Telephone data processing method and device, server, storage medium and product
By cyclically updating the telephone data score and the authenticity probability of service sources, the optimal judgment score is adaptively obtained, which solves the problem of low accuracy of judgement of authenticity of telephone data caused by artificial experience dependence in the prior art, and improves the accuracy of judgment.
Patent Information
- Application Number
- CN202411132971.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-12-06
AI Technical Summary
The existing technology relies on manual experience when judging the authenticity of telephone data in insurance business, and lacks reasonable standards, resulting in a low accuracy rate.
By receiving the telephone service source set, telephone data set and initial judgment score, the score of telephone data and the authenticity probability of the service source are updated in a cycle, and the optimal judgment score is obtained adaptively, and the manual experience value setting is replaced to improve the authenticity of the telephone data. accuracy.
The authenticity probability and optimal judgment score of the telephone service source are realized, the accuracy of judging the authenticity of telephone data is improved, and the manual experience value setting is replaced.
Smart Images

Figure CN119089181A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method, device, server, storage medium and product for processing telephone data. Background Art
[0002] In the insurance business, the corresponding customer is identified based on the incoming call data. Therefore, it is particularly important to determine the authenticity of the call data.
[0003] At present, the existing technology usually judges the authenticity of telephone data based on the telephone authenticity probability and judgment score of each telephone service source set by manual experience.
[0004] However, this method relies on people's subjective judgment and experience accumulation, and lacks reasonable standards to judge whether the authenticity probability and judgment score of each manually set telephone service source are accurate, resulting in a low accuracy rate in judging the authenticity of telephone data. Summary of the invention
[0005] The telephone data processing method, device, server, storage medium and product provided in the embodiments of the present application are used to improve the accuracy of determining the authenticity of telephone data.
[0006] In a first aspect, an embodiment of the present application provides a method for processing telephone data, comprising: receiving a telephone service source set sent by a first data terminal; receiving a telephone data set and an initial judgment score sent by a second data terminal; wherein each telephone data in the telephone data set corresponds to an initial telephone score; receiving a verification telephone data set and multiple judgment scores sent by a third data terminal; determining whether the initial judgment scores converge; if it is determined that the initial judgment scores do not converge, looping through the following steps: obtaining the telephone authenticity probability of each telephone service source in the telephone service source set according to the initial telephone score and the initial judgment score corresponding to each telephone data in the telephone data set; determining the telephone authenticity probability of each telephone service source in the telephone service source set according to the telephone authenticity probability and the telephone .... The telephone data set is used to update the initial telephone score of each telephone data in the telephone data set, and obtain the updated telephone score of each telephone data in the telephone data set; determine the optimal judgment score according to the telephone authenticity probability of each telephone service source in the telephone service source set, the verification telephone data set and multiple judgment scores; judge whether the optimal judgment score converges; if it is judged that the optimal judgment score does not converge and has not reached the preset number of cycles, the telephone score after each telephone data is updated is used as the initial telephone score of each telephone data; the optimal judgment score is used as the initial judgment score; if it is judged that the optimal judgment score converges, or / and reaches the preset number of cycles, the cycle is terminated; the telephone authenticity probability and the optimal judgment score of each telephone service source in the telephone service source set are output. The telephone authenticity probability and the optimal judgment score of each telephone service source are used to judge the authenticity of the telephone data.
[0007] In a possible implementation, each verification phone data in the verification phone data set corresponds to a verification value; accordingly, based on the phone authenticity probability of each phone service source in the phone service source set, the verification phone data set and multiple judgment scores, an optimal judgment score is determined, including: obtaining a phone score for each verification phone data in the verification phone data set based on the phone authenticity probability of each phone service source in the phone service source set and the verification phone data set; obtaining a loss value corresponding to each judgment score based on the phone score and the verification value of each verification phone data in the verification phone data set and each judgment score in multiple judgment scores, so as to obtain multiple loss values; determining the judgment score corresponding to the minimum loss value among the multiple loss values as the optimal judgment score.
[0008] In a possible implementation, the initial telephone score and initial judgment score corresponding to each telephone data in the telephone data set are used to obtain the telephone authenticity probability of each telephone service source in the telephone service source set. The formula is:
[0009]
[0010] In the formula, P(S V >Sc|C i ) represents the authenticity probability of the calls from each call service source, S V represents the set of initial phone scores corresponding to each phone data in the phone data set, Sc represents the initial judgment score, C i Indicates the source of each telephone service.
[0011] In a possible implementation, according to the phone authenticity probability of each phone service source in the phone service source set and the phone data set, the initial phone score of each phone data in the phone data set is updated to obtain the updated phone score of each phone data in the phone data set, and the formula is:
[0012]
[0013] Where V q represents the updated phone score of each phone data in the phone data set, P(S V >Sc|C i ) represents the authenticity probability of the calls from each telephone service source, and m represents the number of telephone service sources in the telephone service source set.
[0014] In a possible implementation, according to the telephone score and the verification value of each verification telephone data in the verification telephone data set, and each judgment score of the multiple judgment scores, the loss value corresponding to each judgment score is obtained, and the formula is:
[0015]
[0016] In the formula, Loss represents the loss value corresponding to each judgment score, h represents the number of all verification phone data that meet the loss condition in the verification phone data set, and R j represents the phone score of each verification phone data in the verification phone data set that meets the loss condition, K j Indicates the verification value corresponding to each verification phone data.
[0017] In one possible implementation, the loss condition is: the telephone score of each verification phone data is greater than each of the multiple judgment scores, and the verification value corresponding to each verification phone data is a first value; or, the telephone score of each verification phone data is less than each of the multiple judgment scores, and the verification value corresponding to each verification phone data is a second value.
[0018] In a second aspect, an embodiment of the present application provides a device for processing telephone data, including:
[0019] A first receiving module, used for receiving a telephone service source set sent by a first data terminal;
[0020] A second receiving module is used to receive a telephone data set and an initial judgment score sent by a second data terminal, wherein each telephone data in the telephone data set corresponds to an initial telephone score;
[0021] A third receiving module, used for receiving a verification phone data set and a plurality of determination points sent by a third data terminal;
[0022] A judgment module is used to judge whether the initial judgment score converges;
[0023] The loop module is used to loop through the following steps if the initial judgment score does not converge:
[0024] The circulation module includes:
[0025] A first acquisition unit is used to acquire the phone authenticity probability of each phone service source in the phone service source set according to the initial phone score and the initial judgment score corresponding to each phone data in the phone data set;
[0026] A second acquisition unit is used to update the initial telephone score of each telephone data in the telephone data set according to the telephone authenticity probability of each telephone service source in the telephone service source set and the telephone data set, and obtain the updated telephone score of each telephone data in the telephone data set;
[0027] A determination unit, configured to determine an optimal judgment score according to the authenticity probability of calls from each telephone service source in the telephone service source set, a verification telephone data set and a plurality of judgment scores;
[0028] A judgment unit, used to judge whether the optimal judgment score converges;
[0029] The first determination unit is configured to use the updated telephone score of each telephone data as the initial telephone score of each telephone data if it is determined that the optimal determination score does not converge and the preset number of cycles has not been reached; and use the optimal determination score as the initial determination score;
[0030] A second determination unit, configured to terminate the loop if it is determined that the optimal determination score converges, or / and a preset number of loops is reached;
[0031] The output module is used to output the authenticity probability and optimal judgment score of the calls from each telephone service source in the telephone service source set, wherein the authenticity probability and optimal judgment score of the calls from each telephone service source are used to judge the authenticity of the telephone data.
[0032] In a third aspect, an embodiment of the present application provides a server, including: a memory, a processor;
[0033] The memory stores computer-executable instructions;
[0034] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.
[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.
[0036] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.
[0037] Embodiments of the present application provide a method, device, server, storage medium, and product for processing telephone data. A telephone service source set sent by a first data terminal, a telephone data set and an initial judgment score sent by a second data terminal, and a verification telephone data set and multiple judgment scores sent by a third data terminal are received; if the initial judgment score does not converge, the following steps are executed cyclically: the telephone authenticity probability of each telephone service source in the telephone service source set is obtained according to the initial telephone score and the initial judgment score corresponding to each telephone data in the telephone data set; the telephone score of each telephone data is obtained according to the telephone authenticity probability of each telephone service source; the optimal judgment score is determined according to the telephone authenticity probability of each telephone service source, the verification telephone data set and the multiple judgment scores; if it is determined that the optimal judgment score does not converge and the preset number of cycles has not been reached, the telephone score after the update of each telephone data is used as the initial telephone score of each telephone data, and the optimal judgment score is used as the initial judgment score; in each cycle process, the telephone authenticity probability of each telephone service source, the telephone score after the update of each telephone data and the optimal judgment score are re-obtained until it is determined that the optimal judgment score converges, or / and the preset number of cycles is reached, and the cycle is terminated; the telephone authenticity probability and the optimal judgment score of each telephone service source in the telephone service source set are output. The method of the present application can adaptively update the phone authenticity probability of each phone service source, and obtain the optimal judgment score on this basis, replacing the manual experience value setting, thereby improving the accuracy of judging the authenticity of phone data. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0039] Figure 1 A schematic diagram of a scenario of a method for processing telephone data provided in an embodiment of the present application;
[0040] Figure 2 A flowchart of a method for processing telephone data provided in an embodiment of the present application;
[0041] Figure 3 A schematic diagram of the structure of a telephone data processing device provided in an embodiment of the present application;
[0042] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present application.
[0043] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0044] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0045] In the insurance business, the corresponding customer is identified based on the incoming call data. Therefore, it is particularly important to judge the authenticity of the call data. At present, the existing technology usually judges the authenticity of the call data based on the call authenticity probability and judgment score of each call service source set by manual experience. However, this method relies on human subjective judgment and experience accumulation, and lacks reasonable standards to judge whether the call authenticity probability and judgment score of each call service source set manually are accurate, resulting in a low accuracy rate in judging the authenticity of the call data.
[0046] In order to solve the above technical problems, the embodiment of the present application proposes the following technical ideas: considering the artificial experience to set the phone authenticity probability and judgment score of each phone service source, resulting in a low accuracy rate in judging the authenticity of phone data. The inventor thought of adaptively updating the phone authenticity probability of each phone service source, and on this basis, obtaining the optimal judgment score, replacing the artificial experience value setting, thereby improving the accuracy rate in judging the authenticity of phone data. A telephone service source set sent by a first data terminal, a telephone data set and an initial judgment score sent by a second data terminal, and a verification telephone data set and multiple judgment scores sent by a third data terminal are received; if the initial judgment score does not converge, the following steps are executed cyclically: the telephone authenticity probability of each telephone service source in the telephone service source set is obtained according to the initial telephone score and the initial judgment score corresponding to each telephone data in the telephone data set; the telephone score of each telephone data is obtained according to the telephone authenticity probability of each telephone service source; the optimal judgment score is determined according to the telephone authenticity probability of each telephone service source, the verification telephone data set and the multiple judgment scores; if it is determined that the optimal judgment score does not converge and the preset number of cycles has not been reached, the telephone score after the update of each telephone data is used as the initial telephone score of each telephone data, and the optimal judgment score is used as the initial judgment score; in each cycle process, the telephone authenticity probability of each telephone service source, the telephone score after the update of each telephone data and the optimal judgment score are re-obtained until it is determined that the optimal judgment score converges, or / and the preset number of cycles is reached, and the cycle is terminated; the telephone authenticity probability and the optimal judgment score of each telephone service source in the telephone service source set are output. The method of the present application can adaptively update the phone authenticity probability of each phone service source during a cycle, and obtain the optimal judgment score on this basis, replacing the manual experience value setting, thereby improving the accuracy of judging the authenticity of phone data.
[0047] The method for processing telephone data provided in this application is intended to solve the above technical problems in the prior art.
[0048] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0049] Figure 1 A schematic diagram of a scenario of a method for processing telephone data provided in an embodiment of the present application, such as Figure 1 As shown, the specific application scenarios of the present application include: a first data terminal 101 , a second data terminal 102 , a third data terminal 103 , a server 104 and a platform terminal 105 .
[0050] refer to Figure 1 , the first data terminal 101 sends the telephone service source set to the server 104, the second data terminal 102 sends the telephone data set and the initial judgment score to the server 104, and the third data terminal 103 sends the verified telephone data set and multiple judgment scores to the server 104; the server 104 performs a series of processing on the telephone service source set, the telephone data set, the initial judgment score, the verified telephone data set and the multiple judgment scores to obtain the telephone authenticity probability and the optimal judgment score of each telephone service source in the telephone service source set, and sends them to the platform terminal 105 for display.
[0051] Figure 2 This is a flow chart of a method for processing telephone data provided in an embodiment of the present application. The execution subject of this embodiment may be Figure 1 The server in the embodiment may also be other devices with similar functions, and this embodiment does not impose any special restrictions here. Figure 2 As shown, the method includes:
[0052] S201: receiving a telephone service source set sent by a first data terminal.
[0053] Specifically, the first data terminal collects multiple telephone service sources in the insurance business.
[0054] For example, the total number of telephone service sources is m, and the telephone service source set can be defined as C = {C1, C2, ..., C m}.
[0055] S202: receiving a telephone data set and an initial determination score sent by a second data terminal; wherein each telephone data in the telephone data set corresponds to an initial telephone score.
[0056] The initial judgment score is used to determine the authenticity of the phone data. If the phone score corresponding to the phone data is greater than the initial judgment score, it means that the phone data is true; if the phone score corresponding to the phone data is less than the initial judgment score, it means that the phone data is false.
[0057] Specifically, the second data terminal cleans the telephone data set to remove duplicate, erroneous or invalid information to ensure data quality; the telephone data set includes a plurality of telephone data.
[0058] For example, the total number of telephone data in the telephone data set is n, and the telephone data set can be defined as V = {V1, V2, ..., V n}.
[0059] In this embodiment, each telephone data corresponds to an initial telephone score. For example, the initial telephone score corresponding to V1 is S v1 .
[0060] S203: Receive the verification telephone data set and multiple determination scores sent by the third data terminal.
[0061] S204: Determine whether the initial judgment score converges.
[0062] S205: If it is determined that the initial determination score does not converge, the following steps are executed in a loop:
[0063] Specifically, the cycle steps include S2051 to S2056:
[0064] S2051: Obtain the phone authenticity probability of each phone service source in the phone service source set according to the initial phone score and initial judgment score corresponding to each phone data in the phone data set.
[0065] Specifically, according to the initial telephone score and initial judgment score corresponding to each telephone data in the telephone data set, the formula for obtaining the telephone authenticity probability of each telephone service source in the telephone service source set is:
[0066]
[0067] In the formula, P(S V >Sc|C i ) represents the authenticity probability of the calls from each call service source, S V represents the set of initial phone scores corresponding to each phone data in the phone data set, Sc represents the initial judgment score, C i Indicates the source of each telephone service.
[0068] In this embodiment, each telephone data in the telephone data set corresponds to an initial telephone score, S V Represents the set of initial phone scores corresponding to each phone data in the phone dataset.
[0069] S2052: According to the telephone authenticity probability of each telephone service source in the telephone service source set and the telephone data set, an initial telephone score of each telephone data in the telephone data set is updated to obtain an updated telephone score of each telephone data in the telephone data set.
[0070] Specifically, according to the telephone authenticity probability of each telephone service source in the telephone service source set and the telephone data set, the initial telephone score of each telephone data in the telephone data set is updated to obtain the updated telephone score of each telephone data in the telephone data set. The formula is:
[0071]
[0072] Where V q represents the updated phone score of each phone data in the phone data set, P(S V >Sc|C i ) represents the authenticity probability of the calls from each telephone service source, and m represents the number of telephone service sources in the telephone service source set.
[0073] In this embodiment, each telephone data is represented by a vector with a dimension of m, such as Indicates the possibility that the phone data V1 comes from C1, Indicates the possibility that the phone data V1 comes from C2, Indicates that the phone data V1 comes from C m possibility.
[0074] For example, if V1=[0,1,...,1], Table 1 is an example of telephone data V1, as shown in Table 1, where Indicates that the telephone data V1 does not come from C1, Indicates that the phone data V1 comes from C2, Indicates that the phone data comes from C m . P(S V >Sc|C1)=0.9 means that the authenticity probability of the call from the call service source C1 is 0.9, P(S V >Sc|C2)=0.8 means that the authenticity probability of the call from the call service source C2 is 0.9, P(S V >Sc|C m )=0.5 indicates that the telephone service source is C m The authenticity probability of the phone call is 0.5; the phone score after the phone data V1 is updated is:
[0075] V1=(1-(1-P(S V >Sc|C1))(1-P(S V>Sc|C2))…(1-P(S V >Sc|C m )))*100
[0076] V1=[0,1,...,1] When i=1, it is not included in the calculation process, that is:
[0077] V1=(1-(1-P(S V >Sc|C2))…(1-P(S V >Sc|C m )))*100=(1-(1-0.9)(1-0.5))*100=95
[0078] Table 1 Example of phone data V1
[0079]
[0080] S2053: Determine the optimal judgment score according to the authenticity probability of the calls from each telephone service source in the telephone service source set, the verification telephone data set and multiple judgment scores.
[0081] Each verification phone data in the verification phone data set corresponds to a verification value.
[0082] Specifically, step S2053 includes Sa~Sc:
[0083] Sa: According to the authenticity probability of the calls from each telephone service source in the telephone service source set and the verification telephone data set, the telephone score of each verification telephone data in the verification telephone data set is obtained.
[0084] In this embodiment, the total number of verification telephones in the verification telephone data set is O. Exemplarily, the verification telephone data set can be defined as R={R1, R2, ..., R O}, each verification phone data uses a vector with dimension m, such as Indicates the possibility that the verification phone data R1 comes from C1, Indicates the possibility that the verification phone data R1 comes from C2, Indicates that the verification phone data R1 comes from C m possibility.
[0085] Specifically, the calculation process of the telephone score of each verified telephone data is the same as the calculation process of step S2052, which will not be repeated here.
[0086] Sb: According to the telephone score and the verification value of each verification telephone data in the verification telephone data set, and each judgment score in the multiple judgment scores, the loss value corresponding to each judgment score is obtained to obtain multiple loss values.
[0087] Specifically, according to the telephone score and verification value of each verification telephone data in the verification telephone data set, and each judgment score in the multiple judgment scores, the loss value corresponding to each judgment score is obtained, and the formula is:
[0088]
[0089] In the formula, Loss represents the loss value corresponding to each judgment score, h represents the number of all verification phone data that meet the loss condition in the verification phone data set, and R j represents the phone score of each verification phone data in the verification phone data set that meets the loss condition, K j Indicates the verification value corresponding to each verification phone data.
[0090] In this embodiment, each verification phone data corresponds to a verification value, which is used to represent the true value of each phone data. For example, the verification value corresponding to R1 is K1, the verification value corresponding to R2 is K2, and R o The corresponding verification value is K o .
[0091] Specifically, the loss conditions are:
[0092] The telephone score of each verification telephone data is greater than the initial judgment score, and the verification value corresponding to each verification telephone data is the first value;
[0093] Or, the telephone score of each verification telephone data is less than the initial determination score, and the verification value corresponding to each verification telephone data is the second value.
[0094] In this embodiment, one judgment score corresponds to one loss value, and multiple judgment scores are S={S1, S2, ..., S t}.
[0095] For example, the verification phone data set R = {R1, R2, ..., R O The corresponding telephone rating set of the verification telephone data is S R ={S R1 ,S R2 ,...,S RO}, that is, the phone score corresponding to the verified phone data R1 is S R1 , the phone score corresponding to the verified phone data R2 is S R2 , verify phone data R o The corresponding phone score is S Ro. Verification phone data set R = {R1, R2, ..., R O The corresponding verification value set is K = {K1, K2, ..., K O}, that is, the verification value corresponding to the verification phone data R1 is K1, the verification value corresponding to the verification phone data R2 is K2, and the verification phone data R O The corresponding verification value is K O .
[0096] For example, if the phone score S of the verified phone data R1 is R1 is greater than S1, and the verification value K1 corresponding to each verification phone data R1 is the first value;
[0097] Or, the phone score S of each verified phone data R1 R1 is smaller than S1, and the verification value K corresponding to each verification phone data R1 is the second value.
[0098] This means that the verification phone data R1 meets the loss condition.
[0099] According to the formula of the loss value corresponding to each judgment score, multiple loss values are calculated. That is, multiple judgment scores S = {S1, S2, ..., S t}Corresponding to multiple loss values Loss={Loss1, Loss2,..., Loss t}.
[0100] Sc: The judgment score corresponding to the minimum loss value among multiple loss values is determined as the optimal judgment score.
[0101] Specifically, Loss={Loss1, Loss2, ..., Loss t The judgment score corresponding to the minimum loss value in} is determined as the optimal judgment score.
[0102] S2054: Determine whether the optimal judgment score converges.
[0103] In this embodiment, the process of judging whether the optimal judgment score has converged is as follows: if the difference between the two optimal judgment scores of any two adjacent cycles is less than a set value, it means that the optimal judgment score has converged.
[0104] S2055: If it is determined that the optimal judgment score does not converge and the preset number of cycles is not reached, the updated telephone score of each telephone data is used as the initial telephone score of each telephone data; and the optimal judgment score is used as the initial judgment score.
[0105] S2056: If the optimal decision score is determined to be converged, or / and the preset number of loops is reached, then the loop ends.
[0106] S206: Output the authenticity probability and optimal judgment score of the calls from each telephone service source in the telephone service source set, wherein the authenticity probability and optimal judgment score of the calls from each telephone service source are used to judge the authenticity of the telephone data.
[0107] In this embodiment, the telephone authenticity probability of each telephone service source in the telephone service source set is used to determine the telephone score of each telephone data, and the telephone score of each telephone data is compared with the optimal judgment score to determine the authenticity of the telephone data.
[0108] In summary, the telephone service source set sent by the first data terminal, the telephone data set and the initial judgment score sent by the second data terminal, and the verification telephone data set and multiple judgment scores sent by the third data terminal are received; if the initial judgment score does not converge, the following steps are executed cyclically: according to the initial telephone score and the initial judgment score corresponding to each telephone data in the telephone data set, the telephone authenticity probability of each telephone service source in the telephone service source set is obtained; according to the telephone authenticity probability of each telephone service source, the telephone score of each telephone data is obtained; according to the telephone authenticity probability of each telephone service source, the optimal judgment score is determined according to the telephone authenticity probability of each telephone service source, the verification telephone data set and the multiple judgment scores, if it is determined that the optimal judgment score does not converge and the preset number of cycles is not reached, the telephone score after the update of each telephone data is used as the initial telephone score of each telephone data, and the optimal judgment score is used as the initial judgment score; in each cycle process, the telephone authenticity probability of each telephone service source, the telephone score after the update of each telephone data and the optimal judgment score are re-obtained until it is determined that the optimal judgment score converges, or / and the preset number of cycles is reached, and the cycle is terminated; the telephone authenticity probability and the optimal judgment score of each telephone service source in the telephone service source set are output. The method of the present application can adaptively update the phone authenticity probability of each phone service source during a cycle, and obtain the optimal judgment score on this basis, replacing the manual experience value setting, thereby improving the accuracy of judging the authenticity of phone data.
[0109] Based on the above facts, in this embodiment, the processing process when the optimal decision score does not converge and the preset number of cycles is not reached is described in detail, as follows:
[0110] The updated telephone score of each telephone data in the telephone data set is used as the initial telephone score of each telephone data; and the optimal judgment score is used as the initial judgment score.
[0111] Specifically, according to the replaced initial telephone score and the replaced initial judgment score, the telephone authenticity probability of each telephone service source in each telephone service source set is updated; according to the updated telephone authenticity probability of each telephone service source in each telephone service source set, the telephone score of each telephone data in each telephone data set and the telephone score of each verified telephone data in each verified telephone data set are re-updated. According to the telephone score and the verification value of each verified telephone data in the verified telephone data set, and each judgment score in the multiple judgment scores, the loss value corresponding to each judgment score is obtained to obtain multiple loss values. The judgment score corresponding to the minimum loss value among the multiple loss values is determined as the optimal judgment score.
[0112] In summary, if the optimal judgment score does not converge, the updated telephone score of each telephone data in the telephone data set is used as the initial telephone score of each telephone data; the optimal judgment score is used as the initial judgment score, and the authenticity probability of the telephone calls of each telephone service source in each telephone service source set is recalculated, and combined with the current initial judgment score, the optimal judgment score is obtained again, and this process continues until the end of the loop. Through the above method, the authenticity probability of the telephone calls of each telephone service source can be adaptively updated during the loop, and the optimal judgment score can be obtained on this basis, replacing the manual experience value setting, thereby improving the accuracy of judging the authenticity of the telephone data.
[0113] Figure 3 A schematic diagram of the structure of a telephone data processing device provided in an embodiment of the present application, such as Figure 3 As shown, the telephone data processing device provided in this embodiment includes: a first receiving module 10, a second receiving module 20, a third receiving module 30, a judging module 40, a loop module 50 and an output module 60. The loop module 50 includes: a first acquiring unit 501, a second acquiring unit 502, a determining unit 503, a judging unit 504, a first judging unit 505 and a second judging unit 506.
[0114] The first receiving module 10 is used to receive a telephone service source set sent by the first data terminal;
[0115] The second receiving module 20 is used to receive the telephone data set and the initial judgment score sent by the second data terminal; wherein each telephone data in the telephone data set corresponds to an initial telephone score;
[0116] A third receiving module 30, configured to receive a verification phone data set and a plurality of determination points sent by a third data terminal;
[0117] A judgment module 40, used to judge whether the initial judgment score converges;
[0118] The loop module 50 is used to loop through the following steps if it is determined that the initial determination score does not converge:
[0119] The circulation module 50 includes:
[0120] The first acquisition unit 501 is used to acquire the phone authenticity probability of each phone service source in the phone service source set according to the initial phone score and initial judgment score corresponding to each phone data in the phone data set;
[0121] The second acquisition unit 502 is used to update the initial telephone score of each telephone data in the telephone data set according to the telephone authenticity probability of each telephone service source in the telephone service source set and the telephone data set, and obtain the updated telephone score of each telephone data in the telephone data set;
[0122] A determination unit 503, configured to determine an optimal judgment score according to the authenticity probability of the calls from each telephone service source in the telephone service source set, the verification telephone data set and the plurality of judgment scores;
[0123] A judging unit 504, used to judge whether the optimal judgment score converges;
[0124] The first determination unit 505 is used to use the updated telephone score of each telephone data as the initial telephone score of each telephone data if it is determined that the optimal determination score does not converge and the preset number of cycles has not been reached; and use the optimal determination score as the initial determination score;
[0125] A second determination unit 506, configured to terminate the loop if the optimal determination score converges or / and reaches a preset number of loops;
[0126] The output module 60 is used to output the authenticity probability and optimal judgment score of the calls from each telephone service source in the telephone service source set, wherein the authenticity probability and optimal judgment score of the calls from each telephone service source are used to judge the authenticity of the telephone data.
[0127] In a possible implementation, each verification phone data in the verification phone data set corresponds to a verification value; accordingly, the determination unit 503 is specifically used to: obtain a phone score for each verification phone data in the verification phone data set based on the phone authenticity probability of each phone service source in the phone service source set and the verification phone data set; obtain a loss value corresponding to each judgment point based on the phone score and the verification value of each verification phone data in the verification phone data set, as well as each judgment point in multiple judgment points, to obtain multiple loss values; determine the judgment point corresponding to the minimum loss value in the multiple loss values as the optimal judgment point.
[0128] In a possible implementation manner, the formula of the first acquisition unit 501′ is:
[0129]
[0130] In the formula, P(SV >Sc|C i ) represents the authenticity probability of the calls from each call service source, S V represents the set of initial phone scores corresponding to each phone data in the phone data set, Sc represents the initial judgment score, C i Indicates the source of each telephone service.
[0131] In a possible implementation manner, the formula of the second acquisition unit 502′ is:
[0132]
[0133] Where V q represents the updated phone score of each phone data in the phone data set, P(S V >Sc|C i ) represents the authenticity probability of the calls from each telephone service source, and m represents the number of telephone service sources in the telephone service source set.
[0134] In a possible implementation, the formula of the determination unit 503′ is:
[0135]
[0136] In the formula, Loss represents the loss value corresponding to each judgment score, h represents the number of all verification phone data that meet the loss condition in the verification phone data set, and R j represents the phone score of each verification phone data in the verification phone data set that meets the loss condition, K j Indicates the verification value corresponding to each verification phone data.
[0137] In one possible implementation, the loss condition is: the telephone score of each verification phone data is greater than each of the multiple judgment scores, and the verification value corresponding to each verification phone data is a first value; or, the telephone score of each verification phone data is less than each of the multiple judgment scores, and the verification value corresponding to each verification phone data is a second value.
[0138] The telephone data processing device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.
[0139] Figure 4 This is a schematic diagram of the structure of the server provided in the embodiment of the present application. Figure 4 As shown, the server provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the server also includes a communication component 403. The processor 401, the memory 402 and the communication component 403 are connected via a bus.
[0140] In a specific implementation process, at least one processor 401 executes the computer-executable instructions stored in the memory 402, so that at least one processor 401 executes the above method.
[0141] The specific implementation process of the processor 401 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0142] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.
[0143] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.
[0144] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0145] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0146] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable interrupt processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.
[0147] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0148] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.
[0149] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0150] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A method for processing telephone data, characterized in that: Applicable to servers, including: receiving a telephone service source set sent by the first data terminal; Receiving a telephone data set and an initial determination score sent by a second data terminal; wherein each telephone data in the telephone data set corresponds to an initial telephone score; receiving a verification telephone data set and a plurality of determination points sent by a third data terminal; Determining whether the initial determination score converges; If it is determined that the initial determination score does not converge, the following steps are executed in a loop: Obtaining the phone authenticity probability of each phone service source in the phone service source set according to the initial phone score corresponding to each phone data in the phone data set and the initial judgment score; According to the telephone authenticity probability of each telephone service source in the telephone service source set and the telephone data set, updating the initial telephone score of each telephone data in the telephone data set to obtain the updated telephone score of each telephone data in the telephone data set; Determining an optimal judgment score according to the authenticity probability of calls from each telephone service source in the telephone service source set, the verification telephone data set and the multiple judgment scores; Determining whether the optimal judgment score converges; If it is determined that the optimal judgment score does not converge and the preset number of cycles is not reached, the updated telephone score of each telephone data is used as the initial telephone score of each telephone data; the optimal judgment score is used as the initial judgment score; If it is determined that the optimal determination score converges, or / and reaches a preset number of cycles, then the cycle ends; Output the authenticity probability of the calls from each telephone service source in the telephone service source set and the optimal judgment score; wherein the authenticity probability of the calls from each telephone service source and the optimal judgment score are used to judge the authenticity of the telephone data.
2. The method according to claim 1, characterized in that Each verification phone data in the verification phone data set corresponds to a verification value; Accordingly, determining the optimal judgment score according to the authenticity probability of the calls from each telephone service source in the telephone service source set, the verification telephone data set and the multiple judgment scores includes: Obtaining a telephone score for each verification telephone data in the verification telephone data set according to the telephone authenticity probability of each telephone service source in the telephone service source set and the verification telephone data set; According to the telephone score and the verification value of each verification telephone data in the verification telephone data set, and each judgment score of the multiple judgment scores, a loss value corresponding to each judgment score is obtained to obtain multiple loss values; The judgment score corresponding to the minimum loss value among the multiple loss values is determined as the optimal judgment score.
3. The method according to claim 1, characterized in that: The formula for obtaining the phone authenticity probability of each phone service source in the phone service source set using the initial phone score and the initial judgment score corresponding to each phone data in the phone data set is: In the formula, P(S V >Sc|C i ) represents the authenticity probability of the calls from the respective call service sources, S V represents the set of initial telephone scores corresponding to each telephone data in the telephone data set, Sc represents the initial judgment score, C i Indicates the sources of each telephone service.
4. The method according to claim 1, characterized in that The formula for updating the initial telephone score of each telephone data in the telephone data set according to the telephone authenticity probability of each telephone service source in the telephone service source set and the telephone data set to obtain the updated telephone score of each telephone data in the telephone data set is: Where V q represents the updated telephone score of each telephone data in the telephone data set, P(S V >Sc|C i ) represents the authenticity probability of the calls from each telephone service source, and m represents the number of telephone service sources in the telephone service source set.
5. The method according to any one of claims 1 to 4, characterized in that: The formula for obtaining the loss value corresponding to each judgment score according to the telephone score and the verification value of each verification telephone data in the verification telephone data set and each judgment score in the multiple judgment scores is: In the formula, Loss represents the loss value corresponding to each judgment score, h represents the number of all verification phone data that meet the loss condition in the verification phone data set, and R j represents the phone score of each verification phone data in all verification phone data satisfying the loss condition in the verification phone data set, K j Indicates the verification value corresponding to each verification phone data.
6. The method according to claim 5, characterized in that The loss conditions are: The telephone score of each verification telephone data is greater than each of the multiple determination scores, and the verification value corresponding to each verification telephone data is a first value; Alternatively, the telephone score of each verification telephone data is less than each of the multiple determination scores, and the verification value corresponding to each verification telephone data is the second value.
7. A telephone data processing device, characterized in that: Applicable to servers, including: A first receiving module, used for receiving a telephone service source set sent by a first data terminal; A second receiving module is used to receive a telephone data set and an initial determination score sent by a second data terminal; wherein each telephone data in the telephone data set corresponds to an initial telephone score; A third receiving module, used for receiving a verification phone data set and a plurality of determination points sent by a third data terminal; A judgment module, used to judge whether the initial judgment score converges; A loop module is used to loop through the following steps if it is determined that the initial determination score does not converge: Wherein, the circulation module comprises: A first acquisition unit, configured to acquire a phone authenticity probability of each phone service source in the phone service source set according to an initial phone score corresponding to each phone data in the phone data set and the initial determination score; A second acquisition unit is used to update the initial telephone score of each telephone data in the telephone data set according to the telephone authenticity probability of each telephone service source in the telephone service source set and the telephone data set, and obtain the updated telephone score of each telephone data in the telephone data set; A determination unit, configured to determine an optimal judgment score according to the authenticity probability of calls from each telephone service source in the telephone service source set, the verification telephone data set and the multiple judgment scores; A judging unit, used to judge whether the optimal judgment score converges; A first determination unit is configured to use the updated telephone score of each telephone data as the initial telephone score of each telephone data if it is determined that the optimal determination score does not converge and the preset number of cycles has not been reached; and use the optimal determination score as the initial determination score; A second determination unit, configured to terminate the loop if it is determined that the optimal determination score converges, or / and reaches a preset number of loops; The output module is used to output the authenticity probability of the calls from each telephone service source in the telephone service source set and the optimal judgment score; wherein the authenticity probability of the calls from each telephone service source and the optimal judgment score are used to judge the authenticity of the telephone data.
8. A server, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.
10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.
Citation Information
Patent Citations
Systems and methods for risk based decision making
CN107533705A
Systems and methods for data and information source reliability estimation
CN107608996A
Behavior recognition method and device, electronic device and storage medium
CN109886699A
User sorting method and device and electronic equipment
CN110661913A
Order classification method and system, computer equipment and readable storage medium
CN111340053A
