Intelligent calling method and device and electronic equipment
By automatically obtaining and utilizing information from enterprise applications and applets in the RPA system, the existing automatic outgoing call solutions are solved, and efficient and flexible call task execution is achieved.
Patent Information
- Application Number
- CN202410847718.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-27
- Publication Date
- 2025-02-18
AI Technical Summary
The existing automatic outgoing call solution requires linking multiple systems, which is costly and has a long version change cycle, which affects flexibility and efficiency.
Through the robot process automation (RPA) system, the enterprise can obtain the login information on the target application and applet, automatically log in and obtain customer information, determine the target customer and call content to be called, generate and execute call tasks, and obtain call results.
Improve the flexibility of call tasks, reduce costs, and ensure the efficiency and reliability of the call process.
Smart Images
Figure CN119484688A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of automation technology, and in particular to an intelligent calling method, device and electronic device. Background Art
[0002] At present, automatic outbound calling solutions often involve system modifications, for example: developing monitoring for changes in certain data items, and linking to the outbound calling system for outbound calls. The above solutions often require the linkage of multiple systems for modification, which is costly. When there is a need to change data items, the version change cycle is long. In addition, outbound calls require the user to install telephone lines and pay call charges, which is costly. Therefore, how to improve the efficiency and flexibility of the outbound calling process and reduce the cost of the outbound calling process has become an urgent problem to be solved. Summary of the invention
[0003] The present disclosure provides an intelligent calling method, device, electronic device, computer-readable storage medium and computer program product to at least solve the problems of low flexibility and efficiency and high cost in the outbound calling process in the related art.
[0004] The technical solution of the present disclosure is as follows:
[0005] According to a first aspect of an embodiment of the present disclosure, an intelligent calling method is provided, which is executed by a robotic process automation (RPA) system, and the method includes: obtaining first login information of an enterprise on a target application, logging in to an enterprise client based on the first login information, and obtaining customer information of a customer from the enterprise client; obtaining second login information of the enterprise on a target applet, logging in to the target applet based on the second login information, and obtaining the enterprise information of the customer from the target applet; determining a target customer to be called and a target call content based on the enterprise information of the customer; generating a call task based on the customer information and the target call content of the target customer and executing the call task to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer.
[0006] According to a second aspect of an embodiment of the present disclosure, there is provided an intelligent calling device, which is applied to a robotic process automation (RPA) system, and the device includes: a first acquisition module, which is used to acquire first login information of an enterprise on a target application, log in to an enterprise client based on the first login information, and acquire customer information of the customer from the enterprise client; a second acquisition module, which is used to acquire second login information of the enterprise on a target applet, log in to the target applet based on the second login information, and acquire the enterprise information of the customer from the target applet; a determination module, which is used to determine a target customer to be called and a target call content based on the enterprise information of the customer; a generation module, which is used to generate a call task based on the customer information and the target call content of the target customer and execute the call task to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer.
[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the intelligent calling method described in the first aspect.
[0008] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the intelligent call method described in the first aspect.
[0009] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the intelligent calling method described in the first aspect is implemented.
[0010] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects: by obtaining the first login information of the enterprise on the target application, logging in to the enterprise client based on the first login information, and obtaining the customer's customer information from the enterprise client, obtaining the second login information of the enterprise on the target applet, logging in to the target applet based on the second login information, and obtaining the customer's enterprise information from the target applet, determining the target customer to be called and the target call content according to the customer's enterprise information, generating a call task and executing the call task based on the target customer's customer information and the target call content to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer. Therefore, the present disclosure generates a call task through the target customer's customer information and the target call content, thereby improving the flexibility of generating call tasks, and the call task is executed by the RPA system, reducing the cost during the call process, and ensuring the efficiency and reliability during the call process.
[0011] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.
[0013] Figure 1 It is a flowchart of an intelligent calling method according to the first embodiment of the present disclosure.
[0014] Figure 2 It is a flowchart of an intelligent calling method according to the second embodiment of the present disclosure.
[0015] Figure 3 It is a structural diagram of an intelligent call system according to the fourth embodiment of the present disclosure.
[0016] Figure 4 is a block diagram of an intelligent calling device according to a first embodiment of the present disclosure.
[0017] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0018] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.
[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure 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 interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0020] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations.
[0021] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards. "
[0022] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.
[0023] Figure 1 It is a flowchart of an intelligent calling method according to the first embodiment of the present disclosure.
[0024] like Figure 1 As shown, the intelligent calling method of the first embodiment of the present disclosure is executed by a robot process automation (RPA) system, and includes the following steps:
[0025] In step S101, first login information of the enterprise on the target application is obtained, the enterprise client is logged in based on the first login information, and the customer information of the customer is obtained from the enterprise client.
[0026] It should be noted that this application does not limit the type of target application and it can be selected according to actual conditions.
[0027] Optionally, the target application may be WeChat for Business.
[0028] The first login information may be the account number, key, and other related login information required to log in to the enterprise client.
[0029] In the embodiment of the present disclosure, after the first login information is acquired, the enterprise client may be logged in based on the first login information.
[0030] For example, for Company A, when the target application is WeChat for Enterprise, after obtaining the first login information of Company A on the target application, the Robot Process Automation (RPA) system can log in to the enterprise client of Company A based on the first login information.
[0031] Among them, in the intelligent calling scenario, enterprises usually conduct business with customers, so enterprises and customers are often friends with each other.
[0032] In the embodiments of the present disclosure, the present disclosure does not limit the specific method of obtaining the customer information of the customer from the enterprise client, and it can be selected according to the actual situation.
[0033] Optionally, a first page including customer information in the client can be determined, and the first page can be entered, a page element on the first page can be located, and the located first page element can be extracted from the first page, wherein the first page element carries unstructured customer information, and the unstructured customer information can be structured to obtain the customer information of the customer.
[0034] Among them, customer information includes but is not limited to customer name, customer contact information and other information.
[0035] In step S102, the second login information of the enterprise on the target mini-program is obtained, the target mini-program is logged in based on the second login information, and the enterprise information of the customer is obtained from the target mini-program.
[0036] It should be noted that this application does not limit the type of target applet, which can be selected according to actual conditions.
[0037] Optionally, the target mini program may be a mini program that can obtain enterprise information, for example, the target mini program may be a mini program corresponding to the National Enterprise Credit Information Publicity System.
[0038] The second login information may be the account number, key, and other related login information required to log in to the target applet.
[0039] In the embodiment of the present disclosure, after the second login information is acquired, the target applet may be logged in based on the second login information.
[0040] For example, for Enterprise A, when the target mini program is the mini program corresponding to the National Enterprise Credit Information Publicity System, after obtaining the second login information of Enterprise A on the mini program corresponding to the National Enterprise Credit Information Publicity System, the RPA system can log in to the mini program corresponding to the National Enterprise Credit Information Publicity System based on the second login information.
[0041] In the embodiments of the present disclosure, the present disclosure does not limit the specific method of obtaining the customer's enterprise information from the target mini program, and it can be selected according to the actual situation.
[0042] Optionally, a second page including corporate information can be determined within the target mini-program, and the second page can be entered to locate page elements on the second page, and the located second page elements can be extracted from the second page, wherein the second page elements carry unstructured corporate information, and the unstructured corporate information is structured to obtain the customer's corporate information.
[0043] Among them, corporate information includes but is not limited to the company's annual report information, personnel information, business information, business information and other information.
[0044] In step S103, the target customer to be called and the target call content are determined according to the customer's enterprise information.
[0045] In the disclosed embodiment, after the enterprise information of the customer is acquired, the target customer to be called and the target call content can be determined according to the enterprise information of the customer.
[0046] Optionally, the customer's business information, transaction information and operating information can be obtained based on the customer's corporate information, and the customer's call content can be determined based on the business information, transaction information and operating information and displayed on the front-end interactive interface, user interaction operations can be received, and based on the user interaction operations, the target customer to be called and the target call content of the target customer can be determined from the customers.
[0047] For example, the business status information and financial status information of the enterprise can be determined based on business information, transaction information and operating information to obtain the customer's call content (text1, text2...textn), and by receiving user interaction operations (check operations, click operations, etc.), the target customers to be called and the target call content of the target customers can be determined from the customers (co1, co2...con).
[0048] In step S104, based on the customer information of the target customer and the target call content, a call task is generated and executed to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer.
[0049] In an embodiment of the present disclosure, configured speech synthesis parameters can be obtained, speech synthesis can be performed on the target call content according to the speech synthesis parameters, the call audio file of the target customer can be obtained and stored, the customer information of the target customer and the storage location of the call audio file can be associated, and based on the customer information of the target customer and the corresponding storage location, a call task for the target user can be generated.
[0050] Furthermore, after the call task is generated, the call task may be executed to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer.
[0051] According to the intelligent calling method provided by the embodiment of the present disclosure, by obtaining the first login information of the enterprise on the target application, logging in to the enterprise client based on the first login information, and obtaining the customer's customer information from the enterprise client, obtaining the second login information of the enterprise on the target applet, logging in to the target applet based on the second login information, and obtaining the customer's enterprise information from the target applet, according to the customer's enterprise information, determining the target customer to be called and the target call content, based on the customer information of the target customer and the target call content, generating a call task and executing the call task to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer, thereby, the present disclosure generates a call task through the customer information and target call content of the target customer, improves the flexibility of generating call tasks, and the call task is executed by the RPA system, reducing the cost during the call process, and ensuring the efficiency and reliability during the call process.
[0052] Figure 2 It is a flowchart of an intelligent calling method according to the second embodiment of the present disclosure.
[0053] like Figure 2 As shown, the intelligent calling method of the second embodiment of the present disclosure includes the following steps:
[0054] In step S201, first login information of the enterprise on the target application is obtained, and the enterprise client is logged in based on the first login information.
[0055] The relevant contents of step S201 can be found in the above embodiment and will not be repeated here.
[0056] As a possible implementation method, based on the above implementation, the specific process of obtaining the customer information of the customer from the enterprise client in step S101 includes steps S202 to S204:
[0057] In step S202, a first page including customer information in the client is determined, and the first page is entered.
[0058] In the embodiment of the present disclosure, when logging into the enterprise client based on the first login information, the first page including the customer information in the client can be determined and the first page can be entered.
[0059] The first page including the client information in the client may be a client communication list, for example, a client communication friend list.
[0060] In step S203, the page element on the first page is located, and the located first page element is extracted from the first page, wherein the first page element carries unstructured customer information.
[0061] Optionally, the page loading status of the client may be monitored, and in response to the page loading of the client being completed, a page jump process to enter the first page is determined, and a page adjustment process is executed to enter the first page.
[0062] For example, an RPA script can be pre-written based on the RPA controller in the RPA system. To simplify development and deployment, for example, to reduce page jumps and skip the more complex dynamic QR code verification stage, you can call components such as rpa.onWindowReConnect(), rpa.setStrogeSync(), and rpa.request() in RPA to perform actions such as page startup, parameter entry, and window event monitoring. The page elements on the first page can be located based on the User Interface Automation tool, and the located first page elements can be extracted from the first page one by one.
[0063] In step S204, the unstructured customer information is structured to obtain the customer information of the customer.
[0064] For example, you can call the WorkBooks and ExcelApp related components in the RPA controller to structure the unstructured customer information and obtain the customer's customer information.
[0065] In step S205, the second login information of the enterprise on the target mini-program is obtained, and the target mini-program is logged in based on the second login information.
[0066] The relevant contents of step S205 can be found in the above embodiment and will not be described again here.
[0067] As a possible implementation method, based on the above implementation, the specific process of obtaining the customer's enterprise information from the target mini program in step S102 includes steps S206 to S208:
[0068] In step S206, a second page including enterprise information in the target applet is determined, and the second page is entered.
[0069] In an embodiment of the present disclosure, after logging into the target applet based on the second login information, a second page including enterprise information in the target applet can be determined and the second page can be entered.
[0070] In step S207, the page element on the second page is located, and the located second page element is extracted from the second page, wherein the second page element carries unstructured enterprise information.
[0071] Optionally, an RPA script can be pre-written based on the RPA controller in the RPA system. In order to simplify development and deployment, for example, to reduce page jumps and skip the more complex dynamic QR code verification stage, the target application can be used as a data source for obtaining the customer's corporate information. The rpa.onWindowReConnect(), rpa.setStrogeSync(), rpa.request() and other components in the RPA can be called to start the target applet, enter parameters, and monitor window events, etc., and the elements of the second page can be located based on the user interface automation tool, and the second page elements (data fields related to corporate information) can be extracted one by one according to the pre-configured corporate information table.
[0072] In step S208, the unstructured enterprise information is structured to obtain the customer's enterprise information.
[0073] In the disclosed embodiment, after unstructured enterprise information is acquired, target enterprise information can be determined from the unstructured candidate enterprise information, and the target enterprise information can be structured to obtain structured customer enterprise information.
[0074] Optionally, a preconfigured enterprise information table to be filled can be obtained, and based on the enterprise information table to be filled, the target enterprise information can be determined from the candidate enterprise information, the target format of the target enterprise information can be determined from the enterprise information template, and the target candidate enterprise information can be structured based on the target format to obtain the customer's enterprise information.
[0075] For example, based on the preset conversion rules, you can call the WorkBooks and ExcelApp related components in the RPA controller to structure the unstructured enterprise information line by line to obtain structured customer enterprise information.
[0076] As a possible implementation method, based on the above implementation, the specific process of determining the target customer to be called and the target call content according to the customer's corporate information in step S103 includes steps S209 to S2011:
[0077] In step S209, the customer's business information, transaction information and operating information are obtained based on the enterprise information.
[0078] Different call contents can be determined according to different business information, transaction information and operating information of customers.
[0079] In step S2010, the content of the customer's call is determined based on the business information, transaction information and operating information and displayed on the front-end interactive interface.
[0080] It should be noted that the business information can be used to determine the specific business transactions between the customer and the enterprise, the transaction information can be used to determine the customer's operating losses, and the business information can be used to determine the status of the customer's business license (normal, changed, or cancelled). Accordingly, the customer's call content can be determined based on the business information, transaction information, and business information, where the call content is a call question list or a call script list.
[0081] In step S2011, a user interaction operation is received, and based on the user interaction operation, a target customer to be called and a target call content of the target customer are determined from the customers.
[0082] It should be noted that customer information and the content of the customer's call are displayed on the front-end interactive interface, and the target customer to be called and the target call content of the target customer are determined from the customers based on the received user operations (such as click operations, check operations, etc.).
[0083] As a possible implementation method, based on the above implementation, the specific process of generating a call task based on the customer information of the target customer and the target call content in step S104 includes steps S2012 to S2013:
[0084] In step S2012, the configured speech synthesis parameters are obtained, speech synthesis is performed on the target call content according to the speech synthesis parameters, the call audio file of the target customer is obtained and the call audio file is stored.
[0085] It should be noted that the present disclosure does not limit the setting of the configured speech synthesis parameters, which can be set according to actual conditions.
[0086] Optionally, the speech synthesis parameters may be target call content tex, language lan (default 0-Chinese), voice per (default 1-standard male voice), speaking speed spd (speaking speed 0-15, default 5-medium speaking speed), and volume vol (volume 0-9, default 5-medium volume).
[0087] In the embodiment of the present disclosure, after the configured speech synthesis parameters are obtained, speech synthesis can be performed on the target call content according to the speech synthesis parameters to obtain the call audio file of the target customer.
[0088] For example, after obtaining the configured speech synthesis parameters, the text to speech (TTS) engine can be integrated to build a speech synthesis module. Based on the speech recognition model (WaveNet) and automatic speech recognition (ASR) technology, text recognition, audio waveform generation and automatic speech synthesis can be achieved to obtain the call audio file of the target customer.
[0089] Furthermore, after acquiring the call audio file of the target customer, the call audio file may be stored in a storage location (storage path) of the RPA server.
[0090] In step S2013, the customer information of the target customer and the storage location of the call audio file are associated, and based on the customer information of the target customer and the corresponding storage location, a call task of the target user is generated.
[0091] Optionally, based on the customer information of the target customer, the target call content and the storage location, a waiting-to-call information table is generated, the customer information and the storage location of the target customer are read from the waiting-to-call information table, and a call task is generated.
[0092] As a possible implementation method, based on the above implementation, the specific process of executing the call task in step S104 to obtain the call result table includes steps S2014 to S2016:
[0093] In step S2014, a call is initiated to the target customer according to the preset call strategy and call task.
[0094] The call strategy includes but is not limited to the outbound call waiting time, the number of recalls, etc.
[0095] It should be noted that, in order to optimize resource utilization, after initiating a call to a target customer, if no reply (response) from the target customer is received after the outbound call waiting time has expired, the process of initiating a call to the target customer is terminated.
[0096] It should be noted that the number of recalls may be preset according to the importance levels of the pre-classified customers.
[0097] In the embodiment of the present disclosure, after the call task of the target user is generated, a call can be initiated to the target customer according to the preset call strategy and call task.
[0098] For example, RPA schedules the enterprise's target application to initiate calls to target customers according to preset call strategies and call tasks. That is, through the enterprise's target application, voice broadcasts are initiated to target customers one by one according to the target call content in the target call task.
[0099] In step S2015, the target customer's reply voice is collected, and the reply content is extracted from the reply voice.
[0100] For example, a call is initiated to the target user, and after the call process ends, the customer's response data (reply voice) can be returned, and the speech-to-text component in the RPA component library is called to extract the reply content from the collected reply voice of the target customer.
[0101] In step S2016, the target call content and the reply content are matched to determine the matching relationship between the target call content and the reply content, and a call result table is generated based on the matching relationship and the target customer.
[0102] In the disclosed embodiment, after the reply content is obtained, the target call content and the reply content can be matched, and the matching relationship between the target call content and the reply content can be determined, and a call result table can be generated based on the matching relationship and the target customer.
[0103] According to the intelligent calling method provided by the embodiment of the present disclosure, the business information, flow information and operating information of the customer are obtained according to the enterprise information, the calling content of the customer is determined according to the business information, flow information and operating information and displayed on the front-end interactive interface, the user interaction operation is received, and based on the user interaction operation, the target customer to be called and the target calling content of the target customer are determined from the customers, and the configured speech synthesis parameters are obtained, and the target calling content is speech synthesized according to the speech synthesis parameters, the calling audio file of the target customer is obtained and the calling audio file is stored, the customer information of the target customer and the storage location of the calling audio file are associated, and the calling task of the target user is generated based on the customer information of the target customer and the corresponding storage location, and according to the preset calling strategy and calling task, a call is initiated to the target customer, the reply voice of the target customer is collected, and the reply content is extracted from the reply voice, the target calling content and the reply content are matched, the matching relationship between the target calling content and the reply content is determined, and a calling result table is generated based on the matching relationship and the target customer. The intelligent calling method proposed by the present disclosure improves the intelligence and automation degree in the calling process, ensures the privacy in the calling process, reduces the cost in the calling process, and the obtained calling result table is conducive to the subsequent business development.
[0104] The specific process of the intelligent calling method proposed in the present disclosure is explained below.
[0105] For example, Figure 3 As shown, based on the intelligent call method proposed in the present invention, an intelligent call system can be constructed, and the intelligent call system is executed through a robot process RPA system, wherein the RPA system includes an RPA controller, an RPA intelligent call robot and an RPA database, the RPA controller includes a data capture component, a data preprocessing component, a speech synthesis component, a call initiation component, an outbound call result processing component, and an outbound call result data processing component, and the RPA intelligent call robot includes a speech synthesis module and an outbound call module.
[0106] For example, Figure 3As shown, the data crawling component can be used to locate the page elements on the first page including customer information in the client (enterprise WeChat), and extract the located first page elements from the first page, wherein the first page elements carry unstructured customer information. Similarly, the page elements on the second page including enterprise information in the target mini-program (the mini-program corresponding to the National Enterprise Credit Information Publicity System) are located, and the located second page elements are extracted from the second page, wherein the second page elements carry unstructured enterprise information. The unstructured customer information is structured through the data preprocessing component to obtain the customer's customer information, and the unstructured enterprise information is structured to obtain the customer's enterprise information. The customer's customer information and the customer's enterprise information are written into the RPA database, and user interaction operations are received. Based on the enterprise information, the customer's business information, flow information and operating information are obtained. Based on the business information, flow information and operating information, the customer's call content is determined and processed on the front-end interactive interface. Display, receive user interaction operations, and based on the user interaction operations, determine the target customer to be called and the target call content of the target customer from the customers, obtain the configured speech synthesis parameters, the speech synthesis module calls the speech synthesis component through the interface, the speech synthesis component performs speech synthesis on the target call content according to the speech synthesis parameters, obtains the call audio file of the target customer and stores the call audio file, associates the customer information of the target customer with the storage location of the call audio file, and generates a call task for the target user based on the customer information of the target customer and the corresponding storage location. The outbound call module calls the call initiation component to initiate a call to the target customer according to the preset call strategy and call task, collects the target customer's reply voice through the outbound call result processing component, and extracts the reply content from the reply voice, matches the target call content and the reply content through the outbound call result data processing component, determines the matching relationship between the target call content and the reply content, and generates a call result table based on the matching relationship and the target customer, and writes the call result table into the RPA database.
[0107] To sum up, the intelligent calling method proposed in the present invention does not require the installation of telephones and the construction of telephone lines. It can directly use network traffic for intelligent calling, which reduces the cost of intelligent calling. It can also make calls based on the enterprise client and customers with whom it has business dealings, thereby meeting the privacy of the calling process. The calling strategies and calling processes can be customized, have strong scalability, and have a wide range of uses. It is independent of existing systems and uses a non-invasive method to achieve process linkage between systems. It will not damage the original Internet technology architecture of the enterprise, and can execute calling tasks uninterruptedly, ensuring the accuracy and reliability of executing calling tasks.
[0108] Figure 4 FIG. 4 is a block diagram of an intelligent calling device according to a first embodiment of the present disclosure.
[0109] like Figure 4 As shown, the intelligent calling device 400 of the embodiment of the present disclosure includes: a first acquisition module 401 , a second acquisition module 402 , a determination module 403 and a generation module 404 .
[0110] A first acquisition module 401 is used to acquire first login information of an enterprise on a target application, log in to an enterprise client based on the first login information, and acquire customer information of a customer from the enterprise client;
[0111] A second acquisition module 402 is used to acquire second login information of the enterprise on the target mini-program, log in to the target mini-program based on the second login information, and acquire the enterprise information of the customer from the target mini-program;
[0112] A determination module 403 is used to determine the target customer to be called and the target call content according to the enterprise information of the customer;
[0113] The generation module 404 is used to generate a call task and execute the call task based on the customer information of the target customer and the target call content to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer.
[0114] In one embodiment of the present disclosure, the first acquisition module 401 is further used to: determine the first page including the customer information in the client and enter the first page; locate the page element on the first page and extract the located first page element from the first page, wherein the first page element carries unstructured customer information; and structure the unstructured customer information to obtain the customer information of the customer.
[0115] In one embodiment of the present disclosure, the second acquisition module 402 is also used to: determine the second page including the enterprise information in the target mini-program and enter the second page; locate the page element on the second page and extract the located second page element from the second page, wherein the second page element carries unstructured enterprise information; structure the unstructured enterprise information to obtain the enterprise information of the customer.
[0116] In one embodiment of the present disclosure, the device 400 is also used to: monitor the page loading status of the client or the target applet, determine the page jump process to enter the first page or the second page in response to the completion of the page loading of the client or the target applet, and execute the page adjustment process to enter the first page or the second page.
[0117] In one embodiment of the present disclosure, the second acquisition module 402 is further used to: receive a credit application instruction sent by the client, and generate the credit contract template according to the credit application instruction.
[0118] In one embodiment of the present disclosure, the device 500 is also used to: obtain a preconfigured enterprise information table to be filled, and based on the enterprise information table to be filled, determine the target enterprise information from the candidate enterprise information; determine the target format of the target enterprise information from the enterprise information template, and perform structured conversion on the target candidate enterprise information based on the target format to obtain the customer's enterprise information.
[0119] In one embodiment of the present disclosure, the determination module 403 is also used to: obtain the customer's business information, transaction information and operating information based on the enterprise information; determine the customer's call content based on the business information, transaction information and operating information and display it on the front-end interactive interface; receive user interaction operations, and based on the user interaction operations, determine the target customer to be called and the target call content of the target customer from the customers.
[0120] In one embodiment of the present disclosure, the determination module 403 is also used to: obtain configured speech synthesis parameters, perform speech synthesis on the target call content according to the speech synthesis parameters, obtain the call audio file of the target customer and store the call audio file; associate the customer information of the target customer and the storage location of the call audio file, and generate a call task for the target user based on the customer information of the target customer and the corresponding storage location.
[0121] In one embodiment of the present disclosure, the determination module 403 is further used to: generate a to-be-called information table based on the customer information of the target customer, the target call content and the storage location; read the customer information of the target customer and the storage location from the to-be-called information table to generate the call task.
[0122] In one embodiment of the present disclosure, the generation module 404 is also used to: initiate a call to the target customer according to a preset call strategy and the call task; collect the target customer's reply voice, and extract the reply content from the reply voice; match the target call content and the reply content, determine the matching relationship between the target call content and the reply content, and generate the call result table based on the matching relationship and the target customer.
[0123] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0124] In summary, the intelligent calling device provided by the embodiment of the present disclosure obtains the first login information of the enterprise on the target application, logs in to the enterprise client based on the first login information, obtains the customer information of the customer from the enterprise client, obtains the second login information of the enterprise on the target applet, logs in to the target applet based on the second login information, and obtains the customer's enterprise information from the target applet, determines the target customer to be called and the target call content according to the customer's enterprise information, generates a call task and executes the call task based on the customer information of the target customer and the target call content, so as to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer. Therefore, the present disclosure generates a call task through the customer information and the target call content of the target customer, improves the flexibility of generating call tasks, and the call task is executed by the RPA system, which reduces the cost during the call process and ensures the efficiency and reliability of the call process.
[0125] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment.
[0126] like Figure 5 As shown, the electronic device 500 includes:
[0127] The memory 510 and the processor 520, a bus 530 connecting different components (including the memory 510 and the processor 520), the memory 510 stores a computer program, and when the processor 520 executes the program, the intelligent calling method described in the first aspect of the present disclosure is implemented.
[0128] Bus 530 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.
[0129] The electronic device 500 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by the electronic device 500, including volatile and non-volatile media, removable and non-removable media.
[0130] The memory 510 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 540 and / or cache memory 550. The electronic device 500 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 560 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 530 via one or more data medium interfaces. The memory 510 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.
[0131] A program / utility 580 having a set (at least one) of program modules 570 may be stored, for example, in the memory 510, such program modules 570 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 570 generally perform the functions and / or methods of the embodiments described in the present disclosure.
[0132] The electronic device 500 may also communicate with one or more external devices 590 (e.g., keyboard, pointing device, display 591, etc.), one or more devices that enable a user to interact with the electronic device 500, and / or any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 592. Furthermore, the electronic device 500 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through a network adapter 593. Figure 5 As shown, the network adapter 593 communicates with other modules of the electronic device 500 via the bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0133] The processor 520 executes various functional applications and data processing by running the programs stored in the memory 510 .
[0134] It should be noted that the implementation process and technical principles of the electronic device of this embodiment refer to the aforementioned explanation of the intelligent calling method of the embodiment of the present disclosure, which will not be repeated here.
[0135] In summary, the electronic device provided by the embodiment of the present disclosure can execute the intelligent calling method as described above, by obtaining the first login information of the enterprise on the target application, logging in to the enterprise client based on the first login information, and obtaining the customer's customer information from the enterprise client, obtaining the second login information of the enterprise on the target applet, logging in to the target applet based on the second login information, and obtaining the customer's enterprise information from the target applet, determining the target customer to be called and the target call content based on the customer's enterprise information, generating a call task and executing the call task based on the target customer's customer information and the target call content, to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer. Therefore, the present disclosure generates a call task through the target customer's customer information and the target call content, thereby improving the flexibility of generating call tasks, and the call task is executed by the RPA system, thereby reducing the cost during the call process and ensuring the efficiency and reliability during the call process.
[0136] In order to implement the above embodiments, the present disclosure also proposes a computer-readable storage medium.
[0137] When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the intelligent calling method as described above. Optionally, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0138] In order to implement the above embodiments, the present disclosure further provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the intelligent calling method described in the first aspect is implemented.
[0139] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0140] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. An intelligent calling method, characterized in that: The method is performed by a robotic process automation (RPA) system and includes: Acquire first login information of the enterprise on the target application, log in to the enterprise client based on the first login information, and acquire customer information of the customer from the enterprise client; Acquire second login information of the enterprise on the target mini-program, log in to the target mini-program based on the second login information, and acquire the enterprise information of the customer from the target mini-program; Determine the target customer to be called and the target call content according to the enterprise information of the customer; Based on the customer information of the target customer and the target call content, a call task is generated and executed to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer.
2. The method according to claim 1, characterized in that: The step of obtaining the customer information of the customer from the enterprise client includes: Determine a first page including the customer information in the client, and enter the first page; Locating a page element on the first page, and extracting the located first page element from the first page, wherein the first page element carries unstructured customer information; The unstructured customer information is structured to obtain the customer information of the customer.
3. The method according to claim 1, characterized in that The obtaining of enterprise information from the target applet includes: Determine a second page including the enterprise information in the target applet, and enter the second page; Locating a page element on the second page, and extracting the located second page element from the second page, wherein the second page element carries unstructured enterprise information; The unstructured enterprise information is structured to obtain the enterprise information of the customer.
4. The method according to claim 2 or 3, characterized in that: The method further comprises: The page loading status of the client or the target applet is monitored, and in response to the completion of the page loading of the client or the target applet, a page jump process to enter the first page or the second page is determined, and the page adjustment process is executed to enter the first page or the second page.
5. The method according to claim 3, characterized in that: The structuring of the unstructured enterprise information to obtain the enterprise information of the customer includes: Determining target enterprise information from the unstructured candidate enterprise information; The target enterprise information is structured to obtain structured enterprise information of the customer.
6. The method according to claim 5, characterized in that The step of determining target enterprise information from the unstructured candidate enterprise information and structuring the target enterprise information to obtain structured enterprise information of the client includes: Acquire a pre-configured enterprise information table to be filled, and determine the target enterprise information from the candidate enterprise information based on the enterprise information table to be filled; The target format of the target enterprise information is determined from the enterprise information template, and the target candidate enterprise information is structurally converted based on the target format to obtain the enterprise information of the client.
7. The method according to claim 1, characterized in that Determining the target calling content of the target customer to be called according to the enterprise information of the customer includes: According to the enterprise information, obtain the business information, transaction information and operating information of the customer; Determine the content of the customer's call based on the business information, transaction information and operating information and display it on the front-end interactive interface; A user interaction operation is received, and based on the user interaction operation, a target customer to be called and target call content of the target customer are determined from among the customers.
8. The method according to claim 7, characterized in that The generating of the call task based on the customer information of the target customer and the target call content includes: Acquire configured speech synthesis parameters, perform speech synthesis on the target call content according to the speech synthesis parameters, acquire the call audio file of the target customer and store the call audio file; The customer information of the target customer and the storage location of the call audio file are associated, and based on the customer information of the target customer and the corresponding storage location, a call task of the target user is generated.
9. The method according to claim 8, characterized in that The generating the call task of the target user based on the customer information of the target customer and the corresponding storage location includes: Generate a waiting-to-call information table based on the customer information of the target customer, the target call content and the storage location; The customer information of the target customer and the storage location are read from the to-be-called information table to generate the calling task.
10. The method according to claim 8, characterized in that The executing the calling task to obtain a calling result table includes: Initiate a call to the target customer according to the preset call strategy and the call task; Collecting the target customer's reply voice and extracting the reply content from the reply voice; The target call content and the reply content are matched to determine a matching relationship between the target call content and the reply content, and the call result table is generated based on the matching relationship and the target customer.
11. An intelligent calling device, characterized in that: Applied to a robotic process automation (RPA) system, the device comprises: A first acquisition module, used to acquire first login information of an enterprise on a target application, log in to an enterprise client based on the first login information, and acquire customer information of a customer from the enterprise client; A second acquisition module, configured to acquire second login information of the enterprise on the target mini-program, log in to the target mini-program based on the second login information, and acquire the enterprise information of the customer from the target mini-program; A determination module, used to determine the target customer to be called and the target call content according to the enterprise information of the customer; A generation module is used to generate a call task and execute the call task based on the customer information of the target customer and the target call content to obtain a call result table, wherein the call result table includes the target customer and the target call content and reply content of the target customer.
12. An electronic device, characterized in that: include: processor; a memory configured to store instructions executable by the processor; The processor is configured to execute the instructions to implement the intelligent calling method as described in any one of claims 1-10.
13. A computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the intelligent call method according to any one of claims 1 to 10.
14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the intelligent calling method according to any one of claims 1 to 10 is implemented.