A number evaluation method and related equipment

Abstract

The present disclosure provides a number evaluation method, device, electronic device and storage medium, which relate to the field of data processing technology. The method includes: performing a first evaluation on the outbound number based on the first attribute information of the outbound number to obtain a first evaluation result; determining the outbound call parameters corresponding to the outbound number according to the second attribute information of the outbound number; when the outbound call parameters match the outbound call rules, performing a second evaluation on the outbound number to obtain a second evaluation result; determining the evaluation result of the outbound number according to the first evaluation result and the second evaluation result. The present disclosure adopts two rounds of evaluation combining two different evaluation methods, namely the first evaluation and the second evaluation, so that the evaluation method is more flexible, the evaluation result is more objective, and the accuracy of the outbound number evaluation is improved, thereby improving the outbound call success rate of intelligent outbound calls.

Description

Background Art

[0002] With the development of the Internet and the popularization of artificial intelligence, the use of intelligent outbound call systems is becoming more and more widespread when interacting with users. After the intelligent outbound call system determines the outbound call list, it evaluates the outbound call list and makes intelligent outbound calls to users based on the evaluation results. The evaluation results of the outbound call list determine the outbound call success rate of the intelligent outbound call system. Therefore, before making an outbound call through the intelligent outbound call system, accurately evaluating the outbound call number has become one of the hot issues that need to be solved in the field of intelligent outbound calls.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The present disclosure provides a number evaluation method, device, electronic device and storage medium, which at least to a certain extent overcome the problem that the evaluation results in the related technology are not objective, resulting in the inability to match the user status and bringing a bad experience to the user when making an outbound call.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0006] According to one aspect of the present disclosure, a number evaluation method is provided, comprising:

[0007] Evaluate the outbound call number based on the first attribute information of the outbound call number to obtain a first evaluation result;

[0008] Determine an outbound call parameter corresponding to the outbound call number according to the second attribute information of the outbound call number;

[0009] When the outbound call parameter matches the outbound call rule, performing a second evaluation on the outbound call number to obtain a second evaluation result;

[0010] An evaluation result of the outbound number is determined according to the first evaluation result and the second evaluation result.

[0011] According to another aspect of the present disclosure, there is also provided a number evaluation device, comprising:

[0012] An evaluation module, configured to perform a first evaluation on the outbound call number based on the first attribute information of the outbound call number to obtain a first evaluation result;

[0013] The evaluation module is further used to determine the outbound call parameters corresponding to the outbound call number according to the second attribute information of the outbound call number; when the outbound call parameters match the outbound call rule, perform a second evaluation on the outbound call number to obtain a second evaluation result;

[0014] A determination module is used to determine the evaluation result of the outbound number according to the first evaluation result and the second evaluation result.

[0015] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the number evaluation methods described above by executing the executable instructions.

[0016] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the number evaluation method described in any one of the above is implemented.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including: a computer program or instructions, wherein when the computer program or instructions are executed by a processor, any one of the above number evaluation methods is implemented.

[0018] The number evaluation method provided in the embodiment of the present disclosure evaluates the outbound number based on the first attribute information of the outbound number to obtain a first evaluation result, determines the outbound call parameters corresponding to the outbound number according to the second attribute information of the outbound number, and when the outbound call parameters match the outbound call rules, performs a second evaluation on the outbound number to obtain a second evaluation result, and determines the evaluation result of the outbound number according to the first evaluation result and the second evaluation result. Compared with the fixed evaluation method in the prior art, by adopting two rounds of evaluation combining two different evaluation methods, the first evaluation and the second evaluation, the evaluation method is more flexible, the evaluation result is more objective, and the accuracy of the outbound number evaluation is improved, thereby improving the outbound call success rate of intelligent outbound calls.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0021] Figure 1 A schematic diagram of the working process of an intelligent outbound calling system in an embodiment of the present disclosure is shown;

[0022] Figure 2A schematic diagram showing an exemplary application system structure of a number evaluation method in an embodiment of the present disclosure;

[0023] Figure 3 A flow chart of a number evaluation method in an embodiment of the present disclosure is shown;

[0024] Figure 4 A schematic diagram showing the architecture of a scoring system in a specific example of the present disclosure;

[0025] Figure 5 A schematic diagram showing the logical division of the outbound call rules shown in Table 3 in a specific example of the present disclosure is shown;

[0026] Figure 6 A schematic diagram showing a specific architecture of a scoring module in a specific example of the present disclosure is shown;

[0027] Figure 7 A schematic diagram showing the workflow of the scoring module in a specific example of the present disclosure is shown;

[0028] Figure 8 A schematic diagram of a number evaluation device in an embodiment of the present disclosure is shown; and

[0029] Fig. 9 A structural block diagram of a number evaluation computer device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0030] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0031] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0032] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0033] like Figure 1 The figure shows the workflow of the intelligent outbound call system, which specifically includes the following processes:

[0034] The upstream business systems of the intelligent outbound calling system, such as sales promotion, anti-fraud, anti-telephone fraud and customer service, push their selected user lists and dialing strategies to the receiving system of the intelligent outbound calling list system;

[0035] After receiving the list, the receiving system queries the user profile, user tag, scheduling information and other related information corresponding to the user list, and then pushes it to the list scheduling system;

[0036] The list dispatching system determines the characteristics of each user list based on relevant information, and allocates outbound call channels according to their characteristics. When dialing, the user list is dialed through the outbound call channel. When dialing, it is necessary to evaluate the outbound numbers in the list, and determine the order of dialing based on the evaluation results, that is, to dispatch the list dialing, so that the timeliness of dialing can meet business needs and / or user expectations.

[0037] After the call is made, once a connection is established with the user, each round of human-computer dialogue is handled by the answering system in the intelligent outbound call system.

[0038] It can be seen that the objectivity and accuracy of the evaluation results of the outbound call numbers in the list are a crucial part of the workflow of the intelligent outbound call system, and determine the outbound call success rate of the intelligent outbound call system. The inventors found that the prior art uses fixed evaluation dimensions to construct a scoring model for evaluation, and generally constructs the model through coding definition. From the moment the definition and coding are completed, the entire scoring model cannot change. If indicators such as business needs or user expectations change, the operator needs to redesign and recode the model. The evaluation method is solidified, and the manpower and time costs are high. And only one evaluation will cause the final evaluation result to be not objective enough. When indicators such as business needs or user expectations change, the evaluation results are not accurate enough and the real-time performance is not strong.

[0039] In order to solve the above technical problems, the present disclosure provides a number evaluation method. Figure 2 FIG. 2 shows an exemplary application system architecture diagram to which the number evaluation method in the embodiment of the present disclosure can be applied. Figure 2 As shown, the system architecture may include a terminal device 201 , a network 202 and a server 203 .

[0040] The network 202 is a medium for providing a communication link between the terminal device 201 and the server 203, and can be a wired network or a wireless network.

[0041] Optionally, the wireless network or wired network described above uses standard communication technology and / or protocol. The network is typically the Internet, but may also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or any combination of a virtual private network). In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged over the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPSec) and the like may be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies may also be used to replace or supplement the above data communication technologies.

[0042] The terminal device 201 can be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, smart speakers, smart watches, wearable devices, augmented reality devices, virtual reality devices, etc.

[0043] Optionally, the client of the application installed in different terminal devices 201 is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0044] The server 203 may be a server that provides various services, such as a background management server that provides support for the device operated by the operator using the terminal device 201. The background management server may analyze and process the received request or instruction data, such as the first evaluation instruction sent by the terminal device 201, and feed back the processing result to the terminal device 201.

[0045] Optionally, server 203 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0046] Those skilled in the art will know that Figure 2 The number of terminal devices, networks and servers in the embodiment is only for illustration, and any number of terminal devices, networks and servers may be provided according to actual needs, and the embodiments of the present disclosure do not limit this.

[0047] Under the above system architecture, a number evaluation method is provided in an embodiment of the present disclosure. The method can be executed by any electronic device with computing and processing capabilities.

[0048] In some embodiments, the terminal device 201 can be used to receive an outbound call list, and the terminal device 201 can also be used to interact with an operator. For example, the operator determines the outbound call evaluation conditions based on business needs or the need to interact with the user. The terminal device 201 can receive the operator's evaluation request to generate a request instruction, which is sent to the server 203 and then processed by the number evaluation method provided in the embodiment of the present disclosure.

[0049] In some embodiments, the number evaluation method provided in the embodiments of the present disclosure can be executed by a terminal device of the above-mentioned system architecture; in other embodiments, the number evaluation method provided in the embodiments of the present disclosure can be executed by a server in the above-mentioned system architecture; in other embodiments, the number evaluation method provided in the embodiments of the present disclosure can be implemented by the terminal device and the server in the above-mentioned system architecture through interaction.

[0050] Figure 3 A flow chart of a number evaluation method in an embodiment of the present disclosure is shown as follows: Figure 3 As shown, the number evaluation method provided in the embodiment of the present disclosure includes the following steps:

[0051] Step S302, performing a first evaluation on the outbound number based on the first attribute information of the outbound number to obtain a first evaluation result;

[0052] Step S304, determining an outbound call parameter corresponding to the outbound call number according to the second attribute information of the outbound call number;

[0053] Step S306, when the outbound call parameters match the outbound call rules, a second evaluation is performed on the outbound call number to obtain a second evaluation result;

[0054] Step S308: Determine an evaluation result of the outbound number based on the first evaluation result and the second evaluation result.

[0055] It should be noted that the outbound call list contains at least multiple outbound call numbers corresponding to multiple users. It can be understood by those skilled in the art that in order to facilitate the intelligent outbound call system to schedule dialing of the outbound call list, the business system will also store the relevant attribute information of each outbound call number in the outbound call list when forming the outbound call list, that is, in some embodiments of the present disclosure, the outbound call list may also include the attribute information of each outbound call number, and the outbound call number and the first attribute information of the outbound call number can be obtained from the outbound call list. The first attribute information represents the relevant attributes of the outbound call number, for example, it may include: user attribute information corresponding to the outbound call number, evaluation time information of the outbound call number, expected dialing information of the outbound call number, etc.

[0056] It should be noted that the user attribute information corresponding to the outbound number refers to the relevant information such as the user level, classification or group corresponding to the outbound number. For example, if a user is more important and is a user who needs to be responded to first in the customer service system, "VIP" can be written into the field corresponding to the user attribute information corresponding to the outbound number to mark the user level corresponding to the outbound number. The evaluation time information of the outbound number refers to the time when the outbound number is evaluated. If the outbound number has been stored in the outbound call list and has not been dialed, the outbound number can be evaluated multiple times, and the time data of each evaluation will be updated in the field corresponding to the outbound number evaluation time information. In specific implementation, the evaluation operation can be initiated at a preset time interval, that is, the outbound number evaluation time information updates the data at the preset time interval. The expected dialing information of the outbound number refers to the time when the outbound number expects to be dialed, which can be generated according to business needs. For example, the anti-fraud business stipulates that an outbound call is made to the user within a period of time after determining that the user may be defrauded, such as no more than 5 minutes, then the expected dialing information of the outbound number can be generated according to the provision; it can be generated according to user expectations. For example, in the customer service reply business, the user leaves a message and hopes to receive a reply call at a certain time point (for example, 12 o'clock), then the field corresponding to the expected dialing information of the outbound number is recorded as 12:00; it can also be generated by comprehensively considering business needs and user expectations. For example, in the customer service reply business, the user leaves a message and hopes to receive a reply call before a certain time point (for example, 12 o'clock), and at the same time, a certain amount of time is required to query and determine the solution to the user's inquiry. For example, after 11:50, the field corresponding to the expected dialing information of the outbound number can be recorded as the 11:50-12:00 period, or any time in the 11:50-12:00 period. It can be understood by those skilled in the art that the above-mentioned example description of the first attribute information is only an example and is not used to limit the scope of protection of the present disclosure.

[0057] In some embodiments of the present disclosure, the specific implementation process of step S302 includes the following steps:

[0058] Determine multiple evaluation models corresponding to the first attribute information, and attribute data corresponding to each evaluation model;

[0059] For each dimension, an evaluation model is used to evaluate the attribute data to obtain the evaluation result corresponding to the dimension;

[0060] According to the evaluation result of each dimension, a first evaluation result is calculated.

[0061] In some exemplary embodiments of the present disclosure, multiple dimensions, that is, multiple dimensions for evaluating outbound numbers, can be determined by business needs and / or user expectations. For example, it can be: at least two of the following dimensions, namely, identity feature dimension, outbound call strategy dimension, behavior preference dimension, large model dimension, risk level dimension, and list level dimension, and any combination thereof. It should be noted that each dimension has a corresponding evaluation model, that is, one evaluation model corresponds to one dimension, and the attribute data required for evaluation of each evaluation model is also different. The attribute data corresponding to each evaluation model is part or all of the data contained in the first attribute information. By determining multiple evaluation models corresponding to the first attribute information and the attribute data corresponding to each evaluation model, the corresponding attribute data can be input into the evaluation model for evaluation, so that the evaluation model outputs the evaluation result corresponding to the dimension.

[0062] In some embodiments of the present disclosure, a first number of dimensions may be pre-set, and for each dimension definition, a second number of dimensions may be selected from the first number of dimensions based on evaluation instructions containing business needs and / or user expectations, and the second number may be greater than one and less than or equal to the first number, so that appropriate dimensions may be selected according to actual needs, thereby eliminating the need to rebuild the evaluation system and enabling flexible evaluation. At the same time, selecting at least two dimensions can avoid the problem of objectivity and inaccuracy caused by single-dimensional evaluation. For example, the initial dimensions of the outbound call list W01 are set to dimensions P1, P3, and P5, but due to changes in business needs, changes in evaluation indicators are caused, and evaluation instructions are generated based on the changes to change the current dimensions of the outbound call list W01 to P1, P3, P5, and P4.

[0063] And because the first number of dimensions is pre-set, there is no need to set and define them each time an evaluation is performed. You only need to select from them according to the actual evaluation instructions, which greatly reduces the time and labor costs consumed by the evaluation. It can be understood by those skilled in the art that the above-mentioned specific dimensions are only examples and are not used to limit the scope of protection of the present disclosure. In order to minimize the time and labor costs consumed by the evaluation, more dimensions and corresponding evaluation models can be pre-set, or the dimensions can be updated in time according to the historical data of the evaluation to ensure the comprehensiveness of the pre-set multiple dimensions.

[0064] It should be noted that the identity feature dimension represents the identity characteristics of the user, such as real-name status, social attributes, living environment, education status, etc. The outbound call strategy dimension represents the number sending and dialing strategy assigned by the upstream business system. When it is implemented, the upstream business system will pre-define at least one number sending and dialing strategy and push it together when pushing the list. The behavior preference dimension represents the behavior characteristics of the user that can be judged by the user's operation behavior on the relevant data platform, such as judging whether the user is interested in a certain marketing campaign by the frequency of clicking on a certain activity page. The user label dimension represents the identifiable label that is given to the user through certain attributes, behaviors or other data of the user. For example, if a user purchases a platform membership, he will be labeled as a member user. For example, if the membership purchased is a super member, he will be labeled as a super member user. The big model dimension represents the comprehensive score of the user evaluated by applying the AI ​​big model. The risk level dimension represents the risk level judged by whether the user has a complaint behavior in the past. For example, if a user has only complained through online customer service, he will be judged as a low risk level. List level dimension: It represents the level classification of the pushed list by the upstream business system, and is pushed together with the list.

[0065] In some embodiments of the present disclosure, the evaluation model corresponding to each dimension is predefined, and in specific implementation, it can be determined by calling the evaluation model pre-configuration file, wherein the pre-configuration file stores the definition of the evaluation model corresponding to each dimension. For example, the evaluation model corresponding to the list level dimension is constructed based on the string feature processing method to determine the evaluation result of the list level dimension.

[0066] In some embodiments of the present disclosure, the attribute data corresponding to each evaluation model may be different depending on the evaluation model. For example, the attribute data corresponding to the evaluation model of the identity feature dimension refers to the user information data corresponding to at least one outbound call number, which can be obtained or called from the user information platform; the dimension attribute data of the attribute data corresponding to the evaluation model of the outbound call strategy dimension refers to the outbound call strategy data pushed by the upstream business system corresponding to at least one outbound call number; the attribute data corresponding to the evaluation model of the behavior preference dimension refers to the user behavior feature data corresponding to at least one outbound call number, which can be obtained or called from the relevant data platform; the attribute data corresponding to the evaluation model of the user label dimension refers to the user label data corresponding to at least one outbound call number, which can be obtained or called from the user label calculation platform; the attribute data corresponding to the evaluation model of the big model dimension refers to the big model scoring data of the user corresponding to at least one outbound call number, which can be obtained or called from the big model calculation platform; the attribute data corresponding to the evaluation model of the risk level dimension refers to the risk level data of the user corresponding to at least one outbound call number, which can be obtained or called from the relevant data platform; the attribute data corresponding to the evaluation model of the list level dimension refers to the outbound call list level data pushed by the upstream business system corresponding to at least one outbound call number.

[0067] In some embodiments of the present disclosure, for each dimension, an evaluation model is used to perform an evaluation based on the attribute data to obtain an evaluation result corresponding to the dimension. In specific implementation, the evaluation model can be run by generating an evaluation calculation task to perform an evaluation calculation based on the attribute data, and the evaluation calculation task is executed to obtain an evaluation result corresponding to the corresponding dimension. In a specific embodiment, the computing task can be published to a computing center so that the computing center can allocate appropriate computing resources to perform the computing task based on the computing resources required for the computing task and the computing resource occupancy used by the computing center, thereby reducing the time required to perform the computing task, and can also reasonably utilize computing resources to avoid resource idleness caused by idle computing resources.

[0068] In some exemplary embodiments of the present disclosure, for each dimension, an evaluation is performed based on the attribute data through an evaluation model, and the evaluation result corresponding to each dimension obtained may be an evaluation score displayed as a binary value.

[0069] In some embodiments of the present disclosure, the specific implementation process of calculating the first evaluation result according to the evaluation result of each dimension includes the following steps:

[0070] According to the preset dimension sorting rules, the evaluation results corresponding to each dimension are arranged to obtain a first value;

[0071] Converting the first value to obtain a second value;

[0072] The second numerical value is determined as the first evaluation result.

[0073] In some embodiments of the present disclosure, the pre-set dimension sorting rules are pre-set to characterize the order of importance between multiple dimensions, and more important dimensions can be placed in a more forward position. The importance of multiple dimensions can be determined according to evaluation needs, so as to ensure that the evaluation results are more in line with the evaluation needs. For example, it can be the order of the outbound call strategy dimension, the identity feature dimension, and the behavior preference dimension.

[0074] It should be noted that the second value has a different cardinality from the first value. The number of digital symbols that can be used in a positional system is called the cardinality or base. Different positional systems have different cardins. For example, the decimal cardinality is 10, and the binary cardinality is 2. In some embodiments of the present disclosure, the first value may be a binary value, and the second value may be a decimal value. In some exemplary embodiments of the present disclosure, the evaluation result corresponding to each dimension may be an evaluation score displayed in a binary value. After arranging multiple binary evaluation scores corresponding to the outbound call number according to a preset dimension sorting rule, a new binary value, that is, the first value, is obtained. The first value is converted into a more intuitive second value for the operator to view and intuitively understand.

[0075] It can be understood by those skilled in the art that the implementation process of calculating the first evaluation result according to the evaluation results of each dimension is only an exemplary process, and the process of forming the first evaluation result by integrating the evaluation results of multiple dimensions falls within the protection scope of the embodiments of the present disclosure. For example, the evaluation results of multiple dimensions can be randomly arranged to form a new binary value as the first evaluation result; the evaluation results of multiple dimensions can also be converted into decimal values, and then the first evaluation result can be obtained by adding or multiplying them by their corresponding weight coefficients. The embodiments of the present disclosure will not be repeated here.

[0076] In some embodiments of the present disclosure, after determining the first evaluation result, the outbound call parameters corresponding to the outbound call number are determined according to the second attribute information of the outbound call number, the outbound call number is monitored, and when the outbound call parameters are found to match the outbound call rule, a second evaluation is performed on the outbound call number to obtain a second evaluation result. The process of determining the outbound call parameters corresponding to the outbound call number according to the second attribute information of the outbound call number includes the following steps:

[0077] Determine the preset outbound call parameter items;

[0078] The information matching the outbound call parameter item is determined in the second attribute information of the outbound call number, and the matching information is determined as the outbound call parameter corresponding to the outbound call number.

[0079] It should be noted that the second attribute information represents the attributes of the outbound call number related to outbound calls, which can be included in the outbound call list and received by the intelligent outbound call system, or stored in the outbound call attribute information configuration file corresponding to the outbound call list to be obtained or called. Outbound call parameters refer to the parameters involved in the pre-set outbound call rules.

[0080] In some exemplary embodiments of the present disclosure, a preset outbound call parameter item is determined. The outbound call parameter item may be one or more items, which are parameter items defined or designed in the outbound call rule and may be predetermined based on the outbound call rule or the real-time requirements of the evaluation. After the outbound call parameter item is determined, the information matching the outbound call parameter item is determined in the second attribute information, and the matching information is determined as the outbound call parameter corresponding to the outbound call number, that is, the information matching the outbound call parameter item determined in the second attribute information based on the outbound call parameter item is used as the parameter value of each parameter item to obtain the outbound call parameter.

[0081] In some embodiments of the present disclosure, outbound call rules are pre-set according to the real-time requirements of the evaluation, and can be pre-defined or extended. It is only necessary to implement the rule interface, use the rule interface to define various outbound call rules and register them in the outbound call rule storage file for subsequent rule configuration.

[0082] In some embodiments of the present disclosure, there may be one or more outbound call rules. When there are multiple outbound call rules, each outbound call rule has an associated relationship. For example, there are three outbound call rules, namely: "expected dialing time is less than the current system time", "VIP level is equal to" and "evaluation time is greater than 10:00", and the association relationship between "expected dialing time is less than the current system time" and "VIP level is equal to" is or, and the association relationship between "expected dialing time is less than the current system time" and "evaluation time is greater than 10:00" is and. By setting the outbound call rules in the above example, it is determined whether the outbound call number meets the outbound call evaluation conditions, so as to screen out the outbound call numbers that need to be arranged for outbound dialing in priority in the outbound call list, such as outbound calls of users who are more valued, such as outbound calls that are close to the expected dialing time but have not been dialed, so as to determine the second evaluation result for them and superimpose it on the first evaluation result, so as to obtain an evaluation result with a higher overall evaluation score, so that the screened outbound call numbers are given priority for outbound dialing when the outbound call list is subsequently scheduled, so as to improve the objectivity and accuracy of the evaluation results, meet business needs and / or user expectations, and improve the real-time and timeliness of outbound calls of the intelligent outbound call system.

[0083] Accordingly, the outbound call parameters may include an expected dialing time parameter, a system time parameter, a VIP level parameter, and an evaluation time parameter. The VIP level parameter may be determined based on the user attribute information in the second attribute information. If the field of the user attribute information contains VIP, the value of the VIP level parameter is yes, which can be identified by 1, otherwise the value of the VIP level parameter is set to no, which can be identified by 0. The parameter values ​​of the evaluation time parameter and the system time parameter may be determined based on the outbound call number evaluation time information in the second attribute information. The parameter value of the expected dialing time parameter may be determined based on the outbound call number expected dialing information in the second attribute information.

[0084] In an exemplary embodiment of the present disclosure, a second evaluation is performed on the outbound call number to obtain a second evaluation result, including the following steps:

[0085] Determine a first score calculation rule according to the outbound call parameters;

[0086] A second evaluation result is obtained based on the first scoring calculation rule and the outbound call parameters.

[0087] In an exemplary embodiment of the present disclosure, the first scoring calculation rule corresponding to the outbound call parameter is determined according to the outbound call parameter. It should be noted that the first scoring calculation rule is pre-set, which represents how to calculate the corresponding evaluation score when the value of the outbound call parameter is in a certain range. For example, when the outbound call parameter includes a VIP level parameter, the first scoring calculation rule includes: different levels of the VIP level parameter will obtain different ranges of digital intervals after processing using string features, and a number is randomly selected in the corresponding digital interval as the evaluation score corresponding to the VIP level parameter, which is the second evaluation result. For example, the VIP level corresponding to an outbound call number is VIP 5, and the digital interval obtained after processing using string features is [40, 60]. A number 59 is randomly selected from it, which is the second evaluation result of the evaluation calculation of the outbound call number.

[0088] In an exemplary embodiment of the present disclosure, another implementation process of performing a second evaluation on an outbound call number to obtain a second evaluation result includes the following steps:

[0089] Determine the time taken to match outbound call parameters with outbound call rules;

[0090] Determine the second scoring calculation rule according to the duration;

[0091] A second evaluation result is obtained based on the second scoring calculation rule and the duration calculation.

[0092] In an exemplary embodiment of the present disclosure, the second evaluation result can also be determined based on the matching situation between the outbound call parameters and the outbound call rules, that is, the second evaluation result can be determined based on the time taken for the outbound call parameters to match the outbound call rules. When determining the match between the outbound call parameters and the outbound call rules, the matching situation between the outbound call parameters and the outbound call rules can be obtained, for example, it can be the time taken for the match. It should be noted that when judging whether the outbound call parameters meet the outbound call rules, it may be an or relationship, that is, the first rule may not be met, but the second rule may be met; or the first rule may be met, and the judgment process ends. This also leads to different time lengths for determining the match between the outbound call parameters and the outbound call rules, some are short, and some are long. This time period is the time taken for the match.

[0093] During specific implementation, the second scoring calculation rule is pre-set, which represents the correlation between the value of the time used for matching and how the corresponding evaluation score is calculated. For example, the second scoring calculation rule stipulates that the time used for matching is calculated by normalization using a linear function to obtain an evaluation score, that is, the second evaluation result. For example, the time used for matching is 0.3 seconds, and the calculated second evaluation result is A; the time used for matching is 0.8 seconds, and the calculated second evaluation result is B. Accordingly, in this embodiment, the outbound call rules with better urgency and higher importance can be programmed at a more forward position in the judgment logic. Once these outbound call rules are met, the judgment logic can be directly jumped out to determine whether the outbound call parameters match the pre-set outbound call rules, thereby reducing the time used for matching, and a higher second evaluation result can be obtained, so that the evaluation result of the outbound call number is more accurate and more objective.

[0094] In specific implementation, after issuing the computing task, the computing center will generate a managed task for monitoring whether the triggered outbound call parameters match the outbound call rules and push it to the managed task center. The managed task center will centrally manage all managed tasks and assign a daemon thread to each managed task to execute the managed task. Once the managed task is triggered, a second evaluation computing task is generated and sent to the computing center for allocation and calculation to obtain a second evaluation result, which will be updated to the storage file or storage database of the overall evaluation result.

[0095] In some embodiments of the present disclosure, the evaluation result of the outbound number is determined based on the first evaluation result and the second evaluation result. The implementation process of determining the evaluation result of the outbound number based on the first evaluation result and the second evaluation result includes the following steps:

[0096] Determine the superposition rules;

[0097] Based on the superposition rule, the first evaluation result and the second evaluation result are superimposed to obtain an evaluation result of the outbound number.

[0098] In some exemplary embodiments of the present disclosure, the first evaluation result and the second evaluation result can be superimposed to obtain the evaluation result of the outbound call number. There are many ways of superposition, that is, there are many superposition rules, which can be selected according to actual needs. For example, the score of the second evaluation result can be added to the score of the first evaluation result in the same system, such as decimal system; the score of the second evaluation result can also be multiplied by a preset weight coefficient and then added to the score of the first evaluation result multiplied by the value of the preset weight coefficient, and the weight coefficient can be adjusted to further improve the timeliness, objectivity and accuracy of the overall evaluation result. For example, in binary, the score of the second evaluation result and the score of the first evaluation result are arranged together and converted into a decimal value to obtain the overall evaluation result. It can be understood that in order to ensure the timeliness of the evaluation result, the binary value of the score of the second evaluation result can be arranged before the binary value of the score of the first evaluation result; it can also be randomly arranged or arranged in other ways. The binary value is arranged, and the embodiment of the present disclosure is not limited here.

[0099] In some embodiments of the present disclosure, it is understandable that, for an outbound call number, the outbound call parameters do not match the outbound call rules, and only the first evaluation result is obtained, and the first evaluation result is used as the evaluation result of the outbound call number.

[0100] It can be seen from the above process that the number evaluation method provided in the embodiment of the present disclosure, on the basis of obtaining the first evaluation result by evaluating the outbound number based on the first attribute information of the outbound number, determines the outbound call parameters corresponding to the outbound number according to the second attribute information of the outbound number, and when the outbound call parameters match the outbound call rules, performs a second evaluation on the outbound number to obtain the second evaluation result, and determines the evaluation result of the outbound number according to the first evaluation result and the second evaluation result. Compared with the fixed evaluation method in the prior art, by adopting two rounds of evaluation combining two different evaluation methods of the first evaluation and the second evaluation, the evaluation method is more flexible, the evaluation result is more objective, and the accuracy of the outbound number evaluation is improved, thereby improving the outbound call success rate of intelligent outbound calls. At the same time, it can also make the intelligent outbound call more compatible with the user status and improve the user experience. On the other hand, even if the evaluation requirements change, the second evaluation result can be adjusted by setting the outbound call rules, so that the evaluation result is suitable for the change without reprogramming the evaluation process.

[0101] It can be understood by those skilled in the art that the number evaluation method provided by the embodiment of the present disclosure can be applied to any scenario where a list needs to be evaluated, especially a scenario where a real-time evaluation is required, and the method can also be applied to products in these scenarios, such as a user list evaluation system, a customer value list evaluation system, a trademark list evaluation system, etc. For example, trademarks with different values ​​can be evaluated, and a second evaluation that reflects real-time performance can be superimposed on the first evaluation. For example, the evaluation rules such as whether the trademark exemption has expired can be configured during the second evaluation. If the trademark exemption has expired, the second evaluation result can be set to a negative score or a negative feedback evaluation result.

[0102] In order to better explain the number evaluation method provided by the embodiment of the present disclosure, a specific example is now provided for detailed description. The specific example is a scoring system constructed by applying the number evaluation method provided by the embodiment of the present disclosure. The evaluation result of the system is reflected in the form of evaluation scores. The system architecture is as follows: Figure 4 As shown, it includes: a scoring rule configuration module and a scoring module. The scoring rule configuration module manages the configuration of various scoring rules in two scoring rounds, specifically including scoring round configuration, scoring model configuration and basic rule configuration; the scoring module is used to build a scoring model, distribute scoring tasks and calculate scoring scores.

[0103] Specifically, the configuration of the scoring round is shown in Table 1.

[0104] Table 1

[0105]

[0106]

[0107] The scoring model configuration includes the scoring dimension configuration and the scoring model configuration for each dimension. Specifically, 7 scoring dimensions are pre-configured and the scoring model configuration table corresponding to each scoring dimension is shown in Table 2.

[0108] Table 2

[0109] Rating Dimensions Dimension attribute data source Scoring model calculation principles Identity User Information Platform String feature processing Outbound Call Strategy Upstream business system push String feature processing Behavioral Preferences Data Platform Linear function normalization User Tags User tag computing platform Zero mean normalization Large model Large model computing platform Linear function normalization Risk Level Data Platform Zero mean normalization List Level Upstream business system push String feature processing

[0110] The scoring model calculation principle refers to the calculation principle used to calculate the score when constructing the scoring model.

[0111] Specifically, linear function normalization is also called maximum-minimum normalization. The principle is to map the data to the range of [0, 1]. By subtracting the difference between the original data and the minimum value in the data set where the original data is located and dividing it by the difference between the maximum and minimum values ​​in the data set where the original data is located, the normalized value of the original data can be obtained, which is in the range of [0, 1]. Zero mean normalization is to map the data to a distribution with a mean of 0 and a standard deviation of 1, that is, if a certain situation is hit, 1 is obtained, otherwise 0 is obtained. String feature processing is to discretize the string, that is, to map the string to discrete intervals. For example, the list level can be divided into three levels: low, medium and high, then it can be mapped to three intervals such as [0, 30], [30, 60] and [60, 100] respectively.

[0112] The basic rule configuration may include the second round of outbound call rule configuration. There may be multiple outbound call rules. When there are multiple outbound call rules, there is an association relationship between the rules, and different rule groups can be divided according to the association relationship. As shown in Table 3, it is a specific configuration of the outbound call rules.

[0113] Table 3

[0114] Outbound call rules Group Outbound call parameters relation Expected call time A set of rules Upstream business system push and Evaluation Moment Rule Group 2 Number evaluation time and VIP Level A set of rules Upstream business system push or

[0115] The above table only lists three rules for illustration. Those skilled in the art can understand that the outbound call rule can be customized and extended. It only needs to implement the rule interface to complete the interface definition and then register it in the outbound call rule repository.

[0116] The logical division of the outbound call rules shown in Table 3 is as follows Figure 5 As shown, it can be seen that there are two judgment conditions in rule group 1: the expected dialing time is less than the current system time and the VIP level is equal to yes. If any of the judgment conditions is met, rule group 1 will be successfully hit. Rule group 2 has only one judgment condition: the evaluation time is greater than 10:00. If this judgment condition is met, rule group 2 will be successfully hit. It should be noted that when determining whether to trigger the second round of scoring, the order of the defined rule groups is judged in sequence. As long as one rule group is hit, the judgment will stop and it will be deemed to have triggered the second round of scoring.

[0117] The specific architecture and workflow of the scoring module are as follows: Figure 6 and Figure 7As shown in the figure, it consists of a computing task center, a computing center, and a hosting center. When an outbound call list is pushed by the upstream business system, the computing task center will receive the outbound call list and generate a computing task after processing and publish it to the computing center; after receiving the computing task, the computing center will calculate the first round of scoring scores and generate a hosting task and send it to the hosting center at the same time; the hosting center will host the current hosting task. Once the hosting task is triggered by conditions, that is, the second round of scoring is triggered, the computing task for the second round of scoring will be regenerated and sent to the computing center for recalculation of the second round of scores.

[0118] Specifically, after receiving the outbound call list pushed by the upstream business system, the computing task center receives an evaluation instruction and selects 5 scoring dimensions from the 7 scoring dimensions shown in Table 2 pre-configured by the scoring rule configuration module, such as identity feature dimension, outbound call strategy dimension, behavior preference dimension, large model dimension and risk level dimension. The evaluation instruction can be pushed by the upstream business system or submitted by the operator. Then obtain the scoring model configuration table corresponding to the five-dimensional scoring dimension from the scoring rule configuration module, and then build a scoring model for each scoring dimension according to its configuration table, and put it into the context of the current list. Obtain the configuration table of the outbound call rule from the scoring rule configuration module, package the outbound call list, the constructed scoring model, the first attribute information, the configuration table of the outbound call rule and the second attribute information together to generate a computing task and send it to the computing center.

[0119] The computing center listens to the computing task center, receives the computing tasks sent by the computing task center, and distributes the computing tasks to the score calculation program. After receiving the assigned computing tasks, the score calculation program starts to execute the score calculation steps:

[0120] Parse the scoring models included in the calculation task and the attribute data corresponding to each scoring model;

[0121] According to the constructed scoring model, the first round of scoring calculations are performed using attribute data;

[0122] Perform a second round of scoring calculation using the configuration table of the outbound call rules and the relevant second attribute information;

[0123] Integrate the calculation results of the first round of scoring and the calculation results of the second round of scoring to calculate a comprehensive score;

[0124] Generate a hosting task using the configuration table of the outbound call rule and send the hosting task to the hosting center.

[0125] When calculating the first round of scores, the specific calculation process is as follows:

[0126] Calculation of identity feature dimension: The required user-related data is obtained from the user information platform through the user ID corresponding to the outbound call number, and the returned user-related data is processed through string features to calculate a unique score. The specific calculation process is shown in Table 4.

[0127] Table 4

[0128] category User-related data String feature processing calculation Register with real name Already registered implementation Zero mean normalization calculates the value 1 Student Information Already perfected Zero mean normalization calculates the value 1 Emergency Contacts Not filled in Zero mean normalization calculates the value 0

[0129] From Table 4, we can see that the score calculated for the identity feature dimension is 110 (binary).

[0130] Outbound call strategy dimension calculation: According to the priority of the pre-configured outbound call strategy transmitted by the upstream business system, its score is calculated by string feature processing and then converted into binary. The calculation process is shown in Table 5.

[0131] Table 5

[0132] Policy Priority String feature map Calculation principles advanced 4 miss Intermediate to Advanced 3 miss intermediate 2 miss Low-intermediate 1 Hit Low Level 0 miss

[0133] From Table 5, it can be seen that the hits are of medium and low level, and the score calculated from the outbound call strategy dimension is 001 (binary).

[0134] Calculation of behavior preference dimension: query the user's behavior preference information in a recent period from the relevant data platform through the user ID corresponding to the outbound call number, and calculate a unique score for the returned user's behavior preference information through string feature processing. The specific calculation process is shown in Table 6.

[0135] Table 6

[0136]

[0137]

[0138] From Table 6, it can be seen that the score calculated for the behavioral preference dimension is 11 (binary).

[0139] Big model dimension calculation: Get the big model score from the big model platform through the user ID corresponding to the outbound call number, use linear function normalization to calculate it as a score of 0-1, and convert it into binary to get the big model dimension score of 10011100.

[0140] Risk level dimension calculation: Use the user ID corresponding to the outbound call number to query the relevant data platform to see whether the user has made any complaints in the recent period of time. If so, what complaint channels were used and other related information. Calculate a unique score for this related information through string feature processing. The specific calculation process is shown in Table 7.

[0141] Table 7

[0142] Risk Level Related information Calculation principles Online customer service complaints miss Zero mean normalization calculates the value 0 Manual customer service complaints miss Zero mean normalization calculates the value 0 Complaints to the CBRC miss Zero mean normalization calculates the value 0

[0143] From Table 7, it can be seen that the score calculated for the risk level dimension is 000 (binary).

[0144] When calculating the second round of scores, the specific calculation process is as follows:

[0145] According to the sequence number of the rule groups configured in Table 3, the rule groups are sorted and judged in sequence whether they are hit or not according to the sorting. As long as one rule group is hit, the judgment procedure is jumped out and the subsequent rule groups are no longer judged. In this specific example, for an outbound call number, the rule group 1 is not hit but the rule group 2 is hit, and the time length used to get the hit is 0.25 seconds. The linear function is used to normalize and calculate this time length to get a score greater than 0 and less than 1, which is also converted into binary 11100110.

[0146] The calculation results of the first round of scoring and the calculation results of the second round of scoring are integrated to calculate the comprehensive score: In order to make the converted decimal score meet the range requirements, the dimension scores of all 0 in the binary score can be filtered, and the 0 before the first 1 in the dimension score can be filtered. For example, 001 is 1 after filtering. The dimension score obtained by linear function normalization is converted to decimal as a decimal, multiplied by 100 and rounded up and then converted to binary. Based on the above processing principles, the dimension scores in this specific example are processed as follows: identity feature dimension score 110, outbound call strategy dimension score 1, behavior preference dimension score 11, and large model sub-dimension score: 10011100 is converted to 156, and it is set to 0.156 as a decimal, multiplied by 100 and rounded to 16, converted to binary as 10000, that is, the large model sub-dimension score is 10000, and the risk level dimension score has been completely filtered.

[0147] The above four binary scores are arranged according to the preset weight order to obtain a new binary value. In this specific example, the binary value 11101110000 is obtained by arranging the outbound call strategy dimension score, identity feature dimension score, behavior preference dimension score, risk level dimension score and large model dimension score in order, which is converted to decimal: 1566.

[0148] Convert the second round scoring result 11100110 to decimal 230, add the two decimal values ​​according to the proportional weight, and according to the weight ratio of 0.6 and 0.4, we get: 1566×0.6+230×0.4=898. This means the comprehensive score is 898.

[0149] After receiving the managed task pushed by the computing center, the managed center will manage the current managed task. Once the managed task is triggered by conditions, that is, the second round of scoring is triggered, the calculation task for the second round of scoring will be regenerated and sent to the computing center for recalculation of the second round of scores to update the comprehensive score. The managed center will continue to wait for the next managed task pushed by the computing center.

[0150] As can be seen from this specific example, this specific example selects some of the pre-set multiple scoring dimensions to construct a multi-dimensional scoring model, which realizes the flexibility, diversity, customizability and modifiability of the scoring model; at the same time, the constructed scoring model is multi-dimensional, which ensures the objectivity and accuracy of the scoring model; by configuring two rounds of scoring, the second round of scoring is conducted on the basis of multi-dimensional scoring combined with real-time outbound call rules, and the second round of scoring is continuously updated over time to ensure the real-time responsiveness of the comprehensive scoring, and to be able to respond to changes in indicators in a timely manner, and improve the objectivity, timeliness and accuracy of the comprehensive scoring. In this way, the purpose of timely responding to relevant business needs is achieved, thereby reducing operation and maintenance costs, enhancing the robustness of core links, and improving resource utilization.

[0151] It should be noted that the acquisition, storage, use, and processing of data or information in the technical solution disclosed in this disclosure are in compliance with the relevant provisions of national laws and regulations, and various types of data such as personal identity data, operation data, behavioral data, etc. related to individuals, customers, and groups obtained in the embodiments of this disclosure have been authorized.

[0152] Based on the same inventive concept, the present disclosure also provides a number evaluation device, as described in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0153] Figure 8 A schematic diagram of a number evaluation device in an embodiment of the present disclosure is shown. Figure 8 As shown, the device comprises:

[0154] An evaluation module 801 is used to perform a first evaluation on the outbound call number based on the first attribute information of the outbound call number to obtain a first evaluation result;

[0155] The evaluation module 801 is further used to determine the outbound call parameters corresponding to the outbound call number according to the second attribute information of the outbound call number; when the outbound call parameters match the outbound call rule, perform a second evaluation on the outbound call number to obtain a second evaluation result;

[0156] The determination module 802 is used to determine the evaluation result of the outbound call number according to the first evaluation result and the second evaluation result.

[0157] It should be noted that the examples and application scenarios implemented by the modules in the above-mentioned device embodiment are the same as those of the corresponding steps S302 to S308 in the method embodiment, but are not limited to the contents disclosed in the above-mentioned method embodiment. It should be noted that the above-mentioned modules as part of the device can be executed in a computer system such as a set of computer executable instructions.

[0158] In some embodiments of the present disclosure, the evaluation module 801 is specifically configured to:

[0159] Determine multiple evaluation models corresponding to the first attribute information, and attribute data corresponding to each evaluation model; one evaluation model corresponds to one dimension;

[0160] For each dimension, an evaluation model is used to evaluate the attribute data to obtain the evaluation result corresponding to the dimension;

[0161] The first evaluation result is calculated based on the evaluation result of each dimension.

[0162] In some embodiments of the present disclosure, the evaluation module 801 is specifically configured to:

[0163] According to the preset dimension sorting rules, the evaluation results corresponding to each dimension are arranged to obtain a first value;

[0164] Converting the first value to obtain a second value; wherein the second value has a different cardinality from the first value;

[0165] The second numerical value is determined as the first evaluation result.

[0166] In some embodiments of the present disclosure, the evaluation module 801 is specifically configured to:

[0167] Determine the preset outbound call parameter items;

[0168] The information matching the outbound call parameter item is determined in the second attribute information of the outbound call number, and the matching information is determined as the outbound call parameter corresponding to the outbound call number.

[0169] In some embodiments of the present disclosure, the evaluation module 801 is specifically configured to:

[0170] Determine a first score calculation rule according to the outbound call parameters;

[0171] A second evaluation result is obtained based on the first scoring calculation rule and the outbound call parameters.

[0172] In some embodiments of the present disclosure, the evaluation module 801 is specifically configured to:

[0173] Determine the time taken to match outbound call parameters with outbound call rules;

[0174] Determine the second scoring calculation rule according to the duration;

[0175] A second evaluation result is obtained based on the second scoring calculation rule and the duration calculation.

[0176] In some embodiments of the present disclosure, the determination module 802 is specifically configured to:

[0177] Determine the superposition rules;

[0178] Based on the superposition rule, the first evaluation result and the second evaluation result are superimposed to obtain an evaluation result of the outbound number.

[0179] Those skilled in the art will appreciate that various aspects of the present disclosure may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation that combines hardware and software aspects, which may be collectively referred to herein as a "circuit," "module," or "system."

[0180] Based on the same inventive concept, an electronic device is also provided in an embodiment of the present disclosure, the electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above number evaluation methods by executing the executable instructions. Since the principle of solving the problem in the electronic device embodiment is similar to that in the above method embodiment, the implementation of the electronic device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0181] Refer to the following Fig. 9 The electronic device 900 according to this embodiment of the present disclosure is described. Fig. 9 The electronic device 900 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0182] like Fig. 9 As shown, the electronic device 900 is in the form of a general computing device. The components of the electronic device 900 may include but are not limited to: at least one processing unit 910, at least one storage unit 920, and a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910).

[0183] The storage unit stores a program code, which can be executed by the processing unit 910, so that the processing unit 910 performs the steps of various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 910 can perform the following steps of the above method embodiment:

[0184] Performing a first evaluation on the outbound call number based on the first attribute information of the outbound call number to obtain a first evaluation result;

[0185] Determine an outbound call parameter corresponding to the outbound call number according to the second attribute information of the outbound call number;

[0186] When the outbound call parameters match the outbound call rules, a second evaluation is performed on the outbound call number to obtain a second evaluation result;

[0187] An evaluation result of the outbound call number is determined based on the first evaluation result and the second evaluation result.

[0188] The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 9201 and / or a cache storage unit 9202 , and may further include a read-only storage unit (ROM) 9203 .

[0189] The storage unit 920 may also include a program / utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0190] Bus 930 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0191] It should be understood that although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0192] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0193] Based on the same inventive concept, the embodiment of the present disclosure also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any of the above number evaluation methods is implemented. Since the principle of solving the problem in the embodiment of the computer-readable storage medium is similar to that in the above method embodiment, the implementation of the embodiment of the computer-readable storage medium can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0194] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, 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), 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.

[0195] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0196] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0197] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0198] Based on the same inventive concept, a computer program product is also provided in an embodiment of the present disclosure, including a computer program product, including: a computer program or an instruction, wherein when the computer program or the instruction is executed by a processor, the number evaluation method of any one of the above method embodiments is implemented. Since the principle of solving the problem in the computer program product embodiment is similar to that in the above method embodiment, the implementation of the computer program product embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0199] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0200] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0201] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0202] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A number evaluation method, characterized in that: include: Performing a first evaluation on the outbound call number based on the first attribute information of the outbound call number to obtain a first evaluation result; Determine an outbound call parameter corresponding to the outbound call number according to the second attribute information of the outbound call number; When the outbound call parameter matches the outbound call rule, performing a second evaluation on the outbound call number to obtain a second evaluation result; An evaluation result of the outbound number is determined according to the first evaluation result and the second evaluation result.

2. The number evaluation method according to claim 1, characterized in that: The performing a first evaluation on the outbound call number based on the first attribute information of the outbound call number to obtain a first evaluation result includes: Determine multiple evaluation models corresponding to the first attribute information, and attribute data corresponding to each evaluation model; one evaluation model corresponds to one dimension; For each dimension, an evaluation is performed based on the attribute data using the evaluation model to obtain an evaluation result corresponding to the dimension; The first evaluation result is calculated based on the evaluation result of each dimension.

3. The number evaluation method according to claim 2, characterized in that: The first evaluation result is calculated based on the evaluation result of each dimension, including: According to the preset dimension sorting rules, the evaluation results corresponding to each dimension are arranged to obtain a first value; Converting the first value to obtain a second value; wherein the second value has a different cardinality from the first value; The second value is determined as the first evaluation result.

4. The number evaluation method according to claim 1, characterized in that: The performing a second evaluation on the outbound call number to obtain a second evaluation result includes: Determine a first score calculation rule according to the outbound call parameter; A second evaluation result is obtained based on the first scoring calculation rule and the outbound call parameter.

5. The number evaluation method according to claim 1, characterized in that: The performing a second evaluation on the outbound call number to obtain a second evaluation result includes: Determining the duration used to match the outbound call parameter with the outbound call rule; Determine a second scoring calculation rule according to the duration; A second evaluation result is obtained based on the second scoring calculation rule and the duration.

6. The method according to claim 1, characterized in that The determining the evaluation result of the outbound number according to the first evaluation result and the second evaluation result includes: Determine the superposition rules; Based on the superposition rule, the first evaluation result and the second evaluation result are superimposed to obtain the evaluation result of the outbound number.

7. The method according to claim 1, characterized in that The determining, according to the second attribute information of the outbound number, an outbound call parameter corresponding to the outbound call number includes: Determine the preset outbound call parameter items; The information matching the outbound call parameter item is determined in the second attribute information of the outbound call number, and the matching information is determined as the outbound call parameter corresponding to the outbound call number.

8. A number evaluation device, characterized in that: include: An evaluation module, configured to perform a first evaluation on the outbound call number based on the first attribute information of the outbound call number to obtain a first evaluation result; The evaluation module is further used to determine the outbound call parameters corresponding to the outbound call number according to the second attribute information of the outbound call number; when the outbound call parameters match the outbound call rule, perform a second evaluation on the outbound call number to obtain a second evaluation result; A determination module is used to determine the evaluation result of the outbound number according to the first evaluation result and the second evaluation result.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the number evaluation method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the number evaluation method according to any one of claims 1 to 7 is implemented.

Images