Call record segmentation method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a call bill splitting method and device, electronic equipment and storage medium. The method comprises taking the user age, tariff, customer type, online time length, monthly average traffic of the previous preset number of months, cumulative traffic of the current month and current balance of a user as the values of static labels respectively, calculating the index variable of the static label and the corresponding first contribution rate according to the values of the static labels, and then calculating the splitting value of the call bill splitting for each user according to the values of the static labels, the index variable of the static label and the first contribution rate. In the embodiments of the present application, the multi-dimensional information of the user is used to agilely judge the call bill splitting opportunity, improve the accuracy of the splitting value for splitting the call bill, adapt the splitting value to the user, avoid frequent splitting of the call bill, reasonably reduce the interaction frequency, accurately control the generation of arrears, thereby reduce unnecessary call bill amount and control the arrears amount to the maximum extent under the premise of low message interaction amount.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a call bill splitting method, a call bill splitting device, an electronic device and a computer readable storage medium. BACKGROUND

[0002] The traditional call bill splitting is to use the flow threshold and time length threshold to split, and the specific steps are as follows: (1) the 4G online flow threshold reaches 100M, the 5G online flow threshold reaches 300M, and the network element will perform a call bill splitting; (2) the 4G online time length threshold and the 5G online time length threshold reach 60 minutes, and a call bill splitting will be performed; (3) when actually performing the call bill splitting, if any of the (1) and (2) is reached, a splitting will be generated; (4) each time the call bill splitting is generated, an interaction between the host systems will be generated.

[0003] However, using the above fixed flow threshold and time length threshold splitting method can easily cause waste of resource energy consumption and large amount of arrears, for example, when the user balance is sufficient and the network condition is relatively good, frequent splitting of the call bill causes resource waste, and when the fixed call bill splitting point starts from the time when the balance is insufficient, a large amount of user arrears is often generated. SUMMARY

[0004] The embodiments of the present application provide a light power distribution method, device, electronic device and storage medium to solve the problem of waste of resource energy consumption and large amount of arrears caused by using the fixed flow threshold and time length threshold splitting method.

[0005] The embodiments of the present application disclose a call bill splitting method, which comprises:

[0006] The user age, the user balance, the customer type, the online time length, the monthly average flow of the previous preset number of months, the cumulative flow of the current month and the current balance of the user are taken as the values of static labels respectively;

[0007] The values of the static labels are standardized to obtain standardized indexes of the static labels;

[0008] A static label correlation coefficient matrix is calculated according to the standardized indexes of the static labels of the user;

[0009] A first characteristic value and a first characteristic vector corresponding to the static label are calculated based on the static label correlation coefficient matrix;

[0010] An index variable of the static label is calculated according to the standardized indexes of the static label and the first characteristic vector corresponding thereto;

[0011] A first information contribution rate corresponding to each first characteristic value is calculated according to the first characteristic value.

[0012] The segmentation value for dividing call detail records is calculated based on the indicator variables of the static label, the value of the static label, and the first contribution rate.

[0013] Optionally, the step of calculating the segmentation value for dividing call detail records based on the indicator variable of the static label, the value of the static label, and the first contribution rate includes:

[0014] Obtain the initial segmentation value of the user;

[0015] Calculate the first difference between the index variable of the static label and the value of the static label;

[0016] The change in the initial segmentation value is calculated based on the first difference and its corresponding first contribution rate;

[0017] The segmentation value used for segmenting call detail records is calculated based on the initial segmentation value and the change in the initial segmentation value.

[0018] Optionally, after calculating the segmentation value for segmenting call detail records based on the indicator variables of the static label, the value of the static label, and the contribution rate, the method further includes:

[0019] The user's current network type, internet access time, current phone bill balance, monthly cumulative data traffic change, and current host call detail record processing capacity are used as the values ​​of the dynamic tag, respectively.

[0020] The values ​​of the dynamic tags are standardized to obtain the standardized index of the dynamic tags;

[0021] Calculate the dynamic tag correlation coefficient matrix based on the standardized metrics of the user's dynamic tags;

[0022] Based on the dynamic label correlation coefficient matrix, calculate the second feature value and the second feature vector corresponding to the dynamic label;

[0023] The indicator variables of the dynamic label are calculated based on the standardized indicators of the dynamic and static labels and their corresponding second feature vectors.

[0024] Calculate the second information contribution rate corresponding to each of the second feature values ​​based on the second feature values;

[0025] The change in call detail record (CDR) segmentation value is calculated based on the indicator variables of the dynamic tag, the value of the dynamic tag, and the contribution rate of the second information.

[0026] The segmentation value is updated by the change in call detail record segmentation to obtain a new segmentation value.

[0027] Optionally, calculating the change in call detail record (CDR) segmentation value based on the indicator variables of the dynamic tag, the value of the dynamic tag, and the second information contribution rate includes:

[0028] Calculate the second difference between the indicator variable of the dynamic label and the value of the dynamic label;

[0029] The change in call detail record (CDR) segmentation value is calculated based on the second difference and its corresponding second contribution rate.

[0030] Optionally, updating the segmentation value based on the change in call detail record segmentation to obtain a new segmentation value includes:

[0031] The sum of the change in call detail record segmentation and the segmentation value is used as the new segmentation value.

[0032] Optionally, after updating the segmentation value using the change in call detail record segmentation to obtain a new segmentation value, the method further includes:

[0033] The return function value is calculated using the new segmentation value, the second information contribution rate, and the standardized index of the dynamic label;

[0034] When the return function value is less than or equal to a preset threshold, the segmentation value is used as the new segmentation value.

[0035] This invention also discloses a call detail record (CDR) splitting device, comprising:

[0036] The tag value determination module is used to determine the user's age, tariff, customer type, network duration, average monthly traffic of the previous preset number of months, cumulative traffic of the current month, and current balance as the values ​​of static tags respectively;

[0037] A standardization processing module is used to standardize the values ​​of the static labels to obtain the standardized index of the static labels;

[0038] The matrix calculation module is used to calculate the static tag correlation coefficient matrix based on the standardized indicators of the user's static tags;

[0039] The feature calculation module is used to calculate the first feature value and the first feature vector corresponding to the static label based on the static label correlation coefficient matrix;

[0040] The variable calculation module is used to calculate the indicator variables of the static label based on the standardized index of the static label and its corresponding first feature vector.

[0041] The contribution rate calculation module is used to calculate the first information contribution rate corresponding to each of the first feature values ​​based on the first feature values.

[0042] The segmentation value calculation module is used to calculate the segmentation value for segmenting call detail records based on the indicator variables of the static label, the value of the static label, and the first contribution rate.

[0043] Optionally, the segmentation value calculation module includes:

[0044] The segmentation value acquisition submodule is used to acquire the user's initial segmentation value;

[0045] The difference calculation submodule is used to calculate the first difference between the index variable of the static label and the value of the static label;

[0046] The change calculation submodule is used to calculate the change in the initial segmentation value based on the first difference and its corresponding first contribution rate.

[0047] The segmentation value calculation submodule is used to calculate the segmentation value for segmenting call detail records based on the initial segmentation value and the change in the initial segmentation value.

[0048] Optionally, after calculating the segmentation value for segmenting call detail records based on the indicator variables of the static label, the value of the static label, and the contribution rate, the method further includes:

[0049] The tag value determination module is also used to determine the user's current network type, online time period, current call balance, monthly cumulative traffic change value, and current host call detail record processing capacity as the values ​​of dynamic tags.

[0050] The standardization processing module is also used to standardize the value of the dynamic label to obtain the standardized index of the dynamic label;

[0051] The matrix calculation module is also used to calculate the dynamic tag correlation coefficient matrix based on the standardized indicators of the user's dynamic tags;

[0052] The feature calculation module is also used to calculate the second feature value and the second feature vector corresponding to the dynamic label based on the dynamic label correlation coefficient matrix;

[0053] The variable calculation module is also used to calculate the indicator variables of the dynamic label based on the standardized indicators of the dynamic and static labels and their corresponding second feature vectors;

[0054] The contribution rate calculation module is also used to calculate the second information contribution rate corresponding to each of the second feature values ​​based on the second feature values;

[0055] The change calculation module is used to calculate the change in call detail record segmentation value based on the indicator variables of the dynamic tag, the value of the dynamic tag, and the contribution rate of the second information.

[0056] The segmentation value update module is used to update the segmentation value based on the change in call detail record segmentation to obtain a new segmentation value.

[0057] Optionally, the change calculation module includes:

[0058] The difference calculation submodule is also used to calculate a second difference between the indicator variable of the dynamic label and the value of the dynamic label;

[0059] The change calculation submodule is used to calculate the change in call detail record segmentation value based on the second difference and its corresponding second contribution rate.

[0060] Optionally, the segmentation value update module includes:

[0061] The segmentation value calculation submodule is used to take the sum of the call detail record segmentation change and the segmentation value as the new segmentation value.

[0062] Optionally, it also includes:

[0063] The reward function value calculation submodule is used to calculate the reward function value using the new segmentation value, the second information contribution rate, and the standardized index of the dynamic label;

[0064] The segmentation value confirmation module is used to use the segmentation value as the new segmentation value when the return function value is less than or equal to a preset threshold.

[0065] This invention also discloses an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0066] The memory is used to store computer programs;

[0067] When the processor executes a program stored in the memory, it implements the method described in the embodiments of the present invention.

[0068] This invention also discloses a computer-readable storage medium storing instructions that, when executed by one or more processors, cause the processors to perform the methods described in this invention.

[0069] The embodiments of this invention include the following advantages: By using a user's age, tariff, customer type, network duration, average monthly traffic over the previous preset number of months, cumulative monthly traffic, and current balance as static tag values, the indicator variables of the static tags and their corresponding first contribution rate are calculated. Furthermore, the segmentation value for each user's call detail record (CDR) can be calculated using the static tag values, the indicator variables of the static tags, and the first contribution rate. Compared to fixed traffic and duration thresholds for call detail record segmentation, this invention, based on multi-dimensional user information, especially balance information, quickly determines the timing of CDR segmentation, improving the accuracy of the segmentation value used for CDR segmentation. This ensures that the CDR segmentation value is adapted to the user, avoiding frequent CDR segmentation, reasonably reducing interaction frequency, thereby reducing message interaction volume and unnecessary CDR volume. Simultaneously, a reasonable CDR segmentation method can prevent users from incurring high outstanding charges. Attached Figure Description

[0070] Figure 1 This is a flowchart of the steps of a call detail record (CDR) segmentation method provided in an embodiment of the present invention;

[0071] Figure 2 This is a schematic diagram illustrating the overdue charges generated by fixed-step call detail record (CDR) segmentation in an embodiment of the present invention.

[0072] Figure 3 This is a schematic diagram illustrating the overdue charges generated by dynamic call detail record (CDR) segmentation in an embodiment of the present invention.

[0073] Figure 4 This is a structural block diagram of a call detail record (CDR) splitting device provided in an embodiment of the present invention;

[0074] Figure 5 This is a block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0075] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0076] The three major characteristics of 5G networks—high bandwidth, low latency, and massive connectivity—determine that 5G networks will possess stronger network capabilities. Traditional call detail record (CDR) segmentation uses traffic and duration thresholds for call splitting. In practice, switching based on both traffic and time dimensions makes it impossible to precisely control information, easily leading to users incurring high unpaid bills.

[0077] Traditional call detail record (CDR) splitting uses traffic thresholds and duration thresholds for splitting calls. The specific steps are as follows:

[0078] (1) When the 4G internet traffic threshold reaches 100M and the 5G internet traffic threshold reaches 300M, the network element will perform a call detail record (CDR) split.

[0079] (2) When the 4G or 5G internet access time threshold reaches 60 minutes, a call detail record (CDR) will be split once.

[0080] (3) In actual call detail record (CDR) splitting, if either (1) or (2) is reached first, a CDR will be generated.

[0081] (4) Each time a call detail record (CDR) is split, interactions between the host systems will occur.

[0082] The arrears generated by the traditional method are as follows:

[0083] (1) When a user uses up the free data allowance, they will be charged for exceeding the standard rate.

[0084] (2) If a user incurs charges exceeding the balance in the current call record and the call record is split when the balance is very small, a large amount of debt will be incurred.

[0085] Traditional call detail record (CDR) segmentation methods have the following shortcomings:

[0086] (1) It is easy to generate large amounts of unpaid bills: If a user incurs charges exceeding the balance in the current call record, and the call record is split when the balance is very small, a large amount of unpaid bills will be generated.

[0087] (2) Waste of resources and energy: When users have sufficient balance and network conditions are good, frequent splitting of call detail records (CDRs) leads to waste of resources.

[0088] Based on this, this invention discloses a call detail record (CDR) segmentation method, apparatus, electronic device, and storage medium to solve the aforementioned problems.

[0089] Reference Figure 1 The diagram illustrates a flowchart of a call detail record (CDR) segmentation method provided in an embodiment of the present invention, which may specifically include the following steps:

[0090] Step 101: Use the user's age, tariff, customer type, network duration, average monthly traffic of the previous preset number of months, cumulative traffic of the current month, and current balance as the values ​​of static tags.

[0091] Specifically, basic user information is obtained, and the user's age, tariff, customer type, online duration, average monthly data usage over a preset number of months (e.g., 3 months, 4 months), cumulative data usage for the current month, and current balance are used as static tag values. There are a total of 7 static tags, denoted as x1, x2, ..., x7, and the number of users is n. The j-th tag value for user i is denoted as x. ij .

[0092] Step 102: Standardize the values ​​of the static labels to obtain the standardized index of the static labels.

[0093] Specifically, the values ​​of static labels are standardized, and the standardization index of each label value is...

[0094] Standard in, and S j Let m be the sample mean and standard deviation of the j-th label, respectively. For this scenario, m = 7.

[0095] Step 103: Calculate the static tag correlation coefficient matrix based on the standardized indicators of the user's static tags.

[0096] Specifically, the static label correlation coefficient matrix R is calculated, which identifies the correlation coefficients of the static labels. The correlation coefficient matrix is ​​calculated as follows: R = (r ij ) m×m ,in,

[0097]

[0098] Step 104: Based on the static label correlation coefficient matrix, calculate the first feature value and the first feature vector corresponding to the static label.

[0099] Specifically, after obtaining the static label correlation coefficient matrix, the first eigenvalues ​​λ1, λ2, ..., λ corresponding to the static labels can be calculated based on the static label correlation coefficient matrix. m , and the first eigenvectors u1, u2, ..., u m .

[0100] It should be noted that calculating eigenvalues ​​and eigenvectors from matrices is common knowledge in this field; therefore, the calculation methods for eigenvalues ​​and eigenvectors will not be elaborated here.

[0101] Step 105: Calculate the index variables of the static label based on the standardized index of the static label and its corresponding first feature vector.

[0102] Specifically, based on the standardized indicators of static labels Its corresponding first feature vector u j multiplication

[0103] The product is used to calculate the index variable y of the static label. j Indicator variables Where y1 corresponds to the first label, y2 corresponds to the second label, ..., y m This corresponds to the m-th label. Therefore, the indicator variables for each static label can be calculated.

[0104] Step 106: Calculate the first information contribution rate corresponding to each of the first feature values ​​based on the first feature values.

[0105] Specifically, based on the first feature value λ of each static label j (j=1,2,...,m) Calculate the first information contribution rate of the first feature value of each static label, as follows:

[0106]

[0107] Step 107: Calculate the segmentation value for segmenting call detail records based on the indicator variables of the static label, the value of the static label, and the first contribution rate.

[0108] Specifically, the segmentation value for dividing call detail records (CDRs) is calculated based on the indicator variables of the static label, the value of the static label, and the first contribution rate. For example, according to the indicator variable y of the static label... j The value x of the static label j The difference is the change h j Then the change in the initial segmentation value of each static tag is z. j =h j ·b j Therefore, the segmentation value for splitting call detail records can be calculated through integration. Where 'c' is the initial segmentation value for call detail records (CDRs), which is set according to the actual situation, such as c = 300M, 500M, etc. Then, the segmentation value can be used to segment the user's CDRs.

[0109] In this embodiment of the invention, the user's age, tariff, customer type, network duration, average monthly traffic over the previous preset number of months, cumulative monthly traffic, and current balance are used as static tag values. The indicator variables of the static tags and their corresponding first contribution rate are calculated. Then, the segmentation value for each user's call detail record (CDR) can be calculated using the static tag values, the indicator variables of the static tags, and the first contribution rate. Compared to fixed traffic and duration thresholds for call detail record segmentation, this embodiment of the invention uses multi-dimensional user information, especially balance information, to quickly determine the timing of CDR segmentation, improving the accuracy of the segmentation value used for CDR segmentation. This ensures that the CDR segmentation value is adapted to the user, avoiding frequent CDR segmentation, reasonably reducing interaction frequency, thereby reducing message interaction volume and unnecessary CDR volume. Simultaneously, a reasonable CDR segmentation method ensures that the CDR segmentation node is just before a small amount of outstanding charges or the existence of outstanding charges, thus preventing users from incurring high outstanding charges.

[0110] Based on the above embodiments, modified embodiments of the above embodiments are proposed. It should be noted that, in order to keep the description brief, only the differences from the above embodiments are described in the modified embodiments.

[0111] In an optional embodiment of the present invention, the step of calculating the segmentation value for splitting call detail records (CDRs) based on the indicator variable of the static tag, the value of the static tag, and the first contribution rate includes: obtaining the initial segmentation value of the user; calculating a first difference between the indicator variable of the static tag and the value of the static tag; calculating the change in the initial segmentation value based on the first difference and the corresponding first contribution rate; and calculating the segmentation value for splitting CDRs based on the initial segmentation value and the change in the initial segmentation value.

[0112] Specifically, obtain the initial segmentation value c of the user's call detail records, such as c = 300M, and calculate the indicator variable y of the static tag. j and the value x of the static tag j The first difference h j Then, based on the first difference and its corresponding first contribution rate, the change in the initial segmentation value of each static label is calculated as z. j =h j ·b j Furthermore, the segmentation value used for segmenting call detail records can be calculated by integrating the initial segmentation value and the change in the initial segmentation value.

[0113] In an optional embodiment of the present invention, after calculating the segmentation value for segmenting call detail records (CDRs) based on the indicator variables of the static tags, the values ​​of the static tags, and the contribution rate, the method further includes: using the user's current network type, internet access time, current call balance, monthly cumulative traffic change value, and current host CDR processing capacity as values ​​of dynamic tags; standardizing the values ​​of the dynamic tags to obtain standardized indicators of the dynamic tags; calculating a dynamic tag correlation coefficient matrix based on the standardized indicators of the user's dynamic tags; calculating a second feature value and a second feature vector corresponding to the dynamic tags based on the dynamic tag correlation coefficient matrix; calculating the indicator variables of the dynamic tags based on the standardized indicators of the dynamic and static tags and their corresponding second feature vectors; calculating a second information contribution rate corresponding to each second feature value based on the second feature value; calculating the change in CDR segmentation value based on the indicator variables of the dynamic tags, the values ​​of the dynamic tags, and the second information contribution rate; and updating the segmentation value using the change in CDR segmentation value to obtain a new segmentation value.

[0114] Specifically, after calculating the segmentation value for splitting call detail records (CDRs), since user traffic usage is a constantly changing process, the following five types of dynamic tag variables are considered: current network type (4G / 5G), internet access time (busy / off-peak), current call balance, monthly cumulative traffic change, and current host CDR processing capacity. The user's current network type, internet access time, current call balance, monthly cumulative traffic change, and current host CDR processing capacity are respectively used as the values ​​of the dynamic tags.

[0115] The values ​​of the dynamic tags are standardized to obtain the standardized index of the dynamic tags. The steps here are the same as those in step 102, and will not be described in detail in this embodiment of the invention.

[0116] Based on the standardized indicators of the user's dynamic tags, the dynamic tag correlation coefficient matrix is ​​calculated. The steps here are the same as those in step 103, and will not be described in detail in this embodiment of the invention.

[0117] Based on the dynamic label correlation coefficient matrix, the second feature value and the second feature vector corresponding to the dynamic label are calculated. The steps here are the same as those in step 104, and will not be described in detail in this embodiment of the invention.

[0118] Based on the standardized indicators of the dynamic and static labels and their corresponding second feature vectors, the indicator variables of the dynamic labels are calculated. The steps here are the same as those in step 105, and will not be described in detail in this embodiment of the invention.

[0119] Calculate the second information contribution rate γ corresponding to each second eigenvalue based on the second eigenvalue. i i = 1, 2, 3, 4, 5. The steps here are the same as those in step 106, and will not be described in detail in this embodiment of the invention.

[0120] Then, based on the indicator variable y of the dynamic label... i The value of the dynamic label x i Second information contribution rate γ i (i = 1, 2, ..., 5) Calculate the change in call detail record (CDR) segmentation value Δz, and adjust the segmentation based on the CDR segmentation value change Δz.

[0121] ′

[0122] The score Z is updated to obtain a new segmentation value Z = Z + Δz.

[0123] In the above embodiments, the user's current network type, internet access time, current call balance, monthly cumulative traffic change, and current host call detail record (CDR) processing capacity are used as dynamic tag values. Then, the CDR segmentation change is calculated, and the CDR segmentation value is dynamically updated based on the CDR segmentation change. This achieves serial judgment and decision-making through static and dynamic tags, dynamically adjusting the CDR segmentation value. With a small cost of CDR growth, it achieves accurate segmentation of excessive traffic CDRs, reduces the generation of arrears, and reasonably reduces the interaction frequency, thereby reducing message interaction volume and unnecessary CDR volume.

[0124] In an optional embodiment of the present invention, the step of calculating the change in call detail record (CDR) segmentation value based on the indicator variable of the dynamic tag, the value of the dynamic tag, and the second information contribution rate includes: calculating a second difference between the indicator variable of the dynamic tag and the value of the dynamic tag; and calculating the change in CDR segmentation value based on the second difference and the corresponding second contribution rate.

[0125] Specifically, the indicator variable y of the dynamic label is calculated. i and the value x of the dynamic label i The second difference h i Based on the second difference hi and its corresponding second contribution rate γ i Calculate the change in call detail record segmentation value Δz = hi * γ i .

[0126] In an optional embodiment of the present invention, updating the segmentation value by the change in call detail record segmentation to obtain a new segmentation value includes: using the sum of the change in call detail record segmentation and the segmentation value as the new segmentation value.

[0127] Specifically, after obtaining the change in call detail record segmentation Δz, the segmentation value Z is dynamically updated, specifically Z′=Z+Δz, to obtain the new segmentation value Z′.

[0128] In an optional embodiment of the present invention, after updating the segmentation value by the change in call detail record segmentation to obtain a new segmentation value, the method further includes: calculating a reward function value using the new segmentation value, the second information contribution rate, and the standardized index of the dynamic tag; when the reward function value is less than or equal to a preset threshold, the segmentation value is used as the new segmentation value.

[0129] Specifically, the Markov decision-making concept is introduced, and a first-come, first-served principle is adopted for dynamic labels, using a reward function. Iteratively calculate the reward function value R resulting from the dynamic label that causes the change. t+1 ,in, This is a standardized metric for dynamic tags. In each iteration, it is determined whether the reward function value is greater than a preset threshold. If the reward function value is greater than the preset threshold, the call detail record (CDR) is segmented using the new segmentation value. If the reward function value is less than or equal to the preset threshold, the new segmentation value is not used, and the segmentation value calculated from the previous tag change is used as the new segmentation value.

[0130] To better understand the embodiments of the present invention, an example is provided below for illustration.

[0131] By dividing tags into two categories—static initial tags (static tags) and dynamic incremental tags (dynamic tags)—and making serial judgments on these two types of tags, a dynamic segmentation scheme for the final call detail records (CDRs) is achieved. This scheme achieves accurate segmentation of excessive CDR traffic with minimal CDR growth costs, reasonably reduces interaction frequency, and minimizes the generation of overdue charges.

[0132] Call detail record (CDR) processing consists of two processes: data collection and pricing. These processes are executed sequentially. The speed and size of CDR collection and segmentation directly affect the speed of pricing. In this embodiment of the invention, considering both the growth in CDR volume and the granularity of CDR segmentation, dynamic CDR segmentation is divided into two steps: The first step is to provide an initial CDR segmentation scheme for each user under normal static conditions based on initial tags; the second step is to dynamically adjust the CDR step size based on the user's initial CDR segmentation value and changes in tags caused by user usage and host resource variations, achieving agile CDR segmentation.

[0133] Based on the user's basic information, the user's age, tariff, customer type, online duration, average monthly data usage over the previous three months, cumulative data usage for the current month, and current balance are used as initial static tags. There are a total of 7 initial static tags, denoted as x1, x2, ..., x7. The number of users is n. The j-th tag value for user i is denoted as x. ij .

[0134] Principal component analysis was performed on these 7 tags to obtain an initial segmentation scheme. The steps are as follows:

[0135] Step 1: Standardize the static label data. Standardization metrics for each label value. in and S j Let m be the sample mean and standard deviation of the j-th label, respectively. For this scenario, m = 7.

[0136] Step 2: Calculate the static label correlation coefficient matrix R, which identifies the correlation coefficients of the static labels. The correlation coefficient matrix is ​​calculated as follows: R = (r ij ) m×m ,in

[0137]

[0138] Step 3: Calculate the eigenvalues ​​(first eigenvalue) and eigenvectors (first eigenvector), and determine the relative sizes of each eigenvalue. This is done by calculating the eigenvalues ​​of the characteristic matrix and sorting them in descending order, i.e., λ1 ≥ λ2 ≥ … ≥ λ m ≥0, and the corresponding eigenvectors u1, u2, ..., u m ,get

[0139] New principal component index variables We get the new y1 as the first label, y2 as the second label, ..., y m It is the m-th tag.

[0140] Step 4: Calculate the comprehensive evaluation value based on the tag feature value, and use this to calculate the initial call detail record (CDR) segmentation size. The information contribution rate (first information contribution rate) of each feature is: The static tags are sorted according to the contribution rate as follows: cumulative traffic for the current month, current balance, average monthly traffic usage for the previous three months, cost, online duration, age, and customer type.

[0141] Step 5, calculate the initial segment size (segment value). Using the existing segment size of 300M as the initial value, and taking the difference between the value of each label (the indicator variable of the static label) and the initial value (the value of the static label) as the change amount h, then the initial segment size change for each label is z. j =h j ·b j Then the initial segment size (segment value) can be obtained.

[0142] Considering that user data usage is constantly changing, the following five categories of dynamic label variables are considered: current network type (4G / 5G), internet access time (peak / off-peak), current balance, cumulative data usage change for the month, and current host call detail record processing capacity. For these five categories of changing labels, a Markov decision mechanism is introduced, and the following steps are used for dynamic adjustment:

[0143] Step 6: Standardize the label data, the same as the static label standardization process (refer to Step 1).

[0144] Step 7: Dynamic tags are judged on a first-come, first-served basis. Using the aforementioned principal component analysis method, the correlation matrix of the standardized dynamic tags is calculated (refer to Step 2). Based on the correlation matrix, the eigenvalues ​​are calculated (refer to Step 3). The principal component contribution rate of the dynamic tags is calculated based on the eigenvalues ​​(refer to Step 4). The information contribution rate (second information contribution rate) of each tag is represented as γ. iWhere i = 1, 2, 3, 4, 5, and then, based on the contribution rate of this label, substitute it into the calculation method of the change in step 5 above to calculate the corresponding change in call segmentation value Δz.

[0145] Step 8: Summing the initial segmentation size Z with the change Δz, calculate the current pseudo-segmentation value, i.e., ′

[0146] Z = Z + Δz.

[0147] Step 9: Calculate the reward function resulting from the dynamic label value that caused this change, denoted as: If the calculated return function value is greater than the preset threshold (e.g., the preset threshold can be 1), then this change is recorded as the call detail record (CDR) splitting point. Otherwise, the next priority label is calculated, and steps 8 and 9 are repeated.

[0148] In this embodiment of the invention, the user's static tags are used as initial tags, and principal component analysis is used to determine the weight values ​​of each tag. The initial segmentation scheme is calculated based on the weight values. Real-time calculation is performed based on the user's dynamic tags. Markov decision-making is introduced to assign corresponding reward function values ​​to tags with large dynamic changes, thereby determining whether the optimal call detail record (CDR) segmentation time for the user has been reached. The process is continuously cyclically executed based on the changes in the user's dynamic tags, thereby achieving the effect of dynamically adjusting the CDR segmentation step size.

[0149] Reference Figure 2 This diagram illustrates a method for handling overdue charges generated by fixed-step call detail record (CDR) segmentation, as provided in an embodiment of the present invention. Statistics show that in October 2022, the traditional method resulted in 6,765 users incurring overdue charges due to traffic overflow, totaling over 70,000 yuan, with an average charge of 10.74 yuan per user.

[0150] Reference Figure 3 This diagram illustrates an overdue payment generated by dynamic call detail record (CDR) segmentation according to an embodiment of the present invention. Through the optimization method in this embodiment, the overdue payment is reduced by 57,000 yuan, and the average overdue payment per household is reduced by 373%, which is a significant effect.

[0151] In the above embodiments, dynamic segmentation is adopted. On the one hand, it increases the number of call detail records (CDRs) at a relatively low cost, in exchange for accurate CDR segmentation, without affecting the efficiency of host task execution and the progress of CDR processing. On the other hand, based on the user's multi-dimensional information, especially balance information, it can quickly determine the timing of CDR segmentation, which greatly reduces the large amount of arrears caused by the fixed CDR segmentation mode and improves the user experience.

[0152] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0153] Reference Figure 4 The diagram shows a structural block diagram of a call detail record (CDR) segmentation device provided in an embodiment of the present invention, which may specifically include the following modules:

[0154] The tag value determination module 401 is used to use the user's age, tariff, customer type, network duration, average monthly traffic of the previous preset number of months, cumulative traffic of the current month and current balance as the values ​​of static tags respectively;

[0155] The standardization processing module 402 is used to standardize the value of the static label to obtain the standardized index of the static label;

[0156] The matrix calculation module 403 is used to calculate the static tag correlation coefficient matrix based on the standardized indicators of the user's static tags;

[0157] The feature calculation module 404 is used to calculate the first feature value and the first feature vector corresponding to the static label based on the static label correlation coefficient matrix;

[0158] The variable calculation module 405 is used to calculate the indicator variable of the static label based on the standardized index of the static label and its corresponding first feature vector.

[0159] The contribution rate calculation module 406 is used to calculate the first information contribution rate corresponding to each of the first feature values ​​based on the first feature values.

[0160] The segmentation value calculation module 407 is used to calculate the segmentation value for segmenting call detail records based on the indicator variables of the static label, the value of the static label, and the first contribution rate.

[0161] Optionally, the segmentation value calculation module includes:

[0162] The segmentation value acquisition submodule is used to acquire the user's initial segmentation value;

[0163] The difference calculation submodule is used to calculate the first difference between the index variable of the static label and the value of the static label;

[0164] The change calculation submodule is used to calculate the change in the initial segmentation value based on the first difference and its corresponding first contribution rate.

[0165] The segmentation value calculation submodule is used to calculate the segmentation value for segmenting call detail records based on the initial segmentation value and the change in the initial segmentation value.

[0166] Optionally, after calculating the segmentation value for segmenting call detail records based on the indicator variables of the static label, the value of the static label, and the contribution rate, the method further includes:

[0167] The tag value determination module is also used to determine the user's current network type, online time period, current call balance, monthly cumulative traffic change value, and current host call detail record processing capacity as the values ​​of dynamic tags.

[0168] The standardization processing module is also used to standardize the value of the dynamic label to obtain the standardized index of the dynamic label;

[0169] The matrix calculation module is also used to calculate the dynamic tag correlation coefficient matrix based on the standardized indicators of the user's dynamic tags;

[0170] The feature calculation module is also used to calculate the second feature value and the second feature vector corresponding to the dynamic label based on the dynamic label correlation coefficient matrix;

[0171] The variable calculation module is also used to calculate the indicator variables of the dynamic label based on the standardized indicators of the dynamic and static labels and their corresponding second feature vectors;

[0172] The contribution rate calculation module is also used to calculate the second information contribution rate corresponding to each of the second feature values ​​based on the second feature values;

[0173] The change calculation module is used to calculate the change in call detail record segmentation value based on the indicator variables of the dynamic tag, the value of the dynamic tag, and the contribution rate of the second information.

[0174] The segmentation value update module is used to update the segmentation value based on the change in call detail record segmentation to obtain a new segmentation value.

[0175] Optionally, the change calculation module includes:

[0176] The difference calculation submodule is also used to calculate a second difference between the indicator variable of the dynamic label and the value of the dynamic label;

[0177] The change calculation submodule is used to calculate the change in call detail record segmentation value based on the second difference and its corresponding second contribution rate.

[0178] Optionally, the segmentation value update module includes:

[0179] The segmentation value calculation submodule is used to take the sum of the call detail record segmentation change and the segmentation value as the new segmentation value.

[0180] Optionally, it also includes:

[0181] The reward function value calculation submodule is used to calculate the reward function value using the new segmentation value, the second information contribution rate, and the standardized index of the dynamic label;

[0182] The segmentation value confirmation module is used to use the segmentation value as the new segmentation value when the return function value is less than or equal to a preset threshold.

[0183] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0184] In addition, this invention also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described data acquisition method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0185] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described data acquisition method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0186] Figure 5 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0187] The electronic device 500 includes, but is not limited to, components such as: a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505, a display unit 504, a user input unit 507, an interface unit 508, a memory 509, a processor 510, and a power supply 511. Those skilled in the art will understand that... Figure 5The electronic device structures shown are not intended to limit the electronic device. An electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements. In embodiments of the present invention, the electronic device includes, but is not limited to, mobile phones, tablet computers, laptops, PDAs, in-vehicle terminals, wearable devices, and pedometers.

[0188] It should be understood that, in this embodiment of the invention, the radio frequency unit 501 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink data from the base station and processes it with the processor 510; additionally, it transmits uplink data to the base station. Typically, the radio frequency unit 501 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc. Furthermore, the radio frequency unit 501 can also communicate with networks and other devices through a wireless communication system.

[0189] The electronic device provides users with wireless broadband internet access through the network module 502, such as helping users send and receive emails, browse web pages, and access streaming media.

[0190] The audio output unit 503 can convert audio data received by the radio frequency unit 501 or the network module 502 or stored in the memory 509 into audio signals and output them as sound. Furthermore, the audio output unit 503 can also provide audio output related to specific functions performed by the electronic device 500 (e.g., call signal reception sound, message reception sound, etc.). The audio output unit 503 includes a speaker, a buzzer, and a receiver, etc.

[0191] Input unit 504 is used to receive audio or video signals. Input unit 504 may include a graphics processing unit (GPU) 5041 and a microphone 5042. The GPU 5041 processes image data of still images or videos acquired by an image capture device (such as a camera) in video capture mode or image capture mode. The processed image frames can be displayed on display unit 506. The image frames processed by GPU 5041 can be stored in memory 509 (or other storage medium) or transmitted via radio frequency unit 501 or network module 502. Microphone 5042 can receive sound and process such sound into audio data. The processed audio data can be converted into a format that can be transmitted to a mobile communication base station via radio frequency unit 501 in telephone call mode.

[0192] The electronic device 500 also includes at least one sensor 505, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 5061 according to the ambient light level, and the proximity sensor can turn off the display panel 5061 and / or backlight when the electronic device 500 is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used to identify the posture of the electronic device (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc. The sensor 505 may also include a fingerprint sensor, pressure sensor, iris sensor, molecular sensor, gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., which will not be described in detail here.

[0193] The display unit 506 is used to display information input by the user or information provided to the user. The display unit 506 may include a display panel 5061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0194] User input unit 507 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of electronic devices. Specifically, user input unit 507 includes a touch panel 5071 and other input devices 5072. Touch panel 5071, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near touch panel 5071). Touch panel 5071 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 510, which receives and executes commands from the processor 510. In addition, touch panel 5071 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides touch panel 5071, user input unit 507 may also include other input devices 5072. Specifically, other input devices 5072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here.

[0195] Furthermore, the touch panel 5071 can cover the display panel 5061. When the touch panel 5071 detects a touch operation on or near it, it transmits the information to the processor 510 to determine the type of touch event. Subsequently, the processor 510 provides corresponding visual output on the display panel 5061 based on the type of touch event. Although in Figure 5 In this embodiment, the touch panel 5071 and the display panel 5061 are two independent components to realize the input and output functions of the electronic device. However, in some embodiments, the touch panel 5071 and the display panel 5061 can be integrated to realize the input and output functions of the electronic device. The specific implementation is not limited here.

[0196] Interface unit 508 serves as an interface for connecting external devices to electronic device 500. For example, external devices may include a wired or wireless headphone port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 506 can be used to receive input from external devices (e.g., data, power, etc.) and transmit the received input to one or more components within electronic device 500, or it can be used to transmit data between electronic device 500 and external devices.

[0197] The memory 509 can be used to store software programs and various data. The memory 509 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback, image playback, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory 509 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0198] The processor 510 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 509, and by calling data stored in the memory 509, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 510 may include one or more processing units; preferably, the processor 510 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 510.

[0199] The electronic device 500 may also include a power supply 511 (such as a battery) for supplying power to various components. Preferably, the power supply 511 can be logically connected to the processor 510 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system.

[0200] In addition, the electronic device 500 includes some functional modules not shown, which will not be described in detail here.

[0201] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0202] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0203] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

[0204] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0205] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0206] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0207] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0208] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0209] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0210] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A call detail record (CDR) segmentation method, characterized in that, The method includes: The user's age, tariff, customer type, network duration, average monthly data usage of the previous preset number of months, cumulative data usage in the current month, and current balance are used as the values ​​of static tags respectively; The values ​​of the static labels are standardized to obtain the standardized index of the static labels; Calculate the static tag correlation coefficient matrix based on the standardized metrics of the user's static tags; Based on the static label correlation coefficient matrix, calculate the first feature value and the first feature vector corresponding to the static label; The index variables of the static label are calculated based on the standardized index of the static label and its corresponding first feature vector. Calculate the first information contribution rate corresponding to each of the first feature values ​​based on the first feature values; The segmentation value for segmenting call detail records is calculated based on the indicator variables of the static label, the value of the static label, and the contribution rate of the first information. The step of calculating the segmentation value for dividing call detail records based on the indicator variables of the static label, the value of the static label, and the first information contribution rate includes: Obtain the initial segmentation value of the user; Calculate the first difference between the index variable of the static label and the value of the static label; The change in the initial segmentation value is calculated based on the first difference and its corresponding contribution rate of the first information. The segmentation value used for segmenting call detail records is calculated based on the initial segmentation value and the change in the initial segmentation value.

2. The method according to claim 1, characterized in that, After calculating the segmentation value for segmenting call detail records based on the indicator variables of the static label, the value of the static label, and the first information contribution rate, the method further includes: The user's current network type, internet access time, current phone bill balance, monthly cumulative data traffic change, and current host call detail record processing capacity are used as the values ​​of the dynamic tag, respectively. The values ​​of the dynamic tags are standardized to obtain the standardized index of the dynamic tags; Calculate the dynamic tag correlation coefficient matrix based on the standardized metrics of the user's dynamic tags; Based on the dynamic label correlation coefficient matrix, calculate the second feature value and the second feature vector corresponding to the dynamic label; The indicator variables of the dynamic tag are calculated based on the standardized index of the dynamic tag and its corresponding second feature vector. Calculate the second information contribution rate corresponding to each of the second feature values ​​based on the second feature values; The change in call detail record (CDR) segmentation value is calculated based on the indicator variables of the dynamic tag, the value of the dynamic tag, and the contribution rate of the second information. The segmentation value is updated by the change in the call detail record (CDR) segmentation value to obtain a new segmentation value.

3. The method according to claim 2, characterized in that, The step of calculating the change in call detail record (CDR) segmentation value based on the indicator variables of the dynamic tag, the value of the dynamic tag, and the second information contribution rate includes: Calculate the second difference between the indicator variable of the dynamic label and the value of the dynamic label; The change in call detail record (CDR) segmentation value is calculated based on the second difference and its corresponding second information contribution rate.

4. The method according to claim 2, characterized in that, The step of updating the segmentation value based on the change in the call detail record (CDR) segmentation value to obtain a new segmentation value includes: The sum of the change in the call detail record (CDR) segmentation value and the segmentation value is used as the new segmentation value.

5. The method according to claim 2, characterized in that, After updating the segmentation value using the change in the call detail record (CDR) segmentation value to obtain a new segmentation value, the method further includes: The return function value is calculated using the new segmentation value, the second information contribution rate, and the standardized index of the dynamic label; When the return function value is less than or equal to a preset threshold, the segmentation value is used as the new segmentation value.

6. A call detail record (CDR) splitting device, characterized in that, include: The tag value determination module is used to determine the user's age, tariff, customer type, network duration, average monthly traffic of the previous preset number of months, cumulative traffic of the current month, and current balance as the values ​​of static tags respectively; A standardization processing module is used to standardize the values ​​of the static labels to obtain the standardized index of the static labels; The matrix calculation module is used to calculate the static tag correlation coefficient matrix based on the standardized indicators of the user's static tags; The feature calculation module is used to calculate the first feature value and the first feature vector corresponding to the static label based on the static label correlation coefficient matrix; The variable calculation module is used to calculate the indicator variables of the static label based on the standardized index of the static label and its corresponding first feature vector. The contribution rate calculation module is used to calculate the first information contribution rate corresponding to each of the first feature values ​​based on the first feature values. The segmentation value calculation module is used to calculate the segmentation value for segmenting call detail records based on the indicator variables of the static label, the value of the static label, and the first information contribution rate; The segmentation value calculation module includes: The segmentation value acquisition submodule is used to acquire the user's initial segmentation value; The difference calculation submodule is used to calculate the first difference between the index variable of the static label and the value of the static label; The change calculation submodule is used to calculate the change in the initial segmentation value based on the first difference and its corresponding first information contribution rate. The segmentation value calculation submodule is used to calculate the segmentation value for segmenting call detail records based on the initial segmentation value and the change in the initial segmentation value.

7. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes a program stored in the memory, it implements the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by one or more processors, cause the processors to perform the method as described in any one of claims 1-5.

Images