A data processing method, device, apparatus, and storage medium

Abstract

A data processing method, device and equipment and storage medium are disclosed. The method comprises: obtaining a feature label and target service data of a target user, the feature label being obtained by classifying user service data; counting the target service data to obtain a handling quantity corresponding to each feature label; determining a handling tendency value of each feature label according to a handling time in the target service data and the handling quantity; determining a handling threshold of each feature label according to the handling tendency value; and outputting a target feature label in the feature label, the handling tendency value of the target feature label being greater than the handling threshold. According to the method provided in the embodiment of the application, the target feature label of the target user handling service is outputted, and when each major communication operator provides service handling service to the target user according to the target feature label, the satisfaction of the target user can be improved.

Description

Technical Field

[0001] This invention belongs to the field of data analysis, and in particular relates to a data processing method, apparatus, device and storage medium. Background Technology

[0002] Currently, major telecommunications operators in my country are proactively providing services to users to improve their user experience and help them handle various business transactions.

[0003] One way telecommunications operators proactively offer services to users is through customer service personnel calling them by phone. However, when these customer service personnel offer services, they often do not consider the user's habits, leading to a high number of users refusing to answer the phone or rejecting marketing calls.

[0004] The current methods used by customer service personnel to provide business processing services to users are likely to cause resentment or even complaints from users. Summary of the Invention

[0005] This invention provides a data processing method, apparatus, device, and storage medium that can output target feature tags for target users to handle business. When major telecommunications operators provide business handling services to target users based on the target feature tags, it can improve the satisfaction of target users.

[0006] In a first aspect, embodiments of the present invention provide a data processing method, the method comprising:

[0007] Obtain feature tags and target business data of target users. Feature tags are obtained by classifying user business data.

[0008] Statistical analysis of the target business data yields the number of transactions corresponding to each feature tag;

[0009] Based on the processing time and number of transactions in the target business data, determine the processing tendency value for each feature tag;

[0010] Based on the processing tendency value, determine the processing threshold for each feature tag;

[0011] Output the target feature label in the feature label, where the processing tendency value of the target feature label is greater than the processing threshold.

[0012] In one possible implementation, the method further includes, before acquiring the feature tags and target user's target business data:

[0013] Obtain user business data;

[0014] Extract business data that meets preset conditions from business data;

[0015] Business data that meets preset conditions is categorized to obtain feature labels;

[0016] The preset conditions include at least one of the following:

[0017] The user's network access time corresponding to the business data is greater than or equal to the preset time;

[0018] Business data is generated when users actively conduct business.

[0019] The user is using the account corresponding to the business data.

[0020] In one possible implementation, based on the processing time and number of transactions in the target business data, the processing tendency value for each feature tag is determined, including:

[0021] The number of processing times is calculated based on the target business data.

[0022] The processing times are sorted in chronological order.

[0023] Based on the quantity and sorting, the weight corresponding to each processing time is calculated using the following formula;

[0024] Based on the number of cases processed and their weights, determine the processing tendency value for each feature tag;

[0025] The formula is ;

[0026] Where i represents the i-th order in the sorting. This represents the weight corresponding to the i-th processing time in the sorting, where n represents the number of processing times, and i is less than or equal to n.

[0027] In one possible implementation, the processing quantity represents the number of times each feature label is processed at each processing time;

[0028] Based on the number of cases processed and their weights, a processing tendency value is determined for each feature tag, including:

[0029] Multiply the number of transactions corresponding to each feature label by its weight to obtain the product of each feature label at each transaction time;

[0030] By summing the multiplicative values ​​corresponding to the same feature label, we can obtain the processing preference value.

[0031] In one possible implementation, a processing threshold for each feature tag is determined based on the processing tendency value, including:

[0032] Calculate the mean and standard deviation of the propensity score;

[0033] The threshold for processing is calculated using the following formula;

[0034] The formula is: ;

[0035] Where C represents the processing threshold, S represents the mean, and S represents the standard deviation.

[0036] In one possible implementation, the feature label includes a business type label;

[0037] The target feature label in the output feature label, where the processing tendency value of the target feature label is greater than the processing threshold, includes:

[0038] Output the target business type label from the business type labels. The processing tendency value of the target business type label is greater than the processing threshold.

[0039] In one possible implementation, the feature label includes a processing time label;

[0040] The target feature label in the output feature label, where the processing tendency value of the target feature label is greater than the processing threshold, includes:

[0041] Output the target processing time tag in the processing time tag, where the processing tendency value of the target processing time tag is greater than the processing threshold.

[0042] In one possible implementation, the feature label includes a processing method label;

[0043] The target feature label in the output feature label, where the processing tendency value of the target feature label is greater than the processing threshold, includes:

[0044] Output the target processing method label from the processing method labels. The processing tendency value of the target processing method label is greater than the processing threshold.

[0045] In a second aspect, embodiments of the present invention provide a data processing apparatus, the apparatus comprising:

[0046] The acquisition module is used to acquire feature tags and target business data of target users. The feature tags are obtained by classifying user business data.

[0047] The statistics module is used to perform statistics on the target business data and obtain the number of transactions corresponding to each feature tag;

[0048] The determination module is used to determine the processing tendency value of each feature tag based on the processing time and processing quantity in the target business data; it is also used to determine the processing threshold of each feature tag based on the processing tendency value.

[0049] The output module is used to output the target feature label in the feature label, where the processing tendency value of the target feature label is greater than the processing threshold.

[0050] Thirdly, embodiments of the present invention provide an electronic device, the device comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the method as described in the first aspect or any possible implementation thereof.

[0051] Fourthly, embodiments of the present invention provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the method as described in the first aspect or any possible implementation thereof.

[0052] The technical solutions provided by the embodiments of the present invention bring at least the following beneficial effects:

[0053] This invention statistically analyzes target business data to obtain the processing quantity corresponding to each feature tag. Based on the processing time and quantity in the target business data, it determines the processing tendency value for each feature tag. Then, based on the processing tendency value, it determines the processing threshold for each feature tag. By comparing the processing tendency value and the processing threshold for each feature tag, the feature tags with processing tendency values ​​greater than the processing threshold are output as target feature tags. When major telecommunications operators provide business processing services to target users based on target feature tags, it can improve the satisfaction of target users. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a flowchart illustrating a data processing method provided in an embodiment of the present invention;

[0056] Figure 2 This is a schematic diagram of the method for classifying user business data to obtain feature tags according to an embodiment of the present invention;

[0057] Figure 3 This is a flowchart illustrating the method for determining the application preference value provided in an embodiment of the present invention;

[0058] Figure 4 This is a flowchart illustrating another method for determining a propensity value provided in an embodiment of the present invention;

[0059] Figure 5 This is a flowchart illustrating the method for determining the processing threshold provided in an embodiment of the present invention;

[0060] Figure 6 This is a flowchart illustrating another data processing method provided in an embodiment of the present invention;

[0061] Figure 7 A schematic diagram of a data processing device provided in an embodiment of the present invention;

[0062] Figure 8 A schematic diagram of the structure of the electronic device provided in the embodiment of the present invention. Detailed Implementation

[0063] The features and exemplary embodiments of various aspects of the present invention will now be described in detail. To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the invention.

[0064] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0065] Currently, major telecommunications operators in my country are proactively providing services to users to improve their user experience and help them handle various business transactions.

[0066] One way telecommunications operators proactively offer services to users is through customer service personnel calling them by phone. However, when these customer service personnel offer services, they often do not consider the user's habits, leading to a high number of users refusing to answer the phone or rejecting marketing calls.

[0067] The current methods used by customer service personnel to provide business processing services to users are likely to cause resentment or even complaints from users.

[0068] This invention provides a data processing method, apparatus, device, and storage medium that can output target feature tags for target users to handle business. When major telecommunications operators provide business handling services to target users based on the target feature tags, it can improve the satisfaction of target users.

[0069] The following will combine Figure 1 This invention provides a detailed description of a data processing method according to one embodiment. For example... Figure 1 As shown, the method may include the following steps:

[0070] S110, obtain feature tags and target business data of target users, wherein the feature tags are obtained by classifying user business data.

[0071] The server extracts user business data from the operator's user information database, classifies the user business data to obtain feature tags, and the method of classifying user business data to obtain feature tags will be described in detail below.

[0072] Feature tags represent characteristics of a user when conducting business. For example, feature tags may include service type tags, which indicate the type of business the user is conducting. Target users are those to whom the operator will provide business services, and target service data can be the business data of the target users conducting business. Before providing business services to target users, the operator first obtains the feature tags and the target user's target service data.

[0073] S120, Perform statistics on the target business data to obtain the number of transactions corresponding to each feature tag.

[0074] Each feature tag represents a characteristic that the target user may have in the business they are handling. For example, the feature tag may include a business type tag, which may include at least one tag from the following categories: data recharge business, invoice business, product change business, payment business, or other business. Among them, data recharge business, invoice business, product change business, payment business, and other business respectively represent the characteristics of handling recharge business, handling invoice business, handling product change business, handling payment business, and handling other business.

[0075] Each time a target user conducts a transaction, they possess a characteristic represented by one of the aforementioned transaction type tags.

[0076] Statistical analysis of the target business data yields the number of transactions corresponding to each feature tag.

[0077] S130, determine the processing tendency value of each feature tag based on the processing time and the processing quantity in the target business data.

[0078] In the target business data, the processing time can be the time period during which the target user has processed a business, and the number of processing can be the number of times each feature tag of the target user has processed a business.

[0079] The service preference value characterizes the degree to which a target user prefers each feature tag when processing a transaction. A higher service preference value indicates that the target user is more likely to process transactions with that feature tag. The service preference value can represent the degree to which a target user prefers each feature tag across all transaction times.

[0080] In one example, the processing time can be the month in which the target user has processed a transaction, the processing quantity can be the number of transactions for each feature tag of the target user in each month, and the processing tendency value can represent the degree of tendency of the target user towards each feature tag when processing transactions in all months.

[0081] S140, Based on the processing tendency value, determine the processing threshold for each feature tag.

[0082] When the difference in the processing inclination values ​​for each feature tag is large, it indicates that the target user has a clear preference when processing the transaction; when the difference in the processing inclination values ​​for each feature tag is small, it indicates that the target user does not have a clear preference when processing the transaction. Therefore, processing inclination values ​​alone cannot accurately determine the target user's preference when processing the transaction.

[0083] The processing threshold is determined based on the processing tendency value, and the processing threshold is used as a comparison value.

[0084] S150, output the target feature label in the feature label, where the processing tendency value of the target feature label is greater than the processing threshold.

[0085] Compare the processing tendency value and processing threshold of each feature label, and output the feature label with the processing tendency value greater than the processing threshold as the target feature label.

[0086] Target feature tags can represent the feature tags that indicate a clear tendency of a target user when handling business.

[0087] The method provided in this invention statistically analyzes the target service data based on feature vectors and target user's target service data to obtain the processing quantity corresponding to each feature tag. It then determines the processing tendency value for each feature tag based on the processing time and quantity in the target service data, and further determines the processing threshold for each feature tag based on the processing tendency value. Finally, it compares the processing tendency value and the processing threshold for each feature tag, outputting the feature tags with processing tendency values ​​greater than the processing threshold as target feature tags. When major telecommunications operators provide service processing to target users based on target feature tags, it can improve the satisfaction of target users.

[0088] The following is combined Figure 2 This section describes methods for classifying user business data to obtain feature labels. For example... Figure 2 As shown, it includes the following steps:

[0089] S210, obtain user business data.

[0090] The server extracts user business data from the operator's user information database.

[0091] S220, extract business data that meets preset conditions from the business data.

[0092] In one embodiment of the present invention, the preset condition includes at least one of the following:

[0093] The user's network access time corresponding to the business data is greater than or equal to a preset time.

[0094] In one example, the user's network access time corresponding to the business data is greater than or equal to 12 months.

[0095] The business data is generated when the user actively conducts a business transaction.

[0096] Business data generated by users actively conducting business is more likely to reflect users' preferences when conducting business.

[0097] The user is using the account corresponding to the business data.

[0098] When a user is in the account corresponding to the business data, that is, the user has not left the network, there may be a need to conduct business.

[0099] The method provided in this embodiment of the invention can extract business data that meets preset conditions, providing a basis for determining feature tags.

[0100] S230, classify the business data that meet the preset conditions to obtain feature tags.

[0101] Business data includes characteristics of users when handling business. By classifying business data that meets preset conditions, feature tags can be obtained.

[0102] In one example, the business data includes business type characteristics, which may include at least one of the following: data recharge service, invoice service, product change service, payment service, or other services. Based on the business type characteristics in the business data, business data that meets preset conditions is categorized to obtain business type tags. Business type tags may include at least one tag from the following categories: data recharge service, invoice service, product change service, payment service, or other services.

[0103] In one example, the business data includes processing time characteristics, which may include at least one of the following: early ten days of the month, middle ten days of the month, late ten days of the month, morning, noon, afternoon, early night, late night, weekday, or weekend. Based on these processing time characteristics, business data that meets preset conditions is categorized to obtain processing time labels. These processing time labels may include at least one of the following: early ten days of the month, middle ten days of the month, late ten days of the month, morning, noon, afternoon, early night, late night, weekday, or weekend.

[0104] In one example, the business data includes processing method characteristics, which may include at least one of the following: customer service processing, online processing, WeChat processing, in-store processing, or SMS processing. Based on these processing method characteristics, business data that meets preset conditions is categorized to obtain processing method tags. These tags may include at least one of the following: customer service processing, online processing, WeChat processing, in-store processing, or SMS processing.

[0105] The method provided in this invention can classify business data that meets preset conditions to obtain feature tags, providing a basis for determining the target feature tags of target users.

[0106] In one embodiment of the present invention, in step S130, the method for determining the processing tendency value of each feature tag based on the processing time and processing quantity in the target business data is as follows: Figure 3 As shown, it includes the following steps:

[0107] S310, Count the number of processing times based on the target business data.

[0108] The number of processing times refers to the number of time periods during which the target user has processed a transaction.

[0109] In one example, the processing time can be the number of months in which the target user has processed a transaction, and the number of processing times can be the number of months in which the target user has processed a transaction. For example, in the target transaction data, the target user has processed a transaction in n months, where n is greater than or equal to 1.

[0110] S320, sort the processing times in chronological order.

[0111] The tendency of target users to conduct business changes over time. Earlier data is less relevant, while later data is more reliable. The data should be sorted by month of transaction, with the earliest month listed first and the latest last.

[0112] S330, based on the quantity and the sorting, the weight corresponding to each processing time is calculated using the following formula.

[0113] The formula is:

[0114]

[0115] Where i represents the i-th order in the sorting. The weight corresponding to the i-th processing time is represented by , and n represents the number of processing times, where i is less than or equal to n.

[0116] make = , ,

[0117] Right now

[0118]

[0119]

[0120] ,

[0121] but , .

[0122] S340, determine the processing tendency value of each feature tag based on the processing quantity and the weight.

[0123] In one example, the processing quantity can represent the number of times each feature tag is processed at each processing time. In step S330, determining the processing tendency value for each feature tag based on the processing quantity and the weight includes, for example... Figure 4 The steps shown are as follows:

[0124] S410, multiply the number of processing and the weight corresponding to each feature label to obtain the product of each feature label at each processing time.

[0125] If the number of feature tags l processed by the target user at the i-th processing time is x i Then the product of each feature label at each processing time is .

[0126] S420, the multiplicative accumulations corresponding to the same feature label are summed to obtain the processing tendency value.

[0127] If a target user has conducted business within a specified time period (n), and the target user's business preference value is [value missing], then [the following is a possible interpretation of the original text:] ,calculate The formula is as follows:

[0128]

[0129] The method provided in this embodiment of the invention can determine the processing tendency value of each feature tag based on the processing time and processing quantity in the target business data, thus providing a basis for obtaining the target feature tag.

[0130] In one embodiment of the present invention, in step S140, the method for determining the processing threshold of each feature tag based on the processing tendency value is as follows: Figure 5 As shown, it includes the following steps:

[0131] S510, calculate the mean and standard deviation of the processing tendency value.

[0132] In one example, the feature label includes a business type label, which includes at least one label from traffic recharge business, invoice business, product change business, payment business, or other business.

[0133] In one example, the feature label includes a processing time label, which includes at least one of the following: early ten days, middle ten days, late ten days, morning, noon, afternoon, first half of the night, second half of the night, weekday, or weekend.

[0134] In one example, the feature label includes a processing method label, which may include at least one of the following: customer service processing, online processing, WeChat processing, business hall processing, or SMS processing.

[0135] The formula for calculating the average of the propensity score is as follows:

[0136]

[0137] m represents the number of feature labels. This represents the average value of the application preference score. S represents the standard deviation of the propensity to process. Let m represent the processing tendency value of the k-th feature label, where m is an integer greater than or equal to 1, k∈[1,m], and k is an integer.

[0138] The formula for calculating the standard deviation of the propensity score is as follows:

[0139]

[0140] S520, the processing threshold is calculated using the following formula.

[0141] The formula is:

[0142]

[0143] Where C represents the processing threshold and S represents the standard deviation.

[0144] The method provided in this embodiment of the invention can determine the processing threshold of each feature tag based on the processing tendency value, and use the processing threshold as a comparison value of the processing tendency value to provide a basis for obtaining the target feature tag.

[0145] In one embodiment provided by the present invention, the feature label includes a business type label;

[0146] Step S150, outputting the target feature label from the feature labels, wherein the processing tendency value of the target feature label is greater than the processing threshold, includes:

[0147] Output the target business type label from the business type labels, where the processing tendency value of the target business type label is greater than the processing threshold.

[0148] The method provided in this invention obtains a target service type label. When major telecommunications operators provide service processing services to target users based on the target service type label, it can improve the target users' satisfaction with the service types provided by the operators.

[0149] In one embodiment of the present invention, the feature tag includes a processing time tag;

[0150] Step S150, outputting the target feature label from the feature labels, wherein the processing tendency value of the target feature label is greater than the processing threshold, includes:

[0151] Output the target processing time tag from the processing time tags, where the processing tendency value of the target processing time tag is greater than the processing threshold.

[0152] The method provided in this invention obtains a target processing time tag. When major telecommunications operators provide business processing services to target users based on the target processing time tag, it can improve the target users' satisfaction with the processing time of the business processing services provided by the operators.

[0153] In one embodiment of the present invention, the feature tag includes a processing method tag;

[0154] Step S150, outputting the target feature label from the feature labels, wherein the processing tendency value of the target feature label is greater than the processing threshold, includes:

[0155] Output the target processing method label from the processing method labels, where the processing tendency value of the target processing method label is greater than the processing threshold.

[0156] The method provided in this invention obtains a target processing method label. When major telecommunications operators provide business processing services to target users based on the target processing method label, it can improve the target users' satisfaction with the processing method provided by the operators.

[0157] The following will combine Figure 6 This paper elaborates on another data processing method provided by an embodiment of the present invention. For example... Figure 6 As shown, the method may include the following steps:

[0158] S610, obtains the user's business data for the past N months;

[0159] Extract business data of users from the user information database of telecommunications operators for the past N months (N can be 12). The business data mainly includes user identity information, business processing time, business type, business unit information, business operator, business processing fee, etc.

[0160] S620, extract business data that meets preset conditions from the business data.

[0161] The preset conditions include at least one of the following:

[0162] The user's network access time corresponding to the business data is greater than or equal to N months.

[0163] Business data is generated when users actively handle business. Business data does not include batch business handling initiated by operators, background logs caused by handling a certain business, batch business operations performed by the operator's government and enterprise departments for the group, etc.

[0164] The user is using the account corresponding to the business data, meaning the user has not left the network.

[0165] It also excludes services that are not initiated by the customer, including bulk service processing initiated by the operator, background logs generated by processing a certain service, and bulk services operated by the operator's government and enterprise departments for the group.

[0166] S630, classify the business data that meets the preset conditions to obtain feature tags.

[0167] Use SQL to classify business data by feature:

[0168] In one example, log processing information is categorized by processing time: ten-day period (early, middle, and late ten days), time period (morning, noon, afternoon, early night, and late night), and weekday (weekday and weekend). Log processing methods are categorized by operation type and operation ID (SMS, customer service, WeChat, business hall, and online). Log business types are categorized by subcategories of business data (data top-up, product change, invoices, other business types, and payments).

[0169] After feature classification, each piece of business data has 14 features, including number ID, log serial number, operation type, business type subcategory, operation unit, operation employee number, operation time, operation fee, fee reduction or exemption, ten-day period, time period, week, business type, and processing method.

[0170] By summarizing and aggregating business data, five categories of feature tags are identified: ten-day period, week, time period, processing method, and business type. These feature tags are then output.

[0171] The business type tag class is treated as a separate vector, which is then combined with other tag classes to form a tag matrix.

[0172] The vector for business type labels is (Payment services, Product change services, Data recharge services, Invoice services, Other services).

[0173] Assign an identifier to each tag of the business type to form a business type tag vector:

[0174]

[0175] Indicates the business type label. Each represents one industry type label.

[0176] The tag matrix for processing time tags and processing method tags is as follows: .

[0177] Each feature label is represented by an identifier, forming a feature label matrix:

[0178] ;

[0179] in , , , , L represents a matrix of processing time tags and processing method tags. Indicating the beginning of the month, Indicates the middle of the month, Indicates the latter part of the month. Indicates morning. It means noon. Indicates afternoon. Indicates the first half of the night, Indicates the latter half of the night, Indicates working days. Indicates the weekend. This indicates that customer service will handle it. It indicates that it can be processed online. It indicates that the application can be processed via WeChat. Indicates that the transaction can be processed at the business hall. This indicates that the transaction will be processed via SMS.

[0180] S640, acquire target business data of the target user.

[0181] The target user can be a user for whom the operator will provide business processing services, and the target business data can be the business data of the target user's business processing.

[0182] In one example, the target business data contains 10 time tags and 5 processing method tags for each business type, for a total of 15 feature tags.

[0183] S650 counts the number of transactions for each feature tag of the target user.

[0184] In one example, Table 1 is obtained by counting the number of transactions for each feature tag of target user A.

[0185] Table 1 Target Business Data for Target User A

[0186]

[0187] S660 calculates the number of processing times and the weight corresponding to each processing time in the target business data.

[0188] Calculate the weights according to formula (1).

[0189] S670 determines the processing tendency value for each feature tag based on the number of processing and its weight.

[0190] In one example, according to The processing tendency value of target user A for each feature tag in each month is calculated as shown in Table 2.

[0191] Table 2. Target User A's processing tendency values ​​for each feature tag in each month.

[0192]

[0193] Based on Table 2, the processing tendency value of each feature tag of the target user is calculated using Formula (II).

[0194] The processing tendency values ​​of each feature tag of target user A are shown in Table 3.

[0195] Table 3. Processing Inclination Values ​​for Each Feature Tag of Target User A

[0196]

[0197] S680, calculate the mean and standard deviation of the propensity score, and calculate the propensity threshold.

[0198] Feature labels in the same row of the label matrix belong to the same category of feature labels.

[0199] ;

[0200] Among them, the feature tags in the first row are ten-day categories, the feature tags in the second row are time-period categories, the feature tags in the third row are weekly categories, and the feature tags in the fourth row are processing method categories.

[0201] The average value of the handling tendency value is calculated using formula (iii).

[0202] The standard deviation of the handling tendency value is calculated using formula (iv).

[0203] The processing threshold is calculated using formula (5).

[0204] The processing thresholds for each feature tag of target user A are shown in Table 4.

[0205] Table 4. Processing thresholds for each tag of target user A.

[0206]

[0207] S690, output the target feature label from the feature label.

[0208] Compare the processing tendency value and processing threshold of each feature label, and output the feature label with the processing tendency value greater than the processing threshold as the target feature label.

[0209] Table 5 shows the preference information of target user A when handling business.

[0210] Table 5. Information on target user A's business preferences.

[0211]

[0212] Table 5 shows the service preferences of target user A. For example, the first row of Table 5 shows that target user A's most preferred service type is data recharge, and that they prefer to do so in the latter part of the month, late at night, and on weekends, and also prefer to do so online.

[0213] The method provided in this invention statistically analyzes the target service data based on feature vectors and target user's target service data to obtain the processing quantity corresponding to each feature tag. It then determines the processing tendency value for each feature tag based on the processing time and quantity in the target service data, and further determines the processing threshold for each feature tag based on the processing tendency value. Finally, it compares the processing tendency value and the processing threshold for each feature tag, outputting the feature tags with processing tendency values ​​greater than the processing threshold as target feature tags. When major telecommunications operators provide service processing to target users based on target feature tags, it can improve the satisfaction of target users.

[0214] Based on the data processing method provided in the above embodiments, this invention also provides a data processing apparatus, such as... Figure 7 As shown, the data processing device 700 includes:

[0215] The acquisition module 710 is used to acquire feature tags and target business data of target users, wherein the feature tags are obtained by classifying user business data;

[0216] The statistics module 720 is used to perform statistics on the target business data to obtain the number of transactions corresponding to each feature tag;

[0217] The determining module 730 is used to determine the processing tendency value of each feature tag based on the processing time and the processing quantity in the target business data; and is also used to determine the processing threshold of each feature tag based on the processing tendency value.

[0218] The output module 740 is used to output the target feature label in the feature label, wherein the processing tendency value of the target feature label is greater than the processing threshold.

[0219] The apparatus provided in this invention performs statistical analysis on the target service data based on feature vectors and target user target service data to obtain the processing quantity corresponding to each feature tag. It then determines the processing tendency value for each feature tag based on the processing time and quantity in the target service data, and further determines a processing threshold for each feature tag based on the processing tendency value. Finally, it compares the processing tendency value and the processing threshold for each feature tag, outputting feature tags with processing tendency values ​​greater than the processing threshold as target feature tags. When major telecommunications operators provide service processing to target users based on target feature tags, it can improve the satisfaction of target users.

[0220] In one embodiment of the present invention, the acquisition module 710 can also be used to acquire user business data.

[0221] The data processing device 700 may further include:

[0222] Extraction module 750 is used to extract business data that meets preset conditions from the business data;

[0223] The classification module 760 is used to classify the business data that meets the preset conditions to obtain feature tags.

[0224] The preset conditions include at least one of the following:

[0225] The user's network access time corresponding to the business data is greater than or equal to a preset time;

[0226] The business data is generated when the user actively handles the business.

[0227] The user is using the account corresponding to the business data.

[0228] The method provided in this invention can classify business data that meets preset conditions to obtain feature tags, providing a basis for determining the target feature tags of target users.

[0229] In one embodiment of the present invention, the determining module 730 may include a statistical unit, a sorting unit, a calculation unit, and a determining unit; wherein:

[0230] The statistics unit is used to count the number of processing times based on the target business data;

[0231] A sorting unit is used to sort the processing times in chronological order.

[0232] The calculation unit is used to calculate the weight corresponding to each processing time according to the quantity and the sorting, using the following formula;

[0233] A determining unit is configured to determine the processing tendency value of each feature tag based on the processing quantity and the weight.

[0234] The formula is: ;

[0235] Where i represents the i-th order in the sorting. The weight corresponding to the i-th processing time is represented by , and n represents the number of processing times, where i is less than or equal to n.

[0236] In one example, the processing quantity represents the number of times each feature label is processed at each processing time. The determining unit is specifically used for:

[0237] Multiply the number of transactions corresponding to each feature label by the weight to obtain the product of each feature label at each transaction time;

[0238] The processing tendency value is obtained by summing the multiplicative values ​​corresponding to the same feature label.

[0239] The apparatus provided in this embodiment of the invention can determine the processing tendency value of each feature tag based on the processing time and the processing quantity in the target business data, providing a basis for obtaining the target feature tag.

[0240] In one embodiment of the present invention, the determining module 730 may include a calculation unit.

[0241] The calculation unit is used to calculate the average and standard deviation of the processing tendency values;

[0242] The processing threshold is calculated using the following formula;

[0243] The formula is: ;

[0244] Wherein, C represents the processing threshold. S represents the average value, and S represents the standard deviation.

[0245] The apparatus provided in this embodiment of the invention can determine the processing threshold of each feature tag based on the processing tendency value, and use the processing threshold as a comparison value of the processing tendency value to provide a basis for obtaining the target feature tag.

[0246] In one embodiment of the present invention, the feature label includes a business type label; the output module 740 can be specifically used for:

[0247] Output the target business type label from the business type labels, where the processing tendency value of the target business type label is greater than the processing threshold.

[0248] The device provided in this embodiment of the invention obtains a target service type label. When major telecommunications operators provide service processing services to target users based on the target service type label, it can improve the target users' satisfaction with the service type in the service processing services provided by the operators.

[0249] In one embodiment of the present invention, the feature tag includes a processing time tag; the output module 740 can be specifically used for:

[0250] Output the target processing time tag from the processing time tags, where the processing tendency value of the target processing time tag is greater than the processing threshold.

[0251] The device provided in this embodiment of the invention obtains a target processing time tag. When major telecommunications operators provide business processing services to target users based on the target processing time tag, it can improve the target users' satisfaction with the processing time of the business processing services provided by the operators.

[0252] In one embodiment of the present invention, the feature tag includes a processing method tag; the output module 740 can be specifically used for:

[0253] Output the target processing method label from the processing method labels, where the processing tendency value of the target processing method label is greater than the processing threshold.

[0254] The device provided in this embodiment of the invention obtains a target processing method label. When major telecommunications operators provide business processing services to target users based on the target processing method label, it can improve the target users' satisfaction with the processing method provided by the operators.

[0255] The data processing device provided in this embodiment of the invention performs... Figure 1 The steps in the method shown can achieve the technical effect of improving the satisfaction of target users when major telecommunications operators provide business processing services to target users based on target feature tags. For the sake of brevity, they will not be described in detail here.

[0256] Figure 8 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention is shown.

[0257] An electronic device may include a processor 801 and a memory 802 storing computer program instructions.

[0258] Specifically, the processor 801 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0259] Memory 802 may include mass storage for data or instructions. For example, and not limitingly, memory 802 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 802 may include removable or non-removable (or fixed) media. Where appropriate, memory 802 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 802 is non-volatile solid-state memory. In a particular embodiment, memory 802 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0260] The processor 801 reads and executes computer program instructions stored in the memory 802 to achieve... Figures 1 to 6 Any of the data processing methods shown in the embodiments.

[0261] In one example, the electronic device may also include a communication interface 803 and a bus 810. For example, Figure 8 As shown, the processor 801, memory 802, and communication interface 803 are connected through bus 810 and complete communication with each other.

[0262] The communication interface 803 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of the present invention.

[0263] Bus 810 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel 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 other suitable buses, or combinations of two or more of these. Where appropriate, bus 810 may include one or more buses. While specific buses are described and illustrated in embodiments of the invention, the invention contemplates any suitable bus or interconnect.

[0264] The electronic device can execute the data processing method in the embodiments of the present invention, thereby achieving the combination Figure 1 Describe the data processing methods.

[0265] Furthermore, in conjunction with the data processing methods described in the above embodiments, this invention can be implemented using a computer storage medium. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the data processing methods described in the above embodiments.

[0266] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0267] The functional blocks shown in the above structural diagram 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, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting 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, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0268] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0269] The above are merely specific embodiments of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A data processing method, characterized by, The method includes: Obtain feature tags and target business data of target users, wherein the feature tags are obtained by classifying user business data; The target business data is statistically analyzed to obtain the number of transactions corresponding to each feature tag; Based on the processing time and the number of transactions in the target business data, determine the processing tendency value for each feature tag; Based on the processing tendency value, a processing threshold is determined for each feature tag; the processing threshold is a comparison value of the processing tendency value. Output the target feature label from the feature labels, wherein the processing tendency value of the target feature label is greater than the processing threshold; The step of determining the processing tendency value of each feature tag based on the processing time and the processing quantity in the target business data includes: The number of processing times is calculated based on the target business data. The processing times are sorted in chronological order. Based on the quantity and the sorting, the weight corresponding to each processing time is calculated using the following formula; Based on the number of applications processed and the weight, the processing tendency value of each feature tag is determined; The formula is: ; wherein i represents the i-th ordered, wherein wi represents the weight corresponding to the i-th ordered handling time, n represents the number of the handling times, and i is less than or equal to n; The step of determining the processing threshold for each feature tag based on the processing tendency value includes: Calculate the mean and standard deviation of the stated propensity values; The processing threshold is calculated using the following formula; The formula is: ; wherein C denotes the handling threshold value, denotes the average value and S denotes the standard deviation.

2. The method of claim 1, wherein, Before acquiring the feature tags and target user's target business data, the method further includes: Obtain user business data; Extract business data that meets preset conditions from the business data; The business data that meets the preset conditions are classified to obtain feature tags; The preset conditions include at least one of the following: The user's network access time corresponding to the business data is greater than or equal to a preset time; The business data is generated when the user actively handles the business. The user is using the account corresponding to the business data.

3. The method according to claim 1, characterized in that, The processing quantity represents the number of times each feature tag is processed at each processing time. The step of determining the processing tendency value for each feature tag based on the processing quantity and the weight includes: Multiply the number of transactions corresponding to each feature label by the weight to obtain the product of each feature label at each transaction time; The processing tendency value is obtained by summing the multiplicative values ​​corresponding to the same feature label.

4. The method of claim 1, wherein, The feature tags include business type tags; The step of outputting the target feature label from the feature labels, wherein the processing tendency value of the target feature label is greater than the processing threshold, includes: Output the target business type label from the business type labels, where the processing tendency value of the target business type label is greater than the processing threshold.

5. The method of claim 1, wherein, The feature tags include processing time tags; The step of outputting the target feature label from the feature labels, wherein the processing tendency value of the target feature label is greater than the processing threshold, includes: Output the target processing time tag from the processing time tags, where the processing tendency value of the target processing time tag is greater than the processing threshold.

6. The method of claim 1, wherein, The feature tags include processing method tags; The step of outputting the target feature label from the feature labels, wherein the processing tendency value of the target feature label is greater than the processing threshold, includes: Output the target processing method label from the processing method labels, where the processing tendency value of the target processing method label is greater than the processing threshold.

7. A data processing apparatus, characterized by The device includes: The acquisition module is used to acquire feature tags and target business data of target users, wherein the feature tags are obtained by classifying user business data; The statistics module is used to perform statistics on the target business data and obtain the number of transactions corresponding to each feature tag; The determination module is used to determine the processing tendency value of each feature tag based on the processing time and the processing quantity in the target business data; it is also used to determine the processing threshold of each feature tag based on the processing tendency value; the processing threshold is a comparison value of the processing tendency value. The determining module is used to determine the processing tendency value of each feature tag based on the processing time and the processing quantity in the target business data, including: The number of processing times is calculated based on the target business data. The processing times are sorted in chronological order. Based on the quantity and the sorting, the weight corresponding to each processing time is calculated using the following formula; Based on the number of applications processed and the weight, the processing tendency value of each feature tag is determined; The formula is ; wherein i represents the i-th ordered, wherein wi represents the weight corresponding to the i-th ordered handling time, n represents the number of the handling times, and i is less than or equal to n; The determining module is further configured to determine the processing threshold for each feature tag based on the processing tendency value, including: Calculate the mean and standard deviation of the stated propensity values; The processing threshold is calculated using the following formula; The formula is: ; wherein C denotes the handling threshold value, denotes the average value and S denotes the standard deviation. The output module is used to output the target feature label in the feature label, wherein the processing tendency value of the target feature label is greater than the processing threshold.

8. An electronic device, comprising: The device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the data processing method as described in any one of claims 1-6.

9. A computer storage medium, characterized in that The computer storage medium stores computer program instructions, which, when executed by a processor, implement the data processing method as described in any one of claims 1-6.

Images