A location-based intelligent outbound calling method, apparatus, device, and medium

Abstract

This invention relates to the field of intelligent outbound calling technology, and more particularly to an intelligent outbound calling method, apparatus, device, and medium based on location services. The method, applied in the financial field, acquires the location information of the user to be called, adds each outbound calling task to its corresponding local task queue, adjusts the outbound calling tasks in the local task queue according to a preset adjustment strategy to obtain an adjusted task queue, retrieves the outbound calling number and script for the outbound calling tasks in the adjusted task queue, collects the user's question-and-answer information, and determines the user's intent information. In this application, the location information of the user to be called is combined with the outbound calling task, and the number corresponding to the location information is called, improving the connection rate of the outbound call to the user. Collecting the intent information of the user to be called can improve the connection rate and information reach rate of subsequent outbound calling tasks.

Description

Technical Field

[0001] This invention relates to the field of intelligent outbound calling technology, and in particular to an intelligent outbound calling method, apparatus, device and medium based on location services. Background Technology

[0002] In the financial sector, telephone sales are a common promotional method used by banks, securities firms, and insurance companies when promoting financial products or other services. Currently, local office staff typically prepare pre-configured outbound call scripts, which are then sent to customers via a call center's customer service robot. However, because the scripts are standardized for the same task, and the robot's voice lacks naturalness and has pauses, some customers may hang up before the message is fully heard, resulting in a low outbound call reach rate. Therefore, improving the outbound call reach rate is a pressing issue that needs to be addressed. Summary of the Invention

[0003] Therefore, it is necessary to provide a location-based intelligent outbound calling method, device, equipment, and medium to address the aforementioned technical problems and solve the issue of low information reach rate in outbound calling tasks.

[0004] A first aspect of this application provides a location-based intelligent outbound calling method, the intelligent outbound calling method comprising:

[0005] Get the location information of the user to be called in each of the N outbound call tasks, where N is an integer greater than 1;

[0006] For any outbound call task, based on the location information of the user to be called in the corresponding outbound call task, the outbound call task is added to the local task queue corresponding to the location information. Each outbound call task in N outbound call tasks is added to the corresponding local task queue, resulting in M ​​local task queues, where M is an integer less than or equal to N.

[0007] According to the preset adjustment strategy, the outbound call tasks in the M local task queues are adjusted to obtain the target local task queue corresponding to each outbound call task. Each outbound call task is added to the corresponding target local task queue to obtain M adjusted task queues.

[0008] For any adjusted task queue, retrieve the outbound call number and outbound call script for the outbound call task in the adjusted task queue based on the local location information corresponding to the adjusted task queue.

[0009] Intelligent outbound calls are made to users in the corresponding adjusted task queue based on the outbound call number and outbound call script. Question and answer information of the users to be called is collected. Based on the question and answer information, the intent information of the users to be called is determined and recorded in the information table of the users to be called, thus obtaining the updated information table.

[0010] A second aspect of this application provides a location-based intelligent outbound calling device, the intelligent outbound calling device comprising:

[0011] The acquisition module is used to acquire the location information of the user to be called in each of the N outbound call tasks, where N is an integer greater than 1;

[0012] The addition module is used to add any outbound call task to the local task queue corresponding to the location information of the user to be called in the corresponding outbound call task, and add each outbound call task in N outbound call tasks to the corresponding local task queue to obtain M local task queues, where M is an integer less than or equal to N.

[0013] The adjustment module is used to adjust the outbound call tasks in the M local task queues according to the preset adjustment strategy, to obtain the target local task queue corresponding to each outbound call task, and to add each outbound call task to the corresponding target local task queue to obtain M adjusted task queues.

[0014] The retrieval module is used to retrieve the outbound call number and outbound call script for any adjusted task queue based on the local location information corresponding to the adjusted task queue.

[0015] The data collection module is used to intelligently call users in the corresponding adjusted task queue according to the outbound call number and outbound call script, collect the question and answer information of the users to be called, determine the intent information of the users to be called according to the question and answer information, and record the intent information in the information table of the users to be called to obtain the updated information table.

[0016] Thirdly, embodiments of the present invention provide a terminal device, the terminal device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the location-based intelligent outbound calling method as described in the first aspect.

[0017] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the location-based intelligent outbound calling method as described in the first aspect.

[0018] The advantages of this invention compared to the prior art are:

[0019] Obtain the location information of the users to be called in each of the N outbound call tasks, where N is an integer greater than 1. For any outbound call task, based on the location information of the users to be called in the corresponding outbound call task, add the outbound call task to the local task queue corresponding to the location information. Add each of the N outbound call tasks to its corresponding local task queue, resulting in M ​​local task queues, where M is an integer less than or equal to N. Adjust the outbound call tasks in the M local task queues according to a preset adjustment strategy to obtain the target local task queue for each outbound call task. Each outbound call task is added to its corresponding target local task queue, resulting in M ​​adjusted task queues. For any adjusted task queue, based on the local location information corresponding to the adjusted task queue, the outbound call number and script are retrieved for the outbound call task in the adjusted task queue. Intelligent outbound calls are then made to the users in the corresponding adjusted task queue based on the outbound call number and script, collecting the user's question and answer information. Based on the question and answer information, the user's intent information is determined and recorded in the user's information table, resulting in an updated information table. In this application, the location information of the user to be called is combined with the outbound call task, and the number corresponding to the location information is called, improving the connection rate of the outbound call to the user. Collecting the intent information of the user to be called can improve the connection rate and information reach rate of subsequent outbound call tasks. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an application environment for a location-based intelligent outbound calling method according to an embodiment of the present invention;

[0022] Figure 2 This is a flowchart illustrating a location-based intelligent outbound calling method according to an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the structure of a location-based intelligent outbound calling device according to an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present invention. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0027] It should also be understood that the term “and / or” as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0028] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0029] Furthermore, in the description of this invention and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0030] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of the invention include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0031] The embodiments of this invention can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that utilize digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0032] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0033] It should be understood that the sequence number of each step in the following embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0034] To illustrate the technical solution of the present invention, specific embodiments are described below.

[0035] An embodiment of the present invention provides a location-based intelligent outbound calling method, which can be applied to applications such as... Figure 1 In this application environment, the client communicates with the server. Clients include, but are not limited to, handheld computers, desktop computers, laptops, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). The server can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0036] See Figure 2 This is a flowchart illustrating a location-based intelligent outbound calling method according to an embodiment of the present invention. The aforementioned location-based intelligent outbound calling method can be applied to... Figure 1 The server in the above-mentioned configuration connects to the corresponding client, such as... Figure 2 As shown, the location-based intelligent outbound calling method may include the following steps.

[0037] S201: Obtain the location information of the user to be called in each of the N outbound call tasks, where N is an integer greater than 1.

[0038] In step S201, the outbound call task can be triggered by the outbound call robot, and the location information of the user to be called can be any address information reserved for the user to be called.

[0039] In this embodiment, the outbound call robot can trigger multiple outbound call tasks simultaneously. Each outbound call task corresponds to a user to be called. The location information of the user to be called can be obtained from the user's insurance policy or historical outbound call records.

[0040] It should be noted that the outbound call task may include a request message, which may include the product to be promoted. For example, the product to be promoted in the outbound call task could be any insurance product. When determining the user to be called in each outbound call task, the request message can be parsed to obtain the message information carried in the message. The information indicating the product can be obtained from the message information as an object number. The product corresponding to the object number is then determined as the request object. The message information includes, but is not limited to, the product to be promoted. Through the above implementation method, the user to be called and the promotional product corresponding to the target user can be quickly obtained.

[0041] It should be noted that when multiple users need to be called, users of products similar to the corresponding product can also be identified as users to be called based on the product corresponding to the object number, thus broadening the channels for users to be called.

[0042] In at least one embodiment of the present invention, similar objects to the requested object are determined from a preset object library based on the object characteristics of the requested object, and user information of the requested object is obtained based on the similar objects. Object characteristics refer to features that can characterize the requested object; for example, the object characteristic of product A could be the premium amount. The preset object library stores multiple objects that have been sold online. Similar objects may include multiple objects, and similar objects refer to preset objects whose object similarity is greater than a preset similarity. User information refers to the initial user's profile information, such as user address, user age, and user income level.

[0043] It should be noted that determining similar objects from a preset object library based on the object characteristics of the requested object includes: obtaining object characteristics from the requested object, obtaining preset characteristics of preset objects in the preset object library, dividing the object characteristics into numerical features and textual features, calculating the distance difference between the numerical features and the preset features, calculating the feature similarity between the textual features and the preset features, generating an object similarity score between the requested object and each preset object based on the distance difference and feature similarity score, and identifying preset objects with an object similarity score greater than the preset similarity score as similar objects. Here, numerical features refer to object features corresponding to numerical values, and textual features refer to object features corresponding to non-numerical values.

[0044] The preset similarity can be set based on the initial user base. By using the distance difference between numerical features and preset features, as well as the feature similarity between textual features and preset features, similar objects to the requested object can be accurately determined. User information can also include gender, age, region, education level, occupation, marital status, family status, etc.

[0045] Optionally, obtain the location information of the user to be called in each of the N outbound calling tasks, including:

[0046] Obtain the first, second, and third location information of the user to be called;

[0047] The location information of the user to be called is determined based on the priority of the first location information, the second location information, and the third location information.

[0048] In this embodiment, the location information of the user to be called can be the first location information of the location of the insurance signing agency, the second location information of the location where the ID card was issued, and the third location information of the location of recent claims or other policy maintenance services. The priority can be sorted from high to low for the first, second, and third location information, with the first location information of the location of the insurance signing agency as the first priority, the second location information of the location where the ID card was issued as the second priority, and the third location information of the location of recent claims or other policy maintenance services as the third priority.

[0049] It should be noted that when obtaining the location information of users to be called, the address on the policy can be extracted, and the specified location on the policy can be read. Users need to fill in their address when purchasing insurance, which facilitates better service from the insurance company's after-sales personnel. The policy format is fixed, and the user's address is also filled in a fixed place. The system reads the information from that fixed place and extracts the user's location information from the policy.

[0050] It should be noted that when a smart outbound call is made based on the first location information corresponding to the first priority and fails to connect, the second location information will be used as the first priority for the smart outbound call. If the smart outbound call fails to connect, the third location information will be used as the first priority, and so on, updating the location information corresponding to the first priority in sequence. If, when making a smart outbound call based on the first, second, and third location information, the user mentions that they are not in their local area or has other related intentions, the location mentioned by the user will be directly updated as the first priority.

[0051] S202: For any outbound call task, according to the location information of the user to be called in the corresponding outbound call task, add the outbound call task to the local task queue corresponding to the location information. Add each outbound call task in N outbound call tasks to the corresponding local task queue to obtain M local task queues, where M is an integer less than or equal to N.

[0052] In step S202, outbound call tasks are added to the corresponding task queues in sequence so that the tasks can be executed sequentially according to the order in the task queues. Each outbound call task out of N is added to the corresponding local task queue, resulting in M ​​local task queues, where M is an integer less than or equal to N.

[0053] In this embodiment, for any outbound call task, based on the location information of the user to be called in the corresponding outbound call task, the outbound call task is added to the local task queue corresponding to the location information. When the location information of the users to be called in the outbound call tasks is the same, the outbound call tasks are added to the same local task queue. Each of the N outbound call tasks is added to its corresponding local task queue, resulting in M ​​local task queues, where M is an integer less than or equal to N. For example, if the location information of the first user to be called is in region A, the outbound call task corresponding to that user is added to the local task queue for region A; if the location information of the second user to be called is in region B, the outbound call task corresponding to that user is added to the local task queue for region B; and if the location information of the third user to be called is in region A, the outbound call task corresponding to that user is added to the local task queue for region A. In this embodiment, the outbound call tasks are added to the local task list to facilitate intelligent outbound calls using local outbound call numbers, thereby improving the triggering efficiency of outbound calls.

[0054] S203: According to the preset adjustment strategy, adjust the outbound call tasks in the M local task queues to obtain the target local task queue corresponding to each outbound call task, and add each outbound call task to the corresponding target local task queue to obtain M adjusted task queues.

[0055] In step S203, since the distribution of the locations of the users to be called is uneven, the number of outbound calling tasks in each local task queue is unevenly distributed. Therefore, according to the preset adjustment strategy, the outbound calling tasks in the M local task queues are adjusted so that the number of outbound calling tasks in each local task queue is as equal as possible, and the target local task queue corresponding to each outbound calling task is obtained. Each outbound calling task is added to the corresponding target local task queue, resulting in M ​​adjusted task queues.

[0056] In this embodiment, according to a preset adjustment strategy, the outbound call tasks in the M local task queues are adjusted, and each outbound call task is adjusted to the corresponding local task queue to reduce the load on the local task queue with a large number of outbound call tasks, thereby obtaining the target local task queue corresponding to each outbound call task. Each outbound call task is added to the corresponding target local task queue to obtain M adjusted task queues.

[0057] Optionally, according to a preset adjustment strategy, the outbound call tasks in the M local task queues are adjusted to obtain the target local task queue corresponding to each outbound call task, including:

[0058] For any local task queue, obtain the first load count of the local task queue. If the number of outbound call tasks in the local task queue is greater than the first load count, determine whether the user to be called is making a smart outbound call for the first time based on the historical smart outbound call records. If it is making a smart outbound call for the first time, use the local task queue as the target local task queue for the corresponding outbound call task, and add the outbound call task corresponding to the user to be called to the local task queue first, and obtain the remaining outbound call tasks that have not been added to the task queue.

[0059] Based on the location information of the users to be called in the remaining outbound call tasks, select the corresponding target local task queue for the remaining outbound call tasks from the remaining local task queues, and add each remaining outbound call task to the corresponding target local task queue to obtain the target local task queue for each outbound call task.

[0060] In this embodiment, when adjusting the local task queue, the first load number of the local task queue is obtained first. It is then determined whether the number of outbound call tasks in the local task queue exceeds the first load number. If the number of outbound call tasks exceeds the first load number, the outbound call tasks are adjusted. Then, it is determined whether the user to be called is making a first-time smart outbound call. If it is, the outbound call task is not adjusted. The local task queue is used as the target local task queue for the corresponding outbound call task. The outbound call task corresponding to the user to be called is added to the local task queue first, and the remaining outbound call tasks not added to the task queue are obtained.

[0061] Based on the location information of the users to be called in the remaining outbound call tasks, a corresponding target local task queue is selected from the remaining local task queues for the remaining outbound call tasks. Each remaining outbound call task is then added to its corresponding target local task queue, resulting in a target local task queue for each outbound call task. For example, the remaining outbound call tasks are added to the local task queue whose location is close to that of the users to be called.

[0062] It should be noted that when the number of users in an outbound call task who are making their first intelligent outbound call exceeds the first load limit, the tasks are adjusted sequentially based on the time each outbound call task was added to the local task queue. This local task queue stores all outbound call tasks where users are making their first intelligent outbound call, and these tasks are added to the local task queue according to their time priority. For example, if both outbound call task A and outbound call task B have users making their first intelligent outbound call, they are added to the local task queue based on the time they were added.

[0063] When outbound call tasks for users making their first intelligent outbound call are added to the local task queue, and the number of outbound call tasks has not reached the first load limit, allowing the local task queue to add other outbound call tasks, if the location information in other non-first intelligent outbound call tasks is local, they are added to the local task queue according to time priority. For example, if both outbound call tasks C and D have users making their first intelligent outbound call, they are added to the local task queue according to the time when outbound call tasks C and D were added.

[0064] Optionally, based on the location information of the users to be called in the remaining outbound call tasks, a corresponding target local task queue is selected from the remaining local task queues for the remaining outbound call tasks, including:

[0065] For any remaining outbound call task, select candidate location information that matches the location information based on the location information of the users to be called in the remaining outbound call task;

[0066] Based on the candidate location information, determine the target local task queue corresponding to the candidate location information, and add the remaining outbound call tasks to the target local task queue.

[0067] In this embodiment, to select a target local task queue for the remaining outbound call tasks that are overloaded in the local task queue, the selection can be made based on the location information of the users to be called in the remaining outbound call tasks. Candidate location information matching the location information is selected, and the target local task queue corresponding to the candidate location information is determined based on the candidate location information. The remaining outbound call tasks are then added to the target local task queue. For example, if the remaining outbound call tasks are in local task queue A, then a local task queue with location information close to that in local task queue A is selected as a candidate local task queue for the remaining outbound call tasks. This candidate local task queue could be local task queue B, where the location information in local task queue A and the location information in local task queue B are in the same region or province. For example, if the location information in local task queue A is the location information of a city in a province, the location information in local task queue B could be the location information of other cities in the same province. When selecting the location information of other cities, locations of other cities that are close in distance to the location information in local task queue A can be selected.

[0068] It should be noted that, for any remaining outbound call task, candidate location information matching the location information is selected based on the location information of the users to be called in the remaining outbound call task. When selecting candidate location information, a pre-set distance score between different location information can be used. When two location information are far apart, the distance score is smaller; when two location information are close together, the distance score is larger. This determines the distance score between the location information corresponding to the remaining outbound call task and the location information corresponding to the other local task queues. When the distance score is greater than a distance threshold, the corresponding location information is used as a candidate location information matching the current location information. The local task queue corresponding to the maximum distance score among the candidate information is selected as the corresponding target location task queue.

[0069] Optionally, after determining the target local task queue corresponding to the candidate location information based on the candidate location information and adding the remaining outbound call tasks to the target local task queue, the method further includes:

[0070] Obtain the second load count of the target local task queue. If the number of outbound call tasks in the target local task queue is greater than the second load count, determine the corresponding target local task queue again after the preset time for the remaining outbound call tasks.

[0071] In this embodiment, after selecting a corresponding target local task queue for the remaining outbound call tasks, it is necessary to obtain the second load factor of the target local task queue. If the number of outbound call tasks in the target local task queue is greater than the second load factor, another target local task queue is selected from the target local task queues corresponding to the candidate location information. If the number of outbound call tasks in all target local task queues corresponding to the candidate location information is greater than the corresponding second load factor, the target local task queue for the remaining outbound call tasks is determined again after a preset time. When selecting a corresponding target local task queue for the remaining outbound call tasks, if all target local task queues corresponding to the selected location information are overloaded, the remaining outbound call tasks wait. After a preset time, the executed outbound call tasks are deleted from the target local task queues, and the remaining outbound call tasks are added to the corresponding target local task queues, thus avoiding the problem of overload during local operation.

[0072] S204: For any adjusted task queue, retrieve the outbound call number and outbound call script for the outbound call tasks in the adjusted task queue based on the local location information corresponding to the adjusted task queue.

[0073] In step S204, based on the local location information corresponding to the adjusted task queue, the corresponding outbound call number is retrieved for the outbound call task in the task queue. The outbound call number corresponds to the local number corresponding to the location information of the user to be called, so as to improve the efficiency of user connection. The outbound call script is retrieved for the outbound call task in the adjusted task queue, and the script that is easier for the user to accept is used to communicate with the user, so as to increase the user's interest in the product being promoted by the outbound call and improve the triggering efficiency of the user to be called.

[0074] In this embodiment, when recommending corresponding products to different users, the outbound call numbers for different locations are different. When locals receive the local number, the connection efficiency for locals can be improved. Different outbound call scripts are used for different users to be called, so as to increase users' interest in the products being promoted and improve the trigger efficiency for users to be called.

[0075] Optionally, based on the local location information corresponding to the adjusted task queue, retrieve outbound call scripts for outbound call tasks in the adjusted task queue, including:

[0076] If the user to be called in the outbound call task is making their first intelligent outbound call, retrieve the first type of outbound call script;

[0077] If the user to be called in the outbound call task is not the first time for intelligent outbound calling, retrieve the second outbound call script.

[0078] In this embodiment, when calling the corresponding outbound call script, the script is retrieved based on whether the user to be called in the outbound call task is making their first intelligent outbound call. If the user is making their first intelligent outbound call, the first type of outbound call script is retrieved; if the user is not making their first intelligent outbound call, the second type of outbound call script is retrieved. The first type of outbound call script can be a script introducing the product to be promoted, and the second type of outbound call script can be a script introducing the advantages of the product to be promoted. Different outbound call scripts can be set according to specific circumstances; this embodiment does not limit this.

[0079] S205: Based on the outbound number and outbound script, intelligently call the users to be called in the corresponding adjusted task queue, collect the question and answer information of the users to be called, determine the intent information of the users to be called based on the question and answer information, record the intent information in the information table of the users to be called, and obtain the updated information table.

[0080] In step S205, intelligent outbound calling is performed using the retrieved outbound number and script. When the intelligent outbound call is answered by a user, the question-and-answer information with the user is collected. Based on the question-and-answer information, the intent information of the user to be called is determined and recorded in the information table of the user to be called, resulting in an updated information table. This updated information table is used to update the corresponding outbound script for the next intelligent outbound call, ensuring that the updated script matches the intent of the user to be called, thereby increasing the probability of the user purchasing the product. The information table of the user to be called is a collection of information about the potential business transactions of each user to be called.

[0081] Optionally, the system collects question-and-answer information from the user to be called, and determines the user's intent information based on the question-and-answer information, including:

[0082] Extract question and answer keywords from the question and answer information, match the question and answer keywords with the business keywords in the preset business, and obtain the matching score with each preset business;

[0083] Based on the matching score, determine the intent information of the pending business of the user to be called.

[0084] In this embodiment, when determining the intent information of the user to be called, it can be determined based on the keywords used by the user during the question-and-answer process. Question-and-answer keywords are extracted from the question-and-answer information and matched with business keywords in preset services to obtain a matching score for each preset service. Based on the matching score, the intent information of the user's pending business is determined. During matching, keywords such as subject + predicate + object in the question-and-answer information can be matched with each preset service to obtain the sum of matching scores for each keyword. The preset service with the highest sum is then taken as the pending business of the user to be called.

[0085] Obtain the location information of the users to be called in each of the N outbound call tasks, where N is an integer greater than 1. For any outbound call task, based on the location information of the users to be called in the corresponding outbound call task, add the outbound call task to the local task queue corresponding to the location information. Add each of the N outbound call tasks to its corresponding local task queue, resulting in M ​​local task queues, where M is an integer less than or equal to N. Adjust the outbound call tasks in the M local task queues according to a preset adjustment strategy to obtain the target local task queue for each outbound call task. Each outbound call task is added to its corresponding target local task queue, resulting in M ​​adjusted task queues. For any adjusted task queue, based on the local location information corresponding to the adjusted task queue, the outbound call number and script are retrieved for the outbound call task in the adjusted task queue. Intelligent outbound calls are then made to the users in the corresponding adjusted task queue based on the outbound call number and script, collecting the user's question and answer information. Based on the question and answer information, the user's intent information is determined and recorded in the user's information table, resulting in an updated information table. In this application, the location information of the user to be called is combined with the outbound call task, and the number corresponding to the location information is called, improving the connection rate of the outbound call to the user. Collecting the intent information of the user to be called can improve the connection rate and information reach rate of subsequent outbound call tasks.

[0086] See Figure 3 , Figure 3 This is a schematic diagram of the structure of a location-based intelligent outbound calling device provided in an embodiment of the present invention. In this embodiment, the terminal includes units used for performing... Figure 2 The steps in the corresponding embodiments. Please refer to the details. Figure 2 as well as Figure 2 The relevant descriptions in the corresponding embodiments are shown below. For ease of explanation, only the parts relevant to this embodiment are shown. Figure 3 As shown, the intelligent outbound calling device 30 includes: an acquisition module 31, an addition module 32, an adjustment module 33, a retrieval module 34, and a data collection module 35.

[0087] The acquisition module 31 is used to acquire the location information of the user to be called in each of the N outbound call tasks, where N is an integer greater than 1;

[0088] Add module 32, which is used to add outbound call tasks to the local task queue corresponding to the location information of the user to be called in the corresponding outbound call task for any outbound call task. Add each outbound call task in N outbound call tasks to the corresponding local task queue to obtain M local task queues, where M is an integer less than or equal to N.

[0089] The adjustment module 33 is used to adjust the outbound call tasks in M ​​local task queues according to a preset adjustment strategy, to obtain the target local task queue corresponding to each outbound call task, and to add each outbound call task to the corresponding target local task queue to obtain M adjusted task queues.

[0090] The retrieval module 34 is used to retrieve the outbound call number and outbound call script for any adjusted task queue based on the local location information corresponding to the adjusted task queue.

[0091] The data collection module 35 is used to make intelligent outbound calls to users in the corresponding adjusted task queue based on the outbound call number and outbound call script, collect the question and answer information of the users to be called, determine the intent information of the users to be called based on the question and answer information, record the intent information in the information table of the users to be called, and obtain the updated information table.

[0092] Optionally, the acquisition module 31 includes:

[0093] The location information acquisition unit is used to acquire the first location information, second location information and third location information of the user to be called;

[0094] The determining unit is used to determine the location information of the user to be called based on the priority of the first location information, the second location information and the third location information.

[0095] Optionally, the adjustment module 33 includes:

[0096] The judgment unit is used to obtain the first load number of any local task queue. If the number of outbound call tasks in the local task queue is greater than the first load number, it determines whether the user to be called is making a smart outbound call for the first time based on the historical smart outbound call records. If it is making a smart outbound call for the first time, the local task queue is used as the target local task queue for the corresponding outbound call task, and the outbound call task corresponding to the user to be called is added to the local task queue first, so as to obtain the remaining outbound call tasks that have not been added to the task queue.

[0097] The selection unit is used to select the corresponding target local task queue for the remaining outbound call tasks from the remaining local task queues based on the location information of the users to be called in the remaining outbound call tasks, and add each remaining outbound call task to the corresponding target local task queue to obtain the target local task queue corresponding to each outbound call task.

[0098] Optionally, the selection unit mentioned above includes:

[0099] The candidate subunit is used to select candidate location information that matches the location information of the user to be called in the remaining outbound call task for any remaining outbound call task.

[0100] The added sub-unit is used to determine the target local task queue corresponding to the candidate location information based on the candidate location information, and add the remaining outbound call tasks to the target local task queue.

[0101] Optionally, the above selection unit further includes:

[0102] The sub-unit is determined again to obtain the second load number of the target local task queue. If the number of outbound tasks in the target local task queue is greater than the second load number, the remaining outbound tasks are determined again according to the preset time after the preset time.

[0103] Optionally, the above-mentioned retrieval module 34 includes:

[0104] The first retrieval unit is used to retrieve the first type of outbound script if the user to be called in the outbound call task is making their first intelligent outbound call.

[0105] The second retrieval unit is used to retrieve a second type of outbound script if the user to be called in the outbound call task is not making the first intelligent outbound call.

[0106] Optionally, the above-mentioned acquisition module 35 includes:

[0107] The extraction unit is used to extract question and answer keywords from the question and answer information, match the question and answer keywords with the business keywords in the preset business, and obtain the matching score with each preset business.

[0108] The intent determination unit is used to determine the intent information of the pending business of the user to be called, based on the matching score.

[0109] It should be noted that the information interaction and execution process between the above-mentioned units are based on the same concept as the method embodiments of the present invention. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0110] Figure 4 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present invention. Figure 4 As shown, the terminal device of this embodiment includes: at least one processor ( Figure 4 Only one is shown in the diagram), a memory, and a computer program stored in the memory that can run on at least one processor, which, when executed by the processor, implements any of the above-described location-based intelligent outbound calling method steps.

[0111] The terminal device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that... Figure 4This is merely an example of a terminal device and does not constitute a limitation on the terminal device. A terminal device may include more or fewer components than shown in the figure, or a combination of certain components, or different components, such as network interfaces, displays, and input devices.

[0112] The processor referred to can be a CPU, but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0113] The memory includes readable storage media, internal memory, etc., wherein the internal memory can be the main memory of the terminal device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions stored in the readable storage media. The readable storage media can be the hard drive of the terminal device, or in some embodiments, it can be an external storage device of the terminal device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital Card (SD), or a Flash Card. Furthermore, the memory can include both internal storage units and external storage devices of the terminal device. The memory is used to store the operating system, applications, bootloader, data, and other programs, such as program code for computer programs. The memory can also be used to temporarily store data that has been output or will be output.

[0114] Those skilled in the art will understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the functions described above can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this invention. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the methods of the above embodiments by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium can include at least: any entity or device capable of carrying computer program code, a recording medium, a computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0115] The present invention can implement all or part of the processes in the above embodiments of the method, or it can be accomplished by a computer program product. When the computer program product is run on a terminal device, the terminal device executes the steps in the above method embodiments.

[0116] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0117] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0118] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0120] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A location-based intelligent outbound calling method, characterized in that, The intelligent outbound calling method includes: Obtain the location information of the users to be called in each of the N outbound calling tasks, where N is an integer greater than 1; wherein, the outbound calling task includes the request message of the outbound calling task. When determining the users to be called in each outbound calling task, parse the request message to obtain the message information carried in the message, extract the information of the indicated product from the message information as the object number, and determine the users of products similar to the corresponding products as the users to be called based on the product corresponding to the object number. The product corresponding to the object number is identified as the request object. Based on the object characteristics of the request object, similar objects of the request object are identified from the preset object library. This includes: obtaining object characteristics based on the request object, obtaining preset characteristics of preset objects in the preset object library, dividing the object characteristics into numerical characteristics and textual characteristics, calculating the distance difference between the numerical characteristics and the preset characteristics, calculating the feature similarity between the textual characteristics and the preset characteristics, generating the object similarity between the request object and each preset object based on the distance difference and feature similarity, and identifying preset objects with object similarity greater than the preset similarity as similar objects. For any outbound call task, based on the location information of the user to be called in the corresponding outbound call task, the outbound call task is added to the local task queue corresponding to the location information. Each outbound call task in N outbound call tasks is added to the corresponding local task queue, resulting in M ​​local task queues, where M is an integer less than or equal to N. According to the preset adjustment strategy, the outbound call tasks in the M local task queues are adjusted to obtain the target local task queue corresponding to each outbound call task. Each outbound call task is added to the corresponding target local task queue to obtain M adjusted task queues. For any adjusted task queue, retrieve the outbound call number and outbound call script for the outbound call task in the adjusted task queue based on the local location information corresponding to the adjusted task queue. Intelligent outbound calls are made to users in the corresponding adjusted task queue based on the outbound call number and outbound call script. Question and answer information of the users to be called is collected. Based on the question and answer information, the intent information of the users to be called is determined and recorded in the information table of the users to be called, thus obtaining the updated information table.

2. The intelligent outbound calling method as described in claim 1, characterized in that, The step of obtaining the location information of the user to be called in each of the N outbound calling tasks includes: Obtain the first location information, second location information, and third location information of the user to be called; The location information of the user to be called is determined based on the priority of the first location information, the second location information, and the third location information.

3. The intelligent outbound calling method as described in claim 1, characterized in that, The step of adjusting the outbound call tasks in the M local task queues according to a preset adjustment strategy to obtain the target local task queue corresponding to each outbound call task includes: For any local task queue, obtain the first load count of the local task queue. If the number of outbound call tasks in the local task queue is greater than the first load count, determine whether the user to be called is making a first intelligent outbound call based on historical intelligent outbound call records. If it is making a first intelligent outbound call, use the local task queue as the target local task queue for the corresponding outbound call task, and add the outbound call task corresponding to the user to be called to the local task queue first, thus obtaining the remaining outbound call tasks that have not been added to the task queue. Based on the location information of the users to be called in the remaining outbound call tasks, a corresponding target local task queue is selected from the remaining local task queues for the remaining outbound call tasks, and each remaining outbound call task is added to the corresponding target local task queue to obtain the target local task queue corresponding to each outbound call task.

4. The intelligent outbound calling method as described in claim 3, characterized in that, The step of selecting a corresponding target local task queue from the remaining local task queues for the remaining outbound call tasks based on the location information of the users to be called in the remaining outbound call tasks includes: For any remaining outbound call task, candidate location information matching the location information is selected based on the location information of the user to be called in the remaining outbound call task. Based on the candidate location information, determine the target local task queue corresponding to the candidate location information, and add the remaining outbound call tasks to the target local task queue.

5. The intelligent outbound calling method as described in claim 4, characterized in that, After determining the target local task queue corresponding to the candidate location information based on the candidate location information, and adding the remaining outbound call tasks to the target local task queue, the method further includes: Obtain the second load count of the target local task queue. If the number of outbound call tasks in the target local task queue is greater than the second load count, determine the corresponding target local task queue again after the preset time for the remaining outbound call tasks.

6. The intelligent outbound calling method as described in claim 1, characterized in that, The step of retrieving outbound call scripts for outbound call tasks in the adjusted task queue based on the local location information corresponding to the adjusted task queue includes: If the user to be called in the outbound call task is making their first intelligent outbound call, retrieve the first type of outbound call script; If the user to be called in the outbound call task is not making a first-time intelligent outbound call, retrieve the second outbound call script.

7. The intelligent outbound calling method as described in claim 1, characterized in that, The step of collecting the question-and-answer information of the user to be called, and determining the intent information of the user to be called based on the question-and-answer information, includes: Extract question and answer keywords from the question and answer information, match the question and answer keywords with business keywords in preset business, and obtain a matching score with each preset business; Based on the matching score, the intent information of the pending business of the user to be called is determined.

8. A location-based intelligent outbound calling device, characterized in that, The intelligent outbound calling device includes: The acquisition module is used to acquire the location information of the users to be called in each of the N outbound call tasks, where N is an integer greater than 1. The outbound call task includes a request message. When determining the users to be called in each outbound call task, the request message is parsed to obtain the message information carried in the message. The information of the indicated product is obtained from the message information as the object number. Based on the product corresponding to the object number, the user with a product similar to the corresponding product is determined as the user to be called. The product corresponding to the object number is identified as the request object. Based on the object characteristics of the request object, similar objects of the request object are identified from the preset object library. This includes: obtaining object characteristics based on the request object, obtaining preset characteristics of preset objects in the preset object library, dividing the object characteristics into numerical characteristics and textual characteristics, calculating the distance difference between the numerical characteristics and the preset characteristics, calculating the feature similarity between the textual characteristics and the preset characteristics, generating the object similarity between the request object and each preset object based on the distance difference and feature similarity, and identifying preset objects with object similarity greater than the preset similarity as similar objects. The addition module is used to add any outbound call task to the local task queue corresponding to the location information of the user to be called in the corresponding outbound call task, and add each outbound call task in N outbound call tasks to the corresponding local task queue to obtain M local task queues, where M is an integer less than or equal to N. The adjustment module is used to adjust the outbound call tasks in the M local task queues according to the preset adjustment strategy, to obtain the target local task queue corresponding to each outbound call task, and to add each outbound call task to the corresponding target local task queue to obtain M adjusted task queues. The retrieval module is used to retrieve the outbound call number and outbound call script for any adjusted task queue based on the local location information corresponding to the adjusted task queue. The data collection module is used to intelligently call users in the corresponding adjusted task queue according to the outbound call number and outbound call script, collect the question and answer information of the users to be called, determine the intent information of the users to be called according to the question and answer information, and record the intent information in the information table of the users to be called to obtain the updated information table.

9. A terminal device, characterized in that, The terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent outbound calling method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent outbound calling method as described in any one of claims 1 to 7.

Images