Self-adaptive full-automatic intelligent outbound customer acquisition system and self-adaptive full-automatic intelligent outbound customer acquisition method

Abstract

The invention relates to the technical field of internet, in particular to a self-adaptive full-automatic intelligent outbound customer acquisition system and method.The self-adaptive full-automatic intelligent outbound customer acquisition system comprises an application layer, a service field layer, a basic field layer and an infrastructure layer, different outbound suppliers are automatically matched and dispatched through a set of configurable outbound system, the process and circulation efficiency are improved, and the service efficiency is improved. And functions of intelligent analysis, intelligent arrangement and the like are realized, so that more accurate and personalized efficient services are realized, and marketing of enterprises is assisted.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to an adaptive fully automatic intelligent outbound customer acquisition system and method. Background Art

[0002] With the development of technology and the continuous updating and iteration of Internet marketing methods, corporate outbound calling services also need to keep up with the trend of the times and master the latest marketing technologies to provide more accurate and personalized services.

[0003] While existing outbound call providers can meet basic marketing needs for businesses, they still require significant manual work (e.g., manual call target screening, call import, and call result analysis), resulting in low efficiency. Furthermore, due to the varying data formats and criteria used by various outbound call providers, downstream businesses are prone to errors, omissions, and numerous bugs when using these providers in combination. This hinders the proper implementation of marketing operations and creates a high risk of dependency on a single provider.

[0004] Therefore, it is necessary to design an adaptive, fully automatic, intelligent outbound customer acquisition system and method that can integrate various outbound call suppliers, improve the connection rate, achieve refined intelligent analysis, reduce manual participation, and improve usage accuracy and work efficiency. Summary of the Invention

[0005] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide an adaptive fully automatic intelligent outbound call customer acquisition system and method, which can integrate different outbound call suppliers, improve the connection rate, realize refined intelligent analysis, reduce manual participation, and improve usage accuracy and work efficiency.

[0006] In order to achieve the above objectives, the present invention provides an adaptive fully automatic intelligent outbound customer acquisition system, comprising an application layer, a business domain layer, a basic domain layer and an infrastructure layer; The application layer includes manual outbound call plans, periodic outbound call plans, and A / B outbound call plans; The A / B outbound calling plan is to use the same or different outbound calling strategies for two or more groups of people and compare the outbound calling results to evaluate the quality. The business domain layer includes a management module, a pre-processing module, a runtime module, and a post-processing module. The management module provides outbound call plan management and global configuration functions. The pre-processing module is used to build an outbound call target pool, filter and group outbound call targets, and intelligently orchestrate suppliers. The runtime module is used for runtime data collection and real-time monitoring. Intelligent orchestration, which uses a priority algorithm to determine the order and number of calls to various providers, with calls being made serially or in parallel; The basic domain layer includes the outbound call engine and the process engine. The outbound call engine is used to provide dynamic multi-vendor adaptation and scheduling capabilities. The process engine is used to provide process orchestration and business node flow capabilities. The outbound call engine communicates with the business domain layer in two directions via the outbound call bus, and the process engine communicates with the business domain layer in two directions via the process bus; The infrastructure layer includes outbound call providers and databases and indexes.

[0007] The post-processing module is used for refined intelligent analysis, and based on the analysis results, it determines potential customers, evaluates outbound call effectiveness, and scores supplier algorithms.

[0008] Identify potential customers as follows: Preset key information collection list and intended question list when making an outgoing call; If key information is collected during an outbound call, each type of information is parsed separately. If address information is collected, it is converted into a unified address code database using LBS search. If time information is collected, it is converted into a precise time database using regular expression matching. If price information is collected, it is converted into a precise price range database using AI semantic recognition. Determine the user's intention based on the result of the user's answer to the intention question. If the intention question is answered in the affirmative, the intention value is increased; if the intention question is answered in the negative, the intention value is decreased. The evaluation of outbound call effectiveness includes overall evaluation and sampling evaluation. The evaluation indicators of the overall evaluation are the connection rate, intention rate and key information collection rate. The evaluation indicators of the sampling evaluation are the key information collection accuracy and the accuracy of the intention question recognition. The specific algorithm scoring is: using the Topsis algorithm to score and rank all suppliers according to the evaluation indicators.

[0009] Refined intelligent analysis includes ASR semantic recognition, AI information extraction and LBS positioning.

[0010] The outbound call engine includes supplier scheduling, supplier adaptation, outbound call function routing and result notification.

[0011] The process engine includes node flow, process query, process orchestration and exception compensation.

[0012] An adaptive fully automatic intelligent outbound customer acquisition method, comprising the following steps: S1, user configuration triggers each outbound call plan at the application layer; S2, the system intelligently screens the outbound call targets based on the outbound call target pool; S3, the system intelligently matches the appropriate outbound call provider and arranges the outbound call process; S4, the supplier makes an outbound call and provides feedback on the call results; S5: The system collects outbound call result data and further processes it to extract feature information. Based on the feature information, the system classifies the outbound call recipients, identifies potential customers, and transmits them to downstream business systems. S6, based on the effect data obtained in S5, labels the outbound call pool and scores the suppliers, and the processing results are fed back to the subsequent outbound call plan to form a feedback loop.

[0013] An electronic device includes a processor and a memory for storing a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the above-mentioned method of adaptive fully automatic intelligent outbound customer acquisition.

[0014] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the above-mentioned adaptive fully automatic intelligent outbound customer acquisition method.

[0015] Compared with the prior art, the present invention has the following beneficial effects: Fully integrate the ability to orchestrate multiple outbound call providers, eliminating the issue of vendor dependency.

[0016] Overall improve the connection rate and intention rate of intelligent outbound calls.

[0017] Significantly reduce manual operations, lower labor costs, and improve the efficiency of intelligent outbound calls.

[0018] Refined intelligent analysis (ASR speech recognition, AI information extraction, LBS positioning, etc.) can fully understand customer needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the overall architecture of the present invention. DETAILED DESCRIPTION

[0020] The present invention will now be further described with reference to the accompanying drawings.

[0021] See also Figure 1 ,The present invention provides an adaptive fully automatic intelligent outbound customer acquisition system, including an application layer, a business domain layer, a basic domain layer and an infrastructure layer; The application layer includes manual outbound call plans, periodic outbound call plans, and A / B outbound call plans; The A / B outbound calling plan is to use the same or different outbound calling strategies for two or more groups of people and compare the outbound calling results to evaluate the quality. The business domain layer includes a management module, a pre-processing module, a runtime module, and a post-processing module. The management module provides outbound call plan management and global configuration functions. The pre-processing module is used to build an outbound call target pool, filter and group outbound call targets, and intelligently orchestrate suppliers. The runtime module is used for runtime data collection and real-time monitoring. Intelligent orchestration, which uses a priority algorithm to determine the order and number of calls to various providers, with calls being made serially or in parallel; The basic domain layer includes the outbound call engine and the process engine. The outbound call engine is used to provide dynamic multi-vendor adaptation and scheduling capabilities. The process engine is used to provide process orchestration and business node flow capabilities. The outbound call engine communicates with the business domain layer in two directions via the outbound call bus, and the process engine communicates with the business domain layer in two directions via the process bus; The infrastructure layer includes outbound call providers and databases and indexes.

[0022] The post-processing module is used for refined intelligent analysis, and based on the analysis results, it determines potential customers, evaluates outbound call effectiveness, and scores supplier algorithms.

[0023] Identify potential customers as follows: Preset key information collection list and intended question list when making an outgoing call; If key information is collected during an outbound call, each type of information is parsed separately. If address information is collected, it is converted into a unified address code database using LBS search. If time information is collected, it is converted into a precise time database using regular expression matching. If price information is collected, it is converted into a precise price range database using AI semantic recognition. Determine the user's intention based on the result of the user's answer to the intention question. If the intention question is answered in the affirmative, the intention value is increased; if the intention question is answered in the negative, the intention value is decreased. The evaluation of outbound call effectiveness includes overall evaluation and sampling evaluation. The evaluation indicators of the overall evaluation are the connection rate, intention rate and key information collection rate. The evaluation indicators of the sampling evaluation are the key information collection accuracy and the accuracy of the intention question recognition. The specific algorithm scoring is: using the Topsis algorithm to score and rank all suppliers according to the evaluation indicators.

[0024] Refined intelligent analysis includes ASR semantic recognition, AI information extraction and LBS positioning.

[0025] The outbound call engine includes supplier scheduling, supplier adaptation, outbound call function routing and result notification.

[0026] The process engine includes node flow, process query, process orchestration and exception compensation.

[0027] An adaptive fully automatic intelligent outbound customer acquisition method, comprising the following steps: S1, user configuration triggers each outbound call plan at the application layer; S2, the system intelligently screens the outbound call targets based on the outbound call target pool; S3, the system intelligently matches the appropriate outbound call provider and arranges the outbound call process; S4, the supplier makes an outbound call and provides feedback on the call results; S5: The system collects outbound call result data and further processes it to extract feature information. Based on the feature information, the system classifies the outbound call recipients, identifies potential customers, and transmits them to downstream business systems. S6, based on the effect data obtained in S5, labels the outbound call pool and scores the suppliers, and the processing results are fed back to the subsequent outbound call plan to form a feedback loop.

[0028] An electronic device includes a processor and a memory for storing a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the above-mentioned method of adaptive fully automatic intelligent outbound customer acquisition.

[0029] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the above-mentioned adaptive fully automatic intelligent outbound customer acquisition method.

[0030] Case study of using the fully automatic intelligent outbound customer acquisition system of the present invention to call out users who intend to rent a house: Integrated suppliers: Supplier A (NetEase Cloud Commerce), Supplier B (Yizhi Intelligence), Supplier C (Wisdom Tooth Technology) Integration process: 2.1 Adapt the three vendors to the outbound call engine and configure routing; 2.2 The process engine is configured with processing nodes for the three suppliers, and the processing logic of each supplier is isolated.

[0031] 2.3 The user interface triggers an outbound call. The business domain layer invokes the process engine based on the specific parameters of this outbound call and orchestrates the supplier process nodes according to the actual situation.

[0032] 2.4 During the execution of the process node, the outbound call engine is invoked and routed to a specific supplier for outbound call operations.

[0033] The above are merely preferred embodiments of the present invention and are intended to help understand the method and core concept of this application. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions based on the concept of the present invention fall within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

[0034] In the description of the present invention, it should be noted that the terms "upper", "lower", "inside", "outside", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limiting the present invention.

[0035] The present invention comprehensively solves the shortcomings of the existing technology, such as high dependence on outbound call service providers, incompatibility in data integration and adaptability, low efficiency and accuracy, etc., and realizes automatic adaptation and scheduling of different outbound call providers through a set of configurable outbound call systems, accelerates process and flow efficiency, and realizes functions such as intelligent analysis and intelligent orchestration, thus achieving more accurate and personalized efficient services and boosting corporate marketing.

Claims

1. An adaptive fully automatic intelligent outbound customer acquisition system, characterized by: Includes application layer, business domain layer, basic domain layer and infrastructure layer; The application layer includes manual outbound call plan, periodic outbound call plan and A / B outbound call plan; The A / B outbound calling plan is to use the same or different outbound calling strategies for two or more groups of people and compare the outbound calling results to evaluate their performance. The business domain layer includes a management module, a pre-processing module, a runtime module and a post-processing module; The management module is used to provide outbound call plan management and global configuration functions; the pre-processing module is used to build an outbound call object pool, screen and group outbound call objects, and intelligently arrange suppliers; the runtime module is used for runtime data collection and real-time monitoring; The intelligent scheduling determines the order and number of repetitions of calls to various suppliers through a priority algorithm, wherein the calls are serial calls or parallel calls; The basic domain layer includes an outbound call engine and a process engine; the outbound call engine is used to provide dynamic multi-supplier adaptation and scheduling capabilities; The process engine is used to provide process orchestration and business node flow capabilities; The outbound call engine communicates bidirectionally with the business domain layer via the outbound call bus, and the process engine communicates bidirectionally with the business domain layer via the process bus; The infrastructure layer includes outbound call providers and databases and indexes.

2. The adaptive fully automatic intelligent outbound customer acquisition system according to claim 1 is characterized in that: The post-processing module is used for refined intelligent analysis, and based on the analysis results, determines the intended customers, evaluates the outbound call effect and the supplier algorithm score; The identified potential customers are: Preset key information collection list and intended question list when making an outgoing call; If key information is collected during an outbound call, each type of information is parsed separately. If address information is collected, it is converted into a unified address code database using LBS search. If time information is collected, it is converted into a precise time database using regular expression matching. If price information is collected, it is converted into a precise price range database using AI semantic recognition. Determine the user's intention based on the result of the user's answer to the intention question. If the intention question is answered in the affirmative, the intention value is increased; if the intention question is answered in the negative, the intention value is decreased. The evaluation of outbound call effectiveness includes overall evaluation and sampling evaluation. The evaluation indicators of the overall evaluation are connection rate, intention rate and key information collection rate. The evaluation indicators of the sampling evaluation are key information collection accuracy and intention question intention identification accuracy. The algorithm scoring is specifically as follows: using the Topsis algorithm to score and rank all suppliers according to the evaluation indicators.

3. The adaptive fully automatic intelligent outbound customer acquisition system according to claim 2 is characterized in that: The refined intelligent analysis includes ASR semantic recognition, AI information extraction and LBS positioning.

4. The adaptive fully automatic intelligent outbound customer acquisition system according to claim 1 is characterized in that: The outbound call engine includes supplier scheduling, supplier adaptation, outbound call function routing and result notification.

5. The adaptive fully automatic intelligent outbound customer acquisition system according to claim 1 is characterized in that: The process engine includes node transfer, process query, process orchestration and exception compensation.

6. An adaptive fully automatic intelligent outbound customer acquisition method according to claim 1, characterized in that: The following steps are involved: S1, user configuration triggers each outbound call plan of the application layer; S2, the system intelligently screens the outbound call targets based on the outbound call target pool; S3, the system intelligently matches the appropriate outbound call provider and arranges the outbound call process; S4, the supplier makes an outbound call and provides feedback on the call results; S5: The system collects outbound call result data, further processes it to extract feature information, and classifies outbound call recipients based on the feature information, identifies potential customers, and transmits them to downstream business systems; S6, based on the effect data obtained in S5, the outbound call pool is labeled and the supplier is scored, and the processing results are fed back to the subsequent outbound call plan to form a feedback closed loop.

7. An electronic device, characterized in that: The method comprises a processor and a memory storing a program, the program comprising instructions which, when executed by the processor, cause the processor to perform the method according to claim 6.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method of claim 6.

Images