A recharging method, a background server and a storage medium

Abstract

The application relates to a recharging method, a background server and a storage medium, wherein the method is characterized in that: a recharging request of an application end is acquired, bill data of a to-be-recharged number and a local number in the recharging request is collected, a user relationship network is established according to the bill data, the close relationship between the to-be-recharged number and the local number is analyzed based on the user relationship network through a relationship analysis engine, the analyzed close relationship is matched with a user relationship, and it is confirmed whether to execute a recharging operation. Therefore, when the close relationship between the to-be-recharged number and the local number is analyzed based on the user relationship network through the relationship analysis engine, the user relationship network is not only established according to the bill data of the local number but also established according to the bill data of the to-be-recharged number, so that the generated user relationship network is more comprehensive and perfect, the accuracy of the close relationship between the to-be-recharged number and the local number is further improved, and the accuracy of the legality verification of the to-be-recharged mobile number is improved.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a recharge method, a back-end server, and a storage medium. Background Technology

[0002] When topping up a mobile phone, the system verifies the legitimacy of the phone number. Traditional systems primarily use three methods: 1. Determining the location and carrier of the number; 2. Checking the phone's contacts to see if the number exists; 3. Providing the user with the last name of the number's owner for confirmation. Method 1 is too general and cannot determine if the user entered the wrong number. Methods 2 and 3 both involve user privacy and are difficult to implement.

[0003] Application No. CN201911184808.9 discloses a "Method and System for Estimating the Density of Social Relationships Based on Call Detail Record Data Analysis." This method calculates the density of social relationships between users by analyzing their call detail record data. Applying this method to a recharge system allows for the analysis of the density of social relationships between the phone number to be recharged and the user's phone number based on the call detail record data. This allows for the verification of the legitimacy of the phone number to be recharged based on the density of social relationships. However, this method still has the following technical shortcomings:

[0004] (1) Analyzing the relationship between the number to be recharged and the user's mobile phone number solely based on the user's mobile phone number call detail record data is too one-sided, and the results of the legality verification of the number to be recharged are inaccurate.

[0005] (2) Only considering the relationship between the mobile phone number to be recharged and the number existing in the call detail record data of the user's mobile phone number makes the density of the generated social relationship too absolute, that is, the result of the legality verification of the mobile phone number to be recharged is not accurate. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a recharge method, a back-end server and a storage medium to improve the accuracy of the verification of the legality of the recharge number.

[0007] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0008] In a first aspect, the present invention provides a recharge method, comprising:

[0009] The system obtains a recharge request from the application and creates a recharge order based on the recharge request, which is then sent to the payment platform. The recharge order instructs the payment platform to deduct funds and generate a recharge order record. The recharge request includes the number to be recharged, the user's phone number, and the user relationship between the number to be recharged and the user's phone number.

[0010] Collect call detail records (CDRs) of the number to be recharged and the local number, and establish a user relationship network based on the CDRs.

[0011] The relationship analysis engine analyzes the close relationship between the number to be recharged and the local number based on the user relationship network, and matches the close relationship with the user relationship. When the match is successful, a recharge instruction is sent to the recharge server to instruct the recharge server to recharge according to the recharge instruction; otherwise, no recharge is performed.

[0012] The beneficial effect of this invention is that the analysis of the close relationship between the number to be recharged and the local number is performed by a relationship analysis engine based on the user relationship network. The user relationship network is established not only based on the call detail records (CDRs) of the local number but also on the CDRs of the number to be recharged, comprehensively considering the relationship between the number to be recharged and the local number. This makes the generated user relationship network more complete, further improving the accuracy of the close relationship between the number to be recharged and the local number, thereby improving the accuracy of the verification of the legality of the mobile phone number to be recharged.

[0013] Optionally, the step of establishing a user relationship network based on the call detail record (CDR) data includes:

[0014] The system obtains number information records from the CRM system and updates the user relationship network in real time. When a number has a cancellation record, all recharge records for that number are marked as unavailable. When the number information record has a family network creation record, a family relationship is established in the user relationship network based on the family network creation record. When the number information record has a family network termination record, the family relationship in the user relationship is deleted based on the family network termination record.

[0015] As described above, the user relationship network is continuously updated and improved. By obtaining number information records from the CRM system, it can be determined whether a number has a cancellation record, or whether a family network has been created or terminated. When a number has a cancellation record, all recharge records for that cancelled number are marked as unavailable, indicating that these recharge records cannot be used for recharge verification of new numbers. Thus, when a number is reissued, it is assumed that there are no recharge records for that number. This is similar to deleting the number from the user relationship network after cancellation, preventing the call detail records (CDRs) of the same number from belonging to different people when a number is cancelled and then reissued, which would affect the accuracy of user relationships. When a number has a family network creation record, user relationships between family numbers are established in the user relationship network, so that even if there are no CDRs between users in the same family, user relationships are still established, further improving the user relationship network. When a number has a family network termination record, the family relationship of that number in the user relationship network is deleted, and the user relationship network is updated, thereby continuously improving the user relationship network and enhancing the accuracy and comprehensiveness of user relationships on the network.

[0016] Optionally, analyzing the close relationship between the number to be recharged and the local number based on the user relationship network using a relationship analysis engine includes:

[0017] Based on the recharge order record, determine whether the number to be recharged is the user's own number. If not, determine whether the number to be recharged has other recharge records. If not, use a relationship analysis engine to analyze the close relationship between the number to be recharged and the user's own number based on the user relationship network.

[0018] As described above, the system checks whether the number to be recharged is the user's own number based on the recharge order records. If the number is not the user's own number, it checks whether the number has been recharged before, i.e., whether there are other recharge records. The system performs a legality verification of the number to be recharged based on the recharge order records, simplifying the process and improving efficiency. When the number to be recharged is neither the user's own number nor has any other recharge record, the system uses a relationship analysis engine to analyze the close relationship between the number to be recharged and the user's own number based on the user's relationship network. This provides multiple scenarios for legality verification of the number to be recharged, improving the comprehensiveness and flexibility of the legality verification.

[0019] Optionally, analyzing the close relationship between the number to be recharged and the local number based on the user relationship network using a relationship analysis engine includes:

[0020] The relationship analysis engine calculates the affinity value between the number to be recharged and the local number based on the user relationship network;

[0021] The relationship between the number to be recharged and the local number is analyzed based on the intimacy value. The intimacy relationship includes immediate family relationship, collateral family relationship, friend relationship, and other relationships.

[0022] As described above, when the relationship analysis engine calculates the close relationship between the number to be recharged and the local number based on the user's relationship network, it first calculates the closeness value between the number to be recharged and the local number, and then judges the closeness relationship based on the closeness value. By dividing the closeness relationship by numerical value, the objectivity of judging the closeness relationship is improved and the subjectivity of human intervention is reduced.

[0023] Optionally, calculating the affinity value between the number to be recharged and the local number based on the user relationship network using a relationship analysis engine includes:

[0024] Calculate the direct affinity value between the local number and the associated numbers in the user's social network:

[0025]

[0026] Among them, DR (l，k) This represents the direct affinity value between the k-th associated number and the local number. This represents the average call duration of the outgoing call detail records (CDRs) between the k-th associated number and the local number, where m represents the number of outgoing calls; and α represents the adjustment factor for the called call detail records. This represents the average call duration of the called party records between the k-th associated number and the local number, where n represents the number of called parties.

[0027] Calculate the indirect affinity value between the number to be recharged and the local phone number:

[0028]

[0029] Among them, DR (l，k) DR represents the direct affinity value between the local number and the k-th number. (k，p) This represents the direct affinity value between the k-th number and the number to be recharged;

[0030] Calculate the relative intimacy value between the number to be recharged and the local number based on the direct intimacy value and the indirect intimacy value:

[0031] R (l，p) =DR (l，p) +β×IR (l，p)

[0032] Among them, R (l，p) DR represents the relative affinity between the number to be recharged and the user's phone number. (l，p) IR represents the direct affinity value between the number to be recharged and the local phone number, β represents the adjustment factor for the indirect affinity value, and IR represents the direct affinity value. (l，p)This indicates the indirect affinity value between the number to be recharged and the user's own number;

[0033] Sort the relative affinity value between the number to be recharged and the mobile number and the direct affinity value, and recalculate the affinity value between the number to be recharged and the mobile number based on the sorting result:

[0034] Where R represents the affinity value between the number to be recharged and the local number, m represents the m-th position in the sorting result, and n represents the n associated numbers of the local number.

[0035] As described above, when calculating the affinity value between the number to be recharged and the user's own number, the direct affinity value between the user's own number and related numbers in the user's relationship network, as well as the indirect affinity value between the number to be recharged and the user's own number, are calculated separately. After obtaining the direct and indirect affinity values, the relative affinity value between the number to be recharged and the user's own number is calculated. This relative affinity value is then sorted with the direct affinity value, and the affinity value between the number to be recharged and the user's own number is recalculated. This progressive calculation takes into account the relationship between the number to be recharged and the user's own number from all angles, improving the accuracy and comprehensiveness of the calculated affinity value between the number to be recharged and the user's own number. This provides a guarantee for subsequent classification of affinity relationships based on affinity value.

[0036] Optionally, the "otherwise no recharge" option includes:

[0037] A recharge confirmation notification is sent to the application, and the confirmation result from the application is obtained in real time. If the confirmation result cannot be obtained within a specified time, the recharge is not performed and a refund is issued. If the confirmation result is successfully obtained within the specified time, it is determined whether the confirmation result indicates that the recharge should continue. If so, a recharge instruction is sent to the recharge server, which instructs the recharge server to perform the recharge. Otherwise, the recharge is not performed and a refund is issued.

[0038] As described above, when the relationship between the number to be recharged and the user's phone number does not match, a recharge confirmation notification will be sent to the application to allow the user to confirm whether to recharge. This allows the user to double-check whether the number to be recharged was entered incorrectly, further reducing the risk of users entering the wrong number. If the user confirms that the recharge is successful, the recharge can proceed. This is not limited to whether the relationship between the number to be recharged and the user's phone number matches, thus improving the flexibility of the recharge process. Furthermore, the system is designed to retrieve the user's confirmation within a specified time. If the specified time is exceeded, the system will default to not recharging the phone number and will issue a refund, thereby improving the security of the recharge process and optimizing the user experience.

[0039] In a second aspect, the present invention provides a backend server, the backend server including a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a recharge method as described in the first aspect.

[0040] Thirdly, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed, it implements a recharge method as described in the first aspect.

[0041] The technical effects of the backend server provided in the second aspect and the computer-readable storage medium provided in the third aspect are the same as those of the recharge method provided in the first aspect. Attached Figure Description

[0042] Figure 1 This is a flowchart of a recharge method provided in an embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of the overall framework of a recharge method provided in an embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram illustrating the process of verifying the legality of the number to be recharged on the application side in an embodiment of the present invention;

[0045] Figure 4 This is a schematic diagram illustrating the process of verifying the legality of the number to be recharged based on the recharge order record, according to an embodiment of the present invention.

[0046] Figure 5 This is a schematic diagram of the structure of a backend server provided in an embodiment of the present invention.

[0047] [Explanation of Labels in the Attached Image]

[0048] 1: A type of backend server;

[0049] 2: Processor;

[0050] 3: Memory. Detailed Implementation

[0051] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0052] Example 1

[0053] Please refer to Figures 1 to 4 This invention provides a recharge method, including the following steps:

[0054] S1. Obtain the recharge request from the application and create a recharge order based on the recharge request and send it to the payment platform. The recharge order is used to instruct the payment platform to deduct the payment based on the recharge order and generate a recharge order record. The recharge request includes the number to be recharged, the user's phone number, and the user relationship between the number to be recharged and the user's phone number.

[0055] In this embodiment, as Figure 2 As shown, taking a mobile device as an example, when a user enters the number to be recharged on the recharge interface of the mobile device application, the application will obtain the number to be recharged and the user's mobile phone number, and generate a recharge request to send to the backend server. After receiving the recharge request sent by the application, the backend server will create a recharge order according to the recharge request and send the recharge order to the payment platform. After the payment platform executes the deduction, a recharge order record is generated.

[0056] Preferably, when a user enters a phone number to be recharged on the mobile application's recharge interface, the application will first verify the validity of the phone number to be recharged, improving efficiency. Figure 3 As shown, the application checks whether the number to be recharged is the user's own number. If it is not the user's own number, it checks whether there is a previous recharge record for the number to be recharged. If there is no record, the application will list user relationships to guide the user to select the user relationship between the number to be recharged and the user's own number. User relationships are divided into: immediate family relationship, collateral family relationship, friend relationship, and other relationship. Then, the user relationship selected by the user, the number to be recharged entered by the user, and the user's own number are sent to the backend server.

[0057] In other equivalent embodiments, the device may also be an operable device such as a tablet or a display.

[0058] S2. Collect call detail records (CDRs) of the number to be recharged and the local number, and establish a user relationship network based on the CDRs.

[0059] In this embodiment, the backend server collects call detail records (CDRs) for the number to be recharged and the local number obtained in step S1, and deletes invalid CDRs, such as those for non-domestic numbers, non-mobile phone numbers, blacklisted numbers, and out-of-town numbers with a call duration of less than 5 seconds in the called party's CDR. This further filters the CDRs to ensure their validity. A user relationship network is then established based on the filtered CDRs to improve its accuracy. Therefore, step S2, after establishing the user relationship network based on the CDRs, includes:

[0060] S21. Obtain the number information records from the CRM (Customer Relationship Management) system and update the user relationship network in real time. When a number has a cancellation record, mark all recharge records for that number as unavailable. When the number information record has a family network creation record, establish a family relationship in the user relationship network based on the family network creation record. When the number information record has a family network termination record, delete the family relationship in the user relationship based on the family network termination record.

[0061] In this embodiment, as Figure 2 As shown, the backend server retrieves number information records from the CRM system and updates user relationships in real time based on these records. When a number has a cancellation record, all recharge records for that number are marked as unavailable, meaning they cannot be used for new number recharge verification. This ensures that the number will not have recharge records after being reissued, similar to deleting the number from the user relationship network after cancellation. This prevents inaccurate user relationship networks caused by call detail records (CDRs) belonging to different users after a number is cancelled and then reissued. Furthermore, when a number has a family creation record, user relationships between family numbers are established in the user relationship network, ensuring that user relationships are established even if there is no CDR between users in the same family, further improving the user relationship network. Similarly, when a number has a family termination record, the family relationship for that number is deleted from the user relationship network. The user relationship network is continuously updated and improved based on the number information records.

[0062] S3. Analyze the relationship between the number to be recharged and the local number based on the user relationship network using the relationship analysis engine, and match the relationship with the user relationship. If the match is successful, send a recharge instruction to the recharge server to instruct the recharge server to recharge according to the recharge instruction; otherwise, do not recharge.

[0063] In this embodiment, as Figure 2As shown, the backend server analyzes the relationship between the number to be recharged and the user's own number using a relationship analysis engine. This engine is based on the user relationship network from step S21, making the analyzed relationship between the number to be recharged and the user's own number more accurate. The backend server then matches the relationship analyzed by the relationship analysis engine with the user's selected user relationships. If a match is successful, the number to be recharged has passed the legality check and can be recharged. If a match fails, the number to be recharged has not passed the legality check and will not be recharged. Step S3, where the backend server analyzes the relationship between the number to be recharged and the user's own number based on the user relationship network using the relationship analysis engine, includes:

[0064] S31. Determine whether the number to be recharged is the local number based on the recharge order record. If not, determine whether there are other recharge records for the number to be recharged. If not, analyze the close relationship between the number to be recharged and the local number based on the user relationship network using the relationship analysis engine.

[0065] In this embodiment, as Figure 4 As shown, the backend server will re-verify the legality of the number to be recharged based on the recharge order record generated in step S1, further improving the rigor of the legality verification. When the number to be recharged is neither the local number nor has any other recharge record, the relationship analysis engine will analyze the close relationship between the number to be recharged and the local number based on the user relationship network, providing different legality verification methods for the number to be recharged in various scenarios, thereby improving the comprehensiveness and flexibility of the legality verification.

[0066] S32. Calculate the affinity value between the number to be recharged and the local number based on the user relationship network using the relationship analysis engine;

[0067] S33. Analyze the relationship between the number to be recharged and the local number based on the intimacy value, wherein the intimacy relationship includes direct relatives, collateral relatives, friends, and other relationships.

[0068] In this embodiment, when the backend server calculates the closeness relationship between the number to be recharged and the local number based on the user relationship network using the relationship analysis engine, it first calculates the closeness value between the number to be recharged and the local number, and then judges the closeness relationship based on the closeness value. By numerically classifying closeness relationships, the objectivity of judging closeness relationships is improved and the influence of human subjectivity is reduced. At this time, the backend server's calculation of the closeness value between the number to be recharged and the local number based on the user relationship network using the relationship analysis engine in step S32 includes:

[0069] S321. Calculate the direct affinity value between the local number and the associated numbers in the user relationship network:

[0070]

[0071] Among them, DR (l，k) This represents the direct affinity value between the k-th associated number and the local number. This represents the average call duration of the outgoing call detail records (CDRs) between the k-th associated number and the local number, where m represents the number of outgoing calls; and α represents the adjustment factor for the called call detail records. This represents the average call duration of the called party records between the k-th associated number and the local number, where n represents the number of called parties.

[0072] In this embodiment, when calculating the direct affinity value between the local number and the associated numbers in the user's relationship network, the main considerations are call frequency (number of calls) and average call duration. Due to the one-way flow of the recharge service, the party recharging others is the active recharge party, and the party waiting to be recharged is the passive recharge party. Correspondingly, there are also call detail records (CDRs) of the active caller (calling CDRs) and CDRs of the passive caller (called receiving CDRs). The party that makes more calls is more inclined to recharge others. Therefore, when calculating the direct affinity value between the local number and the associated numbers in the user's relationship network, the average call duration of the calling CDRs between the local number and the associated numbers and the average call duration of the called CDRs between the local number and the associated numbers are calculated respectively. The average call duration is equal to the sum of the call durations divided by the number of calls. An adjustment factor α is set for the called CDRs. The value range of the adjustment factor α is set between [0, 1]. The value of the adjustment factor can also be increased or decreased to amplify or weaken the influence of the average call duration of the called CDRs.

[0073] In one specific embodiment, the total call duration of the outgoing call records between the 8th associated number and the local number is 60 minutes, and the number of outgoing calls is 2, i.e., m=2. Therefore, the average call duration of the outgoing call records between the 8th associated number and the local number is... The total call duration of the called party records between the 8th associated number and the local number is 20 minutes, and the number of called parties is 1, i.e., n=1. Therefore, the average call duration of the called party records between the 8th associated number and the local number is... When α is 0.5 minutes, That is, the direct affinity value between the 8th associated number and the local number is 13.19.

[0074] S322. Calculate the indirect affinity value between the number to be recharged and the local number:

[0075]

[0076] Among them, DR (l，k) DR represents the direct affinity value between the local number and the k-th number.(k，p) This represents the direct affinity value between the k-th number and the number to be recharged;

[0077] In this embodiment, considering the connectivity of the recharge service with third parties—that is, when a user recharges a number through a third-party user—the third-party user may not have call detail records (CDRs) with the number to be recharged, but the two are still related. Therefore, when calculating the affinity value, it is necessary to consider not only the direct relationship between the number to be recharged and the user's own number, but also the indirect relationship. Specifically, it is necessary to calculate the direct affinity value between the associated users in the user relationship network of the user and the number to be recharged, where DR... (k，p The formula for calculating the direct affinity value between the k-th number and the number to be recharged is the same as DR in step S321. (l，k) Calculation formula.

[0078] S323. Calculate the relative intimacy value between the number to be recharged and the local number based on the direct intimacy value and the indirect intimacy value:

[0079] R (l，p) =DR (l，p) +β×IR (l，p)

[0080] Among them, R (l，p) DR represents the relative affinity between the number to be recharged and the user's phone number. (l，p) IR represents the direct affinity value between the number to be recharged and the local phone number, β represents the adjustment factor for the indirect affinity value, and IR represents the direct affinity value. (l，p) This indicates the indirect affinity value between the number to be recharged and the user's own number;

[0081] In this embodiment, when calculating the relative intimacy value between the number to be recharged and the local number, the direct intimacy value calculated in step S321 and the indirect intimacy value calculated in step S322 are combined to calculate the relative intimacy value between the number to be recharged and the local number. This means that the direct and indirect relationships are considered together to improve the accuracy and comprehensiveness of the intimacy relationship between the number to be recharged and the local number. An adjustment factor β is set for the indirect intimacy value. When there is a family relationship in the user's social network, the adjustment factor β will increase accordingly, which will increase the calculated result of the relative intimacy value. In other words, family relationships will increase the relative intimacy value, reflecting the weighting effect of family relationships. The value range of the adjustment factor β is set between [0, 1]. The value of the adjustment factor can be increased or decreased to amplify or weaken the influence of the indirect intimacy value.

[0082] S324. Sort the relative affinity value between the number to be recharged and the local number and the direct affinity value, and recalculate the affinity value between the number to be recharged and the local number based on the sorting result:

[0083] Where R represents the affinity value between the number to be recharged and the local number, m represents the m-th position in the sorting result, and n represents the n associated numbers of the local number.

[0084] In this embodiment, the relative affinity value between the number to be recharged and the local number calculated in step S323 and the direct affinity value between the local number and the associated numbers in the user's relationship network calculated in step S321 are sorted, and the comparison value between the sorted position and the total number of associated numbers is calculated. The difference is calculated for each pair of comparison values, so that the affinity value between the number to be recharged and the local number is in the range of [0,1]. The affinity values ​​in [0,1] are divided into four relationship thresholds: affinity values ​​in [0.75-1) belong to direct relatives, affinity values ​​in [0.5-0.75) belong to collateral relatives, affinity values ​​in [0.25-0.5) belong to friends, and affinity values ​​in [0-0.25) belong to other relationships. The larger the value, the closer the affinity between the two. The relationship between the number to be recharged and the local number can be obtained by comparing the calculated affinity value between the two numbers with the relationship threshold.

[0085] In a specific embodiment, the sorting result is the 8th position, i.e., m=8. The local number has 80 associated numbers, i.e., n=80. Then the affinity value R between the number to be recharged and the local number is 1-8 / 80=0.9. According to the relationship threshold, the relationship between the number to be recharged and the local number is that of direct relatives.

[0086] The step S3, which includes "otherwise no recharge," includes:

[0087] S34. Send a recharge confirmation notification to the application and obtain the confirmation result from the application in real time. If the confirmation result cannot be obtained within a specified time, the recharge will not be performed and a refund will be issued. If the confirmation result is successfully obtained within a specified time, it will be determined whether the confirmation result indicates that the recharge should continue. If so, a recharge instruction will be sent to the recharge server to instruct the recharge server to perform the recharge. Otherwise, the recharge will not be performed and a refund will be issued.

[0088] In this embodiment, when the relationship between the number to be recharged and the user's phone number does not match the user's relationship, the backend server sends a recharge confirmation notification to the application, prompting the user to reconfirm whether to recharge. This allows the user to double-check if the number to be recharged was entered correctly. If correct, the recharge is processed based on the user's confirmation. If incorrect, the recharge is cancelled based on the user's cancellation, and a refund is issued. To further enhance security, a specified time is set when sending the recharge confirmation notification to the application. Confirmations from the user within this timeframe are received and processed by the backend server. If the specified time is exceeded, the backend server cannot obtain the user's confirmation and defaults to cancellation, resulting in a refund. This not only reduces the risk of users entering the wrong recharge number but also ensures recharge security and optimizes the user experience. The specified time can be set according to specific business scenarios.

[0089] Example 2

[0090] Please refer to Figure 5 A backend server 1 includes a memory 3, a processor 2, and a computer program stored on the memory 3 and executable on the processor 2. When the processor 2 executes the computer program, it implements the steps in Embodiment 1 above.

[0091] Example 3

[0092] The present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed, it implements the steps in Embodiment 1 above.

[0093] Since the systems / devices described in the above embodiments of the present invention are systems / devices used to implement the methods of the above embodiments of the present invention, those skilled in the art can understand the specific structure and modifications of the systems / devices based on the methods described in the above embodiments of the present invention, and therefore will not be repeated here. All systems / devices used in the methods of the above embodiments of the present invention fall within the scope of protection of the present invention.

[0094] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0096] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0097] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0098] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0099] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. A recharge method, characterized in that, include: The system obtains a recharge request from the application and creates a recharge order based on the recharge request, which is then sent to the payment platform. The recharge order instructs the payment platform to perform the deduction and generate a recharge order record. The recharge request includes the number to be recharged, the user's phone number, and the user relationship between the number to be recharged and the user's phone number. Collect call detail records (CDRs) of the number to be recharged and the local number, and establish a user relationship network based on the CDRs. The relationship analysis engine analyzes the close relationship between the number to be recharged and the local number based on the user relationship network, and matches the close relationship with the user relationship. When the match is successful, a recharge instruction is sent to the recharge server to instruct the recharge server to recharge; otherwise, no recharge is performed. The relationship analysis engine analyzes the close relationship between the number to be recharged and the local number based on the user relationship network, including: The relationship analysis engine calculates the affinity value between the number to be recharged and the local number based on the user relationship network; The relationship between the number to be recharged and the local number is analyzed based on the intimacy value, wherein the intimacy relationship includes immediate family relationship, collateral family relationship, friend relationship, and other relationship; The relationship analysis engine calculates the affinity value between the number to be recharged and the local number based on the user relationship network, including: Calculate the direct affinity value between the local number and the associated numbers in the user's social network: in, This represents the direct affinity value between the k-th associated number and the local number. This represents the average call duration of the outgoing call detail records (CDRs) between the k-th associated number and the local number, where m represents the number of outgoing calls; and α represents the adjustment factor for the called call detail records. This represents the average call duration of the called party records between the k-th associated number and the local number, where n represents the number of called parties. Calculate the indirect affinity value between the number to be recharged and the local phone number: in, This represents the direct affinity value between the local number and the k-th number. This represents the direct affinity value between the k-th number and the number to be recharged; Calculate the relative intimacy value between the number to be recharged and the local number based on the direct intimacy value and the indirect intimacy value: in, This indicates the relative affinity between the number to be recharged and the user's phone number. β represents the direct affinity value between the number to be recharged and the local phone number, and β represents the adjustment factor for the indirect affinity value. This indicates the indirect affinity value between the number to be recharged and the user's own number; Sort the relative affinity value between the number to be recharged and the mobile number and the direct affinity value, and recalculate the affinity value between the number to be recharged and the mobile number based on the sorting result: Where R represents the affinity value between the number to be recharged and the local number, m represents the m-th position in the sorting result, and n represents the n associated numbers of the local number.

2. The recharge method as described in claim 1, characterized in that, The step of establishing a user relationship network based on the call detail record data includes: The system obtains number information records from the CRM system and updates the user relationship network in real time. When a number has a cancellation record, all recharge records for that number are marked as unavailable. When the number information record has a family network creation record, a family relationship is established in the user relationship network based on the family network creation record. When the number information record has a family network termination record, the family relationship in the user relationship is deleted based on the family network termination record.

3. The recharge method as described in claim 1, characterized in that, The step of analyzing the close relationship between the number to be recharged and the local number based on the user relationship network using a relationship analysis engine includes: Based on the recharge order record, determine whether the number to be recharged is the user's own number. If not, determine whether the number to be recharged has other recharge records. If not, use a relationship analysis engine to analyze the close relationship between the number to be recharged and the user's own number based on the user relationship network.

4. The recharge method as described in claim 1, characterized in that, The phrase "otherwise no recharge" includes: A recharge confirmation notification is sent to the application, and the confirmation result from the application is obtained in real time. If the confirmation result cannot be obtained within a specified time, the recharge is not performed and a refund is issued. If the confirmation result is successfully obtained within the specified time, it is determined whether the confirmation result indicates that the recharge should continue. If so, a recharge instruction is sent to the recharge server, which instructs the recharge server to perform the recharge. Otherwise, the recharge is not performed and a refund is issued.

5. A backend server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed, implements the method as described in any one of claims 1 to 4.

Images