Intelligent outbound method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an intelligent outbound method and device, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and is suitable for the field of financial science and technology. The method comprises the following steps: receiving a target outbound task; wherein the target call-out task comprises target customer information and an original call-out strategy; performing position analysis on the target customer information to obtain candidate position information; performing outbound call resource allocation based on the original outbound call strategy and the candidate position information to obtain a target outbound call resource; based on the original call-out strategy and the target call-out resource, carrying out call-out on the call-out receiving object, and obtaining call-out feedback data fed back by the call-out receiving object; and performing outbound strategy adjustment on the original outbound strategy based on the outbound feedback data to obtain a target outbound strategy, and performing outbound based on the target outbound strategy. According to the embodiment of the invention, the method can achieve the dynamic optimization of an outbound strategy, guarantees the effective utilization of resources, improves the call quality, and improves the success rate of intelligent outbound.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, is applicable to the field of financial technology, and in particular to an intelligent outbound calling method and device, an electronic device, and a storage medium. Background Art

[0002] Smart outbound calling is an artificial intelligence technology that can automatically make customer calls and conduct business communications. It can be applied to a variety of scenarios. For example, in the financial field, it can be used for business notifications, payment reminders, and other scenarios.

[0003] Currently, smart outbound calls are mainly implemented by telephone. However, in actual application scenarios, smart outbound calls may be blocked by the system or rejected by customers, thereby affecting the success rate of smart outbound calls.

[0004] Therefore, how to improve the success rate of intelligent outbound calls has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The main purpose of the embodiments of the present application is to propose an intelligent outbound calling method and device, an electronic device and a storage medium, aiming to improve the success rate of intelligent outbound calling.

[0006] To achieve the above object, a first aspect of an embodiment of the present application proposes an intelligent outbound calling method, the method comprising:

[0007] Receive a target outbound call task; wherein the target outbound call task includes target customer information and an original outbound call strategy, the target customer information is used to indicate an outbound call recipient, and the original outbound call strategy is used to guide the execution of the target outbound call task;

[0008] Performing location analysis on the target customer information to obtain candidate location information;

[0009] Allocate outbound call resources based on the original outbound call strategy and the candidate location information to obtain target outbound call resources;

[0010] Based on the original outbound call strategy and the target outbound call resource, an outbound call is made to the outbound call receiving object, and outbound call feedback data fed back by the outbound call receiving object is obtained; wherein the outbound call feedback data is used to indicate the call connection status and call content;

[0011] The original outbound call strategy is adjusted based on the outbound call feedback data to obtain a target outbound call strategy, and an outbound call is made based on the target outbound call strategy.

[0012] In some embodiments, the number of the candidate location information is at least one, the original outbound call strategy includes a current outbound call location priority, and the outbound call resource allocation based on the original outbound call strategy and the candidate location information to obtain the target outbound call resource includes:

[0013] For each piece of candidate location information, assigning a priority to the candidate location information to obtain location priority data;

[0014] Filtering and obtaining target location information based on the current outbound call location priority, the location priority data and the candidate location information;

[0015] Determine the original outbound call number pool according to the target location information;

[0016] Allocate number resources according to the original outbound call number pool to obtain a target outbound call number;

[0017] Allocate device resources based on the target outbound call number to obtain the target outbound call device;

[0018] The target outbound call resource is obtained by combining the target outbound call number and the target outbound call device.

[0019] In some embodiments, adjusting the original outbound call strategy based on the outbound call feedback data to obtain a target outbound call strategy includes:

[0020] If the call connection status indicates that the outbound call recipient has not connected the outbound call, a tag query is performed on the target outbound call resource to obtain target resource tag information; wherein the target resource tag information is used to indicate that the target outbound call resource is a trusted outbound call resource or an untrusted outbound call resource;

[0021] Performing resource update on the target outbound call resource based on the target resource tag information;

[0022] The current outbound call position priority in the original outbound call strategy is adjusted to obtain the target outbound call strategy.

[0023] In some embodiments, the obtaining the target location information based on the current outbound call location priority, the location priority data, and the candidate location information by screening includes:

[0024] Matching the current outbound call location priority with the location priority data to obtain priority matching data;

[0025] If the priority matching data indicates that the current outbound call location priority does not match the location priority data, filtering the location with the highest priority from the candidate location information based on the location priority data to obtain the candidate location information;

[0026] Based on the candidate location information, preset adjacent area information is acquired, and the adjacent area information is used as the target location information.

[0027] In some embodiments, the original outbound call strategy also includes the current outbound call communication words and the current outbound call mode, and the outbound call strategy adjustment of the original outbound call strategy based on the outbound call feedback data to obtain the target outbound call strategy includes:

[0028] If the call connection state indicates that the outbound call recipient has connected the outbound call, the speaker of the call content is screened to obtain the target speaker's voice data; wherein the target speaker's voice data is the voice data of the outbound call recipient;

[0029] Performing intent recognition on the target speaker's voice data to obtain target intent data;

[0030] Based on the target intention data, the speech is allocated to obtain the target outbound call speech;

[0031] Allocate an outbound calling method based on the target intention data to obtain a target outbound calling method;

[0032] The current outbound call communication words in the original outbound call strategy are updated based on the target outbound call words, and the current outbound call mode in the original outbound call strategy is updated based on the target outbound call mode to obtain the target outbound call strategy.

[0033] In some embodiments, performing intent recognition on the target speaker's speech data to obtain target intent data includes:

[0034] Converting the target speaker's speech data into text to obtain original text data;

[0035] Performing text preprocessing on the original text data to obtain target text data;

[0036] Performing feature extraction on the target text data to obtain target text feature data;

[0037] The target text feature data is subjected to intent classification to obtain the target intent data.

[0038] In some embodiments, the performing intent classification on the target text feature data to obtain the target intent data includes:

[0039] Performing intent classification on the target text feature data to obtain a plurality of original intent data;

[0040] Performing confidence calculation on each of the original intention data to obtain intention confidence data;

[0041] Based on the intention confidence data, the data with the largest confidence value is filtered out from the multiple original intention data to obtain the target intention data.

[0042] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides an intelligent outbound calling device, the device comprising:

[0043] An outbound call task receiving module, used for receiving a target outbound call task; wherein the target outbound call task includes target customer information and an original outbound call strategy, wherein the target customer information is used to indicate an outbound call receiving object, and the original outbound call strategy is used to guide the execution of the target outbound call task;

[0044] A location analysis module, used to perform location analysis on the target customer information to obtain candidate location information;

[0045] An outbound call resource allocation module, configured to allocate outbound call resources based on the original outbound call strategy and the candidate location information to obtain target outbound call resources;

[0046] An outbound call execution module, used for making an outbound call to the outbound call receiving object based on the original outbound call strategy and the target outbound call resource, and obtaining outbound call feedback data fed back by the outbound call receiving object; wherein the outbound call feedback data is used to indicate the call connection status and call content;

[0047] The outbound call strategy adjustment module is used to adjust the original outbound call strategy based on the outbound call feedback data, obtain a target outbound call strategy, and make an outbound call based on the target outbound call strategy.

[0048] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0049] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0050] The intelligent outbound call method and device, electronic device and storage medium proposed in the present application receive a target outbound call task; wherein the target outbound call task includes target customer information and original outbound call strategy, the target customer information is used to indicate the outbound call recipient, and the original outbound call strategy is used to guide the execution of the target outbound call task; the target customer information is positionally parsed to obtain candidate location information; outbound call resources are allocated based on the original outbound call strategy and the candidate location information to obtain target outbound call resources, thereby improving the efficiency and pertinence of the outbound call; an outbound call is made to the outbound call recipient based on the original outbound call strategy and the target outbound call resources, and the outbound call feedback data fed back by the outbound call recipient is simultaneously obtained; wherein the outbound call feedback data is used to indicate the telephone connection status and call content; the outbound call strategy is adjusted to the original outbound call strategy based on the outbound call feedback data to obtain the target outbound call strategy, and an outbound call is made based on the target outbound call strategy, thereby dynamically optimizing the outbound call strategy, ensuring the effective use of resources and the improvement of call quality, and improving the success rate of intelligent outbound calls. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of the intelligent outbound calling method provided by an embodiment of the present application;

[0052] Figure 2 yes Figure 1 Flow chart of step S103 in FIG.

[0053] Figure 3 yes Figure 2 Flow chart of step S202 in FIG.

[0054] Figure 4 yes Figure 1 A flowchart of step S105 in FIG.

[0055] Figure 5 yes Figure 1 Another flowchart of step S105 in;

[0056] Figure 6 yes Figure 5 Flow chart of step S502 in FIG.

[0057] Figure 7 yes Figure 6 Flow chart of step S604 in FIG.

[0058] Figure 8 It is a structural diagram of the intelligent outbound calling device provided in an embodiment of the present application;

[0059] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0063] First, some nouns involved in this application are analyzed:

[0064] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a 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.

[0065] Smart outbound calling is an artificial intelligence technology that can automatically make customer calls and conduct business communications. It can be applied to a variety of scenarios. For example, in the financial field, it can be used for business notifications, payment reminders, and other scenarios.

[0066] At present, the smart outbound calling is mainly realized by telephone. However, in actual application scenarios, the smart outbound calling may be intercepted by the system or rejected by the customer, causing the customer to miss some important notifications, thus affecting the success rate of the smart outbound calling.

[0067] At present, the common practice in the industry is to push a real-time flash message to the customer while making an outbound call to indicate the purpose of the call and prevent the customer from missing important calls. However, if a flash message is added to every outbound call, it will bring a lot of additional costs and fail to cover some non-smartphone users.

[0068] Based on this, the embodiments of the present application provide an intelligent outbound calling method and device, an electronic device and a storage medium, aiming to improve the success rate of intelligent outbound calling.

[0069] The intelligent outbound calling method and device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the intelligent outbound calling method in the embodiments of the present application is described.

[0070] 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.

[0071] 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.

[0072] The intelligent outbound calling method provided in the embodiment of the present application relates to the field of artificial intelligence technology and is applicable to the field of financial technology. The intelligent outbound calling method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the intelligent outbound calling method, etc., but is not limited to the above forms.

[0073] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0074] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0075] Figure 1 is an optional flow chart of the intelligent outbound calling method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105.

[0076] Step S101, receiving a target outbound call task; wherein the target outbound call task includes target customer information and an original outbound call strategy, the target customer information is used to indicate an outbound call recipient, and the original outbound call strategy is used to guide the execution of the target outbound call task;

[0077] Step S102, performing location analysis on the target customer information to obtain candidate location information;

[0078] Step S103, allocating outbound call resources based on the original outbound call strategy and the candidate location information to obtain target outbound call resources;

[0079] Step S104, making an outbound call to the outbound call receiving object based on the original outbound call strategy and the target outbound call resources, and obtaining outbound call feedback data fed back by the outbound call receiving object; wherein the outbound call feedback data is used to indicate the call connection status and call content;

[0080] Step S105, adjusting the original outbound call strategy based on the outbound call feedback data to obtain a target outbound call strategy, and making an outbound call based on the target outbound call strategy.

[0081] Steps S101 to S105 shown in the embodiment of the present application parse the location information of the target customer to obtain candidate location information, and allocate the most suitable outbound call resources based on the original outbound call strategy and the candidate location information, thereby improving the efficiency and targeting of the outbound calls; at the same time, the outbound call strategy is adjusted in real time according to the feedback from the outbound call recipient, further optimizing the subsequent call process, ensuring the effective use of resources and the improvement of call quality, and improving the success rate of intelligent outbound calls.

[0082] In step S101 of some embodiments, the target outbound call task is a task for making an outbound call to an indicated outbound call recipient. Therefore, the target outbound call task includes target customer information indicating the outbound call recipient and an original outbound call strategy for guiding the execution of the target outbound call task. Specifically, the target outbound call task can be a first outbound call or a second outbound call (non-first outbound call).

[0083] In some embodiments, the original outbound call strategy includes the current outbound call location priority, and the original outbound call strategy also includes the current outbound call communication language and the current outbound call method.

[0084] If the target outbound call task is the first outbound call, the original outbound call strategy includes the preset first outbound call position priority, the preset call communication script and the intelligent outbound call method;

[0085] If the target outbound call task is a secondary outbound call, the original outbound call strategy includes the current outbound call priority, the current outbound call communication language and the current outbound call method (intelligent outbound call or manual outbound call).

[0086] In step S102 of some embodiments, the target customer information includes user identity information, an insurance policy, and a claim policy, wherein the address of the insurance contracting institution corresponding to the insurance policy is the first candidate location information, the identity address recorded in the user identity information is the second candidate location information, and the address of the claim settlement or other preservation service corresponding to the claim settlement policy is the third candidate location information;

[0087] See also Figure 2 In some embodiments, step S103 may include but is not limited to steps S201 to S206:

[0088] Step S201, for each candidate location information, assigning a priority to the candidate location information to obtain location priority data;

[0089] Step S202, obtaining target location information based on the current outbound call location priority, location priority data and candidate location information;

[0090] Step S203, determining the original outbound call number pool according to the target location information;

[0091] Step S204, allocating number resources according to the original outbound call number pool to obtain a target outbound call number;

[0092] Step S205, allocating device resources based on the target outbound call number to obtain the target outbound call device;

[0093] Step S206, combining the target outbound call number and the target outbound call device to obtain the target outbound call resources.

[0094] Steps S201 to S206 shown in the embodiment of the present application can ensure that resources are scheduled in order according to importance by first assigning priority to each candidate location information, and then filtering out the target location information from the candidate location information in combination with the current outbound call location priority and location priority data, thereby improving the pertinence and efficiency of resource allocation. Next, the original outbound call number pool is determined based on the target location information, and number resources and equipment resources are further allocated, and finally the target outbound call resources are combined, which can effectively improve the utilization rate of outbound call resources and the overall outbound call efficiency, and ensure that resources can serve higher priority needs more accurately and efficiently.

[0095] In step S201 of some embodiments, the address of the insurance contracting institution corresponding to the insurance policy is the first candidate location information, the identity address recorded in the user identity information is the second candidate location information, and the address of the claim or other preservation service corresponding to the claim policy is the third candidate location information. Each candidate location information has a corresponding priority relationship. Specifically, the first candidate location information is the first location priority data, the second candidate location information is the second location priority data, and the third candidate location information is the third location priority data, wherein the first location priority data is greater than the second location priority data, and the second location priority data is greater than the third location priority data.

[0096] It should be noted that if the smart outbound call is not connected, the outbound call resources corresponding to the candidate location information are selected according to the location priority data to make another outbound call to improve the success rate of the outbound call. In addition, if one or more of the first candidate location information, the second candidate location information, and the third candidate location information is empty, the candidate location information is directly skipped when allocating outbound call resources to improve the efficiency of outbound calls.

[0097] See also Figure 3 In some embodiments, step S202 may include but is not limited to steps S301 to S303:

[0098] Step S301, matching the current outbound call location priority with the location priority data to obtain priority matching data;

[0099] Step S302, if the priority matching data indicates that the current outbound call location priority does not match the location priority data, the location with the highest priority is selected from the candidate location information based on the location priority data to obtain the candidate location information;

[0100] Step S303: acquiring preset adjacent area information based on the candidate location information, and using the adjacent area information as the target location information.

[0101] Steps S301 to S303 shown in the embodiment of the present application are performed by intelligently matching the current outbound call location priority with the location priority data according to the preset current outbound call location priority. When a mismatch is found, it means that the outbound call resources corresponding to all candidate location information are not applicable. Therefore, based on the location priority data, the location with the highest priority is filtered out from the candidate location information to obtain the alternative location information, and based on the alternative location information, the preset neighboring area information is obtained, and the neighboring area information is used as the target location information, thereby effectively improving the flexibility and accuracy of the outbound call location selection and improving the efficiency of the intelligent outbound call.

[0102] In step S301 of some embodiments, the current outbound call position priority in the original outbound call strategy is different according to the different target outbound call tasks. If the target outbound call task is the first outbound call, the current outbound call position priority is the first position priority data. If the target outbound call task is the second outbound call, the current outbound call position priority is the first position priority data / the second position priority data / the third position priority data / others. The specific needs are determined according to the outbound call feedback data of the last outbound call, but are not limited to this.

[0103] Therefore, the current outbound call location priority can be matched with multiple location priority data to obtain priority matching data.

[0104] After step S301 in some embodiments, the intelligent outbound calling method further includes but is not limited to the following steps:

[0105] If the priority matching data indicates that the current outbound call location priority matches one of the multiple location priority data, a corresponding location is screened out from the candidate location information based on the current outbound call location priority to obtain the target location information.

[0106] In step S302 of some embodiments, if the priority matching data indicates that the current outbound call location priority does not match any of the location priority data, the location with the highest priority is filtered out from the candidate location information based on the location priority data, that is, the first candidate location information whose priority is the first location priority data, and the first candidate location information is used as the alternative location information.

[0107] In step S303 of some embodiments, preset adjacent area information is obtained based on the alternative location information. For example, if the first candidate location information is area A, the adjacent area information may be area B adjacent to area A. Specifically, area B may be preset by a technician, or the nearest area may be calculated based on a distance algorithm, but is not limited thereto.

[0108] It should be noted that each candidate location information has a corresponding outbound call number pool, corresponding to an outbound call task queue.

[0109] Therefore, after determining the target location information according to the target outbound call task, the original outbound number pool is determined, and the target outbound call task is inserted into the outbound task queue corresponding to the target location information, so as to allocate number resources according to the original outbound number pool to obtain the target outbound number, and then allocate device resources based on the target outbound number to obtain the target outbound device, and finally combine the target outbound number and the target outbound device to obtain the target outbound resources.

[0110] In some embodiments, the target outbound calling device is a preset outbound calling smart device, such as an Android phone of a different brand, or an Android virtual machine corresponding to a different brand, wherein each target outbound calling device has a built-in harassing call blocking service provider, but is not limited to this. The specific setting needs to be made according to the actual application scenario, but is not limited to this.

[0111] It should be noted that whenever a target outbound call task is inserted into the outbound call task queue corresponding to the target location information, it is necessary to assign a task priority to the target outbound call task based on the scheduling strategy so that the tasks in the queue can achieve load balancing and improve outbound call efficiency.

[0112] Specifically, the scheduling strategy may include but is not limited to the following rules:

[0113] Rule 1: The first outbound call has a higher priority than the second outbound call;

[0114] Rule 2: Prioritize entering the outbound call task queue corresponding to the target location information, followed by the outbound call task queue corresponding to the adjacent area information. If you fail to successfully enter the outbound call task queue, you will queue again after 30 minutes.

[0115] Rule 3: If all outbound call task queues are overloaded on the day, all new tasks will be suspended and an alarm will be issued to prompt manual processing.

[0116] In step S104 of some embodiments, based on the current outbound call communication words in the original outbound call strategy, the target outbound call number and the target outbound call device are called to make an outbound call to the outbound call recipient, and outbound call feedback data fed back by the outbound call recipient is obtained; wherein the outbound call feedback data is used to indicate the call connection status and the call content;

[0117] It should be noted that if the outbound call recipient answers the outbound call, the outbound call feedback data includes an indication of the call connection status and the content of the call;

[0118] If the outbound call recipient does not answer the outbound call, the outbound call feedback data only includes an indication of the call connection status, while the call content is empty.

[0119] See also Figure 4 In some embodiments, step S105 may include but is not limited to steps S401 to S403:

[0120] Step S401: If the call connection state indicates that the outbound call recipient has not connected the outbound call, a tag query is performed on the target outbound call resource to obtain target resource tag information; wherein the target resource tag information is used to indicate whether the target outbound call resource is a trusted outbound call resource or an untrusted outbound call resource;

[0121] Step S402, updating the target outbound call resource based on the target resource tag information;

[0122] Step S403: Adjust the current outbound call location priority in the original outbound call strategy to obtain a target outbound call strategy.

[0123] In steps S401 to S403 shown in the embodiment of the present application, when the call connection status indicates that the outbound call recipient has not connected the outbound call, a mark query is performed on the target outbound call resource to obtain target resource marking information to distinguish whether the target outbound call resource is a trusted outbound call resource or an untrusted outbound call resource, and then the target outbound call resource is updated based on the target resource marking information, and the current outbound call position priority in the original outbound call strategy is adjusted to obtain the target outbound call strategy, thereby effectively improving the success rate of intelligent outbound calls.

[0124] In step S401 of some embodiments, the target resource includes communication operator marking information and harassing call blocking service provider marking information;

[0125] By regularly performing tag queries to communication operators and harassment call blocking service providers, all marked outbound numbers or outbound devices can be obtained, so that it can be known whether the target outbound number and target outbound device are marked, and the target resource tag information can be obtained.

[0126] Specifically, the communication operator marking information is used to indicate whether a target outbound call number is a trusted outbound call resource or an untrusted outbound call resource. When this number is used to make an outbound call, there is a possibility that the call will be rejected by the user due to the marking information.

[0127] The tag information of the harassing call blocking service provider is used to indicate whether a target outbound call number or target outbound call device is a trusted outbound call resource or an untrusted outbound call resource. When an outbound call is made based on the target outbound call number through the target outbound call device, there is a possibility that it will be blocked by the harassing call blocking service provider.

[0128] Therefore, it is necessary to update the target outbound call resources (target outbound call number or target outbound call device) according to the target resource marking information (communication operator marking information and harassment call blocking service provider marking information). If marked, the target outbound call number will be suspended or other outbound call devices will be used when executing subsequent outbound call tasks, thereby reducing the possibility of being intercepted or rejected due to marking information and improving the success rate of intelligent outbound calls.

[0129] In step S403 of some embodiments, if the target resource marking information indicates that the target outbound call number is an untrusted outbound call resource, the current outbound call location priority in the original outbound call policy is converted into next location priority data with a lower priority.

[0130] For example, if the current outbound call location priority in the original outbound call strategy is the first location priority data, then after the target outbound call number is an untrusted outbound call resource, the current outbound call location priority is adjusted to the second location priority data;

[0131] If the current outbound call location priority in the original outbound call strategy is the second location priority data, then after the target outbound call number is an untrusted outbound call resource, the current outbound call location priority is adjusted to the third location priority data;

[0132] If the current outbound call location priority in the original outbound call strategy is the third location priority data, then after the target outbound call number is an untrusted outbound call resource, the current outbound call location priority will be adjusted to empty or zero, so that when the next outbound call is made, the preset neighboring area information corresponding to the first candidate location information can be obtained according to the current outbound call location priority in the original outbound call strategy, and the neighboring area information can be used as the target location information.

[0133] In some embodiments, if the target resource marking information is used to characterize that the target outbound call device is an untrusted outbound call resource, the target outbound call device corresponding to the target outbound call number is changed and switched to a different target outbound call device to execute the next outbound call.

[0134] For example, for outbound number 1, the outbound calling device used for the last outbound call was model 1 - nuisance call blocking service provider A, and the nuisance call blocking service provider marking information indicates that nuisance call blocking service provider A marked the outbound calling number 1 as an untrusted outbound calling resource, then the corresponding relationship between the outbound calling number 1 and the outbound calling device is modified, that is: for outbound number 1, the outbound calling device used for the next outbound call is model 1 - nuisance call blocking service provider B.

[0135] After step S403 in some embodiments, the intelligent outbound calling method further includes but is not limited to:

[0136] Based on the preset cycle, apply to the communication operator and the harassing call blocking service provider to remove the mark to restore the availability of outbound call resources, thereby improving the efficiency of intelligent outbound calls.

[0137] See also Figure 5 In some embodiments, step S105 may also include but is not limited to steps S501 to S505:

[0138] Step S501, if the call connection state indicates that the outbound call recipient has connected the outbound call, the speaker of the call content is screened to obtain the target speaker's voice data; wherein the target speaker's voice data is the voice data of the outbound call recipient;

[0139] Step S502, performing intent recognition on the target speaker's voice data to obtain target intent data;

[0140] Step S503, assigning a speech technique based on the target intention data to obtain a target outbound call speech technique;

[0141] Step S504, allocating an outbound calling method based on the target intention data to obtain a target outbound calling method;

[0142] Step S505, updating the current outbound call communication words in the original outbound call strategy based on the target outbound call words, and updating the current outbound call mode in the original outbound call strategy based on the target outbound call mode, to obtain the target outbound call strategy.

[0143] In steps S501 to S505 shown in the embodiment of the present application, when the call connection state represents that the outbound call recipient has connected the outbound call, the speaker is screened on the call content to obtain the target speaker's voice data, and the target speaker's voice data is recognized to obtain the target intention data, thereby allocating the most appropriate outbound call speech and outbound call method, and updating the current outbound call communication speech in the original outbound call strategy based on the target outbound call speech, and updating the current outbound call method in the original outbound call strategy based on the target outbound call method to obtain the target outbound call strategy, so that the next outbound call can meet the actual needs of the outbound call recipient, improve the efficiency and success rate of the outbound call, and improve the user experience.

[0144] In step S501 of some embodiments, the speaker of the call content is screened by a preset speaker separation algorithm, and the voice data of the outbound call recipient is screened to obtain the target speaker's voice data. The speaker separation algorithm can be a CTCNet model, a U-Net model, a TasNet model, etc., which needs to be selected in combination with the actual application scenario, and is not limited thereto.

[0145] See also Figure 6 In some embodiments, step S502 includes but is not limited to steps S601 to S604:

[0146] Step S601, converting the target speaker's speech data into text to obtain original text data;

[0147] Step S602, performing text preprocessing on the original text data to obtain target text data;

[0148] Step S603, extracting features from the target text data to obtain target text feature data;

[0149] Step S604, performing intent classification on the target text feature data to obtain target intent data.

[0150] Steps S601 to S604 shown in the embodiment of the present application, by converting the voice data of the target speaker into text, performing preprocessing and feature extraction, and then obtaining the target intent data through intent classification, help to convert unstructured voice information into a structured data form that is easy to analyze and understand, which not only improves the efficiency and accuracy of data processing, but also enables more in-depth exploration and understanding of the communication intentions of the outbound call recipient, providing a more accurate and reliable basis for subsequent speech allocation and outbound call strategy adjustment, thereby optimizing the customer interaction experience and improving the intelligence level of smart outbound calls.

[0151] In step S601 of some embodiments, the target speaker's speech data may be converted into text using a preset general speech recognition algorithm to obtain original text data;

[0152] Among them, the general speech recognition algorithm can be a Wav2Vec algorithm, a DeepSpeech algorithm, a CNN model, an RNN model, etc., but is not limited thereto.

[0153] In step S602 of some embodiments, text preprocessing is performed on the original text data, which may include but is not limited to text cleaning, word segmentation processing, etc., but is not limited thereto.

[0154] Specifically, regular expressions or NLP libraries may be used to implement text cleaning of raw text data, wherein text cleaning includes but is not limited to removing punctuation marks, special symbols, stop words, and the like.

[0155] In addition, the original text data after text cleaning can be segmented by a word segmentation tool (such as Jieba tool, Hanlp tool) to divide the original text data into a sequence of multiple words or units to obtain the target text data.

[0156] In step S603 of some embodiments, feature extraction is performed on the target text data through a pre-trained text feature extraction model to obtain target text feature data; wherein the text feature extraction model is used to convert the text data into word vector data, that is, in the form of embedded features, to facilitate subsequent intent classification.

[0157] See also Figure 7 In some embodiments, step S604 may include but is not limited to steps S701 to S703:

[0158] Step S701, performing intent classification on the target text feature data to obtain a plurality of original intent data;

[0159] Step S702, calculating the confidence of each original intention data to obtain intention confidence data;

[0160] Step S703, based on the intention confidence data, filter out the data with the largest confidence value from the multiple original intention data to obtain the target intention data.

[0161] Steps S701 to S703 shown in the embodiment of the present application classify the target text feature data to obtain multiple possible original intent data, calculate the confidence of each original intent data, and finally screen out the intent with the largest confidence value as the target intent data, which can ensure the accuracy and reliability of intent recognition, and provide a more accurate and reliable basis for subsequent speech allocation and outbound call strategy adjustment, thereby optimizing the customer interaction experience and improving the intelligence level of smart outbound calls.

[0162] In step S701 of some embodiments, a preset intent recognition model may be used to classify the target text feature data to obtain a plurality of original intent data. Specifically, the intent recognition model may be a Bert model, a FastText model, a CNN model, an RNN model, etc., which needs to be selected in combination with the actual application scenario, but is not limited thereto.

[0163] In step S702 of some embodiments, the confidence calculation for each original intent data is also calculated by a preset intent recognition model. The specific calculation process needs to be determined according to the selection of the actual intent recognition model, but is not limited to this.

[0164] It should be noted that the intention confidence data is within a preset confidence interval, and the confidence interval can be a range from 0 to 1, wherein the larger the value of the confidence data is, the higher the credibility of the data is, and the more accurate the prediction is.

[0165] For example, the target text feature data is classified into two original intent data, which are:

[0166] The intention of not wanting to renew the subscription has a corresponding confidence value of 0.6.

[0167] Complaint intention, the corresponding intention confidence data is 0.8;

[0168] Based on the intent confidence data, the data with the largest confidence value is screened out from multiple original intent data, namely, the complaint intent, as the target intent data.

[0169] In some embodiments, the target intent data includes renewal intention, unwillingness to renew intention, and complaint intention.

[0170] As for other types of intent data, they can be set in combination with actual application scenarios, but are not limited to this.

[0171] If the target intention data is unwilling to renew, the target outbound call script is to persuade and guide renewal, for example: I understand your consideration very much, sir. Before making a decision not to renew, I would like to talk to you again about the features and benefits of our product, and this product is also very suitable for your needs. Please consider whether you need to renew.

[0172] If the target intention data is renewal intention, the target outbound call script is the script to guide renewal, for example: We provide you with a variety of renewal methods, including online renewal, telephone renewal and going to our business outlets. Among them, online renewal is the most convenient way. You only need to log in to our official website or use our mobile APP and follow the prompts to easily complete the renewal. Of course, if you encounter any problems during the operation, you can contact our customer service team at any time, and we will provide you with one-on-one guidance and help.

[0173] If the target intent data is a complaint intent, the target outbound call script is the script for handling complaints, for example: Hello, sir / madam, I am XX, the customer service manager of XX company. I am very sorry to bother you. I understand that you have recently made some feedback on our services. First of all, I would like to express my sincerest apologies to you on behalf of the company. We attach great importance to the opinions and feelings of every customer, especially long-term support customers like you. I would like to know first what specific communication problems you encountered during the application process? In this way, we can more accurately locate the problem and solve it for you as soon as possible. I am very sorry to give you such an experience, sir / madam. This is indeed a shortcoming in our process management and communication feedback. I have recorded your situation and will coordinate with the relevant departments immediately. I will ensure that your matter can be handled as a priority and give you a clear reply within 24 hours. If you have any questions or need further help during this period, you can contact me at any time. We express our apologies to you again and thank you for your support and trust.

[0174] It can be understood that the target intent data is the data with the largest confidence value selected from multiple original intent data. Therefore, the target intent data also has intent confidence data.

[0175] In step S504 of some embodiments, if the target intention data is renewal intention or unwillingness to renew intention, the outbound call mode maintains the original outbound call mode, that is, the intelligent outbound call mode, the current outbound call priority remains unchanged, and the current outbound call communication language is replaced with the target outbound call language;

[0176] If the target intent data is a complaint intent, and the intent confidence data of the target intent data exceeds the preset confidence threshold, the current outbound call mode will be converted from an intelligent outbound call mode to a manual outbound call mode, and the current outbound call external priority will remain unchanged, while the current outbound call communication language will be replaced with the target outbound call language.

[0177] In some embodiments, the preset confidence threshold may be 0.8 or 0.75, and needs to be set in combination with actual application scenarios, but is not limited thereto.

[0178] In step S105 of some embodiments, after obtaining the target outbound call strategy, a second outbound call may be made based on the target outbound call strategy at a preset interval period to improve the success rate of the outbound call.

[0179] See also Figure 8 The embodiment of the present application also provides an intelligent outbound calling device, which can implement the above-mentioned intelligent outbound calling method, and the device includes:

[0180] The outbound call task receiving module 801 is used to receive a target outbound call task; wherein the target outbound call task includes target customer information and an original outbound call strategy, the target customer information is used to indicate an outbound call recipient, and the original outbound call strategy is used to guide the execution of the target outbound call task;

[0181] The location analysis module 802 is used to perform location analysis on target customer information to obtain candidate location information;

[0182] The outbound call resource allocation module 803 is used to allocate outbound call resources based on the original outbound call strategy and the candidate location information to obtain target outbound call resources;

[0183] The outbound call execution module 804 is used to make an outbound call to the outbound call receiving object based on the original outbound call strategy and the target outbound call resources, and obtain the outbound call feedback data fed back by the outbound call receiving object; wherein the outbound call feedback data is used to indicate the call connection status and call content;

[0184] The outbound call strategy adjustment module 805 is used to adjust the original outbound call strategy based on the outbound call feedback data, obtain the target outbound call strategy, and make an outbound call based on the target outbound call strategy.

[0185] The specific implementation of the intelligent outbound calling device is basically the same as the specific implementation of the above-mentioned intelligent outbound calling method, and will not be repeated here.

[0186] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned intelligent outbound calling method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0187] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0188] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0189] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the intelligent outbound call method of the embodiment of this application;

[0190] Input / output interface 903, used to implement information input and output;

[0191] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0192] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0193] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0194] An embodiment of 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 above-mentioned intelligent outbound calling method is implemented.

[0195] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0196] The intelligent outbound call method and device, electronic device and storage medium provided by the embodiments of the present application receive a target outbound call task; wherein the target outbound call task includes target customer information and an original outbound call strategy, the target customer information is used to indicate the outbound call recipient, and the original outbound call strategy is used to guide the execution of the target outbound call task; the target customer information is positionally parsed to obtain candidate position information; outbound call resources are allocated based on the original outbound call strategy and the candidate position information to obtain target outbound call resources, thereby improving the efficiency and pertinence of the outbound call; an outbound call is made to the outbound call recipient based on the original outbound call strategy and the target outbound call resources, and at the same time, the outbound call feedback data fed back by the outbound call recipient is obtained; wherein the outbound call feedback data is used to indicate the call connection status and call content; the original outbound call strategy is adjusted based on the outbound call feedback data to obtain the target outbound call strategy, and the outbound call is made based on the target outbound call strategy, thereby dynamically optimizing the outbound call strategy, ensuring the effective use of resources and the improvement of call quality, and improving the success rate of intelligent outbound calls.

[0197] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0198] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0199] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0200] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0201] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0202] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0203] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0204] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0205] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0206] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0207] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. An intelligent outbound calling method, characterized in that: The method comprises: Receive a target outbound call task; wherein the target outbound call task includes target customer information and an original outbound call strategy, the target customer information is used to indicate an outbound call recipient, and the original outbound call strategy is used to guide the execution of the target outbound call task; Performing location analysis on the target customer information to obtain candidate location information; Allocate outbound call resources based on the original outbound call strategy and the candidate location information to obtain target outbound call resources; Based on the original outbound call strategy and the target outbound call resource, an outbound call is made to the outbound call receiving object, and outbound call feedback data fed back by the outbound call receiving object is obtained; wherein the outbound call feedback data is used to indicate the call connection status and call content; The original outbound call strategy is adjusted based on the outbound call feedback data to obtain a target outbound call strategy, and an outbound call is made based on the target outbound call strategy.

2. The method according to claim 1, characterized in that The number of the candidate location information is at least one, the original outbound call strategy includes the current outbound call location priority, and the outbound call resource allocation based on the original outbound call strategy and the candidate location information to obtain the target outbound call resource includes: For each piece of candidate location information, assigning a priority to the candidate location information to obtain location priority data; Filtering and obtaining target location information based on the current outbound call location priority, the location priority data and the candidate location information; Determine the original outbound call number pool according to the target location information; Allocate number resources according to the original outbound call number pool to obtain a target outbound call number; Allocate device resources based on the target outbound call number to obtain the target outbound call device; The target outbound call resource is obtained by combining the target outbound call number and the target outbound call device.

3. The method according to claim 2, characterized in that The adjusting the original outbound call strategy based on the outbound call feedback data to obtain a target outbound call strategy includes: If the call connection status indicates that the outbound call recipient has not connected the outbound call, a tag query is performed on the target outbound call resource to obtain target resource tag information; wherein the target resource tag information is used to indicate that the target outbound call resource is a trusted outbound call resource or an untrusted outbound call resource; Performing resource update on the target outbound call resource based on the target resource tag information; The current outbound call position priority in the original outbound call strategy is adjusted to obtain the target outbound call strategy.

4. The method according to claim 2, characterized in that: The step of obtaining the target location information based on the current outbound call location priority, the location priority data, and the candidate location information includes: Matching the current outbound call location priority with the location priority data to obtain priority matching data; If the priority matching data indicates that the current outbound call location priority does not match the location priority data, filtering the location with the highest priority from the candidate location information based on the location priority data to obtain the candidate location information; Based on the candidate location information, preset adjacent area information is acquired, and the adjacent area information is used as the target location information.

5. The method according to claim 1, characterized in that: The original outbound call strategy also includes the current outbound call communication words and the current outbound call mode. The outbound call strategy is adjusted based on the outbound call feedback data to obtain the target outbound call strategy, including: If the call connection state indicates that the outbound call recipient has connected the outbound call, the speaker of the call content is screened to obtain the target speaker's voice data; wherein the target speaker's voice data is the voice data of the outbound call recipient; Performing intent recognition on the target speaker's voice data to obtain target intent data; Based on the target intention data, the speech is allocated to obtain the target outbound call speech; Allocate an outbound calling method based on the target intention data to obtain a target outbound calling method; The current outbound call communication words in the original outbound call strategy are updated based on the target outbound call words, and the current outbound call mode in the original outbound call strategy is updated based on the target outbound call mode to obtain the target outbound call strategy.

6. The method according to claim 5, characterized in that The performing intention recognition on the target speaker's voice data to obtain target intention data includes: Converting the target speaker's speech data into text to obtain original text data; Performing text preprocessing on the original text data to obtain target text data; Performing feature extraction on the target text data to obtain target text feature data; The target text feature data is subjected to intent classification to obtain the target intent data.

7. The method according to claim 6, characterized in that The performing intent classification on the target text feature data to obtain the target intent data includes: Performing intent classification on the target text feature data to obtain a plurality of original intent data; Performing confidence calculation on each of the original intention data to obtain intention confidence data; Based on the intention confidence data, the data with the largest confidence value is filtered out from the multiple original intention data to obtain the target intention data.

8. An intelligent outbound calling device, characterized in that: The device comprises: An outbound call task receiving module, used for receiving a target outbound call task; wherein the target outbound call task includes target customer information and an original outbound call strategy, wherein the target customer information is used to indicate an outbound call receiving object, and the original outbound call strategy is used to guide the execution of the target outbound call task; A location analysis module, used to perform location analysis on the target customer information to obtain candidate location information; An outbound call resource allocation module, configured to allocate outbound call resources based on the original outbound call strategy and the candidate location information to obtain target outbound call resources; An outbound call execution module, used for making an outbound call to the outbound call receiving object based on the original outbound call strategy and the target outbound call resource, and obtaining outbound call feedback data fed back by the outbound call receiving object; wherein the outbound call feedback data is used to indicate the call connection status and call content; The outbound call strategy adjustment module is used to adjust the original outbound call strategy based on the outbound call feedback data, obtain a target outbound call strategy, and make an outbound call based on the target outbound call strategy.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

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

Images