Intelligent voice outbound control method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an intelligent voice outbound control method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring outbound terminal data; respectively judging the outbound terminal data according to a preset complaint scoring model and / or a preset call rule to obtain a score and a matching result corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model by adopting historical outbound data; and determining an outbound result of the outbound terminal data according to the score and / or the matching result, in the embodiment of the invention, the complaint scoring model and the preset calling rule are preset, the outbound terminal data are judged, and the outbound result with the outbound terminal data, namely whether the outbound terminal is automatically dialed, is determined according to the preset calling rule, so that the outbound terminal data can be automatically dialed. Therefore, the problem of customer complaint can be avoided.

Description

Technical Field

[0001] The present application relates to the field of intelligent outbound call technology, and in particular to a control method, device, electronic device and storage medium for intelligent voice outbound calls. Background Art

[0002] With the rapid development of information technology, intelligent outbound call systems have become one of the key tools in the field of customer relationship management, especially in the fields of customer service, market research and product promotion. Traditional outbound call systems mainly rely on preset scripts and the subjective experience of operators to communicate with customers. This method is incapable of handling complex customer needs and intentions, and often cannot accurately understand the true intentions of customers, resulting in low outbound call efficiency and low customer satisfaction.

[0003] An outbound call system refers to a telecommunications service system that automatically dials users' phones through a computer and plays the recorded voice to the users through a computer. It is an indispensable component of a modern customer service center system based on CTI (Computer Telecommunication Integration) technology. Because outbound call systems are highly automated and intelligent, they are often used in telemarketing business scenarios to achieve business goals and screen potential customers by making phone calls. If you call a user frequently, the user may become dissatisfied and file a complaint. Therefore, how to provide a system that can automatically and intelligently process customer data to avoid customer complaints is an urgent problem that needs to be solved. Summary of the invention

[0004] Some embodiments of the present application aim to provide a method, device, electronic device and storage medium for controlling intelligent voice outbound calls. Through the technical solutions of the embodiments of the present application, outbound terminal data is obtained; the outbound terminal data is judged respectively according to a preset complaint scoring model and / or preset call rules to obtain scores and matching results corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model with historical outbound call data; the outbound call result of the outbound terminal data is determined according to the score and / or the matching result. In the embodiments of the present application, a complaint scoring model and preset call rules are preset to judge the outbound terminal data, and the outbound call result corresponding to the outbound terminal data is determined according to the preset call rules, that is, whether to automatically dial the outbound terminal, thereby avoiding customer complaints.

[0005] In a first aspect, some embodiments of the present application provide a method for controlling an intelligent voice outbound call, including:

[0006] Get outbound terminal data;

[0007] According to a preset complaint scoring model and / or preset call rules, the outbound terminal data is judged respectively to obtain a score and a matching result corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model using historical outbound call data;

[0008] An outbound call result of the outbound call terminal data is determined according to the score and / or the matching result.

[0009] Some embodiments of the present application pre-set complaint scoring models and preset call rules to judge the outbound terminal data, and determine the outbound call result of the outbound terminal data according to the preset call rules, that is, whether to automatically dial the outbound terminal, so as to avoid customer complaints.

[0010] Optionally, the complaint scoring model is obtained in the following manner:

[0011] Acquire historical outbound call data, wherein the historical outbound call data at least includes service type, user behavior data and call time;

[0012] Extracting features from the historical outbound call data to obtain feature vectors corresponding to the historical outbound call data;

[0013] Training the large model according to the feature vector to obtain a score corresponding to the historical outbound call data;

[0014] The score is compared with the preset complaint result, and the complaint scoring model is obtained according to the comparison result.

[0015] Some embodiments of the present application train a large model using historical outbound call data to obtain scores corresponding to the historical outbound call data, which are then compared with preset complaint results. Based on the comparison results, a complaint scoring model is obtained. That is to say, the complaint scoring model is used to score each outbound call data, and determine whether to execute the outbound call service based on the size of the score.

[0016] Optionally, the preset call rule is obtained in the following manner:

[0017] If the score is less than a first preset score, setting the user corresponding to the score to a whitelist;

[0018] If the score is greater than the first preset score and less than the second preset score, the user corresponding to the score is set to the grey list;

[0019] If the score is greater than the second preset score, setting the user corresponding to the score to a blacklist;

[0020] The white list, the black list and the grey list are determined as the preset calling rules.

[0021] Optionally, the preset call rule further includes:

[0022] According to the historical outbound call data, obtain users who have not been ringing, users with empty numbers, and users whose calls have failed;

[0023] If the number of the unringed users is greater than a first preset value, the number of the unused number users is greater than a second preset value, and the number of the call failed users is greater than a third preset value, the unringed users, the unused number users, and the call failed users are determined as the gray list;

[0024] The users whose number triggering the grey list is greater than a fourth preset value are determined as the blacklist.

[0025] Optionally, the blacklist also includes users who have filed complaints and preset marked customers.

[0026] In some embodiments of the present application, a black, white and gray list is obtained by calculating the score through a complaint scoring model and performing statistical analysis on historical outbound call data, and a call strategy is determined based on the black, white and gray list.

[0027] In a second aspect, some embodiments of the present application provide a control device for an intelligent voice outbound call, including:

[0028] The acquisition module is used to obtain the outbound terminal data;

[0029] A judgment module, used to judge the outbound terminal data according to a preset complaint scoring model and / or preset call rules, and obtain a score and a matching result corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model using historical outbound call data;

[0030] A determination module is used to determine the outbound call result of the outbound call terminal data according to the score and / or the matching result.

[0031] Some embodiments of the present application pre-set complaint scoring models and preset call rules to judge the outbound terminal data, and determine the outbound call result of the outbound terminal data according to the preset call rules, that is, whether to automatically dial the outbound terminal, so as to avoid customer complaints.

[0032] Optionally, the device further comprises a training module, wherein the training module is used to:

[0033] Acquire historical outbound call data, wherein the historical outbound call data at least includes service type, user behavior data and call time;

[0034] Extracting features from the historical outbound call data to obtain feature vectors corresponding to the historical outbound call data;

[0035] Training the large model according to the feature vector to obtain a score corresponding to the historical outbound call data;

[0036] The score is compared with the preset complaint result, and the complaint scoring model is obtained according to the comparison result.

[0037] Some embodiments of the present application train a large model using historical outbound call data to obtain scores corresponding to the historical outbound call data, which are then compared with preset complaint results. Based on the comparison results, a complaint scoring model is obtained. That is to say, the complaint scoring model is used to score each outbound call data, and determine whether to execute the outbound call service based on the size of the score.

[0038] Optionally, the training module is used to:

[0039] If the score is less than a first preset score, setting the user corresponding to the score to a whitelist;

[0040] If the score is greater than the first preset score and less than the second preset score, the user corresponding to the score is set to the grey list;

[0041] If the score is greater than the second preset score, setting the user corresponding to the score to a blacklist;

[0042] The white list, the black list and the grey list are determined as the preset calling rules.

[0043] Optionally, the training module is used to:

[0044] According to the historical outbound call data, obtain users who have not been ringing, users with empty numbers, and users whose calls have failed;

[0045] If the number of the unringed users is greater than a first preset value, the number of the unused number users is greater than a second preset value, and the number of the call failed users is greater than a third preset value, the unringed users, the unused number users, and the call failed users are determined as the gray list;

[0046] The users whose number triggering the grey list is greater than a fourth preset value are determined as blacklisted users.

[0047] Optionally, the blacklist also includes users who have filed complaints and preset marked customers.

[0048] In some embodiments of the present application, a black, white and gray list is obtained by calculating the score through a complaint scoring model and performing statistical analysis on historical outbound call data, and a call strategy is determined based on the black, white and gray list.

[0049] In a third aspect, some embodiments of the present application provide an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the control method for intelligent voice outbound calls as described in any embodiment of the first aspect can be implemented.

[0050] In a fourth aspect, some embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the intelligent voice outbound call control method as described in any embodiment of the first aspect.

[0051] In a fifth aspect, some embodiments of the present application provide a computer program product, wherein the computer program product includes a computer program, wherein when the computer program is executed by a processor, it can implement the control method of the intelligent voice outbound call as described in any embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A flowchart of a method for controlling an intelligent voice outbound call provided in an embodiment of the present application;

[0054] Figure 2 A flowchart of another method for controlling an intelligent voice outbound call provided in an embodiment of the present application;

[0055] Figure 3 A schematic diagram of the structure of a control device for intelligent voice outbound calls provided in an embodiment of the present application;

[0056] Figure 4 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0058] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0059] With the rapid development of information technology, intelligent outbound call systems have become one of the key tools in the field of customer relationship management, especially in the fields of customer service, market research and product promotion. Traditional outbound call systems mainly rely on preset scripts and the subjective experience of operators to communicate with customers. This method is incapable of handling complex customer needs and intentions, and often cannot accurately understand the true intentions of customers, resulting in low outbound call efficiency and low customer satisfaction.

[0060] An outbound call system is a telecommunications service system that automatically dials users' phones through a computer and plays the recorded voice to users through a computer. It is an indispensable component of a modern customer service center system based on CTI (Computer Telecommunication Integration) technology. Because the outbound call system is highly automated and intelligent, it is often used in telemarketing business scenarios to achieve business goals and screen potential customers by making phone calls. If calls are made to a certain user frequently, the user may become dissatisfied and file a complaint. Therefore, how to provide a method that can automatically and intelligently process customer data to avoid customer complaints is an urgent problem to be solved. In view of this, some embodiments of the present application provide a method for controlling intelligent voice outbound calls, which includes obtaining outbound terminal data; judging the outbound terminal data according to a preset complaint scoring model and / or preset call rules, and obtaining scores and matching results corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model using historical outbound call data; determining the outbound call result of the outbound terminal data according to the score and / or matching result. In the embodiment of the present application, a complaint scoring model and a preset call rule are preset, and the outbound terminal data are judged. According to the preset call rules, the outbound call result corresponding to the outbound terminal data is determined, that is, whether to automatically dial the outbound terminal, so as to avoid customer complaints.

[0061] like Figure 1 As shown, an embodiment of the present application provides a method for controlling an intelligent voice outbound call, the method comprising:

[0062] S101, obtaining outbound call terminal data;

[0063] Specifically, the terminal device obtains outbound call terminal data, which at least includes a user name, a user telephone number, and a user type.

[0064] S102. According to a preset complaint scoring model and / or preset call rules, the outbound terminal data is judged respectively to obtain scores and matching results corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model using historical outbound call data;

[0065] Specifically, historical outbound call data is obtained on the terminal device, and the historical outbound call data is used to train a large model to obtain a complaint scoring model. The complaint scoring model is used to score different users in the historical outbound call data. Call rules are set according to the scoring results. At the same time, statistical analysis of the historical outbound call data can be performed to enrich the call rules. The outbound terminal data is judged through the call rules to obtain the score and matching result corresponding to the outbound terminal data.

[0066] Exemplarily, the terminal device can use the complaint scoring model to score the outbound terminal data and obtain a score, and use the score to determine whether to make an outbound call. It can also use preset call rules to match the outbound terminal data to obtain a matching result; or, the above two methods can be used to judge the outbound terminal data at the same time.

[0067] S103: Determine the outbound call result of the outbound call terminal data according to the score and / or the matching result.

[0068] The terminal device determines the outbound call strategy of the outbound call terminal data based on the score and / or the matching result, and performs the outbound call operation based on the outbound call strategy. For example, the score is judged, and it is determined whether it belongs to a certain list among black, white and gray based on the score. It can also directly judge based on the matching result to obtain the outbound call strategy, such as a blacklist for banned calls, a gray list for few calls, and a whitelist for normal outbound calls.

[0069] Some embodiments of the present application pre-set complaint scoring models and preset call rules to judge the outbound terminal data, and determine the outbound call result of the outbound terminal data according to the preset call rules, that is, whether to automatically dial the outbound terminal, so as to avoid customer complaints.

[0070] Another embodiment of the present application further supplements the control method of the intelligent voice outbound call provided in the above embodiment.

[0071] Optionally, the complaint scoring model is obtained by:

[0072] Obtaining historical outbound call data, wherein the historical outbound call data at least includes service type, user behavior data and call time;

[0073] Extract features from historical outbound call data to obtain feature vectors corresponding to the historical outbound call data;

[0074] The large model is trained based on the feature vector to obtain the scores corresponding to the historical outbound call data;

[0075] The scores are compared with the preset complaint results, and a complaint scoring model is obtained based on the comparison results.

[0076] During the outbound call process, relevant voice, text, page jump, activation code input, contract cancellation, insurance refund and other operation data will be recorded in real time. Based on the behavior data and complaint results, a corresponding large model will be used to identify user intentions and generate key tags.

[0077] Some embodiments of the present application train a large model using historical outbound call data to obtain scores corresponding to the historical outbound call data, which are then compared with preset complaint results. Based on the comparison results, a complaint scoring model is obtained. That is to say, the complaint scoring model is used to score each outbound call data, and determine whether to execute the outbound call service based on the size of the score.

[0078] Optionally, the preset call rule is obtained in the following manner:

[0079] If the score is less than the first preset score, the user corresponding to the score is set to the whitelist;

[0080] If the score is greater than the first preset score and less than the second preset score, the user corresponding to the score is set to the gray list;

[0081] If the score is greater than a second preset score, the user corresponding to the score is set to a blacklist;

[0082] Define the whitelist, blacklist and greylist as preset call rules.

[0083] Optionally, the preset call rule also includes:

[0084] Based on historical outbound call data, obtain users who have not received a ring, users with empty numbers, and users whose calls have failed;

[0085] If the number of users who have not been ringing is greater than a first preset value, the number of users with empty numbers is greater than a second preset value, and the number of users with failed calls is greater than a third preset value, the users who have not been ringing, the users with empty numbers, and the users with failed calls are determined as gray lists;

[0086] The users whose number triggering the grey list is greater than a fourth preset value are determined as the blacklist.

[0087] Optionally, the blacklist also includes users who have made complaints and preset marked customers.

[0088] In some embodiments of the present application, a black, white and gray list is obtained by calculating the score through a complaint scoring model and performing statistical analysis on historical outbound call data, and a call strategy is determined based on the black, white and gray list.

[0089] Based on the complaint results provided by insurance companies and line operators, as well as the relevant behavior records and attributes of the relevant complaining users, we conduct analysis and statistics to obtain the corresponding rules and related models with high complaint intentions. We train the model based on the user's voice, text, page jump, activation code input, order submission and other operations plus time series, and then define the complaint intention threshold based on the intention score produced by the model and the score distribution of the corresponding complaint user results.

[0090] During outbound calls, the model will judge the user's situation based on the user's tone, environment, and actual feedback information. If there is an intention or tendency to complain, communication will be suspended in time to avoid complaints and continued harassment of the user;

[0091] After the outbound call is completed, the user will be analyzed offline according to the rules with higher complaint intention. If the relevant rules are triggered, the user status will be changed to a black-white-gray related status, a blacklist for banned calls, a gray list for few calls, and a whitelist for normal outbound calls. In order to provide users with better services, there will be a new set of rules for converting blacklist to gray or white.

[0092] Under the operation mode of selling insurance products by phone, there will be related complaints such as complaints against insurance companies and complaints about lines. In order to effectively reduce complaints and avoid unnecessary harassment to users, the external platform defines the blacklist, graylist and whitelist user classification:

[0093] For example: Whitelist: users who have not triggered blacklist or greylist rules;

[0094] Gray list: users whose line providers have replied that their numbers are no longer available for 6 consecutive times, users whose numbers have not been ringing for 6 consecutive times, users whose outbound calls have failed for 6 consecutive times, and users whose complaint intentions in the large model are scored 0.4 to 0.6 points

[0095] Blacklist: users who have made complaints, have empty numbers, or are in preset departments, and users whose large model complaint intention scores are above 0.6 points are on the blacklist;

[0096] like Figure 2 As shown, an embodiment of the present application provides a method for controlling an intelligent voice outbound call, comprising:

[0097] Step 1: The terminal platform stores outbound call records, sales records and user behavior data in the data warehouse, receives voice text from the ASR service terminal and stores it in the data warehouse, and receives activation codes, order submissions, payments and upgrades sent by the Party A platform;

[0098] Step 2: Process the historical outbound call data in the data warehouse;

[0099] Step 3: Count the percentage of user complaints using business rule attributes and set black, white and gray business definition rules:

[0100] Whitelist: users who have not triggered blacklist and greylist rules;

[0101] Grey list: 6 consecutive missed calls, 6 consecutive unavailable numbers, 6 consecutive call failures;

[0102] Blacklist: Users who have triggered the grey list four times in a row; clear complaint intention; preset department number;

[0103] Step 4: Samples are extracted based on user behavior data and historical complaint results to train a scoring model, which scores users;

[0104] Data is stratified based on actual user scores; users with scores above 0.6 are on the grey list; users with scores below 0.6 are normal users who can make calls; users whose scores are below 0.6 for four consecutive times are put on the black list.

[0105] Under the operation mode of selling insurance products by phone, there will be related complaints such as complaints to insurance companies and complaints to lines. In order to effectively reduce complaints and avoid unnecessary harassment to users, the external platform defines the blacklist-graylist-whitelist user classification. During the outbound call process, relevant voice, text, and related behavior data will be recorded in real time, and there will be a corresponding large model to identify user intentions and output key tags. According to the complaint results provided by insurance companies and line providers, as well as the relevant behavior records and attributes of the relevant complaining users, analysis and statistics are conducted to obtain the corresponding rules and related models with higher complaint intentions. During the outbound call process, the model will judge the user situation based on the user's tone, environment, and actual feedback information. If there is an intention and tendency to complain, communication will be suspended in time to avoid complaints and continued harassment of users. After the outbound call is over, the user will be analyzed offline according to the rules with higher complaint intentions. If the relevant rules are triggered, the user status will be changed to black-white-gray related status, blacklist for banned calls, gray list for few calls, and white list for normal outbound calls. In order to provide users with better services, there will be a new set of blacklist to gray or white rules.

[0106] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0107] Another embodiment of the present application provides a control device for intelligent voice outbound calls, which is used to execute the control method for intelligent voice outbound calls provided in the above embodiments.

[0108] like Figure 3, which is a schematic diagram of the structure of the intelligent voice outbound call control device provided in an embodiment of the present application. The intelligent voice outbound call control device includes:

[0109] The acquisition module 301 is used to acquire outbound call terminal data;

[0110] The judgment module 302 is used to judge the outbound terminal data according to the preset complaint scoring model and / or preset call rules, and obtain the score and matching result corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model using historical outbound call data;

[0111] The determination module 303 is used to determine the outbound call result of the outbound call terminal data according to the score and / or the matching result.

[0112] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0113] Some embodiments of the present application pre-set complaint scoring models and preset call rules to judge the outbound terminal data, and determine the outbound call result of the outbound terminal data according to the preset call rules, that is, whether to automatically dial the outbound terminal, so as to avoid customer complaints.

[0114] Another embodiment of the present application further supplements the intelligent voice outbound call control device provided in the above embodiment.

[0115] Optionally, the device further comprises a training module, the training module being used for:

[0116] Obtaining historical outbound call data, wherein the historical outbound call data at least includes service type, user behavior data and call time;

[0117] Extract features from historical outbound call data to obtain feature vectors corresponding to the historical outbound call data;

[0118] The large model is trained based on the feature vector to obtain the scores corresponding to the historical outbound call data;

[0119] The scores are compared with the preset complaint results, and a complaint scoring model is obtained based on the comparison results.

[0120] Some embodiments of the present application train a large model using historical outbound call data to obtain scores corresponding to the historical outbound call data, which are then compared with preset complaint results. Based on the comparison results, a complaint scoring model is obtained. That is to say, the complaint scoring model is used to score each outbound call data, and determine whether to execute the outbound call service based on the size of the score.

[0121] Optionally, the training module is used to:

[0122] If the score is less than the first preset score, the user corresponding to the score is set to the whitelist;

[0123] If the score is greater than the first preset score and less than the second preset score, the user corresponding to the score is set to the gray list;

[0124] If the score is greater than a second preset score, the user corresponding to the score is set to a blacklist;

[0125] Define the whitelist, blacklist and greylist as preset call rules.

[0126] Optionally, the training module is used to:

[0127] Based on historical outbound call data, obtain users who have not received a ring, users with empty numbers, and users whose calls have failed;

[0128] If the number of users who have not been ringing is greater than a first preset value, the number of users with empty numbers is greater than a second preset value, and the number of users with failed calls is greater than a third preset value, the users who have not been ringing, the users with empty numbers, and the users with failed calls are determined as gray lists;

[0129] The users whose number triggering the grey list is greater than a fourth preset value are determined as the blacklist.

[0130] Optionally, the blacklist also includes users who have made complaints and preset marked customers.

[0131] In some embodiments of the present application, a black, white and gray list is obtained by calculating the score through a complaint scoring model and performing statistical analysis on historical outbound call data, and a call strategy is determined based on the black, white and gray list.

[0132] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0133] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0134] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the operation of the method corresponding to any embodiment of the intelligent voice outbound call control method provided in the above embodiments can be implemented.

[0135] An embodiment of the present application also provides a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the operations corresponding to any embodiment of the intelligent voice outbound call control method provided in the above embodiments.

[0136] like Figure 4 As shown, some embodiments of the present application provide an electronic device 400, which includes: a memory 410, a processor 420, and a computer program stored in the memory 410 and executable on the processor 420, wherein the processor 420 reads the program from the memory 410 through a bus 430 and executes the program to implement a method of any embodiment included in the above-mentioned intelligent voice outbound call control method.

[0137] Processor 420 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 420 can be a microprocessor.

[0138] The memory 410 may be used to store instructions executed by the processor 420 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 420 of the disclosed embodiment may be used to execute instructions in the memory 410 to implement the method shown above. The memory 410 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.

[0139] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0140] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0141] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for controlling an intelligent voice outbound call, characterized in that: The method comprises: Get outbound terminal data; According to a preset complaint scoring model and / or preset call rules, the outbound terminal data is judged respectively to obtain a score and a matching result corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model using historical outbound call data; An outbound call result of the outbound call terminal data is determined according to the score and / or the matching result.

2. The intelligent voice outbound call control method according to claim 1, characterized in that: The complaint scoring model is obtained in the following way: Acquire historical outbound call data, wherein the historical outbound call data at least includes service type, user behavior data and call time; Extracting features from the historical outbound call data to obtain feature vectors corresponding to the historical outbound call data; Training the large model according to the feature vector to obtain a score corresponding to the historical outbound call data; The score is compared with the preset complaint result, and the complaint scoring model is obtained according to the comparison result.

3. The intelligent voice outbound call control method according to claim 2, characterized in that: The preset call rule is obtained in the following manner: If the score is less than a first preset score, setting the user corresponding to the score to a whitelist; If the score is greater than the first preset score and less than the second preset score, the user corresponding to the score is set to the grey list; If the score is greater than the second preset score, setting the user corresponding to the score to a blacklist; The white list, the black list and the grey list are determined as the preset calling rules.

4. The intelligent voice outbound call control method according to claim 3, characterized in that: The preset call rules also include: According to the historical outbound call data, obtain users who have not been ringing, users with empty numbers, and users whose calls have failed; If the number of the unringed users is greater than a first preset value, the number of the unused number users is greater than a second preset value, and the number of the call failed users is greater than a third preset value, the unringed users, the unused number users, and the call failed users are determined as the gray list; The users whose number triggering the grey list is greater than a fourth preset value are determined as blacklisted users.

5. The intelligent voice outbound call control method according to claim 4, characterized in that: The blacklist also includes users who have filed complaints and preset marked customers.

6. A control device for intelligent voice outbound calls, characterized in that: The device comprises: The acquisition module is used to obtain the outbound terminal data; A judgment module, used to judge the outbound terminal data according to a preset complaint scoring model and / or preset call rules, and obtain a score and a matching result corresponding to the outbound terminal data; wherein the preset complaint scoring model is obtained by training a large model using historical outbound call data; A determination module is used to determine the outbound call result of the outbound call terminal data according to the score and / or the matching result.

7. The intelligent voice outbound call control device according to claim 6, characterized in that: The device also includes a training module, which is used to: Acquire historical outbound call data, wherein the historical outbound call data at least includes service type, user behavior data and call time; Extracting features from the historical outbound call data to obtain feature vectors corresponding to the historical outbound call data; Training the large model according to the feature vector to obtain a score corresponding to the historical outbound call data; The score is compared with the preset complaint result, and the complaint scoring model is obtained according to the comparison result.

8. The intelligent voice outbound call control device according to claim 7, characterized in that: The training module is used to: If the score is less than a first preset score, setting the user corresponding to the score to a whitelist; If the score is greater than the first preset score and less than the second preset score, the user corresponding to the score is set to the grey list; If the score is greater than the second preset score, setting the user corresponding to the score to a blacklist; The white list, the black list and the grey list are determined as the preset calling rules.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it can implement the control method for intelligent voice outbound calls as described in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the program, when executed by a processor, can implement the intelligent voice outbound call control method described in any one of claims 1 to 5.

Images