiple account data with target hypothesis values; obtaining the average of the category values ​​of the multiple account data; and storing the impact factor, the multiple hypothesis values, and the multiple average values ​​into the storage object.

[0117] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: acquiring multiple account data; the account data includes multiple influence factors affecting the category to which an account belongs; for each influence factor, acquiring multiple initial hypothesis values ​​corresponding to the influence factor; dividing the multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the influence factors; obtaining multiple key-value pairs based on the multiple initial hypothesis values ​​within the hypothesis value intervals; wherein, a key-value pair consists of a target hypothesis value and an influence factor within the hypothesis value interval; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value intervals; assigning the target hypothesis value to the multiple account data with influence factors based on the key-value pairs, calculating the category value corresponding to each account data under each key-value pair, and determining the category of each account data based on the category value; and obtaining the relationship between influence factors of different values ​​and the category of account data based on the categories of multiple account data under each key-value pair.

[0118] In one embodiment, when the computer program is executed by the processor, it further implements the process of obtaining multiple key-value pairs based on multiple initial hypothesis values ​​within the hypothesis value range. This may include: selecting an initial hypothesis value within the hypothesis value range that has not been selected before as the target hypothesis value, and obtaining a key-value pair consisting of the target hypothesis value and the influence factor; repeating the above steps until the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value range.

[0119] In one embodiment, before the computer program is executed by the processor to divide multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the impact factors, the following steps may also be performed: obtaining multiple initial thresholds corresponding to the impact factors from a storage object; for each impact factor, deduplicating and sorting the multiple initial thresholds to obtain a threshold list for the corresponding impact factor; wherein the threshold list includes multiple thresholds corresponding to the impact factors.

[0120] In one embodiment, when the computer program is executed by a processor, it further implements assigning target hypothesis values ​​to multiple account data with influence factors based on key-value pairs. This may include: for each hypothesis value interval, selecting an initial hypothesis value that has not been selected before as the target hypothesis value; determining the order of multiple hypothesis value intervals based on a threshold list; determining the order of multiple target hypothesis values ​​based on the order of the multiple hypothesis value intervals; and assigning the target hypothesis values ​​to the multiple account data with influence factors sequentially based on the order of the multiple target hypothesis values.

[0121] In one embodiment, when the computer program is executed by a processor, it may also perform the following steps: storing the relationship between the influence factor and the category of account data into a storage object.

[0122] In one embodiment, when the computer program is executed by the processor, it further implements storing the relationship between the impact factor and the categories of account data into a storage object, which may include: for each impact factor, obtaining the category values ​​of multiple account data with target hypothesis values; obtaining the average of the category values ​​of the multiple account data; and storing the impact factor, the multiple hypothesis values, and the multiple average values ​​into the storage object.

[0123] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0124] 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. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, 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, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0125] 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.

[0126] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. 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 application should be determined by the appended claims.

Claims

1. A method for identifying account categories, characterized in that, The method includes: Acquire data from multiple accounts; the account data includes: multiple influencing factors that affect the category to which an account belongs; For each of the impact factors, multiple initial hypothesis values ​​are obtained; based on multiple thresholds corresponding to the impact factors, the multiple initial hypothesis values ​​are divided into multiple hypothesis value intervals; Based on multiple initial hypothetical values ​​within the hypothetical value interval, multiple key-value pairs are obtained; wherein, each key-value pair consists of a target hypothetical value within the hypothetical value interval and the influence factor; the number of key-value pairs is the same as the number of initial hypothetical values ​​within the hypothetical value interval. Based on the key-value pairs, the target hypothesis value is assigned to multiple account data with the influence factor, the category value corresponding to each account data under each key-value pair is calculated, and the category of each account data is determined based on the category value; Based on the categories of multiple account data under each key-value pair, the relationship between the influence factor with different values ​​and the category of the account data is obtained; The process of obtaining multiple key-value pairs based on multiple initial hypothesis values ​​within the hypothesis value range includes: Select an initial hypothesis value that has not been selected within the hypothesis value interval as the target hypothesis value, and obtain a key-value pair consisting of the target hypothesis value and the influence factor; repeat the above steps until the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value interval.

2. The method according to claim 1, characterized in that, Before dividing the multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the influence factors, the method further includes: Obtain multiple initial thresholds corresponding to the influence factors from the stored object; For each of the impact factors, the initial thresholds are deduplicated and sorted to obtain a threshold list corresponding to the impact factor; wherein, the threshold list includes multiple thresholds corresponding to the impact factor.

3. The method according to claim 2, characterized in that, The step of assigning the target hypothesis value to multiple account data points having the influence factor based on the key-value pairs includes: For each of the hypothetical value intervals, select an initial hypothetical value that has not been selected before within the hypothetical value interval as the target hypothetical value; Based on the threshold list, the order of the multiple hypothetical value intervals is determined; Based on the sorting of multiple ranges of said hypothetical values, determine the sorting of multiple target hypothetical values; Based on the sorting of multiple target hypothesis values, the target hypothesis values ​​are sequentially assigned to multiple account data with the influence factor.

4. The method according to claim 1, characterized in that, The method further includes: The relationship between the influencing factors and the categories of the account data is stored in a storage object.

5. The method according to claim 4, characterized in that, The step of storing the relationship between the influencing factor and the category of the account data in a storage object includes: For each of the aforementioned influencing factors, obtain category values ​​for multiple account data points that have the target hypothesis value; Obtain the average value of the category values ​​of multiple account data, and store the influence factor, multiple hypothetical values ​​and multiple average values ​​into the storage object.

6. An account category identification device, characterized in that, The device includes: The account data acquisition module is used to acquire data from multiple accounts; the account data includes multiple influencing factors that affect the category to which an account belongs; The hypothesis value interval division module is used to obtain multiple initial hypothesis values ​​corresponding to each influence factor; and to divide the multiple initial hypothesis values ​​into multiple hypothesis value intervals based on multiple thresholds corresponding to the influence factors. The key-value pair acquisition module is used to obtain multiple key-value pairs based on multiple initial hypothesis values ​​within the hypothesis value interval; wherein, each key-value pair consists of a target hypothesis value within the hypothesis value interval and the influence factor; the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value interval; The category determination module is used to assign the target hypothesis value to multiple account data with the influence factor based on the key-value pair, calculate the category value corresponding to each account data under each key-value pair, and determine the category of each account data based on the category value; The category relationship determination module is used to determine the relationship between the influence factor with different values ​​and the category of the account data based on the category of multiple account data under each key-value pair; The key-value pair acquisition module includes: The key-value pair assembly submodule is used to select an initial hypothesis value that has not been selected within the hypothesis value interval as the target hypothesis value, and obtain a key-value pair composed of the target hypothesis value and the influence factor; repeat the above steps until the number of key-value pairs is the same as the number of initial hypothesis values ​​within the hypothesis value interval.

7. The apparatus according to claim 6, characterized in that, The above-mentioned device includes: An initial threshold acquisition module is used to acquire multiple initial thresholds corresponding to the influence factor from a stored object; The threshold list acquisition module is used to deduplicate and sort multiple initial thresholds for each of the impact factors to obtain a threshold list corresponding to the impact factor; wherein, the threshold list includes multiple thresholds corresponding to the impact factor.

8. 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 5.

9. 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 5.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 5.

Images