Recall method, recall device, computer equipment and storage medium

Abstract

The embodiment of the present invention provides a recall method, a recall device, a computer device and a computer-readable storage medium, which relate to the field of artificial intelligence. The method includes: when it is detected that the outbound call operation of the outbound call device fails, the user data corresponding to the outbound call operation is obtained, and the user data is extracted to obtain user information; a pre-configured recall rule is obtained, and the outbound call scenario is determined according to the user information; the recall rule is verified and configured according to the outbound call scenario to obtain a target recall rule, and the target recall rule includes a target number of recalls and a target recall interval duration; after the target recall interval duration has passed, the outbound call device is used to perform a recall operation on the user number until the number of recalls reaches the target number of recalls or the recall operation is successful. This can effectively improve the efficiency of the recall and avoid complaints due to frequent recalls, which results in poor customer service experience.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a recall method, a recall device, a computer device, and a computer-readable storage medium. Background Art

[0002] In existing outbound calling scenarios, agents make calls based on an outbound calling list, or use automatic outbound calling equipment to automatically make outbound calls. After the call is connected, the call is transferred to an agent. However, when making outbound calls, there are various situations where the call is not connected, such as the user is not convenient to answer the call or the mobile phone is not with him. If outbound calls are made continuously or again at short intervals, it may result in a poor customer service experience or even the loss of potential customers. Summary of the invention

[0003] The present application provides a recall method, a recall device, a device and a storage medium, aiming to effectively improve the recall efficiency and avoid complaints due to frequent recalls, resulting in poor customer service experience and even loss of potential customers.

[0004] To achieve the above object, the present application provides a re-call method, the method comprising:

[0005] When it is detected that the outbound call operation of the outbound call device fails, user data corresponding to the outbound call operation is acquired, and information is extracted from the user data to obtain user information, wherein the user information includes a user number;

[0006] Obtaining a pre-configured call back rule and determining an outbound call scenario according to the user information;

[0007] Verify and configure the recall rule according to the outbound call scenario to obtain a target recall rule, wherein the target recall rule includes a target recall number and a target recall interval duration;

[0008] After the target recall interval has elapsed, the outbound calling device is used to perform a recall operation on the user number until the number of recalls reaches the target number of recalls or the recall operation is successful.

[0009] To achieve the above object, the present application also provides a recall device, the recall device comprising:

[0010] An information extraction module, for obtaining user data corresponding to the outbound call operation when detecting that the outbound call operation of the outbound call device fails, and extracting information from the user data to obtain user information, wherein the user information includes a user number;

[0011] A rule generation module, used to obtain a pre-configured re-call rule and determine an outbound call scenario according to the user information;

[0012] A rule determination module, used to verify and configure the recall rule according to the outbound call scenario to obtain a target recall rule, wherein the target recall rule includes a target recall number and a target recall interval duration;

[0013] The recall module is used to perform a recall operation on the user number using the outbound calling device after the target recall interval has passed, until the number of recalls reaches the target number of recalls or the recall operation is successful.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a computer device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement any one of the recall methods provided in the embodiments of the present application when executing the computer program.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements any one of the recall methods provided in the embodiments of the present application.

[0016] The recall method, recall device, computer device and computer-readable storage medium disclosed in the embodiment of the present application, when detecting that the outbound call operation of the outbound call device fails, obtains the user data corresponding to the outbound call operation, determines the outbound call scenario and generates the recall rules according to the user data; verifies and configures the recall rules according to the outbound call scenario to obtain the target recall rules; after the target recall interval has passed, the outbound call device is used to perform the recall operation on the user number until the number of recalls reaches the target number of recalls or the recall operation is successful. This can effectively improve the recall efficiency and avoid customer complaints due to frequent recalls and outbound calls at unreasonable times, resulting in poor customer service experience and even loss of potential customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a scenario schematic diagram of a re-call method provided in an embodiment of the present application;

[0019] Figure 2 It is a flowchart of a re-call method provided in an embodiment of the present application;

[0020] Figure 3is a schematic block diagram of a recall device provided in one embodiment of the present application;

[0021] Figure 4 It is a schematic block diagram of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0023] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps can also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions. In addition, although the functional modules are divided in the device schematic, in some cases, the module division can be different from that in the device schematic.

[0024] The term "and / or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] With the rapid development of AI technology, intelligent AI services have quickly emerged in various service industries such as insurance, real estate, automobiles, and education due to their natural advantages of efficiency and convenience. However, when AI services are called outbound, there are various situations where the user is not convenient to answer the call or the phone is not around, so it is necessary to re-call the AI ​​service outbound call after a certain period of time, otherwise it may result in poor customer service experience or even loss of potential customers.

[0026] In order to meet the needs of on-site operations, improve on-site operation efficiency, and improve the intelligence of AI services, this application proposes a recall method, which can effectively improve the recall efficiency and avoid customer complaints due to frequent recalls and outbound calls at unreasonable times, resulting in poor customer service experience and even loss of potential customers. This method can be applied to outbound call scenarios such as 4S stores and insurance businesses, and can also be used in any other outbound call scenarios, such as food delivery, doctor consultations, and legal consultations.

[0027] The above-mentioned recall method can be applied in a server, and of course can also be applied to a terminal device, so as to effectively improve the recall efficiency and avoid customer complaints due to frequent recalls and outbound calls at unreasonable times, resulting in poor customer service experience and even loss of potential customers, etc. The terminal device may include a fixed terminal with a telephone function such as a mobile phone, a tablet computer, a personal digital assistant (PDA), etc. The server can be, for example, a separate server or a server cluster. However, for ease of understanding, the following embodiments will be described in detail with the recall method applied to the server.

[0028] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0029] like Figure 1 As shown, the risk assessment method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. The application environment includes a terminal device 110 and a server 120, wherein the terminal device 110 can communicate with the server 120 through a network. Specifically, when the server 120 detects that the outbound call operation of the outbound call device fails, it obtains the user data corresponding to the outbound call operation, determines the outbound call scenario and generates a recall rule according to the user data; verifies and configures the recall rule according to the outbound call scenario to obtain the target recall rule; after the target recall interval, the outbound call device is used to perform a recall operation on the user number until the number of recalls reaches the target number of recalls or the recall operation is successful, and the corresponding recall result is sent to the terminal device 110. Among them, the server 120 can be an independent server, or it can be 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, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal device 110 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited to this. The terminal and the server may be connected directly or indirectly via wired or wireless communication, which is not limited in this application.

[0030] See also Figure 2 , Figure 2This is a schematic flow chart of a recall method provided in an embodiment of the present application. The recall method can be applied to a server to realize the intelligence of outbound calls, thereby effectively improving the efficiency of recalls and avoiding customer complaints due to frequent recalls and outbound calls at unreasonable times, resulting in poor customer service experience and even loss of potential customers, thereby improving the user experience.

[0031] like Figure 2 As shown, the recall method includes steps S101 to S104.

[0032] S101. When it is detected that an outbound call operation of an outbound call device fails, user data corresponding to the outbound call operation is acquired, and information is extracted from the user data to obtain user information, where the user information includes a user number.

[0033] Among them, the outbound calling device can be a device such as a landline or a mobile phone that can be used to perform outbound calling operations. Generally, if it is detected that the outbound calling object does not answer the call or the outbound calling object hangs up, it can be considered that the outbound calling operation has failed. The user data corresponding to the outbound calling operation is the user data corresponding to the outbound calling object. The user data can be historical service and sales data, which can be obtained from different subsidiaries, different outbound calling scenarios and different channel sources. The user information is information extracted from the user data, and the user information at least includes a user number, and the user number is used to enable the outbound calling device to perform an outbound calling operation to contact the corresponding outbound calling object.

[0034] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0035] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0036] In some embodiments, the user data is classified to obtain service data of each service category; it is determined whether the service category includes a target service category; if the service category includes the target service category, the user information corresponding to the outbound call operation is extracted from the service data corresponding to the target service category. In this way, the user information corresponding to the outbound call operation can be accurately extracted, thereby improving the efficiency of re-calling.

[0037] Among them, the business categories include insurance business, food delivery business or maintenance business, etc. Since users may have businesses of different business categories, the user data can be user information including a large number of different business categories. The target business category is the business category corresponding to this outbound call operation. The user information may include contact information such as user number and address. If the business category is insurance business, such as auto insurance, the user information may also include ID number, license plate information, vehicle initial registration date, vehicle insurance expiration date and information source, etc.; if the business category is maintenance business, such as furniture maintenance, the user information may also include ID number, maintenance order, initial on-site maintenance date, warranty period and information source, etc.

[0038] It should be noted that the contact information can be used to initiate AI service outbound calls using the phone, follow up with subsequent agents, and send payment links after subsequent orders are issued. The vehicle's initial registration date is used to calculate the age of the vehicle and is used when segmenting the list resources. Young vehicles are high-quality resources and can be used to assist in setting re-call rules. The license plate information is used for quotations, which are mainly divided into simple quotations and precise quotations. A simple quotation can be given based on the license plate, and AI will make a preliminary quotation. After the preliminary quotation, the agent will follow up to understand the customer's specific car model and other information and the customer's willingness to provide protection and give a precise quotation. The address is used to send return slips. Some customers require paper policies, and there are also physical gifts such as shopping cards. The vehicle insurance expiration date is used to determine when it can be sold.

[0039] Specifically, the user data can be classified and processed first to obtain the business data corresponding to the insurance business, take-out business or maintenance business respectively; determine whether the business category included in the above user data includes the target business category; if the business category includes the target business category, extract the user information corresponding to the outbound call operation from the business data corresponding to the target business category; if the business category does not include the target business category, the user information corresponding to the outbound call operation cannot be extracted, and the user data corresponding to the outbound call operation needs to be re-acquired.

[0040] Exemplarily, the target business category can be obtained in advance, for example, the target business category is insurance business; the user data is first classified and processed to obtain the business data corresponding to the insurance business, take-out business or repair business; it is determined whether the business category included in the above user data includes insurance business; it can be determined that the business category included in the above user data includes insurance business, and the user information corresponding to the outbound call operation is extracted from the business data corresponding to the insurance business.

[0041] S102: Obtain a pre-configured recall rule, and determine an outbound call scenario according to the user information.

[0042] Among them, the outbound call scenarios may include outbound call scenarios such as auto insurance, property insurance, and life insurance. Specifically, recall rules can be set according to different outbound call scenarios to achieve batch management of lists of the same type for AI service outbound calls. The recall rules are outbound call rules corresponding to the peripheral device, which are used to enable the outbound call device to perform the corresponding recall operation.

[0043] Specifically, the AI ​​service can be used to automatically and intelligently configure and generate corresponding recall rules in advance. The generated recall rules can meet the needs of most outbound call scenarios, but more accurate recall rules need to be reconfigured according to specific outbound call scenarios. The recall rules may include the number of recalls and the length of the recall interval.

[0044] It should be noted that the recall rule generated at this time may be the recall rule with the highest historical usage rate or the recall rule with the highest favorable comment rate, etc. The recall rule may be stored in the server so as to be called at any time.

[0045] Exemplarily, the name of the generated recall rule can be test1012. The number of recalls under this rule is 3 times. If the current number of recalls is the first time, the interval between the next recall and the next time is 108 hours, and the start time is 10:00 in the morning; if the current number of recalls is the second time, the interval between the next recall and the next time is 96 hours, and the start time is 9:00 in the morning; if the current number of recalls is the third time, the interval between the next recall and the next time is 99 / hour, and the start time is 9:00 in the morning. For example, the first outbound call time for the AI ​​service of list A is 2021-10-12 14:00, and the above-mentioned recall rule test1012 is configured. Then the first outbound call is the current recall number 1. According to the configured interval time, the next recall time can be calculated as 2021-10-17 2:00, and so on, until the number of recalls reaches 3 times or the recall is successful.

[0046] In some embodiments, the user information is segmented to obtain the segmentation result corresponding to the user information; the meaning of each segmentation in the segmentation result is predicted based on the meaning prediction model to obtain the meaning prediction result corresponding to each segmentation; the scene prediction is performed based on the meaning prediction result to obtain the outbound call scene corresponding to the user information. In this way, the outbound call scene can be determined more accurately, so as to accurately configure the call back rule.

[0047] Among them, the user information can be segmented based on a segmentation algorithm, and the segmentation algorithm can be a segmentation algorithm based on a hidden Markov model, a segmentation algorithm based on a conditional random field, and other algorithms. Since most of the extracted user information is not in a standard format, it is not conducive to word meaning prediction to determine the outbound call scenario, so it is necessary to segment and convert the user information to obtain user information in a standard format. The word meaning prediction model is used to predict the similarity between the word segmentation result and the word segmentation in a standard format. The word meaning prediction model is obtained by training a semantic matching model with a standard word segmentation database. The semantic prediction model may include an LSTM matching model, an MV-DSSM model, an ESIM model, and other models. The standard word segmentation database is a database for storing standard word segmentations, wherein the word meaning prediction result is the similarity between each word segmentation and the standard word segmentation in the standard word segmentation database.

[0048] Specifically, the word segmentation matching can be performed in the corresponding standard word segmentation database through the word meaning prediction model, and the similarity between each word segmentation and the standard word segmentation in the standard word segmentation database is calculated. Each word meaning prediction result is sorted according to the similarity to obtain the sorting result; the word segmentation result is filtered based on the sorting result to obtain the word meaning prediction result corresponding to each word segmentation, and finally the scene prediction is performed based on the word meaning prediction result to obtain the outbound call scene corresponding to the user information.

[0049] For example, if the word meaning prediction results include the meanings of vehicle, road, insurance, etc., scene prediction can be performed based on these word meanings. Since these word meanings have the highest matching degree with the outbound call scene corresponding to car insurance, it can be determined that the outbound call scene corresponding to the user information is the outbound call scene corresponding to car insurance.

[0050] S103: Verify and configure the recall rule according to the outbound call scenario to obtain a target recall rule, where the target recall rule includes a target recall number and a target recall interval duration.

[0051] The target recall rule is the recall rule after verification and configuration, the target recall times is the recall times after verification and configuration, and the target recall interval is the recall interval after verification and configuration.

[0052] In some embodiments, it is determined whether the outbound call scenario is a target outbound call scenario; if the outbound call scenario is a target outbound call scenario, the outbound call constraint condition corresponding to the target outbound call scenario is obtained, and the recall rule is reconfigured according to the outbound call constraint condition to obtain the target recall rule. In this way, the corresponding outbound call constraint condition can be accurately determined according to the corresponding outbound call scenario, and a recall rule that is more in line with the outbound call scenario can be generated.

[0053] The target outbound call scenario is an outbound call scenario pre-configured with an outbound call constraint condition. As long as the outbound call scenario is configured with an outbound call constraint condition, it can be used as the target outbound call scenario. The outbound call constraint condition can be used for re-determination, such as including the outbound call start time, the number of outbound calls within a preset time period, etc.

[0054] Specifically, it can be set according to regular working hours, generally between 8:00-9:00. The opening time can be set within this time period according to the specific target outbound call scenario. If the re-call operation is performed before this time period, there will be a greater risk of complaints.

[0055] For example, if the outbound call start time is 10:00, and the next recall time is calculated based on the configured interval time as 2021-10-17 2:00. Since the next recall time is less than the start time of the day, the next recall time is postponed to 2021-10-17 10:00. If the next recall time is greater than the start time of the day, there is no need to postpone it, and the calculated recall time is used as the actual recall time.

[0056] Specifically, it can be set according to the timeliness of the target outbound call scenario and the AI ​​service outbound call results. If it is a target outbound call scenario with particularly high real-time requirements, it can be configured to be called multiple times a day. If it is a target outbound call scenario that does not require particularly high real-time requirements and is prone to complaints, the same number can only be called once a day by the AI ​​service.

[0057] For example, if the target outbound call scenario is a claim urging damage assessment scenario, since the customer has not gone to the repair shop for maintenance after reporting the case, the claim case cannot proceed with the subsequent process. Therefore, this scenario has certain time requirements for the customer to go to the factory, so it is necessary to reconfigure the recall rule according to the outbound call constraint conditions corresponding to the outbound call scenario, i.e., the time requirement, to obtain the target recall rule.

[0058] For example, if the call is hung up right after the opening remarks, or the customer hangs up without indicating a response, and agrees to the repair, it is recommended to re-call the call on the same day or the next day. If no repair is required / self-repair / no accident, or if it is not certain whether repair is required, it is recommended to transfer to the cancellation process, stop re-calling, and end the AI ​​service outbound call. If the repair is agreed and the appointment time is confirmed with the customer, the AI ​​re-call will be made according to the appointment time. If the repair has been completed, or a manual service is required, the AI ​​service outbound call will be ended directly.

[0059] Specifically, the number of recalls within a preset time period can be determined according to the target outbound call scenario, so that the number of recalls within a certain time range of the mobile phone number can be limited according to the outbound call scenario dimension, so that the number of recalls in the outbound call scenario is limited. In addition, a lower limit for the recall interval configuration is added to prevent the manually configured interval from being too short, thereby reducing the risk of complaints.

[0060] For example, if the target outbound call scenario is the outbound call scenario corresponding to auto insurance, the number of recalls within 5 days can be determined to be 2 times based on the target outbound call scenario. If the calculated number of recalls within 5 days is 3 times, the last recall will be eliminated and no recall will be executed to prevent the manually configured interval from being too short, thereby reducing the risk of complaints.

[0061] In some embodiments, it is determined whether the outbound call scenario is a target outbound call scenario. If the outbound call scenario is not a target outbound call scenario, the similarity between the outbound call scenario and each of the target outbound call scenarios is determined; if the similarity between the outbound call scenario and the target outbound call scenario exceeds a preset similarity threshold, the outbound call constraint condition corresponding to the target outbound call scenario is obtained, and the recall rule is reconfigured according to the outbound call constraint condition to obtain a target recall rule. In this way, the most similar outbound call scenario can be determined as the target outbound call scenario, so as to accurately reconfigure the recall rule.

[0062] The preset similarity threshold may be determined by the user, such as 70%, 80%, etc., which is not specifically limited here.

[0063] Specifically, determine the similarity between the outbound call scenario and each of the target outbound call scenarios; if there is a similarity between the outbound call scenario and the target outbound call scenario that exceeds a preset similarity threshold, obtain the outbound call constraint condition corresponding to the target outbound call scenario, and reconfigure the recall rule according to the outbound call constraint condition to obtain the target recall rule; if there is no similarity between the outbound call scenario and the target outbound call scenario that exceeds the preset similarity threshold, redetermine the outbound call scenario.

[0064] Exemplarily, if the outbound call scenario is the outbound call scenario corresponding to property insurance, and the outbound call scenario corresponding to property insurance is not the target outbound call scenario, then the similarity between the outbound call scenario corresponding to property insurance and each target outbound call scenario is determined; if there is an outbound call scenario corresponding to property insurance and the outbound call scenario corresponding to auto insurance, and the similarity is 90%, and the preset similarity threshold is 80%, then the outbound call constraint conditions of the outbound call scenario corresponding to auto insurance are obtained, and the recall rule is reconfigured according to the outbound call constraint conditions to obtain the target recall rule.

[0065] S104: After the target recall interval has elapsed, the outbound calling device is used to perform a recall operation on the user number until the number of recalls reaches the target number of recalls or the recall operation is successful.

[0066] Specifically, after the target recall interval has passed, the outbound calling device is used to perform a recall operation on the user number. If the recall operation is successful, the recall operation is stopped; if the recall operation fails, the recall operation is continued until the number of recalls reaches the target number of recalls or the recall operation is successful.

[0067] For example, if the first target recall interval in the target recall rule is 48 hours, the second target recall interval is 56 hours, and the target recall times is 2. When it is detected that the outbound call operation of the outbound call device fails, and after 48 hours, the outbound call device is used to perform a recall operation on the user number. If the recall operation is successful, the recall operation is stopped; if the recall operation fails, after another 56 hours, the outbound call device is used to perform a recall operation on the user number again. Since the recall times have reached 2, the recall operation is no longer performed regardless of whether the recall is successful.

[0068] In some embodiments, after the target recall interval has passed, the recall time of the recall operation is determined according to the target recall interval, and it is determined whether the recall time is within a preset time period; if the recall time is not within the preset time period, the recall time is reset to within the preset time period, so that the outbound calling device performs the recall operation on the user number within the preset time period. This can avoid performing the recall operation in an inappropriate time period, such as in the early morning, thereby increasing the risk of being complained.

[0069] The preset time period may be any time period, such as 10:00-18:00, etc., and is not specifically limited here.

[0070] Specifically, the recall time of the recall operation is determined according to the target recall interval duration, and it is determined whether the recall time is within a preset time period; if the recall time is not within the preset time period, the recall time is reset to within the preset time period so that the outbound calling device performs a recall operation on the user number within the preset time period; if the recall time is within the preset time period, the recall operation is performed directly at the recall time.

[0071] For example, if the preset time period is 10:00-18:00, after the target recall interval has passed, the recall time of the recall operation is determined to be 3:00 according to the target recall interval, thereby determining that the recall time is not within the preset time period, and then the recall time is reset to 10:00-18:00, for example, it can be set to 10:00, so that the outbound calling device performs the recall operation on the user number within the preset time period. This can avoid performing the recall operation in an inappropriate time period, such as in the early morning, thereby increasing the risk of being complained.

[0072] In some embodiments, before the target recall interval has passed, the date and time corresponding to the outbound call operation failure are obtained; after the target recall interval has passed, the recall date of the recall operation is determined according to the target recall interval and the date and time corresponding to the outbound call operation failure; if the recall time is the preset recall date, the recall date is re-determined. This can avoid recall operations on holidays or sensitive dates, thereby increasing the risk of complaints.

[0073] The preset recall date can be set according to actual conditions and is not specifically limited here.

[0074] Exemplarily, before the target recall interval duration has passed, the date and time corresponding to the failure of the outbound call operation is obtained as 2021-09-27 10:00; after the target recall interval duration has passed, the recall date of the recall operation is determined to be 2021-10-01 10:00 according to the target recall interval duration and the date and time corresponding to the failure of the outbound call operation; however, the recall date is a holiday, that is, the preset recall date, so it is necessary to re-determine the recall date, for example, the recall date of the recall operation is determined to be 2021-10-08 10:00.

[0075] See also Figure 3 , Figure 3 It is a schematic block diagram of a recall device provided in an embodiment of the present application. The recall device can be configured in a server to execute the aforementioned recall method.

[0076] like Figure 3 As shown, the recall device 200 includes: an information extraction module 201 , a rule generation module 202 , a rule determination module 203 and a recall module 204 .

[0077] The information extraction module 201 is used to obtain user data corresponding to the outbound call operation when it is detected that the outbound call operation of the outbound call device fails, and extract information from the user data to obtain user information, wherein the user information includes a user number.

[0078] The rule generation module 202 is used to obtain a pre-configured call rule and determine an outbound call scenario according to the user information.

[0079] The rule determination module 203 is used to verify and configure the recall rule according to the outbound call scenario to obtain a target recall rule, wherein the target recall rule includes a target recall number and a target recall interval duration.

[0080] The recall module 204 is configured to, when the target recall interval has elapsed, use the outbound calling device to perform a recall operation on the user number until the number of recalls reaches the target number of recalls or the recall operation succeeds.

[0081] The information extraction module 201 is also used to classify the user data to obtain business data of each business category; determine whether the business category includes the target business category; if the business category includes the target business category, extract the user information corresponding to the outbound call operation from the business data corresponding to the target business category.

[0082] The rule generation module 202 is also used to perform word segmentation processing on the user information to obtain the word segmentation results corresponding to the user information; perform word meaning prediction on each word in the word segmentation results based on the word meaning prediction model to obtain the word meaning prediction results corresponding to each word segmentation; perform scene prediction based on the word meaning prediction results to obtain the outbound call scene corresponding to the user information.

[0083] The rule determination module 203 is also used to determine whether the outbound call scenario is a target outbound call scenario; if the outbound call scenario is a target outbound call scenario, the outbound call constraint condition corresponding to the target outbound call scenario is obtained, and the recall rule is reconfigured according to the outbound call constraint condition to obtain the target recall rule.

[0084] The rule determination module 203 is also used to determine the similarity between the outbound call scenario and each of the target outbound call scenarios if the outbound call scenario is not the target outbound call scenario; if the similarity between the outbound call scenario and the target outbound call scenario exceeds a preset similarity threshold, the outbound call constraint condition corresponding to the target outbound call scenario is obtained, and the re-call rule is reconfigured according to the outbound call constraint condition to obtain the target re-call rule.

[0085] The recall time determination module 205 is used to determine the recall time of the recall operation according to the target recall interval duration, and determine whether the recall time is within a preset time period; if the recall time is not within the preset time period, the recall time is reset to within the preset time period so that the outbound calling device performs the recall operation on the user number within the preset time period.

[0086] The recall date determination module 206 is used to obtain the date and time corresponding to the outbound call operation failure; determine the recall date of the recall operation according to the target recall interval and the date and time corresponding to the outbound call operation failure; if the recall time is the preset recall date, re-determine the recall date.

[0087] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0088] The method and apparatus of the present application can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer terminal devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices.

[0089] Exemplarily, the above method and apparatus may be implemented in the form of a computer program. The computer program may be implemented in Figure 4 Runs on the computer device shown.

[0090] See also Figure 4 , Figure 4 1 is a schematic diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0091] like Figure 4 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0092] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any one of the recall methods.

[0093] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0094] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the recall methods.

[0095] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that the structure of the computer device is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0096] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0097] Among them, in some embodiments, the processor is used to run a computer program stored in the memory to implement the following steps: when it is detected that an outbound call operation of an outbound call device fails, user data corresponding to the outbound call operation is obtained, and information is extracted from the user data to obtain user information, wherein the user information includes a user number; a pre-configured recall rule is obtained, and an outbound call scenario is determined according to the user information; the recall rule is verified and configured according to the outbound call scenario to obtain a target recall rule, wherein the target recall rule includes a target number of recalls and a target recall interval duration; after the target recall interval duration has passed, a recall operation is performed on the user number using the outbound call device until the number of recalls reaches the target number of recalls or the recall operation is successful.

[0098] In some embodiments, the processor is also used to: classify the user data to obtain business data of each business category; determine whether the business category includes a target business category; if the business category includes a target business category, extract user information corresponding to the outbound call operation from the business data corresponding to the target business category.

[0099] In some embodiments, the processor is also used to: perform word segmentation on the user information to obtain a word segmentation result corresponding to the user information; perform word meaning prediction on each word in the word segmentation result based on a word meaning prediction model to obtain a word meaning prediction result corresponding to each word segmentation; perform scene prediction based on the word meaning prediction result to obtain an outbound call scene corresponding to the user information.

[0100] In some embodiments, the processor is also used to: determine whether the outbound call scenario is a target outbound call scenario; if the outbound call scenario is a target outbound call scenario, obtain the outbound call constraint conditions corresponding to the target outbound call scenario, and reconfigure the recall rule according to the outbound call constraint conditions to obtain the target recall rule.

[0101] In some embodiments, the processor is also used to: if the outbound call scenario is not a target outbound call scenario, determine the similarity between the outbound call scenario and each of the target outbound call scenarios; if the similarity between the outbound call scenario and the target outbound call scenario exceeds a preset similarity threshold, obtain the outbound call constraint condition corresponding to the target outbound call scenario, and reconfigure the recall rule according to the outbound call constraint condition to obtain the target recall rule.

[0102] In some embodiments, the processor is also used to: after the target recall interval duration has passed, determine the recall time of the recall operation according to the target recall interval duration, and determine whether the recall time is within a preset time period; if the recall time is not within the preset time period, re-set the recall time within the preset time period so that the outbound call device performs a recall operation on the user number within the preset time period.

[0103] In some embodiments, the processor is also used to: before the target recall interval duration has passed, obtain the date and time corresponding to the failure of the outbound call operation; after the target recall interval duration has passed, determine the recall date of the recall operation based on the target recall interval duration and the date and time corresponding to the failure of the outbound call operation; if the recall time is a preset recall date, re-determine the recall date.

[0104] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed, any one of the recall methods provided in the embodiments of the present application is implemented.

[0105] The computer-readable storage medium may be an internal storage unit of the computer device described in the above embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device.

[0106] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0107] The present invention refers to a new application model of computer technologies such as storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. of the blockchain language model. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the blockchain underlying platform, platform product service layer, and application service layer.

[0108] 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 various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A recall method, characterized in that: The method comprises: When it is detected that the outbound call operation of the outbound call device fails, user data corresponding to the outbound call operation is acquired, and information is extracted from the user data to obtain user information, wherein the user information includes a user number; Obtaining a pre-configured call back rule and determining an outbound call scenario according to the user information; Verify and configure the recall rule according to the outbound call scenario to obtain a target recall rule, wherein the target recall rule includes a target recall number and a target recall interval duration; When the target recall interval has elapsed, the outbound calling device is used to perform a recall operation on the user number until the number of recalls reaches the target number of recalls or the recall operation is successful; The verifying and configuring the recall rule according to the outbound call scenario to obtain a target recall rule includes: Determining whether the outbound call scenario is a target outbound call scenario; If the outbound call scenario is a target outbound call scenario, obtaining an outbound call constraint condition corresponding to the target outbound call scenario, and reconfiguring the recall rule according to the outbound call constraint condition to obtain a target recall rule; If the outbound call scenario is not a target outbound call scenario, determining a similarity between the outbound call scenario and each of the target outbound call scenarios; If the similarity between the outbound call scenario and the target outbound call scenario exceeds a preset similarity threshold, the outbound call constraint condition corresponding to the target outbound call scenario is obtained, and the recall rule is reconfigured according to the outbound call constraint condition to obtain the target recall rule.

2. The method according to claim 1, characterized in that: The extracting information from the user data to obtain the user information includes: Classify the user data to obtain business data of each business category; determining whether the service category includes a target service category; If the service category includes a target service category, user information corresponding to the outbound call operation is extracted from service data corresponding to the target service category.

3. The method according to claim 1, characterized in that The determining the outbound call scenario according to the user information includes: Performing word segmentation processing on the user information to obtain a word segmentation result corresponding to the user information; Performing word meaning prediction on each word in the word segmentation result based on the word meaning prediction model to obtain a word meaning prediction result corresponding to each word segmentation; The scene prediction is performed according to the word meaning prediction result to obtain the outbound call scene corresponding to the user information.

4. The method according to claim 1, characterized in that: After the target recall interval has passed, the method further includes: Determining a recall time for a recall operation according to the target recall interval duration, and determining whether the recall time is within a preset time period; If the recall time is not within the preset time period, the recall time is reset to be within the preset time period so that the outbound calling device performs a recall operation on the user number within the preset time period.

5. The method according to claim 1, characterized in that Before the target recall interval duration has passed, the method further includes: Obtain the date and time corresponding to when the outbound call operation fails; After the target recall interval has passed, the method further includes: Determining a recall date for the recall operation according to the target recall interval duration and the date and time corresponding to the outbound call operation failure; If the recall time is the preset recall date, the recall date is re-determined.

6. A recall device, characterized in that: include: An information extraction module, for obtaining user data corresponding to the outbound call operation when detecting that the outbound call operation of the outbound call device fails, and extracting information from the user data to obtain user information, wherein the user information includes a user number; A rule generation module, used to obtain a pre-configured re-call rule and determine an outbound call scenario according to the user information; A rule determination module, used to verify and configure the recall rule according to the outbound call scenario to obtain a target recall rule, wherein the target recall rule includes a target recall number and a target recall interval duration; A recall module, configured to, after the target recall interval has elapsed, use the outbound calling device to perform a recall operation on the user number until the number of recalls reaches the target number of recalls or the recall operation is successful; The verifying and configuring the recall rule according to the outbound call scenario to obtain a target recall rule includes: Determining whether the outbound call scenario is a target outbound call scenario; If the outbound call scenario is a target outbound call scenario, obtaining an outbound call constraint condition corresponding to the target outbound call scenario, and reconfiguring the recall rule according to the outbound call constraint condition to obtain a target recall rule; If the outbound call scenario is not a target outbound call scenario, determining a similarity between the outbound call scenario and each of the target outbound call scenarios; If the similarity between the outbound call scenario and the target outbound call scenario exceeds a preset similarity threshold, the outbound call constraint condition corresponding to the target outbound call scenario is obtained, and the recall rule is reconfigured according to the outbound call constraint condition to obtain the target recall rule.

7. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement, when executing the computer program: The recall method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the recall method according to any one of claims 1 to 5.

Images