Method, device and equipment for determining data index and storage medium

Abstract

The application discloses a data index determination method and device, equipment and a storage medium. Specifically, the method comprises the following steps: obtaining behavior characteristic information of a target service in a preset time period; calculating information entropy of each behavior characteristic information; determining behavior characteristic information corresponding to information entropy satisfying a preset threshold condition as a first data index; clustering the first data index by using a preset clustering model to obtain a target data index. According to the embodiment of the application, the data index obtained is more accurate, and the conclusion derived from the data index is more accurate and effective.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computer, and particularly relates to a data index determination method and device, equipment and a storage medium. BACKGROUND

[0002] With the rapid development of the business scale and operation of the operator, the number of supporting system indexes is also increasing, and the business subdivision trend is obvious.

[0003] In the related art, based on the business attribute or index trend analysis, the required data index can be obtained. However, the related art cannot be well applied to the processing of a large number of subdivided business data indexes, resulting in deviation of the data index obtained by analysis, and then resulting in poor accuracy of the conclusion derived from the data index. SUMMARY

[0004] The embodiments of the present application provide a data index determination method, device, equipment and computer storage medium, which can obtain more accurate data indexes, and then derive more accurate and effective conclusions from the data indexes.

[0005] In a first aspect, the embodiments of the present application provide a data index determination method, which comprises:

[0006] Obtaining behavior characteristic information of a target business in a preset time period;

[0007] Calculating information entropy of each behavior characteristic information;

[0008] Determining behavior characteristic information corresponding to the information entropy satisfying a preset threshold condition as a first data index;

[0009] Clustering the first data index by using a preset clustering model to obtain a target data index.

[0010] Optionally, the obtaining of the behavior characteristic information of the target business in the preset time period comprises:

[0011] Obtaining user characteristic information of the target business;

[0012] Determining behavior characteristic information of the target business in a preset time period according to the user characteristic information and a preset business behavior index relationship.

[0013] Optionally, the calculating of the information entropy of each behavior characteristic information comprises:

[0014] Calculating a normalized value corresponding to each behavior characteristic information;

[0015] Determining the information entropy according to the normalized value corresponding to each behavior characteristic information.

[0016] Optionally, the behavior characteristic information corresponding to the information entropy satisfying the preset threshold condition is a first data indicator, and the method comprises:

[0017] When the information entropy is less than the preset threshold, the behavior characteristic information corresponding to the information entropy is determined as the first data indicator.

[0018] Optionally, the preset clustering model comprises a first clustering model and a second clustering model.

[0019] The first data indicator is clustered by using the preset clustering model to obtain a target data indicator, and the method comprises:

[0020] The first data indicator is subjected to density clustering by using the first clustering model to obtain a first clustering result.

[0021] The first data indicator is subjected to prototype clustering by using the second clustering model to obtain a second clustering result.

[0022] The first clustering result and the second clustering result are superimposed to obtain the target data indicator.

[0023] Optionally, the first data indicator is clustered by using the preset clustering model to obtain a target data indicator, and the method comprises:

[0024] The first data indicator is clustered by using the preset clustering model to obtain a first result.

[0025] The first result is clustered by using the preset clustering model to obtain the target data indicator.

[0026] Optionally, the first clustering model is a DBSCAN clustering model, and the second clustering model is a K-means clustering model.

[0027] In a second aspect, an embodiment of the present application provides a data indicator determination apparatus, and the apparatus comprises:

[0028] An acquisition module is configured to acquire behavior characteristic information of a target service in a preset time period.

[0029] A calculation module is configured to calculate information entropy of each behavior characteristic information.

[0030] A determination module is configured to determine behavior characteristic information corresponding to the information entropy satisfying a preset threshold condition as a first data indicator.

[0031] A clustering module is configured to cluster the first data indicator by using a preset clustering model to obtain a target data indicator.

[0032] In a third aspect, an embodiment of the present application provides a data indicator determination device, and the device comprises:

[0033] a processor and a memory storing computer program instructions;

[0034] The processor implements the data index determination method as described in the first aspect and any one of the optional aspects of the first aspect when executing the computer program instructions.

[0035] In a fourth aspect, the embodiments of the present application provide a computer storage medium, which stores computer program instructions. The computer program instructions are executed by a processor to implement the data index determination method as described in the first aspect and any one of the optional aspects of the first aspect.

[0036] The data index determination method, device, equipment and computer storage medium provided by the embodiments of the present application can obtain the first data index with key information by calculating the information entropy of the behavior characteristic information of the target service and filtering the behavior characteristic information. The target data index is determined by using the preset clustering model to exclude the noise data in the first data index. The data index obtained in this way is more accurate, and the conclusion derived from the data index is more accurate and effective. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. Those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0038] Figure 1 is a flowchart of the data index determination method provided by some embodiments of the present application;

[0039] Figure 2 is a flowchart of the clustering analysis provided by some embodiments of the present application;

[0040] Figure 3 is a schematic diagram of the clustering analysis process provided by some other embodiments of the present application;

[0041] Figure 4 is a structural schematic diagram of the data index determination device provided by some embodiments of the present application;

[0042] Figure 5 is a hardware structural schematic diagram of the data index determination equipment provided by some embodiments of the present application. DETAILED DESCRIPTION

[0043] The features and exemplary embodiments of the various aspects of the present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely configured to explain the present application and are not configured to limit the present application. The present application can be implemented without some of the specific details described below. The following description of the embodiments is merely provided to provide a better understanding of the present application by showing examples of the present application.

[0044] It should be noted that, in this document, the terms such as first and second are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the elements defined by the statement "include" do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.

[0045] The currently built index system is subdivided by business logic to form an index system, for example, single classification according to business attributes, or classification according to different historical trends of data indexes. The index system determined based on the method in the related art is remarkable in supporting small-scale marketing or business guarantee effect. However, with the rapid development of operator business, the business subdivision trend is obvious, and the data indexes determined based on the method in the related art have deviations due to insufficient consideration of the correlation between indexes, resulting in poor operation accuracy and operation effect of the data index system, and poor accuracy of conclusions derived from the data indexes.

[0046] To solve the problems in the prior art, the embodiments of the present application provide a data index determination method, device, equipment and computer storage medium, which can obtain more accurate data indexes, and thus the conclusions derived from the data indexes are more accurate and effective.

[0047] The data index determination method, device, equipment and computer storage medium provided by the embodiments of the present application will be described below with reference to the accompanying drawings. It should be noted that these embodiments are not used to limit the scope of the present disclosure.

[0048] The data index determination method provided by the embodiments of the present application will be introduced first.

[0049] Figure 1 is a flowchart of a method for determining a data index provided by some embodiments of the present application. As shown in the figure, in the embodiments of the present application, the method for determining the data index can include the following steps: Figure 1

[0050] S101: Obtain behavior characteristic information of a target business in a preset time period.

[0051] The target business can include a business scenario to be analyzed. The behavior characteristic information can include customer behavior characteristic information or behavior characteristic information of an operator, such as a salesperson. The behavior characteristic information can be a data index to be analyzed and related to the target business.

[0052] For example, the target business can be a revenue management business, and the behavior characteristic information corresponding to the revenue management business can include the following behavior characteristic information: revenue, digital service revenue, main package, traffic volume, user points, customer star rating, customer terminal type, total traffic volume, interworking traffic volume, roaming, local, long distance, roaming calling, roaming called, interworking daily share, interworking monthly share, etc.

[0053] The target business can be a user service management business, and the behavior characteristic information corresponding to the revenue management business can include the following behavior characteristic information: main package, total traffic volume, user points, customer star rating, customer terminal type, interworking traffic volume, roaming, local, long distance, roaming calling, roaming called, interworking daily share, interworking monthly share, etc.

[0054] The preset time period can be a time period of two years before the current date.

[0055] In some embodiments of the present application, determining the behavior characteristic information of the target business in the preset time period can specifically include:

[0056] First, obtain user characteristic information of the target business. Then, determine the behavior characteristic information of the target business in the preset time period according to the user characteristic information and a preset business behavior index relationship.

[0057] The preset business behavior index relationship can be a preset user behavior index relationship portrait. The preset business behavior index relationship can include user characteristic information of the target business and corresponding behavior characteristic information of the user. When analyzing the data index, based on the preset business behavior index relationship, the correlation between the indexes can be better discovered to improve the accuracy of determining the data index.

[0058] In some embodiments of the present application, the behavior characteristic information of the target business can be obtained from a customer relationship management (CRM) system of an operator. ​

[0059] S102: Calculate the information entropy of each behavioral feature.

[0060] Information entropy is a comprehensive measure of system complexity. The average amount of information after eliminating redundancy is called information entropy.

[0061] In some embodiments of this application, firstly, the normalized value corresponding to each behavioral feature information can be calculated. Then, based on the normalized value corresponding to each behavioral feature information, the information entropy is determined.

[0062] For example, as shown in Table 1, user behavior characteristics include: daily operation frequency, number of objects contacted, and amount involved.

[0063] User ID Average operation frequency Number of contact objects Amount involved (ten thousand) XA2238 569 65 12.35 XA2349 772 76 14.58

[0064] Table 1

[0065] Based on the user and behavioral characteristic information in Table 1, first construct the user behavioral characteristic information matrix X = (X... ij ) mxn m is the number of users, n is the number of behavioral features, i represents the i-th user, and j represents the j-th behavioral feature information.

[0066] Calculate the normalized value p of each behavioral feature information. ij For example, as shown in Table 1, the normalized value p of the behavioral characteristic information "average operation frequency" of user XA2238 11 =569÷(569-772)=0.426.

[0067] Based on the normalized values ​​corresponding to each behavioral feature, the information entropy e is calculated using the following formula (1). j :

[0068]

[0069] i = 1, 2, 3, ..., m;

[0070] j = 1, 2, 3, ..., n

[0071] Where, p ij Let i be the normalized value corresponding to the behavioral feature information, where i represents the i-th user and j represents the j-th behavioral feature information.

[0072] S103: Determine the behavioral feature information corresponding to the information entropy that meets the preset threshold condition as the first data indicator.

[0073] In some embodiments of this application, the preset threshold condition may be that the information entropy is less than a preset threshold.

[0074] When the information entropy of the behavior characteristic information of the user is less than a preset threshold, the behavior characteristic information corresponding to the information entropy is determined as the first data index. Exemplarily, the preset threshold can be 0.9.

[0075] Exemplarily, for the user average operation frequency of the behavior characteristic information, if each user behavior characteristic information shows the same trend, the e j value of the corresponding e j is the largest, and at this time, for the comparison of the scheme or the analysis of the index, for example, for the customer segmentation, the behavior characteristic information as the data index is almost meaningless.

[0076] When the behavior characteristic information of each user is more different, the e j is smaller, the difference of the behavior characteristic information is greater, and the role of the behavior characteristic information for the comparison of the scheme or the analysis of the index is greater, for example, the difference of the behavior characteristic information is more beneficial to the comparison of the customer segmentation.

[0077] S104: Clustering the first data index by using a preset clustering model to obtain a target data index.

[0078] In some embodiments of the present application, the preset clustering model can include a first clustering model and a second clustering model. The preset clustering model can be a double-algorithm model. The S104 can be specifically implemented as the following steps:

[0079] First, the first data index is subjected to density clustering by using the first clustering model to obtain a first clustering result. Then, the first data index is subjected to prototype clustering by using the second clustering model to obtain a second clustering result. The first clustering result and the second clustering result are superimposed to obtain the target data index.

[0080] In some embodiments of the present application, the S104 can also be implemented as the following steps:

[0081] First, the first data index is clustered by using the preset clustering model to obtain a first result. Then, the first result is clustered by using the preset clustering model to obtain the target data index.

[0082] Here, the preset clustering model is used twice to cluster to obtain the target data index. The first result can be obtained by clustering the first data index. Then, the data index obtained by the first clustering is clustered again by using the preset clustering model to obtain the target data index.

[0083] Thus, in the embodiments of the present application, the determination method of the data index can calculate the information entropy of the behavior characteristic information of the target service, filter the behavior characteristic information, and obtain the first data index with key information. The preset clustering model is used to exclude the noise data in the first data index, so as to determine the target data index. The data index obtained in this way is more accurate, and the conclusion derived from the data index is more accurate and effective.

[0084] In some embodiments of the present application, in order to further improve the accuracy of the clustering result, the above two implementation manners of the step can be combined to cluster the first data index to obtain the target data index. Figure 2 is a flowchart of the clustering analysis provided by an embodiment of the present application. As shown in Figure 2 The S104 can also be implemented as the following steps.

[0085] S201: using the first clustering model to perform density clustering on the first data index to obtain a first clustering result.

[0086] S202: using the second clustering model to perform prototype clustering on the first data index to obtain a second clustering result.

[0087] S203: superimposing the first clustering result and the second clustering result to obtain a first result.

[0088] Here, superimposing the first clustering result and the second clustering result can include taking the intersection of the first clustering result and the second clustering result.

[0089] S204: using the first clustering model to perform density clustering on the first result to obtain a third clustering result.

[0090] S205: using the first clustering model to perform density clustering on the third clustering result to obtain a fourth clustering result.

[0091] S206: using the preset clustering model to cluster the fourth clustering result to obtain a target data index.

[0092] In some embodiments of the present application, the first clustering model can be a model based on the DBSCAN clustering algorithm. The second clustering model can be a model based on the K-means clustering algorithm.

[0093] DBSCAN clustering is a density-based clustering algorithm. DBSCAN searches for clusters by examining the Eps neighborhood of each point in the dataset. If the Eps neighborhood of a point p contains more than MinPts points, a cluster is created with p as the core object. DBSCAN iteratively gathers objects that are density-reachable from these core objects, and this process can involve merging of some density-reachable clusters. When no new points are added to any cluster, the process ends, and the data points not included in any cluster constitute noise points.

[0094] K-Means clustering is a prototype-based clustering algorithm. The principle includes: first, determine the value of K and initialize the cluster center, select K initial condensation points as the cluster center to be formed. Then, calculate the distance from each observation to the K condensation points, and divide each observation and the nearest condensation point into a group to form K initial classifications. Calculate the distance from each observation to the K condensation points, and divide each observation and the nearest condensation point into a group to form K initial classifications; (4) repeat the above distance calculation until the center of gravity of the initial classification does not change significantly.

[0095] Using the K-Means clustering model and the DBSCAN clustering model, the two result sets are combined, and the superimposed two result sets are obtained by a secondary composite algorithm to obtain the required result set, that is, the target data index.

[0096] In some embodiments of the present application, an example is taken to analyze the sensitive behavior index of the single-day operator operating the CRM system. The behavior characteristic information (data index) shown in Table 2 is obtained by calculating based on information entropy.

[0097]

[0098]

[0099] Table 2

[0100] Figure 3 is a schematic diagram of the clustering analysis process provided by some other embodiments of the present application. As shown in Figure 3 , the data index of the single-day user in Table 2, that is, the average operation frequency, the number of contact objects and the involved amount of each user are respectively subjected to K-Means clustering model and DBSCAN clustering to obtain two clustering results based on the two clustering algorithms. Then, the two clustering results are combined, and the combined clustering results are subjected to secondary clustering by using the K-Means clustering model and the DBSCAN clustering, respectively, to obtain the target data index as the result, that is, the data index for sensitive behavior analysis of the single-day operator operating the CRM system.

[0101] The double algorithm model is formed by combining the K-Means clustering model and the DBSCAN clustering model, the first data index is clustered twice by using the double algorithm model, "white noise" can be effectively removed, and the target data index can be more accurately output by fitting.

[0102] In conclusion, in the embodiment of the present application, the data index determination method can calculate the information entropy of the behavior characteristic information of the target service, filter the behavior characteristic information, and obtain the first data index with key information. The preset clustering model is used to exclude noise data in the first data index to determine the target data index. The data index obtained in this way is more accurate, and the conclusion derived from the data index is more accurate and effective.

[0103] Based on the data index determination method provided in the above embodiments, the present application also provides a specific implementation of a data index determination device. Please refer to the following embodiments.

[0104] Figure 4 is a flowchart of a data index determination device provided by an embodiment of the present application. As shown in Figure 4 In the embodiment of the present application, the data index determination device can include:

[0105] The acquisition module 401 is configured to acquire the behavior characteristic information of the target service in a preset time period.

[0106] The calculation module 402 is configured to calculate the information entropy of each behavior characteristic information.

[0107] The determination module 403 is configured to determine the behavior characteristic information corresponding to the information entropy satisfying the preset threshold condition as the first data index.

[0108] The clustering module 404 is configured to cluster the first data index by using a preset clustering model to obtain the target data index.

[0109] In conclusion, in the embodiment of the present application, the data index determination device can be used to execute the data index determination method in the above embodiments. The method can calculate the information entropy of the behavior characteristic information of the target service, filter the behavior characteristic information, and obtain the first data index with key information. The preset clustering model is used to exclude noise data in the first data index to determine the target data index. The data index obtained in this way is more accurate, and the conclusion derived from the data index is more accurate and effective.

[0110] In some embodiments of the present application, the obtaining module 401 is further configured to obtain user feature information of the target service; and determine the behavior feature information of the target service in the preset time period according to the user feature information and a preset service behavior index relationship.

[0111] In some embodiments of the present application, the calculating module 402 is further configured to calculate a normalized value corresponding to each behavior feature information; and determine the information entropy according to the normalized value corresponding to each behavior feature information.

[0112] In some embodiments of the present application, the determining module 403 is further configured to determine the behavior feature information corresponding to the information entropy as the first data index when the information entropy is less than a preset threshold.

[0113] In some embodiments of the present application, the preset clustering model includes a first clustering model and a second clustering model.

[0114] In some embodiments of the present application, the clustering module 404 is configured to perform density clustering on the first data index by using the first clustering model to obtain a first clustering result; perform prototype clustering on the first data index by using the second clustering model to obtain a second clustering result; and superimpose the first clustering result and the second clustering result to obtain the target data index.

[0115] In some embodiments of the present application, the clustering module 404 is further configured to cluster the first data index by using the preset clustering model to obtain a first result; and cluster the first result by using the preset clustering model to obtain the target data index.

[0116] Figure 4 Each module / unit in the apparatus has the function of implementing each step of the method and can achieve the corresponding technical effects. For brevity, no further description is given here. Figure 1 and 2 Each step of the method and can achieve the corresponding technical effects. For brevity, no further description is given here.

[0117] Based on the data index determination method provided in the above embodiments, the present application also provides a specific implementation of the data index determination apparatus. Please refer to the following embodiments.

[0118] Figure 5 FIG. 1 is a hardware structure schematic diagram of the data index determination apparatus provided in some embodiments of the present application.

[0119] The data index determination apparatus can include a processor 501 and a memory 502 having computer program instructions stored therein.

[0120] In particular, the processor 501 can include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or can be configured to implement one or more integrated circuits that embody the embodiments of the present application.

[0121] The memory 502 can include mass storage for data or instructions. By way of example, and not limitation, the memory 502 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc, a magneto-optical disc, magnetic tape, or a Universal Serial Bus (USB) drive or a combination of two or more of these. The memory 502 can be removable and / or non-removable (or fixed) as appropriate. The memory 502 can be internal or external as appropriate. In certain embodiments, the memory 502 is non-volatile solid-state memory. In certain embodiments, the memory 502 includes read-only memory (ROM). Where appropriate, this ROM can be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0122] The processor 501 implements the determination method of any one of the data indicators in the above embodiments by reading and executing the computer program instructions stored in the memory 502.

[0123] In one example, the data indicator determination device can further include a communication interface 503 and a bus 510. As shown, the processor 501, the memory 502, and the communication interface 503 are connected by the bus 510 and complete communication with each other. Figure 5

[0124] The communication interface 503 is mainly used to realize the communication between the modules, devices, units and / or equipment in the embodiments of the present application.

[0125] ​Bus 510 includes a hardware, software, or both that couples components of the data metric determination apparatus to each other. As an example without limitation, bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand (IB) interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or another suitable bus or a combination of two or more of these. Where appropriate, bus 510 can include one or more buses. Although this application describes and illustrates a particular bus, this application contemplates any suitable bus or interconnect.

[0126] The data metric determination apparatus can execute the data metric determination method in the embodiments of the application, thereby realizing the data metric determination method described in combination with Figure 1 and Figure 2 the embodiments of the application.

[0127] In addition, in combination with the data metric determination method in the above embodiments, the embodiments of the application can provide a computer storage medium to realize. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to realize any one of the data metric determination methods in the above embodiments.

[0128] It needs to be clear that the application is not limited to the specific configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of well-known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after understanding the spirit of the application.

[0129] The functions noted in the description of the structural block diagrams above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transport information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0130] It is also important to note that the examples mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the steps mentioned above, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0131] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer program instructions can also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other processing device to operate in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks. The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer program instructions can also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other processing device to operate in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0132] The above merely describes a specific implementation of the present application. Those skilled in the art can clearly understand the specific working processes of the system, modules and units described above for the convenience and brevity of description, and can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited to this, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A method of determining a data indicator, characterized by, The method comprises: obtaining behavior characteristic information of a target service in a preset time period; calculating information entropy of each behavior characteristic information; determining behavior characteristic information corresponding to the information entropy satisfying a preset threshold condition as a first data index; clustering the first data index by using a preset clustering model to obtain a target data index; the obtaining of the behavior characteristic information of the target service in the preset time period comprises: obtaining user characteristic information of the target service; determining behavior characteristic information of the target service in a preset time period according to the user characteristic information and a preset service behavior index relationship; the calculation of the information entropy of each behavior characteristic information comprises: calculating a normalized value corresponding to each behavior characteristic information; determining the information entropy according to the normalized value corresponding to each behavior characteristic information; the determination of the behavior characteristic information corresponding to the information entropy satisfying the preset threshold condition as the first data index comprises: when the information entropy is less than a preset threshold value, determining the behavior characteristic information corresponding to the information entropy as the first data index; the preset clustering model comprises a first clustering model and a second clustering model; the clustering of the first data index by using the preset clustering model to obtain the target data index comprises: performing density clustering on the first data index by using the first clustering model to obtain a first clustering result; performing prototype clustering on the first data index by using the second clustering model to obtain a second clustering result; superimposing the first clustering result and the second clustering result to obtain the target data index.

2. The method of claim 1, wherein, the clustering of the first data index by using the preset clustering model to obtain the target data index comprises: clustering the first data index by using the preset clustering model to obtain a first result; clustering the first result by using the preset clustering model to obtain the target data index.

3. The method of claim 1, wherein, The first clustering model is a DBSCAN clustering model, and the second clustering model is a K-means clustering model.

4. An apparatus for determining a data indicator, the apparatus comprising: The device comprises: an obtaining module configured to obtain behavior characteristic information of a target service in a preset time period; a calculating module configured to calculate information entropy of each behavior characteristic information; a determining module configured to determine behavior characteristic information corresponding to the information entropy satisfying a preset threshold condition as a first data index; a clustering module configured to cluster the first data index by using a preset clustering model to obtain a target data index; the obtaining module is further configured to obtain the behavior characteristic information of the target service in the preset time period by: obtaining user characteristic information of the target service; determining behavior characteristic information of the target service in a preset time period according to the user characteristic information and a preset service behavior index relationship; the calculating module is further configured to calculate a normalized value corresponding to each behavior characteristic information; determining the information entropy according to the normalized value corresponding to each behavior characteristic information; The determination module is further configured to determine that the behavior feature information corresponding to the information entropy satisfying a preset threshold condition is a first data indicator, including: when the information entropy is less than a preset threshold, determining the behavior feature information corresponding to the information entropy as the first data indicator; The clustering module is further configured to include a first clustering model and a second clustering model in the preset clustering model; The first data indicator is clustered by using the preset clustering model to obtain a target data indicator, including: The first data indicator is subjected to density clustering by using the first clustering model to obtain a first clustering result; The first data indicator is subjected to prototype clustering by using the second clustering model to obtain a second clustering result; The first clustering result and the second clustering result are superimposed to obtain the target data indicator.

5. A data index determining apparatus characterized by comprising: The device comprises a processor and a memory storing computer program instructions; The processor executes the computer program instructions to implement the data indicator determination method of any one of claims 1 to 3.

6. A computer storage medium, characterized in that The computer storage medium stores computer program instructions, and the computer program instructions are executed by the processor to implement the data indicator determination method of any one of claims 1 to 3.

Images