AI short message interaction method and device, equipment, medium and product
By introducing an automated SMS interaction process into the AI SMS system, using a strategy engine and natural language understanding model, the problems of low efficiency, error prone and resource consumption of traditional manual SMS are solved, and efficient and low-cost SMS services are realized. Improve customer experience and operational management capabilities.
Patent Information
- Application Number
- CN202410955071.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-19
AI Technical Summary
Traditional manual SMS sending has problems such as inefficiency, error-prone, high resource consumption, inability to scale, lack of personalization, difficulty in monitoring and reporting, and inability to achieve 24-hour service, resulting in high operating costs and inconsistent customer experience.
By introducing trigger, send, identify and reply steps into the AI SMS system, using the strategy engine and natural language understanding model to generate and send SMS, an automated SMS interaction process is realized, reducing manual intervention, and improving efficiency and accuracy.
Improves the efficiency and accuracy of SMS sending, reduces operating costs, improves customer experience, provides flexibility, privacy protection, cost-effectiveness and data management capabilities, suitable for large-scale and 24/7 service needs.
Smart Images

Figure CN118984442A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of outbound calls, and in particular to an interactive method, device, equipment, medium and product for AI text messaging. Background Art
[0002] In recent years, in customer contact scenarios such as sales, customer service, and after-sales, although traditional manual outbound calls have obvious advantages in emotional intelligence, handling complex cases, and negotiation skills, there is also a vicious cycle of rising labor costs. The rapid increase in labor costs, frequent employee turnover, and high service training difficulties have caused rising labor costs. The manpower hours and response capabilities are limited. It is difficult for manpower to cover all customer inquiries at all times or to respond quickly to complex and massive information. Service demand has peaks and troughs. Due to factors such as time and events, customer demand will fluctuate greatly, resulting in insufficient manpower at peaks and excess manpower at troughs. The quality of manual services varies. Due to individual differences in manual services, the quality is uneven and difficult to be completely unified.
[0003] In the era of intelligence, with the development of AI technology, we hope that combined with the convenience brought by the AI wave, AI outbound calls can help companies improve efficiency, reduce costs, and enhance customer experience. AI outbound phone communication is very efficient, but it also has limitations. For example, in scenarios where it is inconvenient for customers to answer the phone, text messages can make up for the shortcomings of AI outbound calls, but manual text messages, which refer to the method of manually writing and sending text messages instead of automated systems, have the following disadvantages:
[0004] Inefficiency: Manual text messaging requires manual input of content, which is time-consuming. Especially when the same or similar messages need to be sent to a large number of users, the efficiency is much lower than that of the automated text messaging system.
[0005] Error-prone: Manual operation is prone to input errors, such as wrong numbers, wrong information content, etc., which may lead to failure in sending information or miscommunication, affecting communication effectiveness;
[0006] High resource consumption: Manual SMS sending requires human resources. Large-scale SMS sending tasks require more human resources, which increases the operating costs of the enterprise.
[0007] Unable to scale: With tens of thousands of users, manual delivery is difficult to achieve efficient and large-scale operations, which limits the service scope and response speed;
[0008] Lack of personalization: Manual delivery makes it difficult to customize personalized information for each recipient, which may affect user experience and effectiveness in marketing and service scenarios;
[0009] Difficulty in monitoring and reporting: Manual delivery makes it difficult to systematically track delivery status, count delivery results, and analyze data, which is not conducive to subsequent optimization and decision-making;
[0010] Unsustainability: With the growth of business volume, the manual SMS sending method is unsustainable and cannot meet the needs of business expansion;
[0011] Time limit: Manual operation is subject to working hours and cannot provide 24-hour service, which may miss the best time to send urgent or important information;
[0012] Poor user experience consistency: Different people may have different styles and quality when writing text messages, resulting in inconsistent user experience.
[0013] To sum up, manual SMS sending has obvious defects in efficiency, cost, scalability, personalization and data management. With the advancement of technology, more and more companies and individuals tend to adopt automated SMS platforms to improve efficiency and effectiveness.
[0014] It can be seen that whether it is possible to provide an improved interactive technology for AI text messages based on the deficiencies in the existing technology has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention
[0015] Problems to be solved by the invention
[0016] The purpose of the present invention is to overcome the defects of the prior art and provide an improved interactive method, device, equipment and medium for AI text messages. The improved interactive method, device, equipment and medium for AI text messages provided by the present invention solve the technical problems of low efficiency, easy error and high resource consumption of traditional manual text messages, reduce operating costs and improve customer experience.
[0017] Methods for solving problems
[0018] The first aspect of the present invention relates to an interactive method for AI short messages, comprising the following steps:
[0019] The triggering step triggers the opening SMS sending process through the contact information of the upstream business system, creates an SMS session and returns the session ID to the business system;
[0020] The sending step is to call the strategy engine to obtain parameter information of the opening message according to the contact information, generate the opening message according to the parameter information and send it to the customer;
[0021] Identification step: after receiving the customer’s reply to the opening SMS, call the understanding model to obtain the intent identification label;
[0022] In the reply step, the policy engine is called to obtain the parameter information of the reply SMS according to the intent recognition tag and the basic information of the customer, and a reply SMS is generated and sent to the customer.
[0023] Preferably, the contact information includes: business scenario and contact person.
[0024] Preferably, the parameter information of the opening remarks SMS includes: an opening remarks SMS template number and opening remarks SMS template parameters.
[0025] Preferably, the understanding model is a natural language understanding model.
[0026] Preferably, the basic information of the customer includes: the customer's historical phone call information, the customer's historical text message content context, the customer's overdue information, the customer's historical loan information, and the customer's registration portrait.
[0027] Preferably, the predetermined historical data includes a user blacklist.
[0028] A second aspect of the present invention relates to an AI short message interaction device, comprising:
[0029] A trigger module is used to trigger the opening SMS sending process through the contact information of the upstream business system, create an SMS session and return the session ID to the business system;
[0030] A sending module, used to call the strategy engine to obtain parameter information of the opening message according to the contact information, generate the opening message according to the parameter information and send it to the customer;
[0031] The recognition module is used to call the understanding model to obtain the intent recognition label after receiving the customer's reply to the opening text message;
[0032] The reply module is used to call the strategy engine to obtain the parameter information of the reply SMS according to the intent recognition tag and the basic information of the customer, generate the reply SMS and send it to the customer.
[0033] The third aspect of the present invention relates to a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the interaction method of the first aspect when executing the computer program.
[0034] A fourth aspect of the present invention relates to a computer-readable storage medium having a computer program stored thereon, which implements the steps of the interactive method of the first aspect when the computer program is executed by a processor.
[0035] A fifth aspect of the present invention relates to a computer program product, comprising a computer program, which implements the steps of the interaction method of the first aspect when the computer program is executed by a processor.
[0036] Effects of the Invention
[0037] The improved interaction method provided by the present invention solves the technical problems of low efficiency, easy errors and high resource consumption of traditional manual text messages, reduces operating costs and improves customer experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 It is a flowchart of the interaction method of the first embodiment of the present invention.
[0039] Figure 2 This is a structural diagram of a computer device according to a third embodiment of the present invention.
[0040] Figure 3 This is a timing diagram of the main nodes of the specific interaction of Example 1. DETAILED DESCRIPTION
[0041] Hereinafter, the interactive method involved in the present invention will be described in detail.
[0042] Figure 1 FIG. 1 is a flow chart of an interactive method according to a first embodiment of the present invention. Figure 1 As shown, the specific process of the interactive method is to first perform a triggering step (step S100), trigger the opening SMS sending process through the contact information of the upstream business system, create an SMS session and return the ID of the session to the business system. Then perform a sending step (step S101), call the strategy engine to obtain the parameter information of the opening SMS according to the contact information, generate the opening SMS according to the parameter information and send it to the customer. Then perform an identification step (step S102), after receiving the customer's reply to the opening SMS, call the understanding model to obtain the intent recognition tag. Finally, perform a reply step (step S103), call the strategy engine to obtain the parameter information of the reply SMS according to the intent recognition tag and the customer's basic information, generate the reply SMS and send it to the customer.
[0043] Step S100 is explained. Specifically, the interactive method provides an http interface to expose the interactive SMS function, which is triggered by the upstream business system. The interactive SMS creates a session and returns the session ID to the business system. The business system can query all SMS sending records and reply records under the current session based on the session ID, and can also manage the validity period of the current session.
[0044] Step S101 is explained. Specifically, the decision engine is called according to the contact information, the decision engine outputs the opening SMS template number and SMS template parameters as the parameter information of the opening SMS, and the interactive SMS platform calls the downstream SMS channel to send the opening SMS to the customer. The contact information includes information such as business scenarios and contacts, but is not limited thereto.
[0045] Step S102 is explained. Specifically, after receiving the text message, the customer replies to the text message. After receiving the content of the customer's reply, the context communication content is assembled, and the understanding model returns the intent label of the reply by calling the http interface exposed by the understanding model service. It is usually a set, and the set stores label elements. When applied to the financial field, the label elements are, for example, "promise to repay" and "inquire about overdue information". The understanding model is preferably a natural language understanding (NLU) model, but is not limited to this.
[0046] Step S103 is explained. Specifically, the intent label returned by the understanding model is obtained, and the basic information of the customer is queried at the same time. The basic information is preferably: historical phone call information, such as the number of phone calls on the day; the context of the text messages sent and replied by the customer on the day; the customer's registration portrait and other information. When applied to the financial field, the basic information can also be preferably: the customer's overdue information, such as the overdue amount and number of days; the customer's historical loan information, etc. The basic information is used as an input parameter to call the decision system. The decision system returns the SMS template number and SMS template parameters of the reply customer as the parameter information of the reply SMS based on the input elements, and calls the downstream SMS channel to reply to the customer.
[0047] It can be seen that the interactive method according to the first embodiment of the present invention solves the technical problems of low efficiency, easy errors and high resource consumption of traditional manual text messages, reduces operating costs and improves customer experience. Specifically, the interactive method of the first embodiment achieves the following advantages of AI interactive text messages:
[0048] Flexibility of non-instantaneous interactions: Users can read and respond to text messages at their convenience, without the need for an immediate response, which provides users with greater flexibility and control, especially suitable for busy customers or those in different time zones;
[0049] Privacy protection: SMS is a more private form of communication, and users may feel more comfortable and respectful of their personal space than receiving a phone call. Especially when dealing with sensitive information, SMS communication may be seen as less intrusive;
[0050] Cost-effectiveness: SMS is usually cheaper than phone calls, especially for large-scale customer outreach or notifications. AI interactive SMS can reach a wide range of target groups at a lower cost.
[0051] Reading rate and retention: Compared with phone calls, which may be hung up or missed, once a text message is delivered, users tend to check it when they are free, which increases the chances of the message being read. Text messages can also be saved for future reference, which improves the retention of the information;
[0052] Reduce interruptions: AI outbound calls may disturb users at inappropriate times, while SMS allows users to choose when to check and reply, reducing user disgust and potential negative feedback;
[0053] Multitasking: Users can do other activities while reading and replying to text messages, which does not require concentration like answering a phone call, which improves user convenience and efficiency;
[0054] Data tracking and analysis: SMS interactions are easy to record and analyze. Companies can collect data such as user response time and click-through rate to optimize subsequent marketing strategies or service processes.
[0055] Wide applicability: In some areas where network coverage is unstable or voice communication is inconvenient, SMS may be a more reliable way of communication, ensuring the success rate of information delivery.
[0056] To sum up, the AI interactive SMS system involved in the interaction method of the first embodiment is superior to the AI outbound call system in specific scenarios due to its flexibility, cost efficiency, privacy friendliness and wide applicability, especially when users need to independently control the interaction rhythm, reduce costs or reach specific user groups.
[0057] The interaction method of the first implementation mode is specifically described below through an example.
[0058] Embodiment 1:
[0059] like Figure 3 As shown, first, the process of sending the opening SMS is triggered by the upstream business system, and the interactive SMS platform creates a SMS session and returns the ID of the session to the business system. Then the interactive SMS platform calls the strategy engine to determine the template of the opening SMS. The strategy engine returns the parameter information of the opening SMS based on the contact information. The interactive SMS platform generates the opening SMS based on the parameter information and calls the downstream SMS channel to send it to the customer. The SMS channel sends the opening SMS to the customer's mobile terminal. The customer replies to the opening SMS through the mobile terminal. The SMS channel sends the reply content to the interactive SMS platform. The interactive SMS platform calls the NLU model for intent recognition, obtains the intent recognition tag, calls the strategy engine, introduces the intent recognition tag and the current customer's historical SMS sending situation (such as the number of times it is sent) and the number of days the customer is overdue, etc., obtains the parameter information of the reply SMS, generates the reply SMS, and calls the downstream SMS channel to send it to the customer. The SMS channel sends the reply SMS to the customer's mobile terminal.
[0060] The interactive device for AI SMS of the second embodiment of the present invention includes: a trigger module, which is used to trigger the opening SMS sending process through the contact information of the upstream business system, create an SMS session and return the ID of the session to the business system; a sending module, which is used to call the strategy engine to obtain the parameter information of the opening SMS according to the contact information, generate the opening SMS according to the parameter information and send it to the customer; an identification module, which is used to call the understanding model to obtain the intent recognition tag after receiving the customer's reply to the opening SMS; a reply module, which is used to call the strategy engine to obtain the parameter information of the reply SMS according to the intent recognition tag and the customer's basic information, generate the reply SMS and send it to the customer. The interactive device corresponds to the interactive method of the first embodiment, so the various deformation methods in the first embodiment are also applicable to the second embodiment, which will not be repeated here.
[0061] As described above, the interactive device according to the second embodiment of the present invention solves the technical problems of low efficiency, easy errors and high resource consumption of traditional manual text messages, reduces operating costs and improves customer experience.
[0062] A third embodiment of the present invention provides a computer device, the internal structure diagram of which can be shown as follows: Figure 2 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to connect to an external device to exchange data with the external device. When the computer program is executed by the processor, the interaction method involved in the first embodiment of the present invention is implemented.
[0063] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0064] A fourth embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and a processor implements the interactive method involved in the first embodiment of the present invention when executing the computer program.
[0065] A fifth embodiment of the present invention provides a computer program product, including a computer program. When a processor executes the computer program, the interactive method involved in the first embodiment of the present invention is implemented.
[0066] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0067] Industrial Applicability
[0068] The interactive method, apparatus, computer device, storage medium and computer program product involved in the present invention solve the technical problems of low efficiency, easy error and high resource consumption of traditional manual text messages, reduce operating costs and improve customer experience.
[0069] While the present invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims
1. An interactive method of AI text messages, It is characterized in that The following steps are involved: The triggering step triggers the opening SMS sending process through the contact information of the upstream business system, creates an SMS session and returns the session ID to the business system; The sending step is to call the strategy engine to obtain parameter information of the opening message according to the contact information, generate the opening message according to the parameter information and send it to the customer; Identification step: after receiving the customer’s reply to the opening SMS, call the understanding model to obtain the intent identification label; In the reply step, the policy engine is called to obtain the parameter information of the reply SMS according to the intent recognition tag and the basic information of the customer, and a reply SMS is generated and sent to the customer.
2. The interactive method according to claim 1, It is characterized in that Contact information includes: business scenarios and contacts.
3. The interactive method according to claim 1, It is characterized in that The parameter information of the opening remarks SMS includes: the opening remarks SMS template number and the opening remarks SMS template parameters.
4. The interactive method according to claim 1, It is characterized in that The understanding model is a natural language understanding model.
5. The interactive method according to claim 1, It is characterized in that The customer's basic information includes: the customer's historical phone call information, the customer's historical text message content context, the customer's overdue information, the customer's historical loan information, and the customer's registration profile.
6. The interactive method according to claim 1, It is characterized in that The parameter information of the reply SMS includes: reply SMS template number and reply SMS template parameters.
7. An interactive device for AI text messaging, It is characterized in that include: The trigger module is used to trigger the opening SMS sending process through the contact information of the upstream business system, create an SMS session and return the ID of the session to the business system; A sending module, used to call the strategy engine to obtain parameter information of the opening message according to the contact information, generate the opening message according to the parameter information and send it to the customer; The recognition module is used to call the understanding model to obtain the intent recognition label after receiving the customer's reply to the opening text message; The reply module is used to call the strategy engine to obtain the parameter information of the reply SMS according to the intent recognition tag and the basic information of the customer, generate the reply SMS and send it to the customer.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the interaction method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the interaction method according to any one of claims 1 to 6 are implemented.
10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the interaction method according to any one of claims 1 to 6 are implemented.
